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
FlowElements [2] 4.224 1.956 22.704 3.288 1.479 1.419 0.646 1.897 27.596 Visualize Results
PCF-F [3] 4.630 2.197 24.465 3.410 1.737 1.744 0.603 2.131 30.652 Visualize Results
PPAC-HD3 [4] 4.599 2.116 24.852 3.521 1.702 1.637 0.617 2.083 30.457 Visualize Results
MaskFlownet [5] 4.172 2.048 21.494 3.783 1.745 1.310 0.592 2.389 26.253 Visualize Results
HD3-Flow [6] 4.666 2.174 24.994 3.786 1.719 1.647 0.657 2.182 30.579 Visualize Results
LiteFlowNet3 [7] 4.448 2.089 23.681 3.873 1.755 1.344 0.754 2.503 27.471 Visualize Results
MaskFlownet-S [8] 4.384 2.120 22.840 3.905 1.821 1.359 0.645 2.526 27.429 Visualize Results
ScopeFlow [9] 4.098 1.999 21.214 4.028 1.689 1.180 0.725 2.589 24.477 Visualize Results
LiteFlowNet2 [10] 4.686 2.248 24.571 4.048 1.899 1.473 0.811 2.433 29.375 Visualize Results
SelFlow [11] 4.262 2.040 22.369 4.083 1.715 1.287 0.582 2.343 27.154 Visualize Results
LiteFlowNet [12] 5.381 2.419 29.535 4.090 2.097 1.729 0.754 2.747 34.722 Visualize Results
SENSE [13] 4.860 2.301 25.732 4.121 1.991 1.493 0.812 2.606 30.402 Visualize Results
IRR-PWC [14] 4.579 2.154 24.355 4.165 1.843 1.292 0.709 2.423 28.998 Visualize Results
CompactFlow [15] 4.626 2.099 25.253 4.192 1.825 1.233 0.845 2.677 28.120 Visualize Results
CompactFlow-woscv [16] 4.858 2.213 26.439 4.220 1.867 1.453 0.906 2.701 29.709 Visualize Results
VCN [17] 4.404 2.216 22.238 4.381 1.782 1.423 0.955 2.725 25.570 Visualize Results
FrequencyFlow [18] 5.300 2.239 30.244 4.428 1.945 1.349 1.014 3.095 31.887 Visualize Results
pwc_xx [19] 5.319 2.598 27.502 4.500 2.226 1.744 0.996 2.901 32.615 Visualize Results
SegFlow-CNN [20] 5.390 2.269 30.825 4.522 1.968 1.363 1.043 3.331 31.929 Visualize Results
PWC-Net+KF2 [21] 4.979 2.430 25.783 4.571 2.078 1.480 0.778 3.112 30.353 Visualize Results
Pwc_ps [22] 5.773 2.693 30.882 4.584 2.347 1.827 1.011 2.942 36.249 Visualize Results
FPCR-Net [23] 4.935 2.455 25.141 4.589 2.181 1.491 0.914 3.081 29.352 Visualize Results
Semantic_Lattice [24] 4.886 2.456 24.701 4.596 2.082 1.529 0.803 3.024 29.649 Visualize Results
StruPyNet-ft [25] 5.511 2.593 29.316 4.598 2.284 1.675 0.945 3.059 34.112 Visualize Results
PWC-Net+KF [26] 4.964 2.438 25.561 4.603 2.066 1.500 0.739 3.087 30.465 Visualize Results
AutoScaler+ [27] 6.076 2.569 34.656 4.610 2.195 1.863 1.298 3.737 35.431 Visualize Results
PWC-Net [28] 5.042 2.445 26.221 4.636 2.087 1.475 0.799 2.986 31.070 Visualize Results
PWC-Net_ROB [29] 4.903 2.454 24.878 4.636 2.090 1.517 0.799 3.029 29.800 Visualize Results
DCFlow+KF2 [30] 5.067 2.195 28.475 4.652 1.948 1.393 1.021 3.232 29.574 Visualize Results
MFF [31] 4.566 2.216 23.732 4.664 2.017 1.222 0.893 2.902 26.810 Visualize Results
DCFlow [32] 5.119 2.283 28.228 4.665 2.108 1.440 1.052 3.434 29.351 Visualize Results
FDFlowNet [33] 5.111 2.521 26.233 4.667 2.169 1.642 1.034 3.121 30.160 Visualize Results
Lavon [34] 5.905 2.890 30.507 4.682 2.530 2.153 0.997 3.217 36.769 Visualize Results
FlowFields+ [35] 5.707 2.684 30.356 4.691 2.117 1.793 1.131 3.330 34.167 Visualize Results
PST [36] 5.416 2.572 28.592 4.695 2.088 1.761 1.172 3.546 30.987 Visualize Results
ProbFlowFields [37] 5.696 2.545 31.371 4.696 2.150 1.686 1.146 3.658 33.188 Visualize Results
CPM_AUG [38] 5.645 2.737 29.362 4.707 2.150 1.918 1.087 3.306 33.925 Visualize Results
STC-Flow [39] 4.868 2.439 24.669 4.711 2.188 1.459 0.882 3.116 28.866 Visualize Results
F2PD_JJN [40] 5.611 2.861 28.027 4.717 2.595 2.035 0.997 3.432 33.756 Visualize Results
FlowFieldsCNN [41] 5.363 2.303 30.313 4.718 2.020 1.399 1.032 3.065 32.422 Visualize Results
InterpoNet_ff [42] 5.535 2.372 31.296 4.720 2.018 1.532 1.064 3.496 32.633 Visualize Results
Flownet2-IAER [43] 5.493 2.594 29.140 4.730 2.318 1.609 0.941 3.090 33.899 Visualize Results
SPM-BPv2 [44] 5.812 2.754 30.743 4.736 2.255 1.933 1.048 3.468 35.118 Visualize Results
TIMCflow [45] 5.049 2.094 29.134 4.738 1.812 1.221 0.922 3.226 29.926 Visualize Results
S2F-IF [46] 5.417 2.549 28.795 4.745 2.198 1.712 1.157 3.468 31.262 Visualize Results
DCFlow+KF [47] 5.120 2.245 28.557 4.747 1.981 1.473 1.031 3.421 29.511 Visualize Results
FlowSAC_dcf [48] 4.932 2.232 26.936 4.763 2.047 1.303 1.044 3.450 27.794 Visualize Results
PWC-Net+ [49] 4.596 2.254 23.696 4.781 2.045 1.234 0.945 2.978 26.620 Visualize Results
