MPI Sintel Dataset

Results and Rankings

Results for methods appear here after users upload them and approve them for public display.


Final
Clean
EPE all EPE matched EPE unmatched d0-10 d10-60 d60-140 s0-10 s10-40 s40+
GroundTruth [1] 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 Visualize Results
CCMR+ [2] 1.067 0.311 7.235 0.832 0.262 0.143 0.148 0.560 6.864 Visualize Results
MS_RAFT+_RVC [3] 1.232 0.400 8.021 1.101 0.353 0.142 0.159 0.631 8.020 Visualize Results
MEMFOF [4] 0.991 0.407 5.759 1.087 0.338 0.202 0.179 0.629 5.906 Visualize Results
EMD-OER [5] 1.143 0.289 8.113 0.785 0.218 0.156 0.180 0.649 7.119 Visualize Results
MEMFOF-L [6] 0.963 0.397 5.587 1.081 0.331 0.182 0.182 0.633 5.649 Visualize Results
CCAFlow [7] 1.057 0.340 6.908 0.904 0.248 0.194 0.186 0.623 6.432 Visualize Results
GeoViT [8] 0.787 0.274 4.978 0.853 0.179 0.113 0.193 0.565 4.280 Visualize Results
DDVM [9] 1.754 0.834 9.257 1.363 0.712 0.557 0.195 0.631 12.221 Visualize Results
AnyFlow+GMA [10] 1.209 0.416 7.681 1.200 0.330 0.164 0.208 0.739 7.315 Visualize Results
OM_GMFlow [11] 1.148 0.398 7.258 0.974 0.318 0.239 0.211 0.664 6.969 Visualize Results
StreamFlow [12] 1.041 0.381 6.416 1.011 0.319 0.176 0.212 0.690 5.999 Visualize Results
IWarp [13] 1.094 0.445 6.392 1.170 0.338 0.269 0.214 0.694 6.438 Visualize Results
CroCo-Flow [14] 1.092 0.386 6.851 1.226 0.261 0.147 0.219 0.732 6.301 Visualize Results
MS_RAFT [15] 1.374 0.479 8.678 1.340 0.379 0.224 0.221 0.767 8.572 Visualize Results
SEA-RAFT-M [16] 1.442 0.460 9.448 1.189 0.425 0.177 0.224 0.805 9.028 Visualize Results
DPFlow [17] 1.046 0.394 6.361 1.113 0.321 0.159 0.225 0.750 5.838 Visualize Results
LSHRAFT [18] 1.256 0.461 7.736 1.276 0.387 0.183 0.226 0.745 7.607 Visualize Results
SemFlow-2view [19] 1.061 0.394 6.492 1.112 0.307 0.177 0.226 0.755 5.936 Visualize Results
OPPFlow [20] 1.042 0.336 6.796 0.879 0.261 0.184 0.227 0.691 5.934 Visualize Results
GMFlow+ [21] 1.028 0.335 6.680 0.868 0.264 0.183 0.227 0.689 5.826 Visualize Results
SEA-RAFT-L [22] 1.309 0.440 8.396 1.171 0.401 0.157 0.227 0.801 7.907 Visualize Results
AMFFlow [23] 1.228 0.431 7.730 1.131 0.370 0.188 0.227 0.720 7.426 Visualize Results
CasFlow [24] 1.760 0.629 10.994 1.392 0.474 0.342 0.228 0.810 11.669 Visualize Results
VideoFlow-BOF [25] 1.005 0.389 6.023 1.029 0.310 0.189 0.229 0.695 5.605 Visualize Results
CFFlow [26] 0.989 0.396 5.819 1.026 0.317 0.218 0.229 0.694 5.470 Visualize Results
VideoFlow-MOF [27] 0.991 0.397 5.832 1.028 0.317 0.218 0.229 0.694 5.484 Visualize Results
MotionFlow+ [28] 1.128 0.431 6.814 1.189 0.356 0.182 0.230 0.766 6.459 Visualize Results
ProtoFormer [29] 1.056 0.355 6.779 0.901 0.288 0.193 0.232 0.719 5.965 Visualize Results
FlowDiffuser [30] 1.016 0.376 6.231 1.078 0.281 0.174 0.233 0.739 5.573 Visualize Results
MemoFlow [31] 1.000 0.399 5.889 1.035 0.320 0.218 0.233 0.708 5.503 Visualize Results
ViCo_VideoFlow_MOF [32] 0.957 0.381 5.642 1.065 0.297 0.171 0.238 0.705 5.126 Visualize Results
gma+allcv [33] 1.154 0.431 7.048 1.173 0.352 0.188 0.239 0.747 6.680 Visualize Results
ProMotion [34] 1.040 0.389 6.350 1.057 0.304 0.184 0.241 0.752 5.704 Visualize Results
BDFlowNet [35] 1.155 0.457 6.849 1.310 0.360 0.188 0.241 0.829 6.477 Visualize Results
MotionFlow [36] 1.158 0.465 6.806 1.312 0.374 0.189 0.242 0.813 6.534 Visualize Results
RAFT-it+_RVC [37] 1.187 0.441 7.260 1.301 0.338 0.181 0.242 0.834 6.723 Visualize Results
EMD-M [38] 1.337 0.418 8.838 1.123 0.320 0.222 0.244 0.825 8.003 Visualize Results
MemFlow-T [39] 1.081 0.430 6.384 1.171 0.351 0.184 0.246 0.750 6.024 Visualize Results
TransFlow [40] 1.058 0.357 6.770 0.876 0.285 0.194 0.246 0.706 5.943 Visualize Results
PRAFlow_RVC [41] 2.475 1.011 14.423 1.658 0.775 0.745 0.248 0.979 17.169 Visualize Results
HMAFlow [42] 1.389 0.459 8.976 1.310 0.363 0.198 0.248 0.837 8.393 Visualize Results
AMFFlow_3f [43] 1.222 0.448 7.530 1.145 0.369 0.188 0.250 0.720 7.258 Visualize Results
APCAFlow [44] 1.155 0.401 7.307 1.122 0.297 0.185 0.251 0.785 6.537 Visualize Results
SAMFlow [45] 0.995 0.384 5.966 1.012 0.293 0.191 0.252 0.760 5.245 Visualize Results
FlowFormer++ [46] 1.073 0.390 6.635 1.099 0.296 0.179 0.252 0.796 5.810 Visualize Results
MatchFlow_GMA_2-view [47] 1.153 0.420 7.124 1.235 0.307 0.186 0.253 0.852 6.342 Visualize Results
MemFlow [48] 1.046 0.426 6.091 1.169 0.308 0.206 0.253 0.778 5.623 Visualize Results
MMAFlow [49] 1.167 0.416 7.289 1.188 0.316 0.185 0.253 0.818 6.545 Visualize Results
MMAFlow [50] 1.179 0.427 7.305 1.228 0.324 0.186 0.254 0.839 6.590 Visualize Results
PVTFlow [51] 1.225 0.452 7.534 1.228 0.370 0.190 0.255 0.782 7.112 Visualize Results
StreamFlow-Baseline [52] 1.234 0.453 7.604 1.199 0.378 0.200 0.257 0.782 7.179 Visualize Results
FlowFormer [53] 1.159 0.422 7.164 1.183 0.326 0.192 0.259 0.822 6.435 Visualize Results
flowformer_val [54] 1.157 0.421 7.153 1.182 0.324 0.192 0.259 0.822 6.417 Visualize Results
GAFlow-FF [55] 1.145 0.415 7.090 1.176 0.315 0.189 0.261 0.824 6.304 Visualize Results
RAFT-CF [56] 1.519 0.501 9.821 1.309 0.424 0.228 0.261 0.827 9.441 Visualize Results
MCPFlow_RVC [57] 1.346 0.480 8.405 1.268 0.401 0.218 0.263 0.816 8.004 Visualize Results
raft+allcv [58] 1.320 0.439 8.505 1.210 0.345 0.199 0.264 0.831 7.742 Visualize Results
MatchFlow_GMA [59] 1.164 0.431 7.130 1.259 0.311 0.197 0.265 0.845 6.387 Visualize Results
ScaleFLow++ [60] 1.332 0.470 8.360 1.253 0.387 0.208 0.265 0.853 7.782 Visualize Results
ICIMG-Net [61] 1.303 0.522 7.671 1.351 0.423 0.278 0.265 0.839 7.574 Visualize Results
GAFlow [62] 1.211 0.467 7.272 1.303 0.349 0.225 0.267 0.876 6.703 Visualize Results
TSA [63] 0.987 0.368 6.036 0.912 0.286 0.222 0.267 0.632 5.422 Visualize Results
MatchFlow_RAFT [64] 1.329 0.477 8.267 1.295 0.391 0.209 0.267 0.877 7.686 Visualize Results
RAFT+AOIR [65] 1.853 0.666 11.550 1.483 0.450 0.414 0.270 0.943 11.924 Visualize Results
AGM-FlowNet [66] 1.147 0.423 7.047 1.155 0.331 0.200 0.270 0.827 6.269 Visualize Results
SplatFlow [67] 1.119 0.511 6.061 1.410 0.394 0.247 0.272 0.868 5.915 Visualize Results
RFPM [68] 1.411 0.494 8.884 1.335 0.400 0.221 0.273 0.879 8.345 Visualize Results
ce_v214 [69] 1.248 0.501 7.329 1.399 0.402 0.214 0.273 0.896 6.928 Visualize Results
test_mem [70] 1.404 0.475 8.977 1.210 0.392 0.230 0.274 0.801 8.469 Visualize Results
OM_CRAFT [71] 1.367 0.509 8.357 1.355 0.427 0.220 0.277 0.874 7.966 Visualize Results
TSGFlow [72] 1.283 0.526 7.448 1.305 0.417 0.288 0.278 0.870 7.264 Visualize Results
AGF-Flow3 [73] 1.409 0.525 8.618 1.433 0.403 0.250 0.278 0.878 8.303 Visualize Results
SKII [74] 1.302 0.532 7.571 1.494 0.422 0.225 0.278 0.931 7.269 Visualize Results
GMA+LCT-Flow [75] 1.408 0.525 8.611 1.428 0.404 0.251 0.279 0.876 8.299 Visualize Results
RAFTwarm+AOIR [76] 1.544 0.551 9.656 1.515 0.412 0.280 0.279 0.941 9.290 Visualize Results
CrossFlow [77] 1.264 0.516 7.358 1.315 0.440 0.252 0.282 0.855 7.122 Visualize Results
SKFlow [78] 1.298 0.567 7.251 1.555 0.443 0.271 0.282 0.950 7.173 Visualize Results
CGCV-GMA [79] 1.373 0.534 8.215 1.439 0.438 0.240 0.283 0.935 7.841 Visualize Results
ACAFlow [80] 1.597 0.663 9.220 1.576 0.649 0.273 0.284 0.885 9.838 Visualize Results
H-v3 [81] 2.452 0.622 17.409 1.433 0.545 0.389 0.284 1.127 16.444 Visualize Results
ce_skii_skii [82] 1.272 0.522 7.390 1.451 0.415 0.227 0.284 0.925 7.011 Visualize Results
PredFlow [83] 1.970 0.757 11.859 1.504 0.550 0.481 0.284 0.972 12.750 1.970 0.757 11.859 1.504 0.550 0.481 0.284 0.972 12.750 Visualize Results
PredFlow [84] 1.970 0.757 11.859 1.504 0.550 0.481 0.284 0.972 12.750 1.970 0.757 11.859 1.504 0.550 0.481 0.284 0.972 12.750 Visualize Results
RAFT-it [85] 1.554 0.612 9.242 1.664 0.514 0.273 0.287 0.971 9.261 Visualize Results
CE_SKII [86] 1.310 0.548 7.530 1.481 0.447 0.245 0.287 0.926 7.314 Visualize Results
KPA-Flow [87] 1.348 0.504 8.232 1.387 0.395 0.229 0.288 0.917 7.652 Visualize Results
EMD-L [88] 1.321 0.504 7.983 1.378 0.398 0.230 0.288 0.904 7.452 Visualize Results
LLA-FLOW+GMA [89] 1.373 0.567 7.949 1.479 0.488 0.249 0.289 0.900 7.894 Visualize Results
SCFlow [90] 1.258 0.451 7.833 1.051 0.349 0.206 0.290 0.782 7.215 Visualize Results
SCV [91] 1.720 0.574 11.076 1.393 0.457 0.373 0.290 0.911 10.782 Visualize Results
SSTM++3kt [92] 1.570 0.532 10.029 1.434 0.438 0.231 0.291 0.903 9.532 Visualize Results
DPCTF [93] 3.542 1.237 22.350 2.271 0.983 0.792 0.291 1.111 25.580 Visualize Results
MODFlow_ft [94] 1.248 0.505 7.298 1.346 0.409 0.243 0.291 0.896 6.840 Visualize Results
ACAFlow [95] 1.581 0.668 9.035 1.572 0.624 0.313 0.292 0.880 9.680 Visualize Results
AGF-Flow2 [96] 2.030 0.791 12.139 1.479 0.508 0.534 0.293 0.955 13.259 Visualize Results
RAFT+LCT-Flow [97] 2.029 0.791 12.131 1.474 0.509 0.535 0.293 0.952 13.255 Visualize Results
CVEFlow [98] 1.351 0.556 7.829 1.477 0.459 0.254 0.295 0.920 7.626 Visualize Results
BD-Flow_finetune [99] 1.312 0.493 7.979 1.324 0.381 0.241 0.295 0.928 7.279 Visualize Results
DEQ-Flow-H [100] 1.498 0.548 9.239 1.427 0.477 0.232 0.296 0.976 8.720 Visualize Results
AMFlow [101] 1.186 0.470 7.014 1.285 0.372 0.214 0.296 0.888 6.315 Visualize Results
SSTM++nws-main [102] 1.628 0.602 9.998 1.654 0.491 0.262 0.298 0.974 9.811 Visualize Results
NASFlow-RAFT [103] 1.613 0.503 10.664 1.339 0.405 0.238 0.298 0.892 9.883 Visualize Results
SSTM++_ttt_nws [104] 1.603 0.590 9.863 1.645 0.485 0.238 0.299 0.982 9.580 Visualize Results
RAFTwarm+OBS [105] 1.593 0.600 9.692 1.532 0.507 0.309 0.300 0.989 9.470 Visualize Results
RAFT-OCTC [106] 1.419 0.541 8.574 1.455 0.442 0.242 0.301 0.940 8.118 Visualize Results
GMA+TCU-aug [107] 1.440 0.613 8.173 1.510 0.542 0.282 0.301 0.916 8.348 Visualize Results
GMFlow_RVC [108] 1.055 0.420 6.227 1.084 0.326 0.227 0.302 0.754 5.513 Visualize Results
Win-Win [109] 1.151 0.531 6.195 1.510 0.399 0.240 0.303 0.975 5.771 Visualize Results
ACAFlow [110] 1.576 0.686 8.839 1.590 0.622 0.350 0.303 0.912 9.501 Visualize Results
SSTM++_ttt_ws [111] 1.585 0.599 9.634 1.665 0.486 0.251 0.304 0.996 9.372 Visualize Results
OM_GMA [112] 1.198 0.472 7.115 1.194 0.375 0.222 0.305 0.826 6.530 Visualize Results
MFCFlow [113] 1.493 0.653 8.335 1.582 0.569 0.350 0.305 0.964 8.657 Visualize Results
SSTM++warm-main [114] 1.571 0.581 9.648 1.661 0.449 0.241 0.305 0.985 9.271 Visualize Results
NASFlow [115] 1.629 0.639 9.708 1.616 0.540 0.334 0.306 1.001 9.718 Visualize Results
SeparableFlow-2views [116] 1.496 0.567 9.075 1.474 0.481 0.257 0.309 0.958 8.691 Visualize Results
RAFT+OBS [117] 1.809 0.655 11.226 1.499 0.532 0.357 0.309 1.001 11.216 Visualize Results
