Optical flow evaluation results Statistics:     Average   SD   R2.5   R5.0   R10.0   A90   A95   A99  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
A99
interpolation
error
avg. Mequon
(Hidden texture)
im0   GT   im1
Schefflera
(Hidden texture)
im0   GT   im1
Urban
(Synthetic)
im0   GT   im1
Teddy
(Stereo)
im0   GT   im1
Backyard
(High-speed camera)
im0   GT   im1
Basketball
(High-speed camera)
im0   GT   im1
Dumptruck
(High-speed camera)
im0   GT   im1
Evergreen
(High-speed camera)
im0   GT   im1
rank all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext
SoftSplat [169]3.3 8.35 2 11.9 2 2.65 8 11.1 2 15.7 4 3.00 1 4.36 1 8.76 2 2.16 1 11.2 1 15.5 1 6.68 1 31.2 12 39.2 12 8.29 10 16.5 4 29.8 2 4.12 1 23.6 3 50.2 3 3.56 2 19.7 2 28.6 2 2.94 1
DCM [185]8.7 8.54 5 12.2 3 2.58 5 10.8 1 14.7 1 3.56 6 4.83 2 8.50 1 2.38 2 12.6 4 17.1 3 6.98 2 34.2 17 41.8 16 8.79 21 20.3 18 36.6 15 4.20 3 27.1 14 55.8 13 3.87 20 22.9 9 31.6 7 3.32 20
FGME [158]9.8 8.37 3 12.8 5 2.38 1 13.8 23 18.1 16 4.65 118 6.35 5 10.0 4 3.00 12 12.1 2 16.3 2 7.14 6 28.2 1 35.1 1 8.10 3 15.5 2 31.7 5 4.24 10 19.6 2 44.9 2 3.56 2 20.4 3 29.6 3 3.00 5
BMBC [172]12.5 9.11 14 12.8 5 2.71 12 11.8 6 16.8 7 3.56 6 9.56 16 14.3 23 3.37 105 13.1 6 18.7 5 7.00 3 30.1 6 37.1 6 9.35 27 16.3 3 29.8 2 4.24 10 23.7 4 50.9 4 3.70 11 20.9 4 30.1 4 3.11 10
EDSC [174]12.8 9.13 15 15.0 15 2.52 3 12.5 8 17.3 9 4.08 79 9.35 15 12.3 12 2.94 10 14.7 11 21.2 13 7.33 9 30.4 7 37.8 10 8.27 7 19.5 11 38.5 21 4.20 3 23.8 5 53.2 5 3.56 2 23.4 11 36.9 22 3.00 5
EAFI [171]13.0 8.66 6 13.8 9 2.65 8 12.8 10 18.0 15 4.51 106 6.00 4 10.3 5 2.38 2 13.5 9 20.0 9 7.05 4 34.4 18 42.8 18 8.58 17 19.5 11 37.3 17 4.20 3 24.9 10 57.7 15 3.56 2 22.2 7 30.8 6 2.94 1
STAR-Net [164]13.2 8.39 4 12.4 4 2.71 12 14.7 50 20.0 31 3.92 69 10.2 20 10.4 7 2.94 10 14.1 10 19.8 8 7.05 4 28.6 2 35.2 2 8.35 11 19.0 8 33.0 7 4.20 3 24.3 8 54.7 11 3.70 11 21.9 6 31.8 8 3.11 10
CtxSyn [134]17.3 9.38 17 14.7 13 2.58 5 11.5 4 16.1 5 3.65 29 9.04 14 12.7 15 3.00 12 12.6 4 19.2 7 7.33 9 38.7 24 47.5 21 9.56 28 22.9 23 38.0 20 4.76 23 31.6 27 64.3 25 3.92 24 24.8 24 36.2 20 3.37 23