FlowSAC_ff [50] 5.390 2.483 29.086 4.785 2.258 1.459 1.123 3.664 30.723 Visualize Results
Flownet2-IA [51] 5.512 2.608 29.196 4.801 2.320 1.609 0.959 3.107 33.923 Visualize Results
FlowNet2-ft-sintel [52] 5.739 2.752 30.108 4.818 2.557 1.735 0.959 3.228 35.538 Visualize Results
2chPWC-Net [53] 5.523 2.678 28.732 4.839 2.453 1.733 1.011 3.411 33.018 Visualize Results
FlowFields [54] 5.810 2.621 31.799 4.851 2.232 1.682 1.157 3.739 33.890 Visualize Results
FullFlow+KF [55] 5.802 2.761 30.582 4.866 2.438 1.795 1.037 3.287 35.517 Visualize Results
SBFlow [56] 6.114 2.854 32.675 4.871 2.440 2.006 1.076 3.555 37.287 Visualize Results
Deep-EIP [57] 6.123 2.704 34.004 4.887 2.417 1.976 1.236 3.155 37.558 Visualize Results
NNF-Local [58] 7.249 2.973 42.088 4.896 2.817 2.218 1.159 4.183 44.866 Visualize Results
FullFlow [59] 5.895 2.838 30.793 4.905 2.506 1.913 1.136 3.373 35.592 Visualize Results
HSVFlow [60] 6.051 2.967 31.168 4.911 2.682 2.166 1.426 3.942 34.059 Visualize Results
DefFlowP [61] 5.273 2.797 25.426 4.916 2.492 1.852 0.888 3.603 31.014 Visualize Results
FlowFields++ [62] 5.486 2.614 28.900 4.927 2.273 1.706 1.156 3.326 32.200 Visualize Results
SegFlow73 [63] 6.397 2.912 34.808 4.948 2.381 2.053 1.208 3.486 39.197 Visualize Results
SfM-PM [64] 5.466 2.683 28.147 4.963 2.186 1.782 1.031 3.182 32.991 Visualize Results
SegFlow153 [65] 6.191 2.940 32.682 4.969 2.492 2.119 1.201 3.865 36.570 Visualize Results
InterpoNet_cpm [66] 5.627 2.594 30.344 4.975 2.213 1.640 1.042 3.575 33.321 Visualize Results
PGM-C [67] 5.591 2.672 29.389 4.975 2.340 1.791 1.057 3.421 33.339 Visualize Results
ProFlow_ROB [68] 5.015 2.659 24.192 4.985 2.185 1.771 0.964 2.989 29.987 Visualize Results
tfFlowNet2+GLR [69] 6.273 3.081 32.301 4.986 2.870 2.258 1.077 3.702 38.268 Visualize Results
L0-normFlow [70] 6.693 3.207 35.111 5.013 2.579 2.315 1.345 4.022 39.684 Visualize Results
ProFlow [71] 5.017 2.596 24.736 5.016 2.146 1.601 0.910 2.809 30.715 Visualize Results
CPM-Flow [72] 5.960 2.990 30.177 5.038 2.419 2.143 1.155 3.755 35.136 Visualize Results
FlowNetC-MD [73] 5.444 3.060 24.860 5.039 2.752 2.023 1.319 3.537 30.481 Visualize Results
F3-MPLF [74] 6.274 3.093 32.210 5.045 2.859 2.082 1.083 3.227 39.409 Visualize Results
ContinualFlow_ROB [75] 4.528 2.723 19.248 5.050 2.573 1.713 0.872 3.114 26.063 Visualize Results
SegFlow113 [76] 6.423 2.995 34.361 5.050 2.496 2.139 1.193 3.818 38.664 Visualize Results
CPM2 [77] 6.180 3.012 32.008 5.059 2.399 2.126 1.212 3.625 37.014 Visualize Results
SJTU_PAMI418 [78] 4.910 2.496 24.600 5.075 2.268 1.394 1.037 3.219 28.217 Visualize Results
InterpoNet_dm [79] 5.711 2.650 30.642 5.078 2.308 1.762 0.997 3.702 33.929 Visualize Results
ARFlow-mv [80] 5.672 2.759 29.429 5.081 2.520 1.597 1.061 3.510 33.780 Visualize Results
DiscreteFlow [81] 6.077 2.937 31.685 5.106 2.459 1.945 1.074 3.832 36.339 Visualize Results
MR-Flow [82] 5.376 2.818 26.235 5.109 2.395 1.755 0.908 3.443 32.221 Visualize Results
MPIF [83] 5.591 2.663 29.473 5.109 2.206 1.723 1.102 3.163 33.748 Visualize Results
L0-norm-Flow2 [84] 6.802 3.313 35.239 5.112 2.658 2.437 1.413 4.191 39.851 Visualize Results
ARFlow [85] 5.889 2.734 31.602 5.125 2.605 1.553 1.176 3.676 34.611 Visualize Results
FlowNet2 [86] 6.016 2.977 30.807 5.139 2.786 2.102 1.243 4.027 34.505 Visualize Results
SegFlow33 [87] 6.726 3.200 35.458 5.141 2.553 2.280 1.276 4.110 40.076 Visualize Results
RicFlow [88] 5.620 2.765 28.907 5.146 2.366 1.679 1.088 3.364 33.573 Visualize Results
DiscreteFlow+OIR [89] 5.862 2.864 30.303 5.153 2.427 1.825 1.118 3.698 34.633 Visualize Results
InterpoNet_df [90] 6.044 2.788 32.581 5.154 2.404 1.779 0.985 3.377 37.596 Visualize Results
Deep+R [91] 6.769 2.996 37.494 5.182 2.770 2.064 1.157 3.837 41.687 Visualize Results
EpicFlow [92] 6.285 3.060 32.564 5.205 2.611 2.216 1.135 3.727 38.021 Visualize Results
SegFlow193 [93] 7.071 3.380 37.136 5.206 2.781 2.494 1.236 3.613 44.373 Visualize Results
DeepFlow2 [94] 6.928 3.093 38.166 5.207 2.819 2.144 1.182 3.859 42.854 Visualize Results
PPM [95] 7.177 3.392 38.025 5.212 2.771 2.642 1.155 3.790 45.233 Visualize Results
PatchBatch+Inter [96] 6.222 3.167 31.122 5.246 2.862 2.152 0.905 3.200 39.912 Visualize Results