GMA+TCU+aug [118] 1.452 0.606 8.351 1.501 0.509 0.305 0.309 0.923 8.402 Visualize Results
RPKNet [119] 1.315 0.536 7.659 1.387 0.413 0.284 0.310 0.911 7.277 Visualize Results
GMA-two_img [120] 1.391 0.562 8.137 1.512 0.450 0.254 0.310 0.953 7.805 Visualize Results
HD3F+MSDRNet [121] 4.595 1.458 30.167 2.835 1.254 1.024 0.310 1.188 34.124 Visualize Results
CRAFT [122] 1.441 0.611 8.204 1.574 0.552 0.249 0.311 0.991 8.131 Visualize Results
ErrorMatch-GMA [123] 1.446 0.584 8.472 1.503 0.483 0.280 0.311 0.935 8.314 Visualize Results
FTGAN [124] 1.579 0.594 9.609 1.498 0.524 0.264 0.311 0.939 9.416 Visualize Results
COMBO [125] 1.466 0.516 9.206 1.283 0.388 0.276 0.312 0.886 8.595 Visualize Results
SSTM++_reconst [126] 1.612 0.604 9.832 1.654 0.472 0.286 0.312 0.977 9.601 Visualize Results
RAFT-A [127] 2.007 0.868 11.299 1.996 0.684 0.469 0.313 1.076 12.672 Visualize Results
GMFlowNet [128] 1.390 0.520 8.486 1.275 0.395 0.293 0.314 0.991 7.698 Visualize Results
MVFlow [129] 1.526 0.556 9.433 1.487 0.463 0.246 0.314 0.980 8.862 Visualize Results
SCAR [130] 1.579 0.608 9.498 1.613 0.499 0.285 0.314 1.018 9.210 Visualize Results
ErrorMatch-RAFT [131] 1.597 0.645 9.366 1.555 0.546 0.364 0.315 0.981 9.451 Visualize Results
sdex00 [132] 1.753 0.741 10.009 1.639 0.513 0.444 0.316 1.045 10.594 Visualize Results
BD-Flow [133] 1.461 0.527 9.063 1.401 0.407 0.273 0.317 0.969 8.315 Visualize Results
AGFlow [134] 1.431 0.559 8.541 1.501 0.452 0.261 0.319 0.963 8.075 Visualize Results
CGCV-RAFT [135] 1.533 0.575 9.350 1.453 0.466 0.299 0.320 1.006 8.829 Visualize Results
TrepFlow [136] 1.443 0.599 8.316 1.562 0.517 0.270 0.320 0.990 8.099 Visualize Results
RAFTv2-OER-2-view [137] 1.897 0.745 11.304 1.530 0.558 0.475 0.320 1.018 11.854 Visualize Results
GMA-base [138] 1.450 0.591 8.440 1.532 0.470 0.280 0.321 0.951 8.251 Visualize Results
RAFT-DFlow [139] 1.618 0.577 10.104 1.580 0.471 0.255 0.321 1.076 9.367 Visualize Results
SKFlow_RAFT [140] 1.461 0.617 8.346 1.595 0.514 0.307 0.323 1.021 8.173 Visualize Results
FCTR-m [141] 1.524 0.575 9.264 1.512 0.468 0.250 0.325 0.979 8.791 Visualize Results
CVE-RAFT [142] 1.530 0.574 9.319 1.447 0.463 0.295 0.325 1.015 8.754 Visualize Results
SwinTR-RAFT [143] 1.379 0.529 8.304 1.272 0.430 0.277 0.325 0.917 7.726 Visualize Results
SSTM-nws [144] 2.125 0.789 13.029 1.916 0.679 0.373 0.325 1.130 13.474 Visualize Results
submission5367 [145] 1.601 0.636 9.471 1.613 0.545 0.312 0.326 0.971 9.456 Visualize Results
RAFT-FS [146] 1.646 0.634 9.895 1.663 0.531 0.281 0.328 1.027 9.681 Visualize Results
RAFTv2-OER-warm-start [147] 1.594 0.625 9.487 1.567 0.512 0.339 0.328 1.014 9.271 Visualize Results
MFlow [148] 1.676 0.548 10.875 1.384 0.417 0.309 0.329 0.971 10.071 Visualize Results
CSFlow-2-view [149] 1.626 0.584 10.123 1.527 0.492 0.254 0.330 1.015 9.539 Visualize Results
RAFT-base [150] 2.071 0.859 11.961 1.600 0.582 0.567 0.330 1.035 13.219 Visualize Results
GMA [151] 1.388 0.582 7.963 1.537 0.461 0.278 0.331 0.963 7.662 Visualize Results
FCTR [152] 1.744 0.570 11.319 1.438 0.466 0.256 0.332 0.961 10.648 Visualize Results
OM_RAFT [153] 1.544 0.591 9.312 1.563 0.480 0.264 0.333 0.991 8.891 Visualize Results
GMA-FS [154] 1.430 0.602 8.171 1.579 0.470 0.263 0.333 0.977 7.961 Visualize Results
L2L-Flow-ext [155] 1.816 0.664 11.208 1.546 0.541 0.374 0.334 1.019 11.098 Visualize Results
LLA-Flow [156] 1.506 0.572 9.114 1.469 0.467 0.258 0.335 0.992 8.552 Visualize Results
DIP [157] 1.435 0.519 8.919 1.102 0.407 0.312 0.336 0.754 8.546 Visualize Results
MFFC [158] 1.827 0.711 10.951 1.561 0.535 0.412 0.336 1.015 11.201 Visualize Results
Deformable_RAFT [159] 1.667 0.627 10.151 1.631 0.519 0.277 0.338 0.993 9.897 Visualize Results
raft-jm [160] 1.668 0.644 10.014 1.686 0.553 0.276 0.339 1.037 9.785 Visualize Results
RAFT-illumination [161] 2.028 0.800 12.055 1.695 0.629 0.473 0.340 1.057 12.766 Visualize Results
RAFT [162] 1.609 0.623 9.647 1.621 0.518 0.301 0.341 1.036 9.288 Visualize Results
L2L-Flow-ext-warm [163] 1.648 0.622 10.017 1.641 0.516 0.282 0.342 1.018 9.657 Visualize Results
MFR [164] 1.545 0.593 9.295 1.536 0.477 0.299 0.348 1.023 8.736 Visualize Results
MF2C [165] 1.664 0.689 9.612 1.663 0.596 0.372 0.348 1.060 9.651 Visualize Results
Fun-MS-RAFT [166] 2.497 0.859 15.876 2.371 0.725 0.346 0.351 1.182 16.350 Visualize Results
RAFT-TF_RVC [167] 1.837 0.776 10.499 2.125 0.652 0.321 0.352 1.193 10.767 Visualize Results
RAFT-GT-ft [168] 2.427 0.970 14.332 1.803 0.668 0.613 0.352 1.141 15.848 Visualize Results
MeFlow [169] 2.054 0.822 12.109 1.750 0.642 0.517 0.352 1.066 12.894 Visualize Results
DCN-Flow [170] 2.326 0.904 13.930 1.739 0.618 0.594 0.353 1.080 15.138 Visualize Results
PPAC-HD3 [171] 4.589 1.507 29.751 2.788 1.340 1.068 0.355 1.289 33.624 Visualize Results
HCVNet [172] 1.695 0.644 10.267 1.624 0.544 0.309 0.355 1.067 9.865 Visualize Results
sdex001 [173] 1.466 0.661 8.017 1.858 0.496 0.301 0.356 1.112 7.812 Visualize Results
HD3-Flow-OER [174] 4.574 1.535 29.388 2.689 1.386 1.125 0.357 1.366 33.305 Visualize Results
MaskFlownet [175] 2.521 0.989 15.032 2.742 0.908 0.291 0.361 1.285 16.261 Visualize Results
LSM_FLOW_RVC [176] 3.142 1.395 17.394 2.557 1.091 0.873 0.361 1.202 21.652 Visualize Results
OADFlow [177] 2.168 0.832 13.083 1.790 0.658 0.473 0.364 1.078 13.772 Visualize Results
ScaleRAFT [178] 1.883 0.591 12.422 1.465 0.456 0.292 0.366 1.030 11.480 Visualize Results
RAFTv1-OER-2-view [179] 2.534 0.915 15.743 1.968 0.653 0.532 0.367 1.246 16.413 Visualize Results
RAFT+ConvUp [180] 2.160 0.700 14.073 1.739 0.585 0.386 0.369 1.190 13.409 Visualize Results
DICL_update [181] 2.121 0.764 13.200 2.220 0.581 0.315 0.369 1.169 13.131 Visualize Results
ProtoFormer [182] 1.441 0.566 8.569 1.434 0.417 0.280 0.371 1.005 7.802 Visualize Results
RAFT+NCUP [183] 1.661 0.678 9.666 1.872 0.541 0.302 0.371 1.102 9.402 Visualize Results
DICL-Flow+ [184] 1.863 0.741 11.014 2.222 0.519 0.330 0.380 1.167 10.905 Visualize Results
DICL-Flow [185] 2.634 0.967 16.237 2.494 0.621 0.492 0.388 1.349 16.895 Visualize Results
IOFPL-ft [186] 4.394 1.611 27.128 3.059 1.421 0.943 0.391 1.292 31.812 Visualize Results
HD3-Flow [187] 4.788 1.622 30.633 3.225 1.379 1.117 0.395 1.410 34.802 Visualize Results
Flow1D-OER [188] 2.146 0.850 12.713 2.006 0.764 0.458 0.397 1.264 12.957 Visualize Results
SelFlow [189] 3.745 1.449 22.502 3.616 1.374 0.592 0.397 1.570 25.664 Visualize Results
SMURF [190] 3.152 1.550 16.233 3.141 1.310 0.858 0.398 1.371 21.152 Visualize Results
IOFPL-CVr8-ft [191] 3.757 1.337 23.522 2.803 1.141 0.765 0.398 1.288 26.430 Visualize Results
DA_opticalflow [192] 2.254 0.737 14.639 1.790 0.612 0.374 0.400 1.198 14.026 Visualize Results
MobileFlow [193] 1.917 0.716 11.701 1.875 0.575 0.361 0.404 1.245 11.047 Visualize Results
ADLAB-PRFlow [194] 1.885 0.633 12.104 1.599 0.472 0.307 0.406 1.009 11.350 Visualize Results
ADW [195] 2.504 1.158 13.487 2.822 0.987 0.549 0.412 1.457 15.425 Visualize Results
YOIO [196] 1.365 0.599 7.584 1.453 0.492 0.341 0.413 1.113 6.673 Visualize Results
Fun-RAFT [197] 2.944 1.054 18.368 2.851 0.909 0.435 0.415 1.377 19.300 Visualize Results
MaskFlownet-S [198] 2.771 1.077 16.608 2.901 0.996 0.342 0.419 1.404 17.777 Visualize Results
ScaleFlow++_SAG [199] 2.040 0.762 12.472 1.987 0.614 0.449 0.420 1.439 11.540 Visualize Results
RAPIDFlow [200] 2.038 0.849 11.737 2.067 0.650 0.472 0.424 1.266 11.916 Visualize Results
CVPR-1235 [201] 1.889 0.755 11.135 1.972 0.652 0.307 0.431 1.324 10.490 Visualize Results
vcn+MSDRNet [202] 2.595 0.889 16.528 2.632 0.694 0.350 0.435 1.279 16.526 Visualize Results
ScaleFlow_GS58 [203] 2.353 0.876 14.412 2.301 0.743 0.433 0.439 1.472 13.991 Visualize Results
ISDAFlow [204] 2.101 0.878 12.080 1.954 0.731 0.574 0.441 1.428 11.976 Visualize Results
RAFT_Chairs_Things [205] 3.173 0.970 21.173 2.223 0.864 0.573 0.442 1.433 20.963 Visualize Results
MR-Flow [206] 2.527 0.954 15.365 2.866 0.710 0.420 0.446 1.715 14.826 Visualize Results
DistillFlow+ft [207] 3.487 1.479 19.904 3.894 1.415 0.488 0.449 1.742 22.824 Visualize Results
PWC-Net+KF [208] 3.850 1.595 22.276 3.664 1.302 0.734 0.459 1.957 25.289 Visualize Results
PWC-Net+KF2 [209] 3.753 1.588 21.445 3.657 1.298 0.723 0.460 1.863 24.700 Visualize Results
ADW-Net [210] 2.731 0.924 17.484 2.365 0.759 0.478 0.461 1.466 17.066 Visualize Results
metaFlow [211] 2.710 1.089 15.931 2.738 0.706 0.602 0.465 1.456 16.890 Visualize Results
HMFlow [212] 3.206 1.122 20.210 2.786 0.957 0.584 0.467 1.693 20.470 Visualize Results
ProFlow [213] 2.818 1.027 17.428 2.892 0.751 0.496 0.469 1.626 17.369 Visualize Results
less_iter_fine [214] 3.313 1.237 20.261 2.421 0.900 0.731 0.469 1.472 21.891 Visualize Results
DCVNet [215] 2.364 1.152 12.220 2.570 0.980 0.674 0.473 1.660 13.417 Visualize Results
NccFlow [216] 4.264 1.674 25.412 3.952 1.717 0.710 0.473 2.062 28.432 Visualize Results
SPM-BPv2 [217] 3.515 1.020 23.865 2.603 0.841 0.521 0.474 1.773 22.830 Visualize Results
RAFT-VM [218] 2.858 1.124 17.015 2.658 0.961 0.555 0.477 1.612 17.701 Visualize Results
EFlow-M-tile [219] 2.077 0.806 12.430 1.912 0.704 0.401 0.485 1.338 11.759 Visualize Results
ProFlow_ROB [220] 2.709 1.013 16.549 2.843 0.723 0.518 0.485 1.586 16.470 Visualize Results
SegFlow153 [221] 4.151 1.246 27.855 3.072 1.143 0.656 0.486 2.000 27.563 Visualize Results
PatchBatch-CENT+SD [222] 5.789 2.743 30.599 5.232 2.756 1.492 0.492 1.801 41.746 Visualize Results
Scale-flow++_GS58 [223] 2.153 0.708 13.956 1.994 0.588 0.266 0.494 1.476 12.042 Visualize Results
AllTracker [224] 1.673 0.652 9.974 1.617 0.536 0.345 0.496 1.203 8.634 Visualize Results
GMFlow [225] 1.736 0.653 10.555 1.232 0.568 0.462 0.499 0.971 9.724 Visualize Results
ARFlow-mv-ft [226] 3.197 1.358 18.216 3.446 1.240 0.500 0.499 1.624 20.410 Visualize Results
LiteFlowNet [227] 4.539 1.630 28.291 3.274 1.438 0.928 0.500 1.733 31.412 Visualize Results
VCN_RVC [228] 2.827 1.134 16.645 2.864 0.922 0.524 0.506 1.480 17.614 Visualize Results
UFlow [229] 5.205 2.036 31.058 4.000 1.921 1.199 0.507 1.969 36.382 Visualize Results
Flow1D [230] 2.238 0.966 12.585 2.181 0.876 0.545 0.509 1.372 12.889 Visualize Results
PRichFlow [231] 3.967 1.545 23.751 3.865 1.518 0.558 0.512 1.758 26.496 Visualize Results
STaRFlow [232] 2.718 1.111 15.839 2.738 0.891 0.521 0.512 1.372 16.939 Visualize Results
ContinualFlow_ROB [233] 3.341 1.752 16.292 4.057 1.656 0.792 0.512 1.941 20.755 Visualize Results
RichFlow-ft-fnl [234] 4.315 1.609 26.416 3.943 1.574 0.644 0.515 1.774 29.363 Visualize Results
ISDAFlowRAFT [235] 2.550 1.034 14.922 2.652 0.861 0.507 0.520 1.668 14.760 Visualize Results
