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
MR-Flow [2] 2.527 0.954 15.365 2.866 0.710 0.420 0.446 1.715 14.826 Visualize Results
ProFlow_ROB [3] 2.709 1.013 16.549 2.843 0.723 0.518 0.485 1.586 16.470 Visualize Results
ProFlow [4] 2.818 1.027 17.428 2.892 0.751 0.496 0.469 1.626 17.369 Visualize Results
CompactFlow_mix [5] 2.862 1.208 16.364 3.310 1.051 0.414 0.516 1.647 17.457 Visualize Results
SfM-PM [6] 2.910 1.016 18.357 2.797 0.756 0.479 0.559 1.732 17.431 Visualize Results
FlowFields++ [7] 2.943 0.850 20.027 2.550 0.603 0.403 0.560 1.859 17.401 Visualize Results
CompactFlow_ROB [8] 3.004 1.277 17.115 3.370 1.169 0.441 0.514 1.650 18.663 Visualize Results
FlowFields+ [9] 3.102 0.820 21.718 2.340 0.616 0.373 0.593 1.865 18.549 Visualize Results
DIP-Flow [10] 3.103 0.881 21.227 2.574 0.681 0.419 0.548 1.801 18.979 Visualize Results
PST [11] 3.110 0.942 20.809 2.759 0.664 0.378 0.635 2.069 17.919 Visualize Results
MPIF [12] 3.111 1.134 19.218 3.070 0.939 0.523 0.616 1.980 18.220 Visualize Results
PGM-C [13] 3.234 0.929 22.045 2.724 0.659 0.424 0.567 1.999 19.467 Visualize Results
CPM2 [14] 3.253 0.980 21.812 2.663 0.751 0.416 0.615 1.954 19.503 Visualize Results
MirrorFlow [15] 3.316 1.338 19.470 3.684 1.165 0.487 0.566 1.853 20.523 Visualize Results
DiscreteFlow+OIR [16] 3.331 0.942 22.817 2.794 0.712 0.442 0.583 1.948 20.318 Visualize Results
ContinualFlow_ROB [17] 3.341 1.752 16.292 4.057 1.656 0.792 0.512 1.941 20.755 Visualize Results
FlowSAC_ff [18] 3.346 0.972 22.712 2.666 0.822 0.444 0.524 1.986 20.648 Visualize Results
SegFlow33 [19] 3.356 1.033 22.322 2.592 0.769 0.524 0.686 1.937 20.062 Visualize Results
MFF [20] 3.423 1.381 20.099 3.783 1.233 0.486 0.698 2.144 20.062 Visualize Results
LiteFlowNet2 [21] 3.449 1.350 20.609 3.292 1.218 0.564 0.574 1.795 21.757 Visualize Results
PWC-Net+ [22] 3.454 1.413 20.116 3.917 1.247 0.490 0.751 2.230 19.846 Visualize Results
S2F-IF [23] 3.500 0.988 23.986 2.629 0.816 0.533 0.524 1.976 21.960 Visualize Results
SPM-BPv2 [24] 3.515 1.020 23.865 2.603 0.841 0.521 0.474 1.773 22.830 Visualize Results
3DFlow [25] 3.520 1.086 23.385 3.039 0.879 0.485 0.440 1.841 22.879 Visualize Results
DCFlow [26] 3.537 1.103 23.394 2.897 0.868 0.632 0.703 2.015 21.296 Visualize Results
RicFlow [27] 3.550 1.264 22.220 3.248 1.023 0.576 0.601 2.203 21.465 Visualize Results
CompactFlow [28] 3.557 1.266 22.253 3.216 1.140 0.568 0.531 1.657 23.183 Visualize Results
CPM-Flow [29] 3.557 1.189 22.889 3.032 0.973 0.613 0.592 2.064 21.900 Visualize Results
IRR [30] 3.560 1.333 21.742 3.337 1.153 0.553 0.618 1.830 22.369 Visualize Results
DiscreteFlow [31] 3.567 1.108 23.626 3.398 0.799 0.446 0.703 2.277 20.906 Visualize Results
DCFlow+KF [32] 3.585 1.142 23.502 3.036 0.921 0.630 0.597 2.017 22.208 Visualize Results
FullFlow+KF [33] 3.598 1.247 22.779 2.957 0.977 0.677 0.844 1.974 21.212 Visualize Results
SF_Net [34] 3.599 1.375 21.752 3.102 1.144 0.720 0.527 1.640 23.598 Visualize Results
FlowSAC_dcf [35] 3.600 1.161 23.506 2.972 0.930 0.712 0.716 2.121 21.502 Visualize Results
FullFlow [36] 3.601 1.296 22.424 2.944 1.023 0.732 0.933 2.055 20.612 Visualize Results
AugFNG_ROB [37] 3.606 1.603 19.939 3.637 1.376 0.868 0.666 2.142 21.736 Visualize Results
CPM_AUG [38] 3.609 1.135 23.804 2.945 0.935 0.516 0.615 2.099 22.137 Visualize Results
PatchBatch+Inter [39] 3.624 1.324 22.397 3.076 1.115 0.673 0.589 1.824 23.062 Visualize Results
ProbFlowFields [40] 3.631 1.061 24.603 2.719 0.887 0.607 0.551 2.105 22.619 Visualize Results