ERFlow [97] 5.775 3.075 27.800 5.247 2.841 2.055 1.173 3.562 33.949 Visualize Results
DIP-Flow [98] 6.014 2.922 31.224 5.268 2.521 1.848 1.092 3.788 35.821 Visualize Results
SelFlow [99] 6.571 3.119 34.721 5.275 2.834 2.092 1.358 3.883 38.945 Visualize Results
AugFNG_ROB [100] 5.500 2.978 26.052 5.282 2.694 1.956 1.113 4.083 30.666 Visualize Results
GlobalPatchCollider [101] 6.040 2.938 31.309 5.310 2.624 1.824 1.102 3.589 36.455 Visualize Results
StruPyNet [102] 6.389 3.234 32.129 5.318 3.079 2.260 1.087 3.990 38.491 Visualize Results
FF++_ROB [103] 6.496 2.990 35.057 5.319 2.540 2.045 1.030 4.182 39.191 Visualize Results
FALDOI [104] 7.337 3.580 37.904 5.332 3.434 2.885 1.487 4.355 43.526 Visualize Results
Devon [105] 6.350 3.234 31.775 5.338 2.878 2.297 1.120 3.834 38.382 Visualize Results
DeepDiscreteFlow [106] 5.728 2.623 31.042 5.347 2.478 1.590 0.959 3.072 35.819 Visualize Results
DDFlow [107] 7.401 3.409 39.936 5.357 3.092 2.430 1.548 4.198 44.188 Visualize Results
EPMNet [108] 6.134 3.141 30.540 5.431 2.987 2.152 1.306 4.188 34.780 Visualize Results
FGI [109] 6.607 3.101 35.158 5.432 2.970 2.131 1.152 3.986 39.985 Visualize Results
MirrorFlow [110] 6.071 3.186 29.567 5.433 2.801 1.943 0.930 3.183 38.544 Visualize Results
TV-Wavelet-Flow [111] 6.908 3.392 35.552 5.435 2.744 2.404 1.379 4.405 40.366 Visualize Results
SegPM+Interpolation [112] 6.977 3.445 35.761 5.453 2.794 2.486 1.510 4.377 40.371 Visualize Results
tfFlowNet2 [113] 6.485 3.222 33.100 5.454 2.987 2.305 1.299 4.037 38.138 Visualize Results
IHBPFlow [114] 6.100 2.891 32.242 5.501 2.660 1.772 1.081 3.464 37.368 Visualize Results
ZZZ [115] 8.103 3.604 44.772 5.529 3.212 2.925 1.641 4.832 48.068 Visualize Results
SPM-BP [116] 7.325 3.493 38.561 5.534 3.052 2.691 1.279 4.385 44.434 Visualize Results
AggregFlow [117] 7.329 3.696 36.929 5.538 3.435 2.918 1.241 4.296 44.858 Visualize Results
TF+OFM [118] 6.727 3.388 33.929 5.544 3.238 2.551 1.512 3.765 39.761 Visualize Results
PH-Flow [119] 7.423 3.795 36.960 5.550 3.675 2.716 1.119 4.827 44.926 Visualize Results
ResPWCR_ROB [120] 6.530 3.849 28.371 5.565 3.396 2.876 1.306 3.848 38.892 Visualize Results
SparseFlowFused [121] 7.189 3.286 38.977 5.567 3.098 2.159 1.275 3.963 44.319 Visualize Results
PMF [122] 7.630 3.607 40.435 5.584 3.171 2.770 1.266 4.414 46.985 Visualize Results
DMF_ROB [123] 7.475 3.575 39.245 5.650 3.419 2.441 1.165 4.044 47.063 Visualize Results
DeepFlow [124] 7.212 3.336 38.781 5.650 3.144 2.208 1.284 4.107 44.118 Visualize Results
ER-FLOW2 [125] 5.885 3.068 28.868 5.650 2.818 1.883 1.094 3.714 34.911 Visualize Results
M-1px [126] 8.229 3.680 45.306 5.654 3.267 2.997 1.718 5.023 48.284 Visualize Results
LocalLayering [127] 8.043 4.014 40.879 5.680 3.841 3.122 1.186 4.990 49.426 Visualize Results
CNet [128] 8.331 4.455 39.943 5.690 3.877 3.916 1.589 3.779 52.823 Visualize Results
MDP-Flow2 [129] 8.445 4.150 43.430 5.703 3.925 3.406 1.420 5.449 50.507 Visualize Results
PatchWMF-OF [130] 7.971 3.766 42.218 5.712 3.568 2.797 1.279 4.970 48.396 Visualize Results
BOOM+PF.XY [131] 7.600 3.731 39.137 5.766 3.599 2.798 1.488 4.709 44.902 Visualize Results
UFlow [132] 6.807 3.291 35.486 5.771 3.156 2.107 1.410 4.214 39.862 Visualize Results
FAOP-Flow [133] 7.923 3.589 43.239 5.794 3.373 2.861 1.777 5.228 44.927 Visualize Results
BOOM+PF.XYT [134] 7.683 3.828 39.117 5.797 3.694 2.902 1.585 4.794 44.921 Visualize Results
GeoFlow [135] 8.459 3.908 45.553 5.805 3.550 2.899 1.398 4.667 52.653 Visualize Results
EgFlow-cl [136] 8.359 4.490 39.903 5.808 4.101 4.371 1.923 4.926 48.615 Visualize Results
WLIF-Flow [137] 8.049 3.837 42.348 5.851 3.657 2.811 1.290 5.033 48.843 Visualize Results
RGBFlow [138] 7.285 4.002 34.032 5.897 3.644 3.043 1.657 4.151 42.764 Visualize Results
S2D-Matching [139] 6.817 3.737 31.920 5.954 3.380 2.544 1.157 3.831 42.097 Visualize Results
SVFilterOh [140] 7.737 3.920 38.851 5.954 3.499 3.160 1.403 4.731 46.420 Visualize Results
ICALD [141] 7.554 3.784 38.270 6.065 3.812 2.626 1.336 4.939 44.705 Visualize Results
PatchBatch-CENT+SD [142] 6.783 3.507 33.498 6.080 3.408 2.103 0.725 3.064 45.858 Visualize Results
SparseFlow [143] 7.851 3.855 40.401 6.117 3.838 2.557 1.071 3.771 51.353 Visualize Results
DSPyNet+ft [144] 7.453 3.852 36.769 6.147 3.941 2.549 1.261 4.639 44.957 Visualize Results