IRR-PWC-OER [236] 3.669 1.438 21.873 3.043 1.319 0.811 0.523 1.672 24.126 Visualize Results
S2F-IF [237] 3.500 0.988 23.986 2.629 0.816 0.533 0.524 1.976 21.960 Visualize Results
FlowSAC_ff [238] 3.346 0.972 22.712 2.666 0.822 0.444 0.524 1.986 20.648 Visualize Results
RAFT+LCV [239] 2.489 1.002 14.630 2.793 0.686 0.470 0.525 1.448 14.769 Visualize Results
SENSE [240] 3.599 1.375 21.752 3.102 1.144 0.720 0.527 1.640 23.598 Visualize Results
AL-OF-r0.2 [241] 3.790 1.435 23.016 3.739 1.389 0.443 0.531 2.026 24.257 Visualize Results
SegFlow193 [242] 4.893 1.570 31.973 3.375 1.450 1.157 0.533 2.064 33.382 Visualize Results
ScopeFlow [243] 3.592 1.400 21.497 3.457 1.261 0.592 0.534 1.742 23.286 Visualize Results
IRR-PWC [244] 3.844 1.472 23.220 3.509 1.296 0.721 0.535 1.724 25.430 Visualize Results
SAG156+RAFT [245] 2.639 0.968 16.279 2.519 0.834 0.455 0.543 1.619 15.523 Visualize Results
FlowFields [246] 3.748 1.056 25.700 2.784 0.878 0.570 0.546 2.110 23.602 Visualize Results
CompactFlow [247] 3.455 1.294 21.100 3.327 1.180 0.498 0.547 1.658 22.261 Visualize Results
less_iteration [248] 3.492 1.261 21.701 2.469 0.929 0.751 0.547 1.558 22.803 Visualize Results
DIP-Flow [249] 3.103 0.881 21.227 2.574 0.681 0.419 0.548 1.801 18.979 Visualize Results
SegFlow113 [250] 3.869 1.132 26.210 2.855 0.942 0.667 0.550 1.945 25.018 Visualize Results
CompactFlow-woscv [251] 3.596 1.374 21.734 3.399 1.314 0.539 0.551 1.672 23.388 Visualize Results
ProbFlowFields [252] 3.631 1.061 24.603 2.719 0.887 0.607 0.551 2.105 22.619 Visualize Results
Classic+NL-fast [253] 9.129 4.725 44.956 7.157 4.974 3.331 0.558 2.812 66.935 Visualize Results
SfM-PM [254] 2.910 1.016 18.357 2.797 0.756 0.479 0.559 1.732 17.431 Visualize Results
LiteFlowNet3 [255] 2.994 1.148 18.077 3.000 0.985 0.498 0.559 1.670 18.302 Visualize Results
FlowFields++ [256] 2.943 0.850 20.027 2.550 0.603 0.403 0.560 1.859 17.401 Visualize Results
SegFlow73 [257] 3.463 1.008 23.497 2.682 0.781 0.522 0.563 1.977 21.466 Visualize Results
PWC-Net-OER [258] 3.731 1.659 20.639 3.573 1.506 0.805 0.565 1.953 23.758 Visualize Results
RichFlow-ft [259] 3.541 1.335 21.553 3.527 1.201 0.538 0.566 1.857 22.404 Visualize Results
MirrorFlow [260] 3.316 1.338 19.470 3.684 1.165 0.487 0.566 1.853 20.523 Visualize Results
TIMCflow [261] 3.979 1.249 26.243 3.775 0.904 0.540 0.567 2.079 25.518 Visualize Results
PGM-C [262] 3.234 0.929 22.045 2.724 0.659 0.424 0.567 1.999 19.467 Visualize Results
AOD [263] 6.901 2.861 39.768 4.687 2.693 2.153 0.567 2.850 48.101 Visualize Results
VCN-OER [264] 2.810 1.103 16.713 2.716 0.967 0.527 0.567 1.605 16.843 Visualize Results
InterpoNet_ff [265] 3.952 1.232 26.121 3.600 0.946 0.573 0.571 2.228 24.900 Visualize Results
PMC-PWC_without_edge_loss [266] 3.185 1.189 19.479 2.913 1.004 0.571 0.572 1.688 19.788 Visualize Results
Classic+NL [267] 7.961 3.770 42.079 6.191 3.911 2.509 0.573 2.694 57.374 Visualize Results
LiteFlowNet3-S [268] 3.028 1.173 18.182 3.079 0.996 0.527 0.574 1.646 18.566 Visualize Results
Flownet2-IAER [269] 4.061 1.483 25.115 3.324 1.377 0.808 0.575 1.814 26.829 Visualize Results
IHBPFlow [270] 4.347 1.476 27.746 3.573 1.155 0.895 0.577 2.245 28.145 Visualize Results
FC-2Layers-FF [271] 6.781 3.053 37.144 5.841 3.390 1.688 0.580 3.308 45.962 Visualize Results
LocalLayering [272] 5.820 2.143 35.784 3.817 2.342 1.399 0.580 2.461 39.976 Visualize Results
GCA-Net-ft+ [273] 2.695 0.980 16.699 2.671 0.837 0.392 0.581 1.423 16.283 Visualize Results
OF-OEF [274] 4.159 1.716 24.119 3.813 1.541 0.771 0.581 1.948 27.304 Visualize Results
PatchWMF-OF [275] 5.550 1.781 36.257 3.339 1.843 1.277 0.581 2.612 37.319 Visualize Results
InterpoNet_df [276] 3.862 1.193 25.632 3.613 0.885 0.508 0.581 2.253 24.038 Visualize Results
FF++_ROB [277] 3.953 1.148 26.836 3.255 0.910 0.519 0.582 2.351 24.562 Visualize Results
JOF [278] 6.920 3.080 38.195 5.983 3.416 1.678 0.583 2.474 49.143 Visualize Results
DiscreteFlow+OIR [279] 3.331 0.942 22.817 2.794 0.712 0.442 0.583 1.948 20.318 Visualize Results
tfFlowNet2+GLR [280] 4.594 1.736 27.918 3.728 1.566 1.082 0.584 1.963 30.888 Visualize Results
CVENG22+RIC [281] 4.834 1.706 30.335 4.048 1.594 0.944 0.584 2.463 31.675 Visualize Results
DCFlow+KF2 [282] 3.645 1.149 23.992 3.037 0.932 0.640 0.586 1.974 22.867 Visualize Results
PatchBatch+Inter [283] 3.624 1.324 22.397 3.076 1.115 0.673 0.589 1.824 23.062 Visualize Results
A-A [284] 4.430 1.644 27.193 3.527 1.594 0.890 0.589 1.706 30.123 Visualize Results
PH-Flow [285] 4.388 1.714 26.202 3.612 1.713 0.834 0.590 2.430 27.997 Visualize Results
CPM-Flow [286] 3.557 1.189 22.889 3.032 0.973 0.613 0.592 2.064 21.900 Visualize Results
GPNet [287] 2.766 1.148 15.994 3.003 1.035 0.396 0.592 1.656 16.269 Visualize Results
CoT-AMFlow [288] 3.956 1.523 23.818 3.585 1.375 0.760 0.592 2.002 25.391 Visualize Results
FlowFields+ [289] 3.102 0.820 21.718 2.340 0.616 0.373 0.593 1.865 18.549 Visualize Results
DC-RAFT [290] 2.362 1.084 12.769 2.173 0.903 0.597 0.594 1.425 Visualize Results
LiteFlowNet2 [291] 3.483 1.383 20.637 3.293 1.263 0.629 0.597 1.772 21.976 Visualize Results
FlowNet2-ft-sintel [292] 4.157 1.557 25.403 3.272 1.461 0.856 0.597 1.890 27.347 Visualize Results
DCFlow+KF [293] 3.585 1.142 23.502 3.036 0.921 0.630 0.597 2.017 22.208 Visualize Results
WLIF-Flow [294] 5.734 1.759 38.125 3.242 1.818 1.296 0.597 2.512 39.036 Visualize Results
WRTflow [295] 8.236 4.048 42.320 6.413 4.250 2.774 0.598 3.106 58.550 Visualize Results
Semantic_Lattice [296] 3.838 1.700 21.304 3.855 1.434 0.795 0.599 1.995 24.396 Visualize Results
MLDP-OF [297] 7.297 3.260 40.183 5.581 3.304 2.007 0.600 2.916 51.146 Visualize Results
RicFlow [298] 3.550 1.264 22.220 3.248 1.023 0.576 0.601 2.203 21.465 Visualize Results
GCA-Net [299] 2.947 1.032 18.585 2.900 0.830 0.456 0.602 1.645 17.753 Visualize Results
AL-OF-r0.1 [300] 4.062 1.629 23.935 3.828 1.522 0.670 0.604 2.121 25.952 Visualize Results
OF_OCC_LD [301] 9.675 5.296 45.288 7.996 5.632 3.694 0.605 3.025 70.740 Visualize Results
PWC-Net [302] 4.386 1.719 26.166 4.282 1.657 0.674 0.606 2.070 28.793 Visualize Results
Flownet2-IA [303] 4.114 1.520 25.304 3.530 1.377 0.809 0.606 1.877 26.968 Visualize Results
VCN+LCV [304] 2.833 1.093 17.039 3.210 0.875 0.400 0.607 1.607 16.860 Visualize Results
ARFlow+LCT-Flow [305] 4.341 1.680 26.067 3.996 1.697 0.598 0.610 2.327 27.758 Visualize Results
AGIF+OF [306] 5.766 1.695 38.936 3.034 1.709 1.329 0.613 2.554 39.121 Visualize Results
GlobalPatchCollider [307] 4.134 1.432 26.179 3.914 1.268 0.554 0.613 2.232 26.222 Visualize Results
CPM_AUG [308] 3.609 1.135 23.804 2.945 0.935 0.516 0.615 2.099 22.137 Visualize Results
CPM2 [309] 3.253 0.980 21.812 2.663 0.751 0.416 0.615 1.954 19.503 Visualize Results
MPIF [310] 3.111 1.134 19.218 3.070 0.939 0.523 0.616 1.980 18.220 Visualize Results
PWC-Net_RVC [311] 3.897 1.726 21.637 3.950 1.425 0.812 0.618 2.033 24.705 Visualize Results
SAMFL [312] 4.477 1.763 26.643 3.946 1.623 0.811 0.618 1.860 29.995 Visualize Results
Channel-Flow [313] 7.023 3.086 39.084 5.411 3.236 1.918 0.624 2.791 49.021 Visualize Results
UnSAMFlow [314] 3.926 1.671 22.341 3.785 1.602 0.707 0.628 2.100 24.744 Visualize Results
PMF [315] 5.378 1.858 34.102 3.877 1.835 1.235 0.628 2.428 36.128 Visualize Results
StruPyNet-ft [316] 4.401 1.573 27.503 3.613 1.449 0.747 0.630 2.021 28.915 Visualize Results
UnsupSimFlow [317] 5.926 2.159 36.655 4.302 1.977 1.217 0.631 2.508 40.503 Visualize Results
PST [318] 3.110 0.942 20.809 2.759 0.664 0.378 0.635 2.069 17.919 Visualize Results
PMC-PWC_edge_loss [319] 3.173 1.188 19.374 2.882 1.009 0.562 0.636 1.749 19.218 Visualize Results
NASFlow-PWC [320] 3.448 1.398 20.181 2.927 1.106 0.792 0.637 1.517 22.093 Visualize Results
InterpoNet_cpm [321] 4.086 1.371 26.222 3.992 1.064 0.569 0.637 2.325 25.466 Visualize Results
Classic+NLP [322] 6.731 2.949 37.545 5.573 3.291 1.648 0.638 3.296 45.290 Visualize Results
MDP-Flow2 [323] 5.837 1.869 38.158 3.210 1.913 1.441 0.640 2.603 39.459 Visualize Results
SPM-BP [324] 5.202 1.815 32.839 4.008 1.704 1.179 0.643 2.576 34.214 Visualize Results
F2PD_JJN [325] 4.604 1.925 26.456 3.764 1.633 1.232 0.643 2.074 30.396 Visualize Results
DDCNet_Stacked [326] 6.137 3.003 31.681 4.937 2.983 1.995 0.643 2.824 41.406 Visualize Results
EFlow-M [327] 2.980 1.151 17.898 2.383 1.038 0.636 0.643 1.567 18.004 Visualize Results
FlowNet2 [328] 3.959 1.468 24.294 3.089 1.319 0.920 0.643 1.898 25.422 Visualize Results
VCN [329] 2.808 1.108 16.682 3.267 0.867 0.418 0.646 1.669 16.302 Visualize Results
PWC_acn [330] 4.191 1.694 24.584 3.315 1.346 0.980 0.647 1.754 27.699 Visualize Results
OAR-Flow [331] 6.227 2.760 34.455 5.639 3.096 1.375 0.648 3.132 41.378 Visualize Results
FlowFieldsCNN [332] 3.778 0.996 26.469 2.604 0.796 0.631 0.648 2.017 23.582 Visualize Results
AggregFlow [333] 4.754 1.694 29.685 3.705 1.603 0.981 0.650 2.251 31.184 Visualize Results
DDCNet_Multires_ft_sintel [334] 5.342 2.666 27.171 4.643 2.761 1.588 0.656 2.750 34.864 Visualize Results
StruPyNet [335] 4.517 1.728 27.290 3.786 1.755 0.850 0.659 2.227 29.238 Visualize Results
CAR_100 [336] 4.000 1.607 23.550 3.865 1.499 0.641 0.660 2.154 25.083 Visualize Results
AugFNG_ROB [337] 3.606 1.603 19.939 3.637 1.376 0.868 0.666 2.142 21.736 Visualize Results
FGI [338] 4.664 1.540 30.110 3.771 1.336 0.850 0.669 2.310 30.185 Visualize Results
UlDENet [339] 3.496 1.437 20.305 3.937 1.269 0.454 0.669 2.281 20.491 Visualize Results
MDFlow [340] 4.161 1.463 26.193 3.805 1.406 0.506 0.671 2.315 25.982 Visualize Results
EgFlow-cl [341] 6.580 2.706 38.163 4.563 2.463 2.015 0.671 2.449 45.930 Visualize Results
STDC-Flow [342] 6.989 3.235 37.557 6.225 3.619 1.738 0.674 2.873 48.289 Visualize Results
STC-Flow [343] 3.515 1.443 20.438 3.750 1.340 0.539 0.674 2.257 20.680 Visualize Results
M2FLOW [344] 3.378 1.316 20.214 3.294 1.155 0.577 0.675 1.989 20.174 Visualize Results
AL-OF-r0.05 [345] 3.959 1.454 24.417 3.891 1.365 0.455 0.678 2.384 24.083 Visualize Results
F3-MPLF [346] 4.771 2.063 26.863 3.458 1.809 1.244 0.678 1.884 32.091 Visualize Results
CARflow-mv [347] 3.425 1.275 20.998 3.508 1.126 0.423 0.679 2.167 20.139 Visualize Results
tfFlowNet2 [348] 4.486 1.684 27.364 3.694 1.477 1.064 0.681 2.078 29.232 Visualize Results
SparseFlow [349] 6.197 2.357 37.460 4.642 2.273 1.392 0.681 2.533 42.422 Visualize Results
HAST [350] 6.802 3.081 37.112 4.641 3.111 2.245 0.683 3.022 46.330 Visualize Results
NNF-Local [351] 5.386 1.397 37.896 2.722 1.341 1.004 0.683 2.245 36.342 Visualize Results