DCFlow+KF2 [41] 3.645 1.149 23.992 3.037 0.932 0.640 0.586 1.974 22.867 Visualize Results
CVPR-236+ft [42] 3.745 1.449 22.502 3.616 1.374 0.592 0.397 1.570 25.664 Visualize Results
FlowFields [43] 3.748 1.056 25.700 2.784 0.878 0.570 0.546 2.110 23.602 Visualize Results
PWC-Net+KF2 [44] 3.753 1.588 21.445 3.657 1.298 0.723 0.460 1.863 24.700 Visualize Results
FlowFieldsCNN [45] 3.778 0.996 26.469 2.604 0.796 0.631 0.648 2.017 23.582 Visualize Results
PWC-Net+KF [46] 3.850 1.595 22.276 3.664 1.302 0.734 0.459 1.957 25.289 Visualize Results
InterpoNet_df [47] 3.862 1.193 25.632 3.613 0.885 0.508 0.581 2.253 24.038 Visualize Results
DeepDiscreteFlow [48] 3.863 1.296 24.820 3.077 0.975 0.803 0.794 2.024 23.575 Visualize Results
SegFlow113 [49] 3.869 1.132 26.210 2.855 0.942 0.667 0.550 1.945 25.018 Visualize Results
FlowSR [50] 3.875 1.718 21.497 3.956 1.431 0.796 0.617 2.035 24.524 Visualize Results
PWC-Net_ROB [51] 3.897 1.726 21.637 3.950 1.425 0.812 0.618 2.033 24.705 Visualize Results
SBFlow [52] 3.930 1.285 25.541 3.352 1.093 0.614 0.569 2.161 24.922 Visualize Results
InterpoNet_ff [53] 3.952 1.232 26.121 3.600 0.946 0.573 0.571 2.228 24.900 Visualize Results
FF++_ROB [54] 3.953 1.148 26.836 3.255 0.910 0.519 0.582 2.351 24.562 Visualize Results
FlowNet2 [55] 3.959 1.468 24.294 3.089 1.319 0.920 0.643 1.898 25.422 Visualize Results
InterpoNet_dm [56] 3.973 1.412 24.852 4.015 1.032 0.636 0.706 2.142 24.619 Visualize Results
TIMCflow [57] 3.979 1.249 26.243 3.775 0.904 0.540 0.567 2.079 25.518 Visualize Results
EPMNet [58] 3.986 1.502 24.251 3.230 1.349 0.908 0.695 1.981 25.181 Visualize Results
PPM [59] 4.026 1.167 27.353 2.783 0.847 0.690 0.797 2.093 24.748 Visualize Results
InterpoNet_cpm [60] 4.086 1.371 26.222 3.992 1.064 0.569 0.637 2.325 25.466 Visualize Results
EpicFlow [61] 4.115 1.360 26.595 3.660 1.079 0.599 0.712 2.117 25.859 Visualize Results
GlobalPatchCollider [62] 4.134 1.432 26.179 3.914 1.268 0.554 0.613 2.232 26.222 Visualize Results
SegFlowd015 [63] 4.151 1.246 27.855 3.072 1.143 0.656 0.486 2.000 27.563 Visualize Results
FlowNet2-ft-sintel [64] 4.157 1.557 25.403 3.272 1.461 0.856 0.597 1.890 27.347 Visualize Results
Devon [65] 4.343 1.742 25.577 4.115 1.531 0.816 0.763 2.449 26.716 Visualize Results
IHBPFlow [66] 4.347 1.476 27.746 3.573 1.155 0.895 0.577 2.245 28.145 Visualize Results
PWC-Net [67] 4.386 1.719 26.166 4.282 1.657 0.674 0.606 2.070 28.793 Visualize Results
PH-Flow [68] 4.388 1.714 26.202 3.612 1.713 0.834 0.590 2.430 27.997 Visualize Results
LiteFlowNet [69] 4.539 1.630 28.291 3.274 1.438 0.928 0.500 1.733 31.412 Visualize Results
FGI [70] 4.664 1.540 30.110 3.771 1.336 0.850 0.669 2.310 30.185 Visualize Results
AggregFlow [71] 4.754 1.694 29.685 3.705 1.603 0.981 0.650 2.251 31.184 Visualize Results
F3-MPLF [72] 4.771 2.063 26.863 3.458 1.809 1.244 0.678 1.884 32.091 Visualize Results
DeepFlow2 [73] 4.891 1.403 33.317 3.714 1.119 0.626 0.800 2.210 31.690 Visualize Results
SegFlow193 [74] 4.893 1.570 31.973 3.375 1.450 1.157 0.533 2.064 33.382 Visualize Results
TF+OFM [75] 4.917 1.874 29.735 3.676 1.689 1.309 0.839 2.349 31.391 Visualize Results
FALDOI [76] 4.927 1.542 32.535 3.307 1.318 0.885 1.047 2.647 29.719 Visualize Results
Deep+R [77] 5.041 1.481 34.047 3.710 1.102 0.722 0.929 2.333 31.999 Visualize Results
FAOP-Flow [78] 5.065 1.349 35.368 3.548 1.044 0.694 1.028 2.726 30.774 Visualize Results
2chPWC-Net-ft [79] 5.113 2.099 29.719 3.879 1.929 1.301 0.629 1.955 35.051 Visualize Results
SPM-BP [80] 5.202 1.815 32.839 4.008 1.704 1.179 0.643 2.576 34.214 Visualize Results