ComponentFusion [145] 8.231 4.274 40.460 6.221 4.252 3.193 1.702 5.701 46.696 Visualize Results
ContFusion [146] 7.857 4.010 39.194 6.265 4.022 2.797 1.333 4.981 47.158 Visualize Results
AnyFlow [147] 7.933 3.994 40.027 6.284 3.997 2.756 2.279 5.391 42.122 Visualize Results
EPIflow [148] 8.506 4.070 44.676 6.286 3.897 2.777 1.246 3.761 56.015 Visualize Results
SAnet [149] 7.304 4.087 33.493 6.289 4.151 2.779 1.287 4.285 44.408 Visualize Results
MLDP-OF [150] 8.287 4.165 41.905 6.345 4.127 2.996 1.312 5.122 50.540 Visualize Results
FlowNetS+ft+v [151] 7.218 3.752 35.445 6.439 3.635 2.292 1.358 4.609 42.571 Visualize Results
FlowNetC+ft+v [152] 7.883 4.132 38.426 6.466 3.952 2.860 1.369 5.049 47.005 Visualize Results
TVL1_LD_GF [153] 7.735 3.478 42.372 6.479 3.764 1.982 0.910 3.391 52.099 Visualize Results
COF_2019 [154] 8.065 4.327 38.535 6.483 4.171 3.217 1.499 5.498 46.827 Visualize Results
Classic+NLP [155] 8.291 4.287 40.925 6.520 4.265 2.984 1.208 5.090 51.162 Visualize Results
FC-2Layers-FF [156] 8.137 4.261 39.723 6.537 4.257 2.946 1.034 4.835 51.349 Visualize Results
EPPM [157] 8.377 4.286 41.695 6.556 4.024 3.323 1.834 4.955 49.083 Visualize Results
WOLF_ROB [158] 8.351 4.512 39.607 6.663 4.462 3.278 1.437 5.348 49.879 Visualize Results
SPyNet+ft [159] 8.360 4.512 39.687 6.694 4.368 3.290 1.395 5.534 49.707 Visualize Results
HAST [160] 9.185 5.116 42.360 6.698 4.956 4.345 1.614 5.856 54.781 Visualize Results
Grts-Flow-V2 [161] 8.764 4.718 41.737 6.748 4.276 3.902 2.105 6.536 47.153 Visualize Results
Channel-Flow [162] 8.835 4.754 42.064 6.757 4.566 3.657 1.292 5.349 54.648 Visualize Results
DDC-Net [163] 7.461 4.168 34.312 6.777 4.162 2.710 1.182 4.941 44.675 Visualize Results
COF [164] 8.204 4.448 38.805 6.788 4.500 3.324 1.561 5.560 47.534 Visualize Results
DF [165] 9.188 4.758 45.309 6.821 4.594 3.675 1.708 6.093 53.782 Visualize Results
DF-Beta [166] 9.196 4.765 45.327 6.829 4.603 3.677 1.706 6.085 53.877 Visualize Results
H-1px [167] 10.148 4.454 56.545 6.832 4.306 3.637 2.173 6.606 58.262 Visualize Results
LDOF [168] 9.116 5.037 42.344 6.849 4.928 4.003 1.485 4.839 57.296 Visualize Results
IPOL_Brox [169] 9.198 4.869 44.479 6.856 4.682 3.789 1.679 6.106 53.956 Visualize Results
AGIF+OF [170] 8.514 4.355 42.390 6.873 4.284 2.869 1.190 5.010 53.305 Visualize Results
SPyNet [171] 8.431 4.549 40.042 6.921 4.511 3.179 1.442 5.545 50.042 Visualize Results
DSPyNet [172] 8.328 4.608 38.675 6.959 4.675 3.221 1.703 5.643 47.680 Visualize Results
DictFlowS [173] 8.486 4.681 39.477 6.983 4.718 3.383 1.507 4.902 51.733 Visualize Results
TV-L1+EM [174] 8.916 4.712 43.157 7.021 4.788 3.401 1.456 5.188 54.932 Visualize Results
JOF [175] 8.818 4.599 43.175 7.049 4.617 3.131 1.170 4.196 57.923 Visualize Results
OatNet01 [176] 8.858 5.408 36.943 7.066 5.389 4.396 2.334 5.675 48.831 Visualize Results
NLTGV-SC [177] 8.746 4.635 42.242 7.084 4.749 3.391 1.587 4.780 53.860 Visualize Results
RLOF_DENSE [178] 8.286 4.499 39.169 7.137 4.496 2.952 1.097 4.125 54.018 Visualize Results
OAR-Flow [179] 8.179 4.578 37.525 7.146 4.611 3.131 1.316 5.593 48.445 Visualize Results
Back2FutureFlow_UFO [180] 8.814 5.031 39.647 7.153 4.880 3.904 1.752 5.961 50.725 Visualize Results
RC-LSTM-1dir [181] 7.939 4.486 36.069 7.183 4.551 2.991 1.881 5.869 42.936 Visualize Results
Classic+NL [182] 9.153 4.814 44.509 7.215 4.822 3.427 1.113 4.496 60.291 Visualize Results
RC-LSTM-4dir [183] 7.905 4.466 35.921 7.223 4.557 2.950 1.849 5.854 42.848 Visualize Results
CPNFlow [184] 8.589 4.575 41.327 7.234 4.542 2.986 1.856 5.484 49.511 Visualize Results
PosetOptimization [185] 11.961 6.281 58.181 7.275 5.620 6.151 3.271 8.917 62.365 Visualize Results
IIOF-NLDP [186] 8.715 4.705 41.403 7.280 4.778 3.265 1.263 4.538 55.795 Visualize Results
PCA-Layers [187] 7.886 4.256 37.480 7.284 4.250 2.739 1.672 4.276 47.449 Visualize Results
SFL [188] 7.870 4.476 35.499 7.289 4.547 2.890 1.505 4.818 46.753 Visualize Results
Data-Flow [189] 8.868 4.601 43.675 7.294 4.698 3.021 1.794 5.294 52.635 Visualize Results
DF-Auto [190] 9.723 5.200 46.594 7.483 5.027 3.988 1.705 6.311 57.743 Visualize Results
WRTflow [191] 9.457 4.943 46.217 7.494 5.043 3.556 1.646 4.347 60.566 Visualize Results
HCOF+multi [192] 8.799 4.980 39.941 7.547 4.752 3.732 1.682 5.786 51.363 Visualize Results