ADF-Scaleflow [352] 2.568 0.911 16.066 2.436 0.756 0.418 0.683 1.682 14.056 Visualize Results
IRR-PWC_RVC [353] 3.785 2.039 18.039 4.046 1.703 1.039 0.684 2.114 23.234 Visualize Results
SegFlow33 [354] 3.356 1.033 22.322 2.592 0.769 0.524 0.686 1.937 20.062 Visualize Results
CVENG22+Epic [355] 4.592 1.506 29.757 3.650 1.329 0.889 0.687 2.290 29.562 Visualize Results
DDCNet_stacked2 [356] 5.342 2.677 27.075 4.770 2.763 1.562 0.688 2.837 34.486 Visualize Results
ContFusion [357] 6.263 2.518 36.767 5.092 2.801 1.302 0.694 3.115 41.506 Visualize Results
EPMNet [358] 3.986 1.502 24.251 3.230 1.349 0.908 0.695 1.981 25.181 Visualize Results
EdgeFlow [359] 2.300 1.134 11.781 2.765 0.987 0.580 0.695 1.773 11.507 Visualize Results
MFF [360] 3.423 1.381 20.099 3.783 1.233 0.486 0.698 2.144 20.062 Visualize Results
FPCR-Net2 [361] 4.074 1.692 23.519 3.761 1.550 0.798 0.699 2.157 25.483 Visualize Results
FPCR-Net [362] 4.074 1.692 23.516 3.760 1.550 0.798 0.700 2.157 25.479 Visualize Results
ARFlow-mv [363] 4.494 1.887 25.801 4.415 1.853 0.794 0.700 2.299 28.676 Visualize Results
DCFlow [364] 3.537 1.103 23.394 2.897 0.868 0.632 0.703 2.015 21.296 Visualize Results
DiscreteFlow [365] 3.567 1.108 23.626 3.398 0.799 0.446 0.703 2.277 20.906 Visualize Results
InterpoNet_dm [366] 3.973 1.412 24.852 4.015 1.032 0.636 0.706 2.142 24.619 Visualize Results
DefFlowP [367] 4.334 2.131 22.272 4.271 1.910 1.206 0.710 2.679 26.284 Visualize Results
SimpleFlow [368] 12.617 7.848 51.435 10.693 8.422 6.170 0.711 8.411 81.786 Visualize Results
EpicFlow [369] 4.115 1.360 26.595 3.660 1.079 0.599 0.712 2.117 25.859 Visualize Results
OCRAFT [370] 2.431 0.896 14.958 2.090 0.677 0.577 0.713 1.333 13.630 Visualize Results
FlowSAC_dcf [371] 3.600 1.161 23.506 2.972 0.930 0.712 0.716 2.121 21.502 Visualize Results
ROF-NND [372] 8.061 3.944 41.603 6.365 4.145 2.756 0.717 3.301 56.051 Visualize Results
GANFlow [373] 4.131 1.770 23.423 4.192 1.704 0.716 0.718 2.259 25.636 Visualize Results
DistillFlow [374] 4.230 1.548 26.131 3.965 1.541 0.491 0.720 2.502 25.865 Visualize Results
risc [375] 3.005 1.150 18.147 2.930 0.908 0.607 0.721 1.957 16.885 Visualize Results
GeoFlow [376] 6.527 2.420 40.043 3.945 2.193 1.857 0.723 2.620 44.833 Visualize Results
ricom20201202 [377] 3.002 1.150 18.125 2.915 0.911 0.609 0.723 1.949 16.869 Visualize Results
RICBCDN [378] 3.080 1.212 18.319 3.241 0.945 0.577 0.724 2.077 17.197 Visualize Results
COF_2019 [379] 6.171 2.596 35.298 5.385 2.883 1.263 0.725 3.298 40.142 Visualize Results
IIOF-NLDP [380] 7.796 3.806 40.287 6.651 4.175 2.300 0.731 3.328 53.670 Visualize Results
Lavon [381] 4.120 1.603 24.631 3.162 1.359 1.038 0.736 2.029 25.968 Visualize Results
RLOF_DENSE [382] 7.977 3.887 41.315 6.689 4.005 2.415 0.739 3.080 55.766 Visualize Results
MDFlow-Fast [383] 4.733 1.673 29.718 4.085 1.597 0.674 0.742 2.439 30.125 Visualize Results
CNet [384] 6.866 3.122 37.403 4.890 3.002 2.283 0.743 2.405 48.087 Visualize Results
CARflow [385] 3.660 1.373 22.346 3.749 1.252 0.455 0.745 2.482 21.007 Visualize Results
OAS-Net [386] 3.653 1.490 21.322 3.809 1.393 0.587 0.749 2.129 21.783 Visualize Results
PWC-Net+ [387] 3.454 1.413 20.116 3.917 1.247 0.490 0.751 2.230 19.846 Visualize Results
pwc_xx [388] 5.767 2.495 32.479 4.493 2.229 1.628 0.752 2.121 39.523 Visualize Results
DMF_ROB [389] 5.368 1.742 34.899 4.271 1.613 0.831 0.753 2.511 35.180 Visualize Results
AnisoHuber.L1 [390] 12.642 7.983 50.472 10.457 8.675 6.320 0.753 9.976 77.835 Visualize Results
SDFlow [391] 4.080 1.393 26.037 3.680 1.248 0.583 0.757 2.352 24.794 Visualize Results
ICALD [392] 6.002 2.376 35.550 4.835 2.636 1.213 0.758 3.459 38.169 Visualize Results
Devon [393] 4.343 1.742 25.577 4.115 1.531 0.816 0.763 2.449 26.716 Visualize Results
FlowNetC+ft+v [394] 6.081 2.576 34.620 5.079 2.371 1.480 0.764 2.686 40.676 Visualize Results
SelFlow [395] 6.555 2.665 38.298 4.816 2.532 1.661 0.766 2.277 45.691 Visualize Results
FlowNetS+ft+v [396] 6.158 2.800 33.491 5.535 2.687 1.563 0.766 2.938 40.686 Visualize Results
ARFlow-base [397] 4.512 1.839 26.359 4.400 1.804 0.672 0.774 2.535 27.895 Visualize Results
SVFilterOh [398] 5.540 2.043 34.067 3.875 1.865 1.625 0.778 2.713 36.033 Visualize Results
FastFlow [399] 3.997 1.832 21.653 4.469 1.719 0.833 0.779 2.538 23.496 Visualize Results
RAFT-GT [400] 4.061 1.590 24.259 3.289 1.377 0.974 0.780 1.828 25.771 Visualize Results
MRDFlow [401] 3.762 1.216 24.557 3.362 0.959 0.404 0.786 2.340 22.001 Visualize Results
DeepDiscreteFlow [402] 3.863 1.296 24.820 3.077 0.975 0.803 0.794 2.024 23.575 Visualize Results
PPM [403] 4.026 1.167 27.353 2.783 0.847 0.690 0.797 2.093 24.748 Visualize Results
FastFlowNet-ft+ [404] 4.193 1.648 24.992 4.196 1.483 0.696 0.798 2.368 25.490 Visualize Results
DeepFlow2 [405] 4.891 1.403 33.317 3.714 1.119 0.626 0.800 2.210 31.690 Visualize Results
ARFlow [406] 4.782 1.908 28.261 4.413 1.865 0.768 0.807 2.576 29.893 Visualize Results
Pwc_ps [407] 6.199 2.631 35.330 4.653 2.370 1.718 0.808 2.241 42.582 Visualize Results
CompactFlowNet [408] 4.431 1.802 25.898 3.879 1.495 1.043 0.810 2.095 28.077 Visualize Results
Steered-L1 [409] 10.864 6.018 50.244 7.976 6.187 4.832 0.811 6.049 72.292 Visualize Results
FastFlowNet [410] 4.886 1.789 30.182 4.252 1.638 0.912 0.814 2.363 31.242 Visualize Results
OIFlow [411] 4.259 1.731 24.918 4.197 1.609 0.658 0.819 2.563 25.473 Visualize Results
SPyNet+ft [412] 6.640 3.013 36.190 5.501 3.122 1.719 0.832 3.343 43.442 Visualize Results
FDFlowNet [413] 3.707 1.543 21.376 3.814 1.421 0.690 0.837 2.198 21.630 Visualize Results
DDCNet_B0_tf_sintel [414] 7.198 3.847 34.528 6.103 3.886 2.611 0.839 3.735 47.119 Visualize Results
TF+OFM [415] 4.917 1.874 29.735 3.676 1.689 1.309 0.839 2.349 31.391 Visualize Results
FullFlow+KF [416] 3.598 1.247 22.779 2.957 0.977 0.677 0.844 1.974 21.212 Visualize Results
SJTU_PAMI418 [417] 3.576 1.542 20.193 4.123 1.409 0.555 0.851 2.328 20.156 Visualize Results
COF [418] 6.496 2.849 36.216 5.679 3.176 1.450 0.859 3.656 41.334 Visualize Results
VCN-WARP [419] 3.177 1.421 17.485 3.227 1.226 0.827 0.859 1.845 17.892 Visualize Results
DDFlow [420] 6.176 2.269 38.053 4.208 2.084 1.416 0.860 2.562 41.337 Visualize Results
ResPWCR_ROB [421] 5.674 3.138 26.380 4.941 2.769 2.127 0.879 2.506 37.143 Visualize Results
SparseFlowFused [422] 5.257 1.627 34.834 4.211 1.397 0.729 0.880 2.567 33.489 Visualize Results
htjnewfull [423] 3.674 1.581 20.723 3.029 1.329 1.077 0.881 1.736 22.214 Visualize Results
DSPyNet+ft [424] 6.224 2.743 34.602 5.102 2.937 1.562 0.881 2.842 40.954 Visualize Results
htjwarp2 [425] 3.341 1.449 18.757 3.093 1.286 0.876 0.881 1.793 19.283 Visualize Results
EPIflow [426] 7.003 2.907 40.443 5.098 2.712 1.809 0.882 2.789 47.616 Visualize Results
FastFlow2 [427] 4.128 1.887 22.415 4.323 1.765 0.919 0.894 2.609 23.855 Visualize Results
mask [428] 3.275 1.396 18.593 3.056 1.243 0.856 0.898 1.752 18.757 Visualize Results
Classic++ [429] 8.721 4.259 45.047 6.983 4.494 2.753 0.902 3.295 60.645 Visualize Results
ER-FLOW2 [430] 4.986 2.181 27.878 4.968 2.217 1.010 0.909 2.848 30.416 Visualize Results
SegPM+Interpolation [431] 3.513 1.269 21.839 2.894 1.012 0.727 0.910 2.164 19.723 Visualize Results
ComponentFusion [432] 6.065 2.033 38.912 4.114 2.063 1.213 0.910 2.996 39.074 Visualize Results
SPyNet [433] 6.689 3.020 36.596 5.770 3.289 1.562 0.911 3.455 43.207 Visualize Results
TV-L1+EM [434] 7.675 3.340 42.946 6.277 3.576 1.962 0.914 3.549 51.185 Visualize Results
BOOM+PF.XY [435] 5.204 1.696 33.826 3.512 1.540 1.021 0.927 2.921 31.976 Visualize Results
Deep+R [436] 5.041 1.481 34.047 3.710 1.102 0.722 0.929 2.333 31.999 Visualize Results
FullFlow [437] 3.601 1.296 22.424 2.944 1.023 0.732 0.933 2.055 20.612 Visualize Results
LDOF [438] 7.563 3.432 41.170 5.353 3.284 2.454 0.936 2.908 51.696 Visualize Results
ERFlow [439] 4.393 2.002 23.912 4.481 2.041 0.875 0.937 2.423 26.331 Visualize Results
Deep-EIP [440] 5.434 2.023 33.258 3.793 1.837 1.614 0.952 2.147 35.657 Visualize Results
DeepFlow [441] 5.377 1.771 34.751 4.519 1.534 0.837 0.960 2.730 33.701 Visualize Results
TVL1_BWMFilter [442] 8.361 3.421 48.551 6.524 3.687 2.095 0.968 3.867 55.892 Visualize Results
TV-L1 [443] 9.471 4.875 46.845 7.630 5.151 3.337 0.976 3.856 65.165 Visualize Results
WOLF_ROB [444] 6.947 3.238 37.153 5.828 3.405 1.835 0.976 3.454 45.036 Visualize Results
UPFlow [445] 4.680 1.709 28.948 3.696 1.547 0.856 0.980 2.553 28.223 Visualize Results
ZZZ [446] 6.027 1.681 41.429 3.637 1.547 1.038 0.994 2.809 38.798 Visualize Results
NLTGV-SC [447] 7.680 3.565 41.168 6.132 3.801 2.170 0.996 3.557 50.808 Visualize Results
SAnet [448] 6.953 3.682 33.584 5.694 3.714 2.432 1.018 3.487 44.750 Visualize Results
FAOP-Flow [449] 5.065 1.349 35.368 3.548 1.044 0.694 1.028 2.726 30.774 Visualize Results
FALDOI [450] 4.927 1.542 32.535 3.307 1.318 0.885 1.047 2.647 29.719 Visualize Results
BOOM+PF.XYT [451] 5.311 1.820 33.809 3.552 1.661 1.180 1.049 3.031 32.008 Visualize Results
DF-Auto [452] 8.480 3.945 45.399 6.445 4.149 2.537 1.057 3.732 56.780 Visualize Results
FlowNetC-MD [453] 4.411 2.196 22.472 4.188 2.040 1.173 1.057 2.475 25.727 Visualize Results
M-1px [454] 6.209 1.783 42.262 3.807 1.625 1.093 1.078 3.081 39.236 Visualize Results
DF-Beta [455] 7.391 3.153 41.890 5.492 3.337 1.895 1.087 3.597 47.836 Visualize Results
IPOL_Brox [456] 7.283 3.150 40.931 5.705 3.347 1.831 1.090 3.647 46.796 Visualize Results
DF [457] 7.406 3.164 41.936 5.504 3.345 1.908 1.091 3.594 47.949 Visualize Results
HSVFlow [458] 4.778 1.962 27.739 3.470 1.617 1.423 1.120 2.462 28.554 Visualize Results
PCA-Layers [459] 5.730 2.455 32.468 5.447 2.337 1.415 1.129 3.051 35.079 Visualize Results
Horn+Schunck [460] 8.739 4.525 43.032 7.542 5.045 2.891 1.141 3.860 58.243 Visualize Results
DDCNet_B1_ft-sintel [461] 6.185 3.518 27.881 5.533 3.540 2.305 1.168 3.957 36.381 Visualize Results
FlowNetADF [462] 7.464 3.915 36.404 6.853 4.094 2.377 1.171 4.412 46.057 Visualize Results
TVL1_RVC [463] 8.233 4.012 42.600 7.010 4.432 2.381 1.172 4.480 52.331 Visualize Results
TVL1_ROB [464] 8.233 4.012 42.600 7.010 4.432 2.381 1.172 4.480 52.331 Visualize Results
FlowNetProbOut [465] 7.472 3.888 36.700 6.833 4.056 2.424 1.196 4.422 45.962 Visualize Results
DictFlowS [466] 8.139 4.297 39.446 6.630 4.470 2.977 1.222 4.096 52.219 Visualize Results
HCOF+multi [467] 6.717 3.244 35.046 5.724 3.175 2.290 1.223 4.158 40.158 Visualize Results
Back2FutureFlow_UFO [468] 7.227 3.603 36.779 6.100 3.497 2.458 1.224 4.003 44.836 Visualize Results
DSPyNet [469] 6.552 3.105 34.690 5.497 3.351 1.857 1.225 3.365 40.738 Visualize Results