BOOM+PF.XY [81] 5.204 1.696 33.826 3.512 1.540 1.021 0.927 2.921 31.976 Visualize Results
SparseFlowFused [82] 5.257 1.627 34.834 4.211 1.397 0.729 0.880 2.567 33.489 Visualize Results
HTC [83] 5.295 2.037 31.897 3.453 1.820 1.468 0.515 1.547 38.125 Visualize Results
BOOM+PF.XYT [84] 5.311 1.820 33.809 3.552 1.661 1.180 1.049 3.031 32.008 Visualize Results
DMF_ROB [85] 5.368 1.742 34.899 4.271 1.613 0.831 0.753 2.511 35.180 Visualize Results
DeepFlow [86] 5.377 1.771 34.751 4.519 1.534 0.837 0.960 2.730 33.701 Visualize Results
PMF [87] 5.378 1.858 34.102 3.877 1.835 1.235 0.628 2.428 36.128 Visualize Results
NNF-Local [88] 5.386 1.397 37.896 2.722 1.341 1.004 0.683 2.245 36.342 Visualize Results
Deep-EIP [89] 5.434 2.023 33.258 3.793 1.837 1.614 0.952 2.147 35.657 Visualize Results
SVFilterOh [90] 5.540 2.043 34.067 3.875 1.865 1.625 0.778 2.713 36.033 Visualize Results
PatchWMF-OF [91] 5.550 1.781 36.257 3.339 1.843 1.277 0.581 2.612 37.319 Visualize Results
FDFlowNet [92] 5.594 2.541 30.532 4.406 2.435 1.574 1.024 2.555 35.665 Visualize Results
ResPWCR_ROB [93] 5.674 3.138 26.380 4.941 2.769 2.127 0.879 2.506 37.143 Visualize Results
PCA-Layers [94] 5.730 2.455 32.468 5.447 2.337 1.415 1.129 3.051 35.079 Visualize Results
WLIF-Flow [95] 5.734 1.759 38.125 3.242 1.818 1.296 0.597 2.512 39.036 Visualize Results
AGIF+OF [96] 5.766 1.695 38.936 3.034 1.709 1.329 0.613 2.554 39.121 Visualize Results
PatchBatch-CENT+SD [97] 5.789 2.743 30.599 5.232 2.756 1.492 0.492 1.801 41.746 Visualize Results
LocalLayering [98] 5.820 2.143 35.784 3.817 2.342 1.399 0.580 2.461 39.976 Visualize Results
MDP-Flow2 [99] 5.837 1.869 38.158 3.210 1.913 1.441 0.640 2.603 39.459 Visualize Results
ICALD [100] 6.002 2.376 35.550 4.835 2.636 1.213 0.758 3.459 38.169 Visualize Results
ZZZ [101] 6.027 1.681 41.429 3.637 1.547 1.038 0.994 2.809 38.798 Visualize Results
ComponentFusion [102] 6.065 2.033 38.912 4.114 2.063 1.213 0.910 2.996 39.074 Visualize Results
AnyFlow [103] 6.066 2.412 35.852 5.211 2.432 1.215 1.429 3.665 34.900 Visualize Results
AutoScaler+ [104] 6.076 2.569 34.656 4.610 2.195 1.863 1.298 3.737 35.431 Visualize Results
FlowNetC+ft+v [105] 6.081 2.576 34.620 5.079 2.371 1.480 0.764 2.686 40.676 Visualize Results
FlowNetS+ft+v [106] 6.158 2.800 33.491 5.535 2.687 1.563 0.766 2.938 40.686 Visualize Results
DDFlow [107] 6.176 2.269 38.053 4.208 2.084 1.416 0.860 2.562 41.337 Visualize Results
SparseFlow [108] 6.197 2.357 37.460 4.642 2.273 1.392 0.681 2.533 42.422 Visualize Results
M-1px [109] 6.209 1.783 42.262 3.807 1.625 1.093 1.078 3.081 39.236 Visualize Results
DSPyNet+ft [110] 6.224 2.743 34.602 5.102 2.937 1.562 0.881 2.842 40.954 Visualize Results
OAR-Flow [111] 6.227 2.760 34.455 5.639 3.096 1.375 0.648 3.132 41.378 Visualize Results
ContFusion [112] 6.263 2.518 36.767 5.092 2.801 1.302 0.694 3.115 41.506 Visualize Results
Grts-Flow-V2 [113] 6.415 2.664 36.995 5.177 2.482 1.773 1.310 3.983 37.635 Visualize Results
EPPM [114] 6.494 2.675 37.632 4.997 2.422 1.948 1.402 3.446 39.152 Visualize Results
COF [115] 6.496 2.849 36.216 5.679 3.176 1.450 0.859 3.656 41.334 Visualize Results
GeoFlow [116] 6.527 2.420 40.043 3.945 2.193 1.857 0.723 2.620 44.833 Visualize Results
DSPyNet [117] 6.552 3.105 34.690 5.497 3.351 1.857 1.225 3.365 40.738 Visualize Results
CVPR-236 [118] 6.555 2.665 38.298 4.816 2.532 1.661 0.766 2.277 45.691 Visualize Results
SPyNet+ft [119] 6.640 3.013 36.190 5.501 3.122 1.719 0.832 3.343 43.442 Visualize Results
SPyNet [120] 6.689 3.020 36.596 5.770 3.289 1.562 0.911 3.455 43.207 Visualize Results