ROF-NND [193] 9.286 5.130 43.129 7.561 5.350 3.796 1.221 4.700 60.367 Visualize Results
PCA-Flow [194] 8.652 4.725 40.671 7.602 4.818 3.196 1.961 4.524 51.844 Visualize Results
2bit-BM-tele [195] 10.978 5.793 53.220 7.710 5.603 4.814 2.338 6.959 63.521 Visualize Results
FlowNetProbOut [196] 8.302 4.610 38.405 7.876 4.788 2.907 1.726 6.067 46.290 Visualize Results
TVL1_ROB [197] 9.861 5.435 45.916 7.906 5.545 4.105 1.759 6.727 57.603 Visualize Results
Horn+Schunck [198] 9.610 5.419 43.734 7.950 5.658 3.976 1.882 5.335 58.274 Visualize Results
FlowNetC+OFR [199] 9.206 5.584 38.724 7.957 5.906 4.014 2.124 6.233 51.465 Visualize Results
FlowNetADF [200] 8.532 4.768 39.222 8.002 4.979 3.060 1.846 6.304 47.067 Visualize Results
Classic+NL-fast [201] 10.088 5.659 46.145 8.010 5.738 4.160 1.092 4.666 67.801 Visualize Results
Classic++ [202] 9.959 5.410 47.000 8.072 5.554 3.750 1.403 5.098 64.135 Visualize Results
TV-L1 [203] 10.462 5.848 48.013 8.193 5.860 4.431 1.551 6.012 65.384 Visualize Results
OF_OCC_LD [204] 10.024 5.815 44.272 8.370 6.009 4.170 1.064 4.017 68.986 Visualize Results
UnFlow [205] 10.219 6.061 44.110 8.407 5.828 4.665 1.742 6.689 60.765 Visualize Results
DIS-Fast [206] 10.127 5.905 44.541 8.503 6.142 4.162 2.174 5.925 59.698 Visualize Results
Steered-L1 [207] 12.277 7.489 51.200 9.143 7.683 6.369 1.254 8.198 76.703 Visualize Results
AnisoHuber.L1 [208] 11.927 7.323 49.366 9.464 7.692 5.929 1.155 7.966 74.796 Visualize Results
H+S_ROB [209] 12.451 8.230 46.801 9.968 8.497 7.220 2.909 8.739 68.643 Visualize Results
SimpleFlow [210] 13.364 8.620 51.949 10.872 8.884 7.171 1.475 9.582 81.350 Visualize Results
Model_model [211] 14.669 10.081 51.960 11.437 10.100 9.394 3.502 12.036 76.191 Visualize Results
AtrousFlow [212] 14.173 9.573 51.548 11.511 10.027 8.092 2.011 12.052 79.484 Visualize Results
WKSparse [213] 16.036 11.653 51.588 13.401 12.398 10.150 2.471 16.450 86.918 Visualize Results
BASELINE-Mean [214] 15.422 11.488 47.336 14.676 12.649 9.350 5.310 14.717 66.922 Visualize Results
AVG_FLOW_ROB [215] 18.799 14.422 54.251 16.903 15.516 12.457 4.566 19.946 86.008 Visualize Results
BASELINE-zero [216] 18.926 14.396 55.633 17.050 15.613 12.172 4.049 20.873 87.342 Visualize Results
C-2px [217] 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]
FlowElements
Anonymous. The Five Elements of Flow
[3]
PCF-F
Anonymous. Detail Preserving Propagation for Coarse-to-Fine Matching - Optical Flow Version
[4]
PPAC-HD3
Anonymous.
[5]
MaskFlownet
Anonymous.
[6]
HD3-Flow
Zhichao Yin, Trevor Darrell, Fisher Yu. Hierarchical Discrete Distribution Decomposition for Match Density Estimation (CVPR 2019)
[7]
LiteFlowNet3
Anonymous.
[8]
MaskFlownet-S
Anonymous.
[9]
ScopeFlow
Anonymous.
[10]
LiteFlowNet2
Tak-Wai Hui, Xiaoou Tang, and Chen Change Loy. A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization
[11]
SelFlow
Pengpeng Liu, Michael R. Lyu, Irwin King, Jia Xu. SelFlow: Self-Supervised Learning of Optical Flow (CVPR 2019)
[12]
LiteFlowNet
Tak-Wai Hui, Xiaoou Tang, and Chen Change Loy. LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018.
[13]
SENSE
Anonymous. TBA
[14]
IRR-PWC
Junhwa Hur and Stefan Roth. Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation. CVPR 2019
[15]
CompactFlow
Anonymous. ICCV submission.
[16]
CompactFlow-woscv
Anonymous.
[17]
VCN
Gengshan Yang and Deva Ramanan. Volumetric Correspondence Networks for Optical Flow, NeurIPS 2019
[18]
FrequencyFlow
FrequencyFlow+SegPM
[19]
pwc_xx
[20]
SegFlow-CNN
SegFlow-CNN
[21]
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.
[22]
Pwc_ps
Anonymous.
[23]
FPCR-Net
Anonymous.
[24]
Semantic_Lattice
Anne S. Wannenwetsch, Martin Kiefel, Peter V. Gehler, Stefan Roth. Learning Task-Specific Generalized Convolutions in the Permutohedral Lattice. GCPR 2019.
[25]
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.
[26]
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.
[27]
AutoScaler+
Anonymous. AutoScaler+
[28]
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.
[29]
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.
[30]
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.
[31]
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)
[32]
DCFlow
Jia Xu, René Ranftl, Vladlen Koltun. Accurate Optical Flow via Direct Cost Volume Processing. CVPR 2017.