RGBFlow [470] 6.133 3.060 31.156 4.835 2.727 2.125 1.257 2.888 38.165 Visualize Results
Data-Flow [471] 7.972 3.494 44.527 6.341 3.665 1.921 1.258 3.970 51.049 Visualize Results
AutoScaler+ [472] 6.076 2.569 34.656 4.610 2.195 1.863 1.298 3.737 35.431 Visualize Results
Grts-Flow-V2 [473] 6.415 2.664 36.995 5.177 2.482 1.773 1.310 3.983 37.635 Visualize Results
UnFlow [474] 9.379 5.365 42.105 7.853 5.151 3.886 1.312 5.116 59.713 Visualize Results
CPNFlow [475] 7.660 3.853 38.695 6.804 4.130 2.223 1.347 3.952 47.942 Visualize Results
PCA-Flow [476] 6.828 3.014 37.939 6.444 3.038 1.655 1.363 3.484 42.048 Visualize Results
RC-LSTM-4dir [477] 6.694 3.419 33.345 5.930 3.513 2.162 1.375 3.826 39.961 Visualize Results
2bit-BM-tele [478] 9.274 4.219 50.491 6.233 4.119 3.323 1.390 4.564 59.833 Visualize Results
EPPM [479] 6.494 2.675 37.632 4.997 2.422 1.948 1.402 3.446 39.152 Visualize Results
RC-LSTM-1dir [480] 6.717 3.445 33.352 5.916 3.527 2.209 1.410 3.820 40.001 Visualize Results
AnyFlow [481] 6.066 2.412 35.852 5.211 2.432 1.215 1.429 3.665 34.900 Visualize Results
TVL1_LD_GF [482] 8.791 4.648 42.525 7.118 4.795 3.193 1.429 4.979 54.510 Visualize Results
SFL [483] 7.455 4.129 34.548 7.148 4.322 2.448 1.437 4.756 43.773 Visualize Results
flownetnew [484] 7.195 3.848 34.482 6.707 4.054 2.310 1.475 4.267 42.637 Visualize Results
H+S_ROB [485] 13.278 8.654 50.879 11.490 9.560 6.700 1.552 10.011 79.168 Visualize Results
testS [486] 7.332 3.986 34.592 6.988 4.220 2.379 1.619 4.518 42.429 Visualize Results
FlowNetC+OFR [487] 8.525 4.864 38.360 6.873 5.189 3.675 1.665 4.551 52.146 Visualize Results
AtrousFlow [488] 14.200 9.584 51.758 11.964 10.338 7.926 1.702 12.440 80.185 Visualize Results
DIS-Fast [489] 9.353 5.165 43.503 8.317 5.677 3.212 1.906 4.899 57.071 Visualize Results
OatNet01 [490] 8.533 5.090 36.559 7.084 5.251 3.809 1.932 5.233 49.168 Visualize Results
PosetOptimization [491] 9.874 3.639 60.633 5.005 3.366 3.207 1.981 6.486 57.189 Visualize Results
H-1px [492] 10.148 4.454 56.545 6.832 4.306 3.637 2.173 6.606 58.262 Visualize Results
H+S_RVC [493] 10.495 6.400 43.824 8.992 7.084 4.920 2.504 7.319 57.754 Visualize Results
WKSparse [494] 15.765 11.414 51.045 13.469 11.864 10.609 2.756 15.781 81.907 Visualize Results
Model_model [495] 14.669 10.081 51.960 11.437 10.100 9.394 3.502 12.036 76.191 Visualize Results
BASELINE-zero [496] 18.926 14.396 55.633 17.050 15.613 12.172 4.049 20.873 87.342 Visualize Results
AVG_FLOW_ROB [497] 18.799 14.422 54.251 16.903 15.516 12.457 4.566 19.946 86.008 Visualize Results
BASELINE-Mean [498] 15.422 11.488 47.336 14.676 12.649 9.350 5.310 14.717 66.922 Visualize Results
S2D-Matching [499] 18.485 13.372 59.935 13.676 12.747 12.149 9.472 15.466 70.185 Visualize Results
C-2px [500] 44.062 37.047 101.160 37.366 36.580 37.093 34.342 35.847 112.424 Visualize Results
cascade [501] 251.861 248.182 281.682 239.648 246.757 242.071 251.816 244.707 269.519 Visualize Results

Metrics


EPE Endpoint error over the complete frames
EPE matched Endpoint error over regions that remain visible in adjacent frames
EPE unmatched Endpoint error over regions that are visible only in one of two adjacent frames
d0-10 Endpoint error over regions closer than 10 pixels to the nearest occlusion boundary
d10-60 Endpoint error over regions between 10 and 60 pixels apart from the nearest occlusion boundary
d60-140 Endpoint error over regions between 60 and 140 pixels apart from the nearest occlusion boundary
s0-10 Endpoint error over regions with velocities lower than 10 pixels per frame
s10-40 Endpoint error over regions with velocities between 10 and 40 pixels per frame
s40+ Endpoint error over regions with velocities larger than 40 pixels per frame
All error images are normalized to be in the range between 0 and 1.

References
[1]
GroundTruth
[2]
CCMR+
Azin Jahedi, Maximilian Luz, Marc Rivinius, Andrés Bruhn "CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoning", WACV 2024
[3]
MS_RAFT+_RVC
Azin Jahedi, Maximilian Luz, Marc Rivinius, Lukas Mehl, and Andrés Bruhn: "MS-RAFT+: High Resolution Multi-Scale RAFT", IJCV 2023
[4]
MEMFOF
V. Bargatin, E. Chistov, A. Yakovenko, and D. Vatolin. "MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation", ICCV 2025.
[5]
EMD-OER
Anonymous.
[6]
MEMFOF-L
V. Bargatin, E. Chistov, A. Yakovenko, and D. Vatolin. "MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation", ICCV 2025.
[7]
CCAFlow
Anonymous. Submission
[8]
GeoViT
[9]
DDVM
Anonymous. NeurIPS 2023 submission #14395
[10]
AnyFlow+GMA
AnyFlow: Arbitrary Scale Optical Flow with Implicit Neural Representation. CVPR, 2023.
[11]
OM_GMFlow
Anonymous.
[12]
StreamFlow
Shangkun Sun, Jiaming Liu, Thomas Li, Huaxia Li, Guoqing Liu, Wei Gao, NeurIPS 2024
[13]
IWarp
Anonymous.
[14]
CroCo-Flow
CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow. Weinzaepfel et al. ICCV 2023.
[15]
MS_RAFT
Azin Jahedi, Lukas Mehl, Marc Rivinius, Andrés Bruhn, "Multi-scale RAFT: Combining Hierarchical Concepts for Learning-based Optical Flow Estimation", ICIP 2022
[16]
SEA-RAFT-M
Anonymous.
[17]
DPFlow
H. Morimitsu, X. Zhu, R. Cesar-Jr., X. Ji and X. Yin: DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework. CVPR 2025.
[18]
LSHRAFT
Anonymous.
[19]
SemFlow-2view
Anonymous.
[20]
OPPFlow
Anonymous.
[21]
GMFlow+
Haofei Xu, Jing Zhang, Jianfei Cai, Hamid Rezatofighi, Fisher Yu, Dacheng Tao, Andreas Geiger. Unifying Flow, Stereo and Depth Estimation. TPAMI 2023
[22]
SEA-RAFT-L
Anonymous.
[23]
AMFFlow
Anonymous.
[24]
CasFlow
Anonymous. CasFlow
[25]
VideoFlow-BOF
VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation, ICCV 2023
[26]
CFFlow
Anonymous.
[27]
VideoFlow-MOF
VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation, ICCV 2023
[28]
MotionFlow+
Anonymous.
[29]
ProtoFormer
Anonymous.
[30]
FlowDiffuser
FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models, CVPR 2024
[31]
MemoFlow
Anonymous.
[32]
ViCo_VideoFlow_MOF
[33]
gma+allcv
[34]
ProMotion
Anonymous. Anonymous submission
[35]
BDFlowNet
Anonymous.
[36]
MotionFlow
Anonymous. Z. Wang, C. Zhang, C. Zhen, H. Chen, L. Ge and K. Lu: MotionFlow: Joint Motion Priors and Appearance Enhancement for High-Accuracy Optical Flow Estimation. ICASSP 2025 .
[37]
RAFT-it+_RVC
D. Sun, C. Herrmann, F. Reda, M. Rubinstein, D. Fleet and W. Freeman: Disentangling Architecture and Training for Optical Flow. ECCV 2022. Scaled up RAFT.
[38]
EMD-M
Anonymous. Anonymous
[39]
MemFlow-T
Qiaole Dong, Yanwei Fu. MemFlow: Optical Flow Estimation and Prediction with Memory. CVPR 2024.
[40]
TransFlow
Anonymous. CVPR 2023 anonymous submission
[41]
PRAFlow_RVC
Anonymous.
[42]
HMAFlow
Anonymous.
[43]
AMFFlow_3f
[44]
APCAFlow
Anonymous.
[45]
SAMFlow
SAMFlow: Eliminating Any Fragmentation in Optical Flow with Segment Anything Model. Accepted in AAAI 2024.
[46]
FlowFormer++
FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation
[47]
MatchFlow_GMA_2-view
Anonymous.
[48]
MemFlow
Qiaole Dong, Yanwei Fu. MemFlow: Optical Flow Estimation and Prediction with Memory. CVPR 2024.
[49]
MMAFlow
Anonymous.
[50]
MMAFlow
Anonymous.
[51]
PVTFlow
Anonymous.
[52]
StreamFlow-Baseline
[53]
FlowFormer
FlowFormer: A Transformer Architecture for Optical Flow
[54]
flowformer_val
Anonymous.
[55]
GAFlow-FF
Anonymous. GAFlow: Incorporating Gaussian Attention into Optical Flow, ICCV 2023.
[56]
RAFT-CF
[57]
MCPFlow_RVC
RVC 2022 submission
[58]
raft+allcv
[59]
MatchFlow_GMA
Qiaole Dong, Chenjie Cao, Yanwei Fu. Rethinking Optical Flow from Geometric Matching Consistent Perspective. CVPR 2023.
[60]
ScaleFLow++
Improved version of Scale-flow with added flight foreground, sports field initialization, and improved iterators
[61]
ICIMG-Net
Anonymous.
[62]
GAFlow
Anonymous. GAFlow: Incorporating Gaussian Attention into Optical Flow, ICCV 2023.
[63]
TSA
Anonymous.
[64]
MatchFlow_RAFT
Qiaole Dong, Chenjie Cao, Yanwei Fu. Rethinking Optical Flow from Geometric Matching Consistent Perspective. CVPR 2023.
[65]
RAFT+AOIR
L. Mehl, C. Beschle, A. Barth, A. Bruhn: An Anisotropic Selection Scheme for Variational Optical Flow Methods with Order-Adaptive Regularisation. SSVM 2021.
[66]
AGM-FlowNet
Anonymous.
[67]
SplatFlow
SplatFlow: Learning Multi-frame Optical Flow via Splatting; https://arxiv.org/abs/2306.08887; IJCV 2024
[68]
RFPM
Anonymous.
[69]
ce_v214
Anonymous.
[70]
test_mem
Anonymous.
[71]
OM_CRAFT
Anonymous.
[72]
TSGFlow
Anonymous. Tri-branch self-guided Transformer for optical flow estimation.
[73]
AGF-Flow3
Anonymous. AGF-Flow3
[74]
SKII
Anonymous.
[75]
GMA+LCT-Flow
GMA+LCT-Flow
[76]
RAFTwarm+AOIR
L. Mehl, C. Beschle, A. Barth, A. Bruhn: An Anisotropic Selection Scheme for Variational Optical Flow Methods with Order-Adaptive Regularisation. SSVM 2021.
[77]
CrossFlow
Anonymous.
[78]
SKFlow
Shangkun Sun, Yuanqi Chen, Yu Zhu, Guodong Guo, Ge Li. Learning Optical Flow with Super Kernels. NeurIPS 2022.
[79]
CGCV-GMA
[80]
ACAFlow
Anonymous.
[81]
H-v3
Anonymous.
[82]
ce_skii_skii
Anonymous.
[83]
PredFlow
[84]
PredFlow
[85]
RAFT-it
D. Sun, C. Herrmann, F. Reda, M. Rubinstein, D. Fleet and W. Freeman: Disentangling Architecture and Training for Optical Flow. ECCV 2022.
[86]
CE_SKII
Anonymous.
[87]
KPA-Flow
Anonymous. Learning Optical Flow with Kernel Patch Attention, CVPR 2022.
[88]
EMD-L
Anonymous. Anonymous
[89]
LLA-FLOW+GMA
LLA-FLOW: A Lightweight Local Aggregation on Cost Volume for Optical Flow Estimation. ICIP 2023.
[90]
SCFlow
Anonymous.
[91]
SCV
Anonymous. CVPR 2021 submission #3221
[92]
SSTM++3kt
[93]
DPCTF
Anonymous. Detail Preserving Coarse-to-Fine Matching for Stereo Matching and Optical Flow
[94]
MODFlow_ft
Anonymous. A Matching-Guided and Occlusion-Aware Decoder for Accurate Optical Flow Estimation
[95]
ACAFlow
Anonymous.
[96]
AGF-Flow2
Anonymous. AGF-Flow2
[97]
RAFT+LCT-Flow
RAFT+LCT-Flow
[98]
CVEFlow
ljp
[99]
BD-Flow_finetune
[100]
DEQ-Flow-H
Deep Equilibrium Optical Flow Estimation
[101]
AMFlow
Anonymous. Efficient Optical Flow Estimation via Attentional Cost Volume and Matching Initialization
[102]
SSTM++nws-main
[103]
NASFlow-RAFT
Anonymous.
[104]
SSTM++_ttt_nws
Fisseha Admasu Ferede, Madhusudhanan Balasubramanian. SSTM: Spatiotemporal Recurrent Transformers for Multi-frame Optical Flow Estimation. Neurocomputing 2023.
[105]
RAFTwarm+OBS
Anonymous. train the RAFT network on new our datasets and applying warmup
[106]
RAFT-OCTC
Anonymous.
[107]
GMA+TCU-aug
Anonymous.
[108]
GMFlow_RVC
GMFlow RVC 2022 submission.
[109]
Win-Win
Anonymous. Win-Win: Training High-Resolution Vision Transformers from Two Windows ICLR 2024 submission
[110]
ACAFlow
Anonymous.