RC-LSTM-4dir [121] 6.694 3.419 33.345 5.930 3.513 2.162 1.375 3.826 39.961 Visualize Results
RC-LSTM-1dir [122] 6.717 3.445 33.352 5.916 3.527 2.209 1.410 3.820 40.001 Visualize Results
HCOF+multi [123] 6.717 3.244 35.046 5.724 3.175 2.290 1.223 4.158 40.158 Visualize Results
Classic+NLP [124] 6.731 2.949 37.545 5.573 3.291 1.648 0.638 3.296 45.290 Visualize Results
FC-2Layers-FF [125] 6.781 3.053 37.144 5.841 3.390 1.688 0.580 3.308 45.962 Visualize Results
HAST [126] 6.802 3.081 37.112 4.641 3.111 2.245 0.683 3.022 46.330 Visualize Results
PCA-Flow [127] 6.828 3.014 37.939 6.444 3.038 1.655 1.363 3.484 42.048 Visualize Results
EPIflow [128] 6.836 2.868 39.232 5.060 2.653 1.802 0.852 2.717 46.552 Visualize Results
CNet [129] 6.866 3.122 37.403 4.890 3.002 2.283 0.743 2.405 48.087 Visualize Results
JOF [130] 6.920 3.080 38.195 5.983 3.416 1.678 0.583 2.474 49.143 Visualize Results
WOLF_ROB [131] 6.947 3.238 37.153 5.828 3.405 1.835 0.976 3.454 45.036 Visualize Results
Channel-Flow [132] 7.023 3.086 39.084 5.411 3.236 1.918 0.624 2.791 49.021 Visualize Results
Back2FutureFlow [133] 7.227 3.603 36.779 6.100 3.497 2.458 1.224 4.003 44.836 Visualize Results
DeformableFlow [134] 7.232 3.810 35.142 6.016 3.945 2.555 1.144 3.821 45.676 Visualize Results
IPOL_Brox [135] 7.283 3.150 40.931 5.705 3.347 1.831 1.090 3.647 46.796 Visualize Results
MLDP-OF [136] 7.297 3.260 40.183 5.581 3.304 2.007 0.600 2.916 51.146 Visualize Results
DF-Beta [137] 7.391 3.153 41.890 5.492 3.337 1.895 1.087 3.597 47.836 Visualize Results
DF [138] 7.406 3.164 41.936 5.504 3.345 1.908 1.091 3.594 47.949 Visualize Results
SFL [139] 7.455 4.129 34.548 7.148 4.322 2.448 1.437 4.756 43.773 Visualize Results
FlowNetADF [140] 7.464 3.915 36.404 6.853 4.094 2.377 1.171 4.412 46.057 Visualize Results
FlowNetProbOut [141] 7.472 3.888 36.700 6.833 4.056 2.424 1.196 4.422 45.962 Visualize Results
LDOF [142] 7.563 3.432 41.170 5.353 3.284 2.454 0.936 2.908 51.696 Visualize Results
CPNFlow [143] 7.660 3.853 38.695 6.804 4.130 2.223 1.347 3.952 47.942 Visualize Results
TV-L1+EM [144] 7.675 3.340 42.946 6.277 3.576 1.962 0.914 3.549 51.185 Visualize Results
NLTGV-SC [145] 7.680 3.565 41.168 6.132 3.801 2.170 0.996 3.557 50.808 Visualize Results
IIOF-NLDP [146] 7.796 3.806 40.287 6.651 4.175 2.300 0.731 3.328 53.670 Visualize Results
Classic+NL [147] 7.961 3.770 42.079 6.191 3.911 2.509 0.573 2.694 57.374 Visualize Results
Data-Flow [148] 7.972 3.494 44.527 6.341 3.665 1.921 1.258 3.970 51.049 Visualize Results
RLOF_DENSE [149] 7.977 3.887 41.315 6.689 4.005 2.415 0.739 3.080 55.766 Visualize Results
ROF-NND [150] 8.061 3.944 41.603 6.365 4.145 2.756 0.717 3.301 56.051 Visualize Results
TVL1_ROB [151] 8.233 4.012 42.600 7.010 4.432 2.381 1.172 4.480 52.331 Visualize Results
WRTflow [152] 8.236 4.048 42.320 6.413 4.250 2.774 0.598 3.106 58.550 Visualize Results
DF-Auto [153] 8.480 3.945 45.399 6.445 4.149 2.537 1.057 3.732 56.780 Visualize Results
Classic++ [154] 8.721 4.259 45.047 6.983 4.494 2.753 0.902 3.295 60.645 Visualize Results
Horn+Schunck [155] 8.739 4.525 43.032 7.542 5.045 2.891 1.141 3.860 58.243 Visualize Results
Classic+NL-fast [156] 9.129 4.725 44.956 7.157 4.974 3.331 0.558 2.812 66.935 Visualize Results
2bit-BM-tele [157] 9.274 4.219 50.491 6.233 4.119 3.323 1.390 4.564 59.833 Visualize Results
DIS-Fast [158] 9.353 5.165 43.503 8.317 5.677 3.212 1.906 4.899 57.071 Visualize Results
UnFlow [159] 9.379 5.365 42.105 7.853 5.151 3.886 1.312 5.116 59.713 Visualize Results
TV-L1 [160] 9.471 4.875 46.845 7.630 5.151 3.337 0.976 3.856 65.165 Visualize Results