[33]
FDFlowNet
[34]
Lavon
Anonymous.
[35]
FlowFields+
C. Bailer, B. Taetz and D. Stricker. Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation. T-PAMI.
[36]
PST
Anonymous. ACCV2018 submission #1195
[37]
ProbFlowFields
Anne S. Wannenwetsch, Margret Keuper, Stefan Roth. ProbFlow: Joint Optical Flow and Uncertainty Estimation. ICCV 2017.
[38]
CPM_AUG
Anonymous. CVPR 18 submission #1939
[39]
STC-Flow
Anonymous.
[40]
F2PD_JJN
Anonymous. With Deformable Convolutional Networks
[41]
FlowFieldsCNN
C. Bailer, K Varanasi and D. Stricker. CNN-based Patch Matching for Optical Flow with Thresholded Hinge Embedding Loss. CVPR 2017.
[42]
InterpoNet_ff
S. Zweig, L Wolf. InterpoNet, A brain inspired neural network for optical flow dense interpolation. CVPR 2017.
[43]
Flownet2-IAER
Anonymous. Flownet2 combining with illumination adjustment and edge refinement
[44]
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.
[45]
TIMCflow
Anonymous.
[46]
S2F-IF
Yanchao Yang, Stefano Soatto. S2F: Slow-To-Fast Interpolator Flow. CVPR 2017.
[47]
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.
[48]
FlowSAC_dcf
Anonymous.
[49]
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
[50]
FlowSAC_ff
Anonymous
[51]
Flownet2-IA
Anonymous. Flownet2 combining with illumination adjustment
[52]
FlowNet2-ft-sintel
Anonymous. CVPR Submission #900
[53]
2chPWC-Net
An Embedding Scheme of Heterogeneous Optical Flow Networks for Small and Fast Moving Objects
[54]
FlowFields
C. Bailer, B. Taetz and D. Stricker. Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation. ICCV 2015.
[55]
FullFlow+KF
W. Bao, Y. Xiao, L. Chen, and Z. Gao. Kalmanflow: Efficient Kalman Filtering for Video Optical Flow. ICIP 2018.
[56]
SBFlow
Fast Optical Flow Estimation Based on the Split Bregman Method. TCSVT 2016.
[57]
Deep-EIP
Anonymous. End-2-End learning for energy based inpainting of optical flow. ACCV submission 572
[58]
NNF-Local
Anonymous. Large Displacement Optical Flow from Nearest Neighbor Fields
[59]
FullFlow
Q. Chen, V. Koltun. Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids. CVPR 2016.
[60]
HSVFlow
Syed Tafseer Haider Shah, Xiang Xuezhi, Harbin Engineering University. Photometric Invariance of Optical Flow With Color Space Transformations
[61]
DefFlowP
Anonymous.
[62]
FlowFields++
R. Schuster, C. Bailer, O. Wasenmüller, D. Stricker. FlowFields++: Accurate Optical Flow Correspondences Meet Robust Interpolation. ICIP 2018
[63]
SegFlow73
Efficient Segmentation-Based PatchMatch for Large displacement Optical Flow Estimation. 2019 TCSVT. (d0=7,d1=3)
[64]
SfM-PM
D. Maurer, N. Marniok, B. Goldluecke, A. Bruhn: Structure-from-Motion-Aware PatchMatch for Adaptive Optical Flow Estimation. ECCV 2018.
[65]
SegFlow153
Efficient Segmentation-Based PatchMatch for Large displacement Optical Flow Estimation. 2019 TCSVT. (d0=15,d1=3)
[66]
InterpoNet_cpm
S. Zweig, L Wolf. InterpoNet, A brain inspired neural network for optical flow dense interpolation. CVPR 2017.
[67]
PGM-C
Anonymous
[68]
ProFlow_ROB
D. Maurer, A. Bruhn: ProFlow: Learning to Predict Optical Flow. BMVC 2018. (ROB setting)
[69]
tfFlowNet2+GLR
Anonymous.
[70]
L0-normFlow
OPC
[71]
ProFlow
D. Maurer, A. Bruhn: ProFlow: Learning to Predict Optical Flow. BMVC 2018.
[72]
CPM-Flow
Yinlin Hu, Rui Song, Yunsong Li. Efficient Coarse-to-Fine PatchMatch for Large Displacement Optical Flow. CVPR 2016.
[73]
FlowNetC-MD
Anonymous.
[74]
F3-MPLF
Sathya N. Ravi, Yunyang Xiong, Lopamudra Mukherjee, Vikas Singh: Filter Flow made Practical: Massively Parallel and Lock-Free -- CVPR 2017
[75]
ContinualFlow_ROB
Michal Neoral, Jan Šochman and Jiří Matas. Continual Occlusions and Optical Flow Estimation, ACCV 2018
[76]
SegFlow113
Efficient Segmentation-Based PatchMatch for Large displacement Optical Flow Estimation. 2019 TCSVT. (d0=11,d1=3)
[77]
CPM2
Coarse-to-fine PatchMatch for dense correspondence, Yunsong Li, Yinlin Hu, Rui Song, Peng Rao, Yangli Wang, submitted to T-CSVT
[78]
SJTU_PAMI418
[79]
InterpoNet_dm
S. Zweig, L Wolf. InterpoNet, A brain inspired neural network for optical flow dense interpolation. CVPR 2017.
[80]
ARFlow-mv
Anonymous.
[81]
DiscreteFlow
M. Menze, C. Heipke and A. Geiger. Discrete Optimization for Optical Flow. GCPR 2015
[82]
MR-Flow
J. Wulff, L. Sevilla-Lara, M. J. Black: Optical Flow in Mostly Rigid Scenes. CVPR 2017.
[83]
MPIF
Anonymous. multi-level interpolation for optical flow estimation
[84]
L0-norm-Flow2
OPL
[85]
ARFlow
Anonymous.
[86]
FlowNet2
Anonymous. CVPR Submission #900
[87]
SegFlow33
Efficient Segmentation-Based PatchMatch for Large displacement Optical Flow Estimation. 2019 TCSVT. (d0=3, d1=3)
[88]
RicFlow
Yinlin Hu, Yunsong Li, Rui Song. Robust Interpolation of Correspondences for Large Displacement Optical Flow. CVPR 2017.