[111]
SSTM++_ttt_ws
Fisseha Admasu Ferede, Madhusudhanan Balasubramanian. SSTM: Spatiotemporal Recurrent Transformers for Multi-frame Optical Flow Estimation. Neurocomputing 2023.
[112]
OM_GMA
Anonymous.
[113]
MFCFlow
Anonymous.
[114]
SSTM++warm-main
[115]
NASFlow
Anonymous.
[116]
SeparableFlow-2views
Feihu Zhang, Oliver Woodford, Victor Prisacariu, Philip Torr, "Separable Flow: Learning Motion Cost Volumes for Optical Flow Estimation", ICCV 2021
[117]
RAFT+OBS
Anonymous. We change the dataset to train RAFT.
[118]
GMA+TCU+aug
Anonymous.
[119]
RPKNet
Henrique Morimitsu, Xiaobin Zhu, Xiangyang Ji, and Xu-Cheng Yin. Recurrent Partial Kernel Network for Efficient Optical Flow Estimation. AAAI, 2024.
[120]
GMA-two_img
Anonymous.
[121]
HD3F+MSDRNet
Anonymous. HD3F+MSDRNet
[122]
CRAFT
Anonymous. Cross-Attentional Flow Transformer
[123]
ErrorMatch-GMA
Anonymous. tba
[124]
FTGAN
The Application of Counter Learning of Reverse Residual Attention in Optical Flow Estimation
[125]
COMBO
Anonymous.
[126]
SSTM++_reconst
[127]
RAFT-A
2-frame result. Deqing Sun, Daniel Vlasic, Charles Herrmann, Varun Jampani, Michael Krainin, Huiwen Chang, Ramin Zabih, William T. Freeman, and Ce Liu. "AutoFlow: Learning a Better Training Set for Optical Flow" CVPR 2021 https://arxiv.org/abs/2104.14544
[128]
GMFlowNet
Shiyu Zhao, Long Zhao, Zhixing Zhang, Enyu Zhou and Dimitris Metaxas. Global Matching with Overlapping Attention for Optical Flow Estimation. CVPR 2022
[129]
MVFlow
Anonymous.
[130]
SCAR
Anonymous.
[131]
ErrorMatch-RAFT
Anonymous. tba
[132]
sdex00
Anonymous.
[133]
BD-Flow
[134]
AGFlow
Ao Luo, Fan Yang, Kunming Luo, Xin Li, Haoqiang Fan, Shuaicheng Liu. Learning Optical Flow with Adaptive Graph Reasoning, In AAAI, 2022.
[135]
CGCV-RAFT
[136]
TrepFlow
Anonymous. Submission
[137]
RAFTv2-OER-2-view
Anonymous.
[138]
GMA-base
Anonymous. GMA-base
[139]
RAFT-DFlow
Anonymous.
[140]
SKFlow_RAFT
Anonymous.
[141]
FCTR-m
Anonymous.
[142]
CVE-RAFT
ljp
[143]
SwinTR-RAFT
Anonymous.
[144]
SSTM-nws
[145]
submission5367
Anonymous.
[146]
RAFT-FS
Anonymous. Semi-Supervised Learning of Optical Flow by Flow Supervisor
[147]
RAFTv2-OER-warm-start
Anonymous.
[148]
MFlow
Anonymous.
[149]
CSFlow-2-view
Shi, H., Zhou, Y., Yang, K., Yin, X., & Wang, K. (2022). CSFlow: Learning Optical Flow via Cross Strip Correlation for Autonomous Driving. arXiv preprint arXiv:2202.00909.
[150]
RAFT-base
Anonymous. RAFT-base
[151]
GMA
Shihao Jiang, Dylan Campbell, Yao Lu, Hongdong Li, Richard Hartley. Learning to Estimate Hidden Motions with Global Motion Aggregation, ICCV 2021.
[152]
FCTR
Anonymous.
[153]
OM_RAFT
Anonymous. Used method with channel shuffle to enhance feature.
[154]
GMA-FS
Anonymous. Semi-Supervised Learning of Optical Flow by Flow Supervisor
[155]
L2L-Flow-ext
Anonymous.
[156]
LLA-Flow
LLA-FLOW: A Lightweight Local Aggregation on Cost Volume for Optical Flow Estimation. ICIP 2023.
[157]
DIP
Anonymous. Deep Inverse Patchmatch for High-Resolution Optical Flow
[158]
MFFC
Anonymous
[159]
Deformable_RAFT
Anonymous. RAFT with deformable
[160]
raft-jm
Anonymous. mix raft_test
[161]
RAFT-illumination
Anonymous. RAFT-illumination
[162]
RAFT
Zachary Teed and Jia Deng. RAFT: Recurrent All-Pairs Field Transforms for Optical Flow, ECCV 2020.
[163]
L2L-Flow-ext-warm
Anonymous.
[164]
MFR
Anonymous. Motion Feature Recovery
[165]
MF2C
Anonymous
[166]
Fun-MS-RAFT
[167]
RAFT-TF_RVC
Deqing Sun, Charles Herrmann, Varun Jampani, Mike Krainin, Forrester Cole, Austin Stone, Rico Jonschkowski, Ramin Zabih, William Freeman, and Ce Liu. A TensorFlow implementation of RAFT (Zachary Teed and Jia Deng. RAFT: Recurrent all-pairs field transforms for optical flow. ECCV 2020.) RVC 2020 submission.
[168]
RAFT-GT-ft
Anonymous. CVPR 2021 submission
[169]
MeFlow
Anonymous.
[170]
DCN-Flow
DCN-Flow
[171]
PPAC-HD3
Anne S. Wannenwetsch, Stefan Roth. Probabilistic Pixel-Adaptive Refinement Networks. CVPR 2020.
[172]
HCVNet
Anonymous.
[173]
sdex001
Anonymous.
[174]
HD3-Flow-OER
Anonymous.
[175]
MaskFlownet
Shengyu Zhao, Yilun Sheng, Yue Dong, Eric I-Chao Chang, and Yan Xu. MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask, CVPR 2020 (Oral).
[176]
LSM_FLOW_RVC
LSM: Learning Subspace Minimization for Low-level Vision for RVC2020
[177]
OADFlow
Anonymous.
[178]
ScaleRAFT
Anonymous. ScaleRAFT
[179]
RAFTv1-OER-2-view
Anonymous.
[180]
RAFT+ConvUp
Anonymous.
[181]
DICL_update
Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation (NeurIPS 2020)
[182]
ProtoFormer
[183]
RAFT+NCUP
Normalized Convolution Upsampling for Refined Optical Flow Estimation
[184]
DICL-Flow+
Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation (NeurIPS 2020)
[185]
DICL-Flow
Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation (NeurIPS 2020)
[186]
IOFPL-ft
Anonymous. IOFPL - Improving Optical Flow on a Pyramid Level (ECCV2020)
[187]
HD3-Flow
Zhichao Yin, Trevor Darrell, Fisher Yu. Hierarchical Discrete Distribution Decomposition for Match Density Estimation (CVPR 2019)
[188]
Flow1D-OER
Anonymous.
[189]
SelFlow
Pengpeng Liu, Michael R. Lyu, Irwin King, Jia Xu. SelFlow: Self-Supervised Learning of Optical Flow (CVPR 2019)
[190]
SMURF
Austin Stone, Daniel Maurer, Alper Ayvaci, Anelia Angelova, Rico Jonschkowski. SMURF: Self-Teaching Multi-Frame Unsupervised RAFT With Full-Image Warping, CVPR 2021
[191]
IOFPL-CVr8-ft
Anonymous. IOFPL - Improving Optical Flow on a Pyramid Level (ECCV2020)
[192]
DA_opticalflow
Anonymous.
[193]
MobileFlow
Anonymous. Optical flow estimation framework using an enhanced MobileNet and Transformer with a large-kernel upsampler.
[194]
ADLAB-PRFlow
Anonymous.
[195]
ADW
Anonymous.
[196]
YOIO
Anonymous.
[197]
Fun-RAFT
[198]
MaskFlownet-S
Shengyu Zhao, Yilun Sheng, Yue Dong, Eric I-Chao Chang, and Yan Xu. MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask, CVPR 2020 (Oral).
[199]
ScaleFlow++_SAG
ScaleFlow trained using GS58 in SAG++
[200]
RAPIDFlow
Henrique Morimitsu, Xiaobin Zhu, Roberto M. Cesar-Jr., Xiangyang Ji, and Xu-Cheng Yin. RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for efficient optical flow estimation. ICRA, 2024.
[201]
CVPR-1235
Anonymous.
[202]
vcn+MSDRNet
Anonymous. None
[203]
ScaleFlow_GS58
Train ScaleFlow by GS58
[204]
ISDAFlow
Anonymous. ISDAFlow: Self-supervised Infusion of Segmented and Depth Anything Models into Optical Flow
[205]
RAFT_Chairs_Things
Anonymous.
[206]
MR-Flow
J. Wulff, L. Sevilla-Lara, M. J. Black: Optical Flow in Mostly Rigid Scenes. CVPR 2017.
[207]
DistillFlow+ft
Anonymous. Supervised result.
[208]
PWC-Net+KF
W. Bao, Y. Xiao, L. Chen, and Z. Gao. KalmanFlow 2.0: Efficient Video Optical Flow Estimation via Context-Aware Kalman Filtering. submitted to TIP.
[209]
PWC-Net+KF2
W. Bao, Y. Xiao, L. Chen, and Z. Gao. KalmanFlow 2.0: Efficient Video Optical Flow Estimation via Context-Aware Kalman Filtering. submitted to TIP.
[210]
ADW-Net
Anonymous. ADW-Net，20201024 submit
[211]
metaFlow
Anonymous.
[212]
HMFlow
HMFlow: Hybrid Matching Optical Flow Network for Small and Fast-Moving Objects
[213]
ProFlow
D. Maurer, A. Bruhn: ProFlow: Learning to Predict Optical Flow. BMVC 2018.
[214]
less_iter_fine
Anonymous. optimization with fewer iterations used.
[215]
DCVNet
Anonymous. 0.03s with a GTX 1080ti GPU.
[216]
NccFlow
Anonymous.
[217]
SPM-BPv2
Y. Li, D. Min, M. S. Brown, M. N. Do, and J. Lu. SPM-BP: Sped-up PatchMatch Belief Propagation for Continuous MRFs. ICCV 2015. Improved version. Details coming soon.
[218]
RAFT-VM
[219]
EFlow-M-tile
Anonymous.
[220]
ProFlow_ROB
D. Maurer, A. Bruhn: ProFlow: Learning to Predict Optical Flow. BMVC 2018. (ROB setting)
[221]
SegFlow153
Efficient Segmentation-Based PatchMatch for Large displacement Optical Flow Estimation. 2019 TCSVT. (d0=15,d1=3)(Matlab code is available.)
[222]
PatchBatch-CENT+SD
Anonymous.
[223]
Scale-flow++_GS58
Efficient and Accurate Monocular 3D Motion Estimation Trained by GS58
[224]
AllTracker
Anonymous.
[225]
GMFlow
Haofei Xu, Jing Zhang, Jianfei Cai, Hamid Rezatofighi, Dacheng Tao. GMFlow: Learning Optical Flow via Global Matching. CVPR 2022, Oral
[226]
ARFlow-mv-ft
Liang Liu, Jiangning Zhang, Ruifei He, Yong Liu, Yabiao Wang, Ying Tai, et al. Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation. CVPR 2020.
[227]
LiteFlowNet
Tak-Wai Hui, Xiaoou Tang, and Chen Change Loy. LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018.
[228]
VCN_RVC
Gengshan Yang and Deva Ramanan. Volumetric Correspondence Networks for Optical Flow, NeurIPS 2019
[229]
UFlow
R. Jonschkowski, A. Stone, J. Barron, A. Gordon, K. Konolige, and A. Angelova. What Matters in Unsupervised Optical Flow. ECCV 2020. (Code is available)
[230]
Flow1D
Haofei Xu, Jiaolong Yang, Jianfei Cai, Juyong Zhang, Xin Tong. High-Resolution Optical Flow from 1D Attention and Correlation. ICCV 2021, Oral
[231]
PRichFlow
Anonymous.
[232]
STaRFlow
Pierre Godet, Alexandre Boulch, Aurélien Plyer, Guy Le Besnerais. STaRFlow: A SpatioTemporal Recurrent Cell for Lightweight Multi-Frame Optical Flow Estimation, ICPR 2020 (https://arxiv.org/abs/2007.05481)
[233]
ContinualFlow_ROB
Michal Neoral, Jan Šochman and Jiří Matas. Continual Occlusions and Optical Flow Estimation, ACCV 2018
[234]
RichFlow-ft-fnl
Anonymous. final pass version
[235]
ISDAFlowRAFT
Anonymous. ISDAFlow+RAFT
[236]
IRR-PWC-OER
Anonymous.
[237]
S2F-IF
Yanchao Yang, Stefano Soatto. S2F: Slow-To-Fast Interpolator Flow. CVPR 2017.
[238]
FlowSAC_ff
Anonymous
[239]
RAFT+LCV
Taihong Xiao, Jinwei Yuan, Deqing Sun, Qifei Wang, Xin-Yu Zhang, Kehan Xu, Ming-Hsuan Yang. Learnable Cost Volume using the Cayley Representation, ECCV 2020
[240]
SENSE
Anonymous. TBA
[241]
AL-OF-r0.2
Shuai Yuan, Xian Sun, Hannah Kim, Shuzhi Yu, Carlo Tomasi. Optical Flow Training Under Limited Label Budget via Active Learning. (ECCV-2022)
[242]
SegFlow193
Efficient Segmentation-Based PatchMatch for Large displacement Optical Flow Estimation. 2019 TCSVT. (d0=19,d1=3)(Matlab code is available.)
[243]
ScopeFlow
Aviram Bar-Haim and Lior Wolf. ScopeFlow: Dynamic Scene Scoping for Optical Flow, CVPR 2020.
[244]
IRR-PWC
Junhwa Hur and Stefan Roth. Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation. CVPR 2019
[245]
SAG156+RAFT
Anonymous. SAG156+RAFT
[246]
FlowFields
C. Bailer, B. Taetz and D. Stricker. Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation. ICCV 2015.
[247]
CompactFlow
Anonymous. ICCV submission.
[248]
less_iteration
Anonymous.
[249]
DIP-Flow
D. Maurer, M. Stoll, A. Bruhn: Directional Priors for Multi-Frame Optical Flow. BMVC 2018.
[250]
SegFlow113
Efficient Segmentation-Based PatchMatch for Large displacement Optical Flow Estimation. 2019 TCSVT. (d0=11,d1=3)(Matlab code is available.)
[251]
CompactFlow-woscv
Anonymous.
[252]
ProbFlowFields
Anne S. Wannenwetsch, Margret Keuper, Stefan Roth. ProbFlow: Joint Optical Flow and Uncertainty Estimation. ICCV 2017.
[253]
Classic+NL-fast
D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR, pages 2432-2439, 2010.
[254]
SfM-PM
D. Maurer, N. Marniok, B. Goldluecke, A. Bruhn: Structure-from-Motion-Aware PatchMatch for Adaptive Optical Flow Estimation. ECCV 2018.
[255]
LiteFlowNet3
Tak-Wai Hui and Chen Change Loy. LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation, ECCV 2020.
[256]
FlowFields++
R. Schuster, C. Bailer, O. Wasenmüller, D. Stricker. FlowFields++: Accurate Optical Flow Correspondences Meet Robust Interpolation. ICIP 2018
[257]
SegFlow73
Efficient Segmentation-Based PatchMatch for Large displacement Optical Flow Estimation. 2019 TCSVT. (d0=7,d1=3)(Matlab code is available.)