OF_OCC_LD [161] 9.675 5.296 45.288 7.996 5.632 3.694 0.605 3.025 70.740 Visualize Results
PosetOptimization [162] 9.874 3.639 60.633 5.005 3.366 3.207 1.981 6.486 57.189 Visualize Results
H-1px [163] 10.148 4.454 56.545 6.832 4.306 3.637 2.173 6.606 58.262 Visualize Results
Steered-L1 [164] 10.864 6.018 50.244 7.976 6.187 4.832 0.811 6.049 72.292 Visualize Results
SimpleFlow [165] 12.617 7.848 51.435 10.693 8.422 6.170 0.711 8.411 81.786 Visualize Results
AnisoHuber.L1 [166] 12.642 7.983 50.472 10.457 8.675 6.320 0.753 9.976 77.835 Visualize Results
H+S_ROB [167] 13.278 8.654 50.879 11.490 9.560 6.700 1.552 10.011 79.168 Visualize Results
AtrousFlow [168] 14.200 9.584 51.758 11.964 10.338 7.926 1.702 12.440 80.185 Visualize Results
BASELINE-Mean [169] 15.422 11.488 47.336 14.676 12.649 9.350 5.310 14.717 66.922 Visualize Results
WKSparse [170] 15.765 11.414 51.045 13.469 11.864 10.609 2.756 15.781 81.907 Visualize Results
S2D-Matching [171] 18.485 13.372 59.935 13.676 12.747 12.149 9.472 15.466 70.185 Visualize Results
AVG_FLOW_ROB [172] 18.799 14.422 54.251 16.903 15.516 12.457 4.566 19.946 86.008 Visualize Results
BASELINE-zero [173] 18.926 14.396 55.633 17.050 15.613 12.172 4.049 20.873 87.342 Visualize Results
C-2px [174] 44.062 37.047 101.160 37.366 36.580 37.093 34.342 35.847 112.424 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]
MR-Flow
J. Wulff, L. Sevilla-Lara, M. J. Black: Optical Flow in Mostly Rigid Scenes. CVPR 2017.
[3]
ProFlow_ROB
D. Maurer, A. Bruhn: ProFlow: Learning to Predict Optical Flow. BMVC 2018. (ROB setting)
[4]
ProFlow
D. Maurer, A. Bruhn: ProFlow: Learning to Predict Optical Flow. BMVC 2018.
[5]
CompactFlow_mix
Anonymous. We further improve the current flow model by: (1) Parameter sharing, allowing models to train faster (2) Revisit classic shiftable window idea, and adapt the idea to construct a better cost volume for flow estimation.
[6]
SfM-PM
D. Maurer, N. Marniok, B. Goldluecke, A. Bruhn: Structure-from-Motion-Aware PatchMatch for Adaptive Optical Flow Estimation. ECCV 2018.
[7]
FlowFields++
R. Schuster, C. Bailer, O. Wasenmüller, D. Stricker. FlowFields++: Accurate Optical Flow Correspondences Meet Robust Interpolation. ICIP 2018
[8]
CompactFlow_ROB
Anonymous. - parameter sharing - implicit occlusion reasoning
[9]
FlowFields+
C. Bailer, B. Taetz and D. Stricker. Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation. T-PAMI.
[10]
DIP-Flow
D. Maurer, M. Stoll, A. Bruhn: Directional Priors for Multi-Frame Optical Flow. BMVC 2018.
[11]
PST
Anonymous. ACCV2018 submission #1195
[12]
MPIF
Anonymous. multi-level interpolation for optical flow estimation
[13]
PGM-C
Anonymous
[14]
CPM2
Coarse-to-fine PatchMatch for dense correspondence, Yunsong Li, Yinlin Hu, Rui Song, Peng Rao, Yangli Wang, submitted to T-CSVT
[15]
MirrorFlow
Junhwa Hur and Stefan Roth. MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation. ICCV 2017
[16]
DiscreteFlow+OIR
D. Maurer, M. Stoll, A. Bruhn: Order-Adaptive and Illumination Aware Variational Optical Flow Refinement. BMVC 2017.
[17]
ContinualFlow_ROB
Michal Neoral, Jan Šochman and Jiří Matas. Continual Occlusions and Optical Flow Estimation, ACCV 2018
[18]
FlowSAC_ff
Anonymous
[19]
SegFlow33
d0=3, d1=3
[20]
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)
[21]
LiteFlowNet2
Tak-Wai Hui, Xiaoou Tang, and Chen Change Loy
[22]
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. arXiv paper: https://arxiv.org/abs/1809.05571
[23]
S2F-IF
Yanchao Yang, Stefano Soatto. S2F: Slow-To-Fast Interpolator Flow. CVPR 2017.