[89]
DiscreteFlow+OIR
D. Maurer, M. Stoll, A. Bruhn: Order-Adaptive and Illumination Aware Variational Optical Flow Refinement. BMVC 2017.
[90]
InterpoNet_df
S. Zweig, L Wolf. InterpoNet, A brain inspired neural network for optical flow dense interpolation. CVPR 2017.
[91]
Deep+R
B. Drayer and T. Brox. Combinatorial Regularization of Descriptor Matching for Optical Flow Estimation. BMVC 2015
[92]
EpicFlow
J. Revaud, P. Weinzaepfel, Z. Harchaoui and C. Schmid. EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow. CVPR 2015.
[93]
SegFlow193
Efficient Segmentation-Based PatchMatch for Large displacement Optical Flow Estimation. 2019 TCSVT. (d0=19,d1=3)
[94]
DeepFlow2
J. Revaud, P. Weinzaepfel, Z. Harchaoui and C. Schmid. DeepMatching: Hierarchical Deformable Dense Matching. Submitted to IJCV.
[95]
PPM
Parametric PatchMatch, Fangjun Kuang, master thesis, 2017
[96]
PatchBatch+Inter
T. Schuster, L. Wolf and D. Gadot: Optical Flow Requires Multiple Strategies (but only one network). CVPR 2017.
[97]
ERFlow
Anonymous.
[98]
DIP-Flow
D. Maurer, M. Stoll, A. Bruhn: Directional Priors for Multi-Frame Optical Flow. BMVC 2018.
[99]
SelFlow
Pengpeng Liu, Michael R. Lyu, Irwin King, Jia Xu. SelFlow: Self-Supervised Learning of Optical Flow (CVPR 2019)
[100]
AugFNG_ROB
Anonymous.
[101]
GlobalPatchCollider
Shenlong Wang, Sean Fanello, Christoph Rhemann, Shahram Izadi and Pushmeet Kohli, The Global Patch Collider, CVPR, 2016
[102]
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.
[103]
FF++_ROB
Accurate matching and robust interpolation. KITTI parameters as given by the paper. Edge detector trained on KITTI + Sintel + BSDS500.
[104]
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
[105]
Devon
Anonymous. CVPR submission #1906
[106]
DeepDiscreteFlow
F. Güney and A. Geiger. Deep Discrete Flow. Asian Conference on Computer Vision (ACCV) 2016.
[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]
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.
[109]
FGI
Y. Li, D. Min, M. N. Do, and J. Lu. Fast Guided Global Interpolation for Depth and Motion. ECCV 2016
[110]
MirrorFlow
Junhwa Hur and Stefan Roth. MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation. ICCV 2017
[111]
TV-Wavelet-Flow
SegPM+TV-Wavelet-Flow
[112]
SegPM+Interpolation
SegPM+Interpolation
[113]
tfFlowNet2
Anonymous.
[114]
IHBPFlow
Anonymous.
[115]
ZZZ
Anonymous.
[116]
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
[117]
AggregFlow
D. Fortun, P. Bouthemy and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. CVIU 2016
[118]
TF+OFM
R. Kennedy and C.J. Taylor. Optical Flow with Geometric Occlusion Estimation and Fusion of Multiple Frames. EMMCVPR 2015.
[119]
PH-Flow
Jiaolong Yang and Hongdong Li. Dense, Accurate Optical Flow Estimation with Piecewise Parametric Model. CVPR 2015
[120]
ResPWCR_ROB
Anonymous.
[121]
SparseFlowFused
Radu Timofte and Luc Van Gool. SparseFlow: Sparse Matching for Small to Large Displacement Optical Flow. WACV 2015
[122]
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
[123]
DMF_ROB
Baseline submission for ROB flow challenge: Deepflow with Deepmatching as prior
[124]
DeepFlow
P. Weinzaepfel, J. Revaud, Z. Harchaoui and C. Schmid. DeepFlow: Large displacement optical flow with deep matching. ICCV 2013.
[125]
ER-FLOW2
Anonymous. Adjusted ERFlow
[126]
M-1px
Anonymous.
[127]
LocalLayering
D. Sun, C. Liu, and H. Pfister. Local Layering for Joint Motion Estimation and Occlusion Detection. CVPR 2014.
[128]
CNet
Anonymous.
[129]
MDP-Flow2
L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012.
[130]
PatchWMF-OF
Zhigang Tu, Coert Van Gemeren and Remco C. Veltkamp. Improved Color Patch Similarity Measure Based Weighted Median Filter. ACCV2014
[131]
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
[132]
UFlow
UFlow is method for unsupervised learning of optical flow that integrates occlusion aware structural similarity, edge-aware smoothness, and self-supervision. Our model also includes modifications to existing self-supervision methods, improvements through cost volume normalization, and alterations to input image resolutions.
[133]
FAOP-Flow
Anonymous.
[134]
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
[135]
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.
[136]
EgFlow-cl
Anonymous. edge-guided, small parameter optical flow network based on CNN
[137]
WLIF-Flow
Z. Tu, R. Poppe, and R. C. Veltkamp. Weighted local intensity fusion method for variational optical flow estimation.Pattern Recognition,2015
[138]
RGBFlow
Syed Tafseer Haider Shah, Xiang Xuezhi, Harbin Engineering University. Photometric Invariance of Optical Flow With Color Space Transformations
[139]
S2D-Matching
M. Leordeanu, A. Zanfir, C. Sminchisescu. Locally Affine Sparse-to-Dense Matching for Motion and Occlusion estimation. ICCV 2013
[140]
SVFilterOh
Mohamed A. Helala, Faisal Z. Qureshi, Fast Estimation of Large Displacement Optical Flow Using Dominant Motion Patterns & Sub-Volume PatchMatch Filtering, CRV 2017
[141]
ICALD
M. Stoll, D. Maurer, S. Volz and A. Bruhn. Illumination-Aware Large Displacement Optical Flow. EMMCVPR 2017.
[142]
PatchBatch-CENT+SD
Anonymous.
[143]
SparseFlow
Radu Timofte and Luc Van Gool. SparseFlow: Sparse Matching for Small to Large Displacement Optical Flow. WACV 2015
[144]
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.