[258]
PWC-Net-OER
Anonymous.
[259]
RichFlow-ft
Anonymous.
[260]
MirrorFlow
Junhwa Hur and Stefan Roth. MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation. ICCV 2017
[261]
TIMCflow
Fei Yang, Yongmei Cheng, Joost Van de Weijer, Mikhail G. Mozerov. 'Improved Discrete Optical Flow Estimation with Triple Image Matching Cost', IEEE Access
[262]
PGM-C
Anonymous
[263]
AOD
[264]
VCN-OER
Anonymous.
[265]
InterpoNet_ff
S. Zweig, L Wolf. InterpoNet, A brain inspired neural network for optical flow dense interpolation. CVPR 2017.
[266]
PMC-PWC_without_edge_loss
Congxuan Zhang, Cheng Feng, Zhen Chen, Weiming Hu, Ming Li, Parallel multiscale context-based edge-preserving optical flow estimation with occlusion detection, Signal Processing: Image Communication, Volume 101, 2022, doi: 10.1016/j.image.2021.116560
[267]
Classic+NL
D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR, pages 2432-2439, 2010.
[268]
LiteFlowNet3-S
Tak-Wai Hui and Chen Change Loy. LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation, ECCV 2020.
[269]
Flownet2-IAER
Anonymous. Flownet2 combining with illumination adjustment and edge refinement
[270]
IHBPFlow
Anonymous.
[271]
FC-2Layers-FF
D. Sun, J. Wulff, E. Sudderth, H. Pfister, M.J. Black. A fully connected layered model of foreground and background flow. CVPR 2013
[272]
LocalLayering
D. Sun, C. Liu, and H. Pfister. Local Layering for Joint Motion Estimation and Occlusion Detection. CVPR 2014.
[273]
GCA-Net-ft+
Anonymous. finetune GCA-Net with a better data augmentation method
[274]
OF-OEF
Anonymous. Optical flow estimation combining with objects edge features
[275]
PatchWMF-OF
Zhigang Tu, Coert Van Gemeren and Remco C. Veltkamp. Improved Color Patch Similarity Measure Based Weighted Median Filter. ACCV2014
[276]
InterpoNet_df
S. Zweig, L Wolf. InterpoNet, A brain inspired neural network for optical flow dense interpolation. CVPR 2017.
[277]
FF++_ROB
Accurate matching and robust interpolation. KITTI parameters as given by the paper. Edge detector trained on KITTI + Sintel + BSDS500.
[278]
JOF
Zhang Congxuan, Ge Liyue, Chen Zhen, Li Ming, Liu Wen, Chen Hao. Refined TV-L1 Optical Flow Estimation Using Joint Filtering, IEEE Transactions on Multimedia, 2020, 22(2):349-364.
[279]
DiscreteFlow+OIR
D. Maurer, M. Stoll, A. Bruhn: Order-Adaptive and Illumination Aware Variational Optical Flow Refinement. BMVC 2017.
[280]
tfFlowNet2+GLR
Anonymous.
[281]
CVENG22+RIC
Anonymous.
[282]
DCFlow+KF2
W. Bao, Y. Xiao, L. Chen, and Z. Gao. KalmanFlow 2.0: Efficient Video Optical Flow Estimation via Context-Aware Kalman Filtering. submitted to TIP.
[283]
PatchBatch+Inter
T. Schuster, L. Wolf and D. Gadot: Optical Flow Requires Multiple Strategies (but only one network). CVPR 2017.
[284]
A-A
Anonymous.
[285]
PH-Flow
Jiaolong Yang and Hongdong Li. Dense, Accurate Optical Flow Estimation with Piecewise Parametric Model. CVPR 2015
[286]
CPM-Flow
Yinlin Hu, Rui Song, Yunsong Li. Efficient Coarse-to-Fine PatchMatch for Large Displacement Optical Flow. CVPR 2016.
[287]
GPNet
Anonymous.
[288]
CoT-AMFlow
H. Wang, R. Fan, and M. Liu. CoT-AMFlow: Adaptive Modulation Network with Co-Teaching Strategy for Unsupervised Optical Flow Estimation, CoRL 2020.
[289]
FlowFields+
C. Bailer, B. Taetz and D. Stricker. Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation. T-PAMI.
[290]
DC-RAFT
Anonymous.
[291]
LiteFlowNet2
Tak-Wai Hui, Xiaoou Tang, and Chen Change Loy. A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization, TPAMI 2020.
[292]
FlowNet2-ft-sintel
Anonymous. CVPR Submission #900
[293]
DCFlow+KF
W. Bao, Y. Xiao, L. Chen, and Z. Gao. KalmanFlow 2.0: Efficient Video Optical Flow Estimation via Context-Aware Kalman Filtering. submitted to TIP.
[294]
WLIF-Flow
Z. Tu, R. Poppe, and R. C. Veltkamp. Weighted local intensity fusion method for variational optical flow estimation.Pattern Recognition,2015
[295]
WRTflow
We proposed a weighted regularization transform to reduce the influence of illumination variations of optical flow estimation. We submit it to TCSVT.
[296]
Semantic_Lattice
Anne S. Wannenwetsch, Martin Kiefel, Peter V. Gehler, Stefan Roth. Learning Task-Specific Generalized Convolutions in the Permutohedral Lattice. GCPR 2019.
[297]
MLDP-OF
M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. Accepted in IEEE TCSVT 2014.
[298]
RicFlow
Yinlin Hu, Yunsong Li, Rui Song. Robust Interpolation of Correspondences for Large Displacement Optical Flow. CVPR 2017.
[299]
GCA-Net
Anonymous.
[300]
AL-OF-r0.1
Shuai Yuan, Xian Sun, Hannah Kim, Shuzhi Yu, Carlo Tomasi. Optical Flow Training Under Limited Label Budget via Active Learning. (ECCV-2022)
[301]
OF_OCC_LD
V. Lazcano, L. Garrido, C. Ballester. Jointly Optical flow and Occlusion Estimation for images with Large Displacements.
[302]
PWC-Net
Deqing Sun, Xiaodong Yang, Ming-Yu Liu, and Jan Kautz. PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018.
[303]
Flownet2-IA
Anonymous. Flownet2 combining with illumination adjustment
[304]
VCN+LCV
Taihong Xiao, Jinwei Yuan, Deqing Sun, Qifei Wang, Xin-Yu Zhang, Kehan Xu, Ming-Hsuan Yang. Learnable Cost Volume using the Cayley Representation, ECCV 2020
[305]
ARFlow+LCT-Flow
ARFlow+LCT-Flow
[306]
AGIF+OF
Anonymous. Signal Processing 2015
[307]
GlobalPatchCollider
Shenlong Wang, Sean Fanello, Christoph Rhemann, Shahram Izadi and Pushmeet Kohli, The Global Patch Collider, CVPR, 2016
[308]
CPM_AUG
Anonymous. CVPR 18 submission #1939
[309]
CPM2
Coarse-to-fine PatchMatch for dense correspondence, Yunsong Li, Yinlin Hu, Rui Song, Peng Rao, Yangli Wang, submitted to T-CSVT
[310]
MPIF
Anonymous. multi-level interpolation for optical flow estimation
[311]
PWC-Net_RVC
Deqing Sun, Xiaodong Yang, Ming-Yu Liu, and Jan Kautz. PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018. Renamed from PWC-Net_ROB to PWC-Net_RVC.
[312]
SAMFL
Zhang Congxuan, Zhou Zhongkai, Chen Zhen, Hu Weming, Li Ming, Jiang Shaofeng. Self-attention-based Multiscale Feature Learning Optical Flow with Occlusion Feature Map Prediction, IEEE Transactions on Multimedia, 2021, DOI: 10.1109/TMM.2021.3096083.
[313]
Channel-Flow
L. Sevilla-Lara, D. Sun, E. Learned-Miller, and M. Black. Optical Flow Estimation with Channel Constancy. ECCV, pages 423-438, 2014.
[314]
UnSAMFlow
Accepted by CVPR 2024
[315]
PMF
J. Lu, Y. Li, H. Yang, D. Min, W. Eng, M. N. Do. PatchMatch Filter: Edge-Aware Filtering Meets Randomized Search for Visual Correspondence. TPAMI 2016
[316]
StruPyNet-ft
Zefeng Sun, Hanli Wang, Yun Yi, and Qinyu Li, Structural Pyramid Network for Cascaded Optical Flow Estimation, The 26th International Conference on Multimedia Modeling (MMM’20) , Daejeon, Korea, Jan. 5-8, 2020.
[317]
UnsupSimFlow
Unsupervised Learning of Optical Flow with Deep Feature Similarity, ECCV 2020
[318]
PST
Anonymous. ACCV2018 submission #1195
[319]
PMC-PWC_edge_loss
Congxuan Zhang, Cheng Feng, Zhen Chen, Weiming Hu, Ming Li, Parallel multiscale context-based edge-preserving optical flow estimation with occlusion detection, Signal Processing: Image Communication, Volume 101, 2022, doi: 10.1016/j.image.2021.116560
[320]
NASFlow-PWC
Anonymous.
[321]
InterpoNet_cpm
S. Zweig, L Wolf. InterpoNet, A brain inspired neural network for optical flow dense interpolation. CVPR 2017.
[322]
Classic+NLP
D. Sun, S. Roth, and M. Black. A Quantitative Analysis of Current Practices in Optical Flow Estimation and The Principles behind Them. International Journal of Computer Vision (IJCV), 106(2):115-137, 2014.
[323]
MDP-Flow2
L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012.
[324]
SPM-BP
Y. Li, D. Min, M. S. Brown, M. N. Do, and J. Lu. SPM-BP: Sped-up PatchMatch Belief Propagation for Continuous MRFs. ICCV 2015
[325]
F2PD_JJN
Anonymous. With Deformable Convolutional Networks
[326]
DDCNet_Stacked
Anonymous. Two blocks of simple DDCNet
[327]
EFlow-M
Anonymous.
[328]
FlowNet2
Anonymous. CVPR Submission #900
[329]
VCN
Gengshan Yang and Deva Ramanan. Volumetric Correspondence Networks for Optical Flow, NeurIPS 2019
[330]
PWC_acn
Anonymous.
[331]
OAR-Flow
D. Maurer, M. Stoll, A. Bruhn: Order-Adaptive Regularisation for Variational Optical Flow: Global, Local and in Between. SSVM 2017.
[332]
FlowFieldsCNN
C. Bailer, K Varanasi and D. Stricker. CNN-based Patch Matching for Optical Flow with Thresholded Hinge Embedding Loss. CVPR 2017.
[333]
AggregFlow
D. Fortun, P. Bouthemy and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. CVIU 2016
[334]
DDCNet_Multires_ft_sintel
DDCNet Multires fine tuned on Sintel
[335]
StruPyNet
Zefeng Sun, Hanli Wang, Yun Yi, and Qinyu Li, Structural Pyramid Network for Cascaded Optical Flow Estimation, The 26th International Conference on Multimedia Modeling (MMM’20) , Daejeon, Korea, Jan. 5-8, 2020.
[336]
CAR_100
Anonymous.
[337]
AugFNG_ROB
Anonymous.
[338]
FGI
Y. Li, D. Min, M. N. Do, and J. Lu. Fast Guided Global Interpolation for Depth and Motion. ECCV 2016
[339]
UlDENet
Anonymous.
[340]
MDFlow
Lingtong Kong and Jie Yang. MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation, TCSVT 2022.
[341]
EgFlow-cl
Anonymous. edge-guided, small parameter optical flow network based on CNN
[342]
STDC-Flow
STDC-Flow: large displacement flow field estimation using similarity transformationbased dense correspondence, IET Computer Vision, 2020
[343]
STC-Flow
Anonymous.
[344]
M2FLOW
Xunpei Sun, Gang Chen, and Zuoxun Hou, “M2Flow: A Motion Information Fusion Framework for Enhanced Unsupervised Optical Flow Estimation in Autonomous Driving,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, no. 7, pp. 7140–7148, 2025.
[345]
AL-OF-r0.05
Shuai Yuan, Xian Sun, Hannah Kim, Shuzhi Yu, Carlo Tomasi. Optical Flow Training Under Limited Label Budget via Active Learning. (ECCV-2022)
[346]
F3-MPLF
Sathya N. Ravi, Yunyang Xiong, Lopamudra Mukherjee, Vikas Singh: Filter Flow made Practical: Massively Parallel and Lock-Free -- CVPR 2017
[347]
CARflow-mv
Anonymous.
[348]
tfFlowNet2
Anonymous.
[349]
SparseFlow
Radu Timofte and Luc Van Gool. SparseFlow: Sparse Matching for Small to Large Displacement Optical Flow. WACV 2015
[350]
HAST
Yinlin Hu, Rui Song, Yunsong Li, Peng Rao, Yangli Wang. Highly Accurate Optical Flow Estimation on Superpixel Tree. Image and Vision Computing (IVC), 2016
[351]
NNF-Local
Anonymous. Large Displacement Optical Flow from Nearest Neighbor Fields
[352]
ADF-Scaleflow
Anonymous. Scaleflow trained by ADF58
[353]
IRR-PWC_RVC
RVC 2020 submission
[354]
SegFlow33
Efficient Segmentation-Based PatchMatch for Large displacement Optical Flow Estimation. 2019 TCSVT. (d0=3, d1=3)(Matlab code is available.)
[355]
CVENG22+Epic
Anonymous.
[356]
DDCNet_stacked2
Anonymous. two times down-sampling of feature maps, 128 filters each layer, fine-tuned on sintel
[357]
ContFusion
M. Stoll, D. Maurer, and A. Bruhn. Variational Large Displacement Optical Flow without Feature Matches. EMMCVPR 2017.
[358]
EPMNet
Anonymous. The high accuracy for both small and large motion estimation are mainly cause by two contributions: firstly, we present and implement an edge preserve patch match (EPM) layer that propagates self-similarity patterns in addition to offsets. The accuracy of optical flow prediction has greatly improved by this method. Secondly, we develop a course-to-fine network architecture to tackle large displacement estimation and introduce a residual flow method to solve small displacement estimation.
[359]
EdgeFlow
Anonymous.
[360]
MFF
Zhile Ren, Orazio Gallo, Deqing Sun, Ming-Hsuan Yang, Erik B. Sudderth and Jan Kautz: A Fusion Approach for Multi-Frame Optical Flow Estimation. IEEE Winter Conference on Applications of Computer Vision (WACV 2019)
[361]
FPCR-Net2
Anonymous.
[362]
FPCR-Net
Anonymous.
[363]
ARFlow-mv
Liang Liu, Jiangning Zhang, Ruifei He, Yong Liu, Yabiao Wang, Ying Tai, et al. Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation. CVPR 2020.
[364]
DCFlow
Jia Xu, René Ranftl, Vladlen Koltun. Accurate Optical Flow via Direct Cost Volume Processing. CVPR 2017.
[365]
DiscreteFlow
M. Menze, C. Heipke and A. Geiger. Discrete Optimization for Optical Flow. GCPR 2015
[366]
InterpoNet_dm
S. Zweig, L Wolf. InterpoNet, A brain inspired neural network for optical flow dense interpolation. CVPR 2017.
[367]
DefFlowP
Anonymous.