[24]
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.
[25]
3DFlow
Anonymous. Improved
[26]
DCFlow
Jia Xu, René Ranftl, Vladlen Koltun. Accurate Optical Flow via Direct Cost Volume Processing. CVPR 2017.
[27]
RicFlow
Yinlin Hu, Yunsong Li, Rui Song. Robust Interpolation of Correspondences for Large Displacement Optical Flow. CVPR 2017.
[28]
CompactFlow
Anonymous. We further improve the current flow model by: (1) Parameter sharing, allowing models to train faster (2) Revisit classic shiftable window idea, and adapt the idea to construct a better cost volume for flow estimation.
[29]
CPM-Flow
Yinlin Hu, Rui Song, Yunsong Li. Efficient Coarse-to-Fine PatchMatch for Large Displacement Optical Flow. CVPR 2016.
[30]
IRR
Anonymous. CVPR Submission #2597
[31]
DiscreteFlow
M. Menze, C. Heipke and A. Geiger. Discrete Optimization for Optical Flow. GCPR 2015
[32]
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.
[33]
FullFlow+KF
W. Bao, Y. Xiao, L. Chen, and Z. Gao. Kalmanflow: Efficient Kalman Filtering for Video Optical Flow. ICIP 2018.
[34]
SF_Net
Anonymous. TBA
[35]
FlowSAC_dcf
Anonymous.
[36]
FullFlow
Q. Chen, V. Koltun. Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids. CVPR 2016.
[37]
AugFNG_ROB
Anonymous.
[38]
CPM_AUG
Anonymous. CVPR 18 submission #1939
[39]
PatchBatch+Inter
T. Schuster, L. Wolf and D. Gadot: Optical Flow Requires Multiple Strategies (but only one network). CVPR 2017.
[40]
ProbFlowFields
Anne S. Wannenwetsch, Margret Keuper, Stefan Roth. ProbFlow: Joint Optical Flow and Uncertainty Estimation. ICCV 2017.
[41]
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.
[42]
CVPR-236+ft
Anonymous. Anonymous CVPR Submission 236
[43]
FlowFields
C. Bailer, B. Taetz and D. Stricker. Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation. ICCV 2015.
[44]
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.
[45]
FlowFieldsCNN
C. Bailer, K Varanasi and D. Stricker. CNN-based Patch Matching for Optical Flow with Thresholded Hinge Embedding Loss. CVPR 2017.
[46]
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.
[47]
InterpoNet_df
S. Zweig, L Wolf. InterpoNet, A brain inspired neural network for optical flow dense interpolation. CVPR 2017.
[48]
DeepDiscreteFlow
F. Güney and A. Geiger. Deep Discrete Flow. Asian Conference on Computer Vision (ACCV) 2016.
[49]
SegFlow113
[50]
FlowSR
Anonymous.
[51]
PWC-Net_ROB
Deqing Sun, Xiaodong Yang, Ming-Yu Liu, and Jan Kautz. PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018.
[52]
SBFlow
Fast Optical Flow Estimation Based on the Split Bregman Method. 2016 TCSVT.
[53]
InterpoNet_ff
S. Zweig, L Wolf. InterpoNet, A brain inspired neural network for optical flow dense interpolation. CVPR 2017.
[54]
FF++_ROB
Accurate matching and robust interpolation. KITTI parameters as given by the paper. Edge detector trained on KITTI + Sintel + BSDS500.
[55]
FlowNet2
Anonymous. CVPR Submission #900
[56]
InterpoNet_dm
S. Zweig, L Wolf. InterpoNet, A brain inspired neural network for optical flow dense interpolation. CVPR 2017.
[57]
TIMCflow
Anonymous.
[58]
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.
[59]
PPM
Parametric PatchMatch, Fangjun Kuang, master thesis, 2017
[60]
InterpoNet_cpm
S. Zweig, L Wolf. InterpoNet, A brain inspired neural network for optical flow dense interpolation. CVPR 2017.
[61]
EpicFlow
J. Revaud, P. Weinzaepfel, Z. Harchaoui and C. Schmid. EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow. CVPR 2015.
[62]
GlobalPatchCollider
Shenlong Wang, Sean Fanello, Christoph Rhemann, Shahram Izadi and Pushmeet Kohli, The Global Patch Collider, CVPR, 2016
[63]
SegFlowd015
Anonymous.