[145]
ComponentFusion
Anonymous. Fast Optical Flow by Component Fusion. Submitted to ECCV 2014. Paper ID 941.
[146]
ContFusion
M. Stoll, D. Maurer, and A. Bruhn. Variational Large Displacement Optical Flow without Feature Matches. EMMCVPR 2017.
[147]
AnyFlow
Anonymous. PAMI pending review
[148]
EPIflow
Deep Epipolar Flow
[149]
SAnet
Anonymous.
[150]
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.
[151]
FlowNetS+ft+v
Anonymous. ICCV submission 235
[152]
FlowNetC+ft+v
Anonymous. ICCV sumbmission 235
[153]
TVL1_LD_GF
V. Lazcano. TVL1 to handle large displacements using gradient patches. Parameter where optimized using PSO.
[154]
COF_2019
H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[155]
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.
[156]
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
[157]
EPPM
L. Bao, Q. Yang, and H. Jin. Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow. CVPR 2014.
[158]
WOLF_ROB
[159]
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
[160]
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
[161]
Grts-Flow-V2
En Zhu, Yuanwei Li, Yanling Shi. Fast Optical Flow Estimation without Parallel Architectures. TCSVT
[162]
Channel-Flow
L. Sevilla-Lara, D. Sun, E. Learned-Miller, and M. Black. Optical Flow Estimation with Channel Constancy. ECCV, pages 423-438, 2014.
[163]
DDC-Net
Anonymous.
[164]
COF
H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[165]
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
[166]
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
[167]
H-1px
Anonymous.
[168]
LDOF
T. Brox, J. Malik. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(3): 500-513, 2011.
[169]
IPOL_Brox
J. Sánchez, N. Monzón, and A. Salgado, Robust Optical Flow Estimation, Image Processing On Line (IPOL), 3 (2013), pp. 252–270.
[170]
AGIF+OF
Anonymous. Signal Processing 2015
[171]
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
[172]
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.
[173]
DictFlowS
Anonymous.
[174]
TV-L1+EM
V. Lazcano. EXHAUSTIVE MATCHING EMPIRICAL STUDY FOR IMPROVING THE MOTION FIELD ESTIMATION
[175]
JOF
Anonymous.
[176]
OatNet01
Anonymous.
[177]
NLTGV-SC
R. Ranftl, K. Bredies, T. Pock. Non-Local Total Generalized Variation for Optical Flow Estimation, ECCV 2014
[178]
RLOF_DENSE
Jonas Geistert, Tobias Senst and Thomas Sikora, Robust Local Optical Flow: Dense Motion Vector Field Interpolation, PCS 2016
[179]
OAR-Flow
D. Maurer, M. Stoll, A. Bruhn: Order-Adaptive Regularisation for Variational Optical Flow: Global, Local and in Between. SSVM 2017.
[180]
Back2FutureFlow_UFO
J. Janai, F. Güney, A. Ranjan, M. Black and A. Geiger. Unsupervised Learning of Multi-Frame Optical Flow with Occlusions. ECCV, 2018.
[181]
RC-LSTM-1dir
Learning Contextual Dependencies for Optical Flow with Recurrent Neural Networks (ACCV 2016)
[182]
Classic+NL
D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR, pages 2432-2439, 2010.
[183]
RC-LSTM-4dir
Learning Contextual Dependencies for Optical Flow with Recurrent Neural Networks (ACCV 2016)
[184]
CPNFlow
Conditional Prior Networks for Optical Flow, Yanchao Yang, Stefano Soatto; The European Conference on Computer Vision (ECCV), 2018, pp. 271-287
[185]
PosetOptimization
Anonymous.
[186]
IIOF-NLDP
Dinh-Hoan Trinh, Walter Blondel, and Christian Daul. A General Form of Illumination-Invariant Descriptors in Variational Optical Flow Estimation. ICIP 2017.
[187]
PCA-Layers
J. Wulff and M. J. Black: Efficient sparse-to-dense optical flow estimation using a learned basis and layers. CVPR 2015.
[188]
SFL
Jingchun Cheng, Yi-Hsuan, Tsai, Shengjin Wang, Ming-Hsuan Yang. SegFlow: Joint Learning for Video Object Segmentation and Optical Flow. ICCV 2017
[189]
Data-Flow
Anonymous. CSAD data cost + second order smoothness
[190]
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
[191]
WRTflow
We proposed a weighted regularization transform to reduce the influence of illumination variations of optical flow estimation. We submit it to TCSVT.
[192]
HCOF+multi
R. Kennedy and C. J. Taylor. Hierarchically-Constrained Optical Flow. CVPR 2015.
[193]
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.
[194]
PCA-Flow
J. Wulff and M. J. Black: Efficient sparse-to-dense optical flow estimation using a learned basis and layers. CVPR 2015.
[195]
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
[196]
FlowNetProbOut
Lightweight Probabilistic Deep Networks
[197]
TVL1_ROB
Baseline submission for the robust vision flow challenge: TV-L1 Optical Flow Estimation
[198]
Horn+Schunck
A modern Matlab implementation of the Horn & Schunck method by Deqing Sun.
[199]
FlowNetC+OFR
Anonymous.
[200]
FlowNetADF
Lightweight Probabilistic Deep Networks
[201]
Classic+NL-fast
D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR, pages 2432-2439, 2010.
[202]
Classic++
D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR, pages 2432-2439, 2010.
[203]
TV-L1
Anonymous. It is a well-known model that uses TV-L1 (coupled) as the regularization term and an L1 data term.
[204]
OF_OCC_LD
V. Lazcano, L. Garrido, C. Ballester. Jointly Optical flow and Occlusion Estimation for images with Large Displacements.
[205]
UnFlow
Anonymous.
[206]
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.
[207]
Steered-L1
Anonymous.
[208]
AnisoHuber.L1
M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009.
[209]
H+S_ROB
Baseline submission for the ROB flow challenge: Horn-Schunck Optical Flow with a Multi-Scale Strategy
[210]
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)
[211]
Model_model
Anonymous. this is a model
[212]
AtrousFlow
Anonymous. Real-time dense optical flow using CUDA
[213]
WKSparse
[214]
BASELINE-Mean
[215]
AVG_FLOW_ROB
Average flow field of ROB2018 training set. No image information used!
[216]
BASELINE-zero
[217]
C-2px
Anonymous.