[368]
SimpleFlow
M. W. Tao, J. Bai, P. Kohli, and S. Paris. "SimpleFlow: A Non-iterative, Sublinear Optical Flow Algorithm". Computer Graphics Forum (Eurographics 2012), 2012. (OpenCV 2.4.5 Implementation, parameters provided by OpenCV sample)
[369]
EpicFlow
J. Revaud, P. Weinzaepfel, Z. Harchaoui and C. Schmid. EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow. CVPR 2015.
[370]
OCRAFT
[371]
FlowSAC_dcf
Anonymous.
[372]
ROF-NND
Sharib Ali, Christian Daul, Ernest Galbrun, Walter Blondel, Illumination invariant optical flow using neighborhood descriptors, Computer Vision and Image Understanding, Available online 17 December 2015, ISSN 1077-3142.
[373]
GANFlow
Anonymous.
[374]
DistillFlow
Anonymous. Unsupervise result
[375]
risc
Anonymous.
[376]
GeoFlow
Anonymous. Submission to Electrocnic Letters in 2018, we propose a simple but novel algorithm to achieve global belief propagation called geodesic-based Probability Propagation for optical flow estimation.
[377]
ricom20201202
Anonymous.
[378]
RICBCDN
Anonymous.
[379]
COF_2019
H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[380]
IIOF-NLDP
Dinh-Hoan Trinh, Walter Blondel, and Christian Daul. A General Form of Illumination-Invariant Descriptors in Variational Optical Flow Estimation. ICIP 2017.
[381]
Lavon
Anonymous.
[382]
RLOF_DENSE
Jonas Geistert, Tobias Senst and Thomas Sikora, Robust Local Optical Flow: Dense Motion Vector Field Interpolation, PCS 2016
[383]
MDFlow-Fast
Lingtong Kong and Jie Yang. MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation, TCSVT 2022.
[384]
CNet
Anonymous.
[385]
CARflow
[386]
OAS-Net
Lingtong Kong, Xiaohang Yang and Jie Yang. OAS-Net: Occlusion Aware Sampling Network for Accurate Optical Flow, ICASSP 2021.
[387]
PWC-Net+
Deqing Sun, Xiaodong Yang, Ming-Yu Liu, and Jan Kautz. Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation. TPAMI, to appear. arXiv link https://arxiv.org/abs/1809.05571
[388]
pwc_xx
[389]
DMF_ROB
Baseline submission for ROB flow challenge: Deepflow with Deepmatching as prior
[390]
AnisoHuber.L1
M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009.
[391]
SDFlow
Anonymous.
[392]
ICALD
M. Stoll, D. Maurer, S. Volz and A. Bruhn. Illumination-Aware Large Displacement Optical Flow. EMMCVPR 2017.
[393]
Devon
Anonymous. CVPR submission #1906
[394]
FlowNetC+ft+v
Anonymous. ICCV sumbmission 235
[395]
SelFlow
Pengpeng Liu, Michael R. Lyu, Irwin King, Jia Xu. SelFlow: Self-Supervised Learning of Optical Flow (CVPR 2019)
[396]
FlowNetS+ft+v
Anonymous. ICCV submission 235
[397]
ARFlow-base
Anonymous. ARFlow-base
[398]
SVFilterOh
Mohamed A. Helala, Faisal Z. Qureshi, Fast Estimation of Large Displacement Optical Flow Using Dominant Motion Patterns & Sub-Volume PatchMatch Filtering, CRV 2017
[399]
FastFlow
Anonymous.
[400]
RAFT-GT
Anonymous. CVPR 2021 submission
[401]
MRDFlow
Anonymous.
[402]
DeepDiscreteFlow
F. Güney and A. Geiger. Deep Discrete Flow. Asian Conference on Computer Vision (ACCV) 2016.
[403]
PPM
Parametric PatchMatch, Fangjun Kuang, master thesis, 2017
[404]
FastFlowNet-ft+
Anonymous.
[405]
DeepFlow2
J. Revaud, P. Weinzaepfel, Z. Harchaoui and C. Schmid. DeepMatching: Hierarchical Deformable Dense Matching. Submitted to IJCV.
[406]
ARFlow
Liang Liu, Jiangning Zhang, Ruifei He, Yong Liu, Yabiao Wang, Ying Tai, et al. Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation. CVPR 2020.
[407]
Pwc_ps
Anonymous.
[408]
CompactFlowNet
Anonymous.
[409]
Steered-L1
Anonymous.
[410]
FastFlowNet
Lingtong Kong, Chunhua Shen and Jie Yang. FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation, ICRA 2021.
[411]
OIFlow
occlusion-inpainting Flow
[412]
SPyNet+ft
Ranjan, Anurag and Black, Michael J., Optical Flow Estimation using a Spatial Pyramid Network, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017
[413]
FDFlowNet
Lingtong Kong and Jie Yang. FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network, ICIP 2020.
[414]
DDCNet_B0_tf_sintel
Anonymous. DDCNet_B0 fine-tuned on Sintel
[415]
TF+OFM
R. Kennedy and C.J. Taylor. Optical Flow with Geometric Occlusion Estimation and Fusion of Multiple Frames. EMMCVPR 2015.
[416]
FullFlow+KF
W. Bao, Y. Xiao, L. Chen, and Z. Gao. Kalmanflow: Efficient Kalman Filtering for Video Optical Flow. ICIP 2018.
[417]
SJTU_PAMI418
[418]
COF
H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[419]
VCN-WARP
Anonymous.
[420]
DDFlow
Pengpeng Liu, Irwin King, Michael R. Lyu, Jia Xu.  DDFlow: Learning Optical Flow with Unlabeled Data Distillation.  Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), Jan 2019
[421]
ResPWCR_ROB
Anonymous.
[422]
SparseFlowFused
Radu Timofte and Luc Van Gool. SparseFlow: Sparse Matching for Small to Large Displacement Optical Flow. WACV 2015
[423]
htjnewfull
Anonymous. a
[424]
DSPyNet+ft
Zefeng Sun and Hanli Wang, Deeper Spatial Pyramid Network with Refined Up-Sampling for Optical Flow Estimation, 2018 Pacific Rim Conference on Multimedia (PCM'18), LNCS 11164, pp. 492-501, 2018.
[425]
htjwarp2
Anonymous. htjwarp2
[426]
EPIflow
Deep Epipolar Flow
[427]
FastFlow2
Anonymous.
[428]
mask
Anonymous. mask
[429]
Classic++
D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR, pages 2432-2439, 2010.
[430]
ER-FLOW2
Anonymous. Adjusted ERFlow
[431]
SegPM+Interpolation
SegPM+Interpolation
[432]
ComponentFusion
Anonymous. Fast Optical Flow by Component Fusion. Submitted to ECCV 2014. Paper ID 941.
[433]
SPyNet
Ranjan, Anurag and Black, Michael J., Optical Flow Estimation using a Spatial Pyramid Network, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017
[434]
TV-L1+EM
V. Lazcano. EXHAUSTIVE MATCHING EMPIRICAL STUDY FOR IMPROVING THE MOTION FIELD ESTIMATION
[435]
BOOM+PF.XY
Fast optical flow method (0.54s single core i7 @3.1GHz) that employs the permeability filter to interpolate NNF correspondences. The NNF is an improved version of CPM that uses a new binary descriptor termed BOOM instead of SiftFlow in order to efficiently compute matching costs. Publication: Towards Edge-Aware Spatio-Temporal Filtering in Real-Time. M. Schaffner, F. Scheidegger, L. Cavigelli, H. Kaeslin, L. Benini and A. Smolic. Accepted for publication in Trans. on Image Processing (TIP), 2017. DOI: 10.1109/TIP.2017.2757259
[436]
Deep+R
B. Drayer and T. Brox. Combinatorial Regularization of Descriptor Matching for Optical Flow Estimation. BMVC 2015
[437]
FullFlow
Q. Chen, V. Koltun. Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids. CVPR 2016.
[438]
LDOF
T. Brox, J. Malik. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(3): 500-513, 2011.
[439]
ERFlow
Anonymous.
[440]
Deep-EIP
Anonymous. End-2-End learning for energy based inpainting of optical flow. ACCV submission 572
[441]
DeepFlow
P. Weinzaepfel, J. Revaud, Z. Harchaoui and C. Schmid. DeepFlow: Large displacement optical flow with deep matching. ICCV 2013.
[442]
TVL1_BWMFilter
Balanced Weighted Median Filter and Bilateral Filter.
[443]
TV-L1
Anonymous. It is a well-known model that uses TV-L1 (coupled) as the regularization term and an L1 data term.
[444]
WOLF_ROB
[445]
UPFlow
[446]
ZZZ
Anonymous.
[447]
NLTGV-SC
R. Ranftl, K. Bredies, T. Pock. Non-Local Total Generalized Variation for Optical Flow Estimation, ECCV 2014
[448]
SAnet
Anonymous.
[449]
FAOP-Flow
Anonymous.
[450]
FALDOI
Roberto P.Palomares, Enric Meinhardt-Llopis, Coloma Ballester and Gloria Haro. FALDOI: A new minimization strategy for large displacement variational optical flow. To appear in JMIV
[451]
BOOM+PF.XYT
Fast optical flow method (0.59s single core i7 @3.1GHz) that employs the permeability filter to interpolate NNF correspondences. The NNF is an improved version of CPM that uses a new binary descriptor termed BOOM instead of SiftFlow in order to efficiently compute matching costs. Publication: Towards Edge-Aware Spatio-Temporal Filtering in Real-Time. M. Schaffner, F. Scheidegger, L. Cavigelli, H. Kaeslin, L. Benini and A. Smolic. Accepted for publication in Trans. on Image Processing (TIP), 2017. DOI: 10.1109/TIP.2017.2757259
[452]
DF-Auto
Nelson Monzón, Agustín Salgado and Javier Sánchez. Regularization Strategies for Discontinuity-Preserving Optical Flow Methods. IEEE Transactions on Image Processing, Vol 25(4), pp. 1580 - 1591, 2016
[453]
FlowNetC-MD
Anonymous.
[454]
M-1px
Anonymous.
[455]
DF-Beta
Nelson Monzón, Agustín Salgado and Javier Sánchez. Regularization Strategies for Discontinuity-Preserving Optical Flow Methods. IEEE Transactions on Image Processing, Vol 25(4), pp. 1580 - 1591, 2016
[456]
IPOL_Brox
J. Sánchez, N. Monzón, and A. Salgado, Robust Optical Flow Estimation, Image Processing On Line (IPOL), 3 (2013), pp. 252–270.
[457]
DF
Nelson Monzón, Agustín Salgado and Javier Sánchez. Regularization Strategies for Discontinuity-Preserving Optical Flow Methods. IEEE Transactions on Image Processing, Vol 25(4), pp. 1580 - 1591, 2016
[458]
HSVFlow
Syed Tafseer Haider Shah, Xiang Xuezhi, Harbin Engineering University. Photometric Invariance of Optical Flow With Color Space Transformations
[459]
PCA-Layers
J. Wulff and M. J. Black: Efficient sparse-to-dense optical flow estimation using a learned basis and layers. CVPR 2015.
[460]
Horn+Schunck
A modern Matlab implementation of the Horn & Schunck method by Deqing Sun.
[461]
DDCNet_B1_ft-sintel
DDCNet B1 finetuned on Sintel
[462]
FlowNetADF
Lightweight Probabilistic Deep Networks
[463]
TVL1_RVC
RVC 2020 baseline submission, based on: J. Sanchez, E. Meinhardt-Llopis, and G. Facciolo
[464]
TVL1_ROB
Baseline submission for the robust vision flow challenge: TV-L1 Optical Flow Estimation
[465]
FlowNetProbOut
Lightweight Probabilistic Deep Networks
[466]
DictFlowS
Anonymous.
[467]
HCOF+multi
R. Kennedy and C. J. Taylor. Hierarchically-Constrained Optical Flow. CVPR 2015.
[468]
Back2FutureFlow_UFO
J. Janai, F. Güney, A. Ranjan, M. Black and A. Geiger. Unsupervised Learning of Multi-Frame Optical Flow with Occlusions. ECCV, 2018.
[469]
DSPyNet
Zefeng Sun and Hanli Wang, Deeper Spatial Pyramid Network with Refined Up-Sampling for Optical Flow Estimation, 2018 Pacific Rim Conference on Multimedia (PCM'18), LNCS 11164, pp. 492-501, 2018.
[470]
RGBFlow
Syed Tafseer Haider Shah, Xiang Xuezhi, Harbin Engineering University. Photometric Invariance of Optical Flow With Color Space Transformations
[471]
Data-Flow
Anonymous. CSAD data cost + second order smoothness
[472]
AutoScaler+
Anonymous. AutoScaler+
[473]
Grts-Flow-V2
En Zhu, Yuanwei Li, Yanling Shi. Fast Optical Flow Estimation without Parallel Architectures. TCSVT
[474]
UnFlow
Anonymous.
[475]
CPNFlow
Conditional Prior Networks for Optical Flow, Yanchao Yang, Stefano Soatto; The European Conference on Computer Vision (ECCV), 2018, pp. 271-287
[476]
PCA-Flow
J. Wulff and M. J. Black: Efficient sparse-to-dense optical flow estimation using a learned basis and layers. CVPR 2015.
[477]
RC-LSTM-4dir
Learning Contextual Dependencies for Optical Flow with Recurrent Neural Networks (ACCV 2016)
[478]
2bit-BM-tele
Rui Xu & David Taubman, Robust Dense Block-Based Motion Estimation Using a Two-Bit Transform on a Laplacian Pyramid, ICIP 2013 +telescopic search
[479]
EPPM
L. Bao, Q. Yang, and H. Jin. Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow. CVPR 2014.
[480]
RC-LSTM-1dir
Learning Contextual Dependencies for Optical Flow with Recurrent Neural Networks (ACCV 2016)
[481]
AnyFlow
Anonymous. PAMI pending review
[482]
TVL1_LD_GF
V. Lazcano. TVL1 to handle large displacements using gradient patches. Parameter where optimized using PSO.
[483]
SFL
Jingchun Cheng, Yi-Hsuan, Tsai, Shengjin Wang, Ming-Hsuan Yang. SegFlow: Joint Learning for Video Object Segmentation and Optical Flow. ICCV 2017
[484]
flownetnew
[485]
H+S_ROB
Baseline submission for the ROB flow challenge: Horn-Schunck Optical Flow with a Multi-Scale Strategy
[486]
testS
[487]
FlowNetC+OFR
Anonymous.
[488]
AtrousFlow
Anonymous. Real-time dense optical flow using CUDA
[489]
DIS-Fast
T. Kroeger, R. Timofte, D. Dai, L. Van Gool, Fast Optical Flow using Dense Inverse Search. ECCV 2016. Run-time: 0.023 s (20ms preprocessing, 3ms flow computation). Using operating point 2 of the paper.
[490]
OatNet01
Anonymous.
[491]
PosetOptimization
Anonymous.
[492]
H-1px
Anonymous.
[493]
H+S_RVC
RVC 2020 baseline submission, based on: E. Meinhardt-Llopis, J. Sanchez, and D. Kondermann.
[494]
WKSparse
[495]
Model_model
Anonymous. this is a model
[496]
BASELINE-zero
[497]
AVG_FLOW_ROB
Average flow field of ROB2018 training set. No image information used!
[498]
BASELINE-Mean
[499]
S2D-Matching
M. Leordeanu, A. Zanfir, C. Sminchisescu. Locally Affine Sparse-to-Dense Matching for Motion and Occlusion estimation. ICCV 2013
[500]
C-2px
Anonymous.
[501]
cascade
Anonymous.