[64]
FlowNet2-ft-sintel
Anonymous. CVPR Submission #900
[65]
Devon
Anonymous. CVPR submission #1906
[66]
IHBPFlow
Anonymous.
[67]
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.
[68]
PH-Flow
Jiaolong Yang and Hongdong Li. Dense, Accurate Optical Flow Estimation with Piecewise Parametric Model. CVPR 2015
[69]
LiteFlowNet
Tak-Wai Hui, Xiaoou Tang, and Chen Change Loy. LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018.
[70]
FGI
Y. Li, D. Min, M. N. Do, and J. Lu. Fast Guided Global Interpolation for Depth and Motion. ECCV 2016
[71]
AggregFlow
D. Fortun, P. Bouthemy and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. CVIU 2016
[72]
F3-MPLF
Sathya N. Ravi, Yunyang Xiong, Lopamudra Mukherjee, Vikas Singh: Filter Flow made Practical: Massively Parallel and Lock-Free -- CVPR 2017
[73]
DeepFlow2
J. Revaud, P. Weinzaepfel, Z. Harchaoui and C. Schmid. DeepMatching: Hierarchical Deformable Dense Matching. Submitted to IJCV.
[74]
SegFlow193
d0=19,d1=3
[75]
TF+OFM
R. Kennedy and C.J. Taylor. Optical Flow with Geometric Occlusion Estimation and Fusion of Multiple Frames. EMMCVPR 2015.
[76]
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
[77]
Deep+R
B. Drayer and T. Brox. Combinatorial Regularization of Descriptor Matching for Optical Flow Estimation. BMVC 2015
[78]
FAOP-Flow
Anonymous.
[79]
2chPWC-Net-ft
An Embedding Scheme of Optical Flow Networks with Small Size for Fast and Small Objects, and Occlusions
[80]
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
[81]
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
[82]
SparseFlowFused
Radu Timofte and Luc Van Gool. SparseFlow: Sparse Matching for Small to Large Displacement Optical Flow. WACV 2015
[83]
HTC
Anonymous.
[84]
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
[85]
DMF_ROB
Baseline submission for ROB flow challenge: Deepflow with Deepmatching as prior
[86]
DeepFlow
P. Weinzaepfel, J. Revaud, Z. Harchaoui and C. Schmid. DeepFlow: Large displacement optical flow with deep matching. ICCV 2013.
[87]
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
[88]
NNF-Local
Anonymous. Large Displacement Optical Flow from Nearest Neighbor Fields
[89]
Deep-EIP
Anonymous. End-2-End learning for energy based inpainting of optical flow. ACCV submission 572
[90]
SVFilterOh
Mohamed A. Helala, Faisal Z. Qureshi, Fast Estimation of Large Displacement Optical Flow Using Dominant Motion Patterns & Sub-Volume PatchMatch Filtering, CRV 2017
[91]
PatchWMF-OF
Zhigang Tu, Coert Van Gemeren and Remco C. Veltkamp. Improved Color Patch Similarity Measure Based Weighted Median Filter. ACCV2014
[92]
FDFlowNet
[93]
ResPWCR_ROB
Anonymous.
[94]
PCA-Layers
J. Wulff and M. J. Black: Efficient sparse-to-dense optical flow estimation using a learned basis and layers. CVPR 2015.
[95]
WLIF-Flow
Z. Tu, R. Poppe, and R. C. Veltkamp. Weighted local intensity fusion method for variational optical flow estimation.Pattern Recognition,2015
[96]
AGIF+OF
Anonymous. Signal Processing 2015
[97]
PatchBatch-CENT+SD
Anonymous.
[98]
LocalLayering
D. Sun, C. Liu, and H. Pfister. Local Layering for Joint Motion Estimation and Occlusion Detection. CVPR 2014.
[99]
MDP-Flow2
L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012.
[100]
ICALD
M. Stoll, D. Maurer, S. Volz and A. Bruhn. Illumination-Aware Large Displacement Optical Flow. EMMCVPR 2017.
[101]
ZZZ
Anonymous.
[102]
ComponentFusion
Anonymous. Fast Optical Flow by Component Fusion. Submitted to ECCV 2014. Paper ID 941.
[103]
AnyFlow
Anonymous. PAMI pending review
[104]
AutoScaler+
Anonymous. AutoScaler+
[105]
FlowNetC+ft+v
Anonymous. ICCV sumbmission 235
[106]
FlowNetS+ft+v
Anonymous. ICCV submission 235
[107]
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
[108]
SparseFlow
Radu Timofte and Luc Van Gool. SparseFlow: Sparse Matching for Small to Large Displacement Optical Flow. WACV 2015
[109]
M-1px
Anonymous.
[110]
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.
[111]
OAR-Flow
D. Maurer, M. Stoll, A. Bruhn: Order-Adaptive Regularisation for Variational Optical Flow: Global, Local and in Between. SSVM 2017.
[112]
ContFusion
M. Stoll, D. Maurer, and A. Bruhn. Variational Large Displacement Optical Flow without Feature Matches. EMMCVPR 2017.
[113]
Grts-Flow-V2
En Zhu, Yuanwei Li, Yanling Shi. Fast Optical Flow Estimation without Parallel Architectures. TCSVT
[114]
EPPM
L. Bao, Q. Yang, and H. Jin. Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow. CVPR 2014.
[115]
COF
H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[116]
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.
[117]
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.
[118]
CVPR-236
Anonymous. Anonymous CVPR Submission 236
[119]
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
[120]
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
[121]
RC-LSTM-4dir
Learning Contextual Dependencies for Optical Flow with Recurrent Neural Networks (ACCV 2016)
[122]
RC-LSTM-1dir
Learning Contextual Dependencies for Optical Flow with Recurrent Neural Networks (ACCV 2016)
[123]
HCOF+multi
R. Kennedy and C. J. Taylor. Hierarchically-Constrained Optical Flow. CVPR 2015.
[124]
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.
[125]
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
[126]
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
[127]
PCA-Flow
J. Wulff and M. J. Black: Efficient sparse-to-dense optical flow estimation using a learned basis and layers. CVPR 2015.
[128]
EPIflow
Deep Epipolar Flow
[129]
CNet
Anonymous.
[130]
JOF
Anonymous.
[131]
WOLF_ROB
[132]
Channel-Flow
L. Sevilla-Lara, D. Sun, E. Learned-Miller, and M. Black. Optical Flow Estimation with Channel Constancy. ECCV, pages 423-438, 2014.
[133]
Back2FutureFlow
J. Janai, F. Güney, A. Ranjan, M. Black and A. Geiger. Unsupervised Learning of Multi-Frame Optical Flow with Occlusions. ECCV, 2018.
[134]
DeformableFlow
Anonymous.
[135]
IPOL_Brox
J. Sánchez, N. Monzón, and A. Salgado, Robust Optical Flow Estimation, Image Processing On Line (IPOL), 3 (2013), pp. 252–270.
[136]
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.
[137]
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
[138]
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
[139]
SFL
Jingchun Cheng, Yi-Hsuan, Tsai, Shengjin Wang, Ming-Hsuan Yang. SegFlow: Joint Learning for Video Object Segmentation and Optical Flow. ICCV 2017
[140]
FlowNetADF
Lightweight Probabilistic Deep Networks
[141]
FlowNetProbOut
Lightweight Probabilistic Deep Networks
[142]
LDOF
T. Brox, J. Malik. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(3): 500-513, 2011.
[143]
CPNFlow
Anonymous. ECCV 2018 submission, Paper ID: 448
[144]
TV-L1+EM
V. Lazcano. EXHAUSTIVE MATCHING EMPIRICAL STUDY FOR IMPROVING THE MOTION FIELD ESTIMATION
[145]
NLTGV-SC
R. Ranftl, K. Bredies, T. Pock. Non-Local Total Generalized Variation for Optical Flow Estimation, ECCV 2014
[146]
IIOF-NLDP
Dinh-Hoan Trinh, Walter Blondel, and Christian Daul. A General Form of Illumination-Invariant Descriptors in Variational Optical Flow Estimation. ICIP 2017.
[147]
Classic+NL
D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR, pages 2432-2439, 2010.
[148]
Data-Flow
Anonymous. CSAD data cost + second order smoothness
[149]
RLOF_DENSE
Jonas Geistert, Tobias Senst and Thomas Sikora, Robust Local Optical Flow: Dense Motion Vector Field Interpolation, PCS 2016
[150]
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.
[151]
TVL1_ROB
Baseline submission for the robust vision flow challenge: TV-L1 Optical Flow Estimation
[152]
WRTflow
We proposed a weighted regularization transform to reduce the influence of illumination variations of optical flow estimation. We submit it to TCSVT.
[153]
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
[154]
Classic++
D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR, pages 2432-2439, 2010.
[155]
Horn+Schunck
A modern Matlab implementation of the Horn & Schunck method by Deqing Sun.
[156]
Classic+NL-fast
D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR, pages 2432-2439, 2010.
[157]
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
[158]
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.
[159]
UnFlow
Anonymous.
[160]
TV-L1
Anonymous. It is a well-known model that uses TV-L1 (coupled) as the regularization term and an L1 data term.
[161]
OF_OCC_LD
V. Lazcano, L. Garrido, C. Ballester. Jointly Optical flow and Occlusion Estimation for images with Large Displacements.
[162]
PosetOptimization
Anonymous.
[163]
H-1px
Anonymous.
[164]
Steered-L1
Anonymous.
[165]
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)
[166]
AnisoHuber.L1
M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009.
[167]
H+S_ROB
Baseline submission for the ROB flow challenge: Horn-Schunck Optical Flow with a Multi-Scale Strategy
[168]
AtrousFlow
Anonymous. Real-time dense optical flow using CUDA
[169]
BASELINE-Mean
[170]
WKSparse
[171]
S2D-Matching
M. Leordeanu, A. Zanfir, C. Sminchisescu. Locally Affine Sparse-to-Dense Matching for Motion and Occlusion estimation. ICCV 2013
[172]
AVG_FLOW_ROB
Average flow field of ROB2018 training set. No image information used!
[173]
BASELINE-zero
[174]
C-2px
Anonymous.