AdaCoF [165]17.7 9.18 16 15.6 19 2.83 44 12.2 7 16.6 6 3.87 63 10.3 21 11.4 9 3.00 12 17.1 27 22.6 17 7.72 94 34.7 19 43.0 19 8.35 11 16.9 6 30.9 4 4.12 1 25.0 11 54.0 7 3.51 1 21.0 5 30.7 5 2.94 1
DSepConv [162]20.5 9.49 19 17.4 26 2.71 12 13.2 18 17.8 14 4.73 122 9.68 17 12.7 15 3.00 12 18.3 57 24.5 25 7.33 9 30.4 7 37.5 7 8.49 13 20.0 15 36.8 16 4.24 10 24.0 6 54.4 8 3.65 7 24.5 21 37.5 26 3.11 10
STSR [170]23.1 9.49 19 14.9 14 2.65 8 11.2 3 15.3 2 4.20 88 8.68 11 12.5 14 2.71 4 13.3 7 20.0 9 8.19 135 38.8 25 48.0 25 8.68 19 23.3 26 40.7 25 4.43 17 30.4 24 63.9 23 3.70 11 24.5 21 34.3 15 3.11 10
DAIN [152]24.0 9.06 13 15.1 16 2.83 44 13.0 14 17.6 10 5.03 134 8.35 7 12.4 13 2.71 4 15.7 15 22.7 19 8.68 152 30.7 10 37.6 9 8.27 7 19.1 9 34.6 9 4.32 16 28.7 20 59.7 18 3.65 7 23.6 13 33.1 11 3.00 5
TC-GAN [166]24.2 9.04 11 15.2 18 2.83 44 12.9 13 17.6 10 5.07 135 8.68 11 12.7 15 2.71 4 15.8 16 23.2 20 8.76 156 30.5 9 37.5 7 8.23 6 19.1 9 34.7 11 4.24 10 28.5 18 59.8 19 3.65 7 23.7 15 33.1 11 3.00 5
MEMC-Net+ [160]27.5 8.83 9 14.0 10 2.94 82 13.2 18 17.7 12 5.10 143 10.7 26 13.3 19 3.00 12 15.5 14 22.5 16 8.76 156 33.9 16 41.7 15 8.58 17 19.6 13 34.2 8 4.20 3 28.2 17 58.5 16 3.65 7 23.6 13 33.2 13 3.00 5
MAF-net [163]27.7 8.70 7 14.4 11 2.38 1 15.3 62 19.6 25 5.07 135 8.76 13 12.7 15 3.00 12 16.2 17 21.9 14 8.12 129 38.1 21 47.5 21 8.89 23 22.7 22 41.4 27 4.51 20 27.1 14 58.6 17 3.70 11 23.8 16 33.8 14 3.16 18
FRUCnet [153]29.0 9.49 19 16.1 21 3.42 160 13.1 17 17.7 12 4.55 110 9.68 17 12.0 11 3.56 128 15.3 13 21.9 14 7.59 62 31.6 14 39.4 13 7.94 1 18.3 7 34.6 9 4.24 10 25.0 11 54.4 8 3.70 11 22.8 8 32.7 10 3.11 10
OFRI [154]29.8 8.70 7 12.8 5 3.00 100 13.8 23 18.7 20 4.83 129 7.00 6 9.04 3 2.71 4 13.4 8 18.7 5 8.74 155 31.1 11 38.2 11 8.50 14 22.0 20 37.5 18 4.43 17 28.5 18 61.2 20 4.08 69 23.0 10 32.6 9 3.42 34
ADC [161]30.8 9.68 24 16.1 21 2.94 82 12.7 9 17.1 8 4.43 103 12.0 93 13.4 20 3.00 12 19.3 79 24.9 26 8.04 122 33.7 15 41.9 17 8.27 7 20.0 15 35.9 14 4.20 3 24.0 6 53.9 6 3.56 2 24.4 20 37.3 24 3.11 10
CyclicGen [149]31.2 8.29 1 11.7 1 3.46 162 11.6 5 15.3 2 5.94 161 9.68 17 15.0 25 3.42 123 16.7 20 21.0 11 10.3 169 29.8 5 37.0 5 8.04 2 12.4 1 21.2 1 4.65 21 18.4 1 39.9 1 3.70 11 16.6 1 22.9 1 2.94 1
PMMST [112]32.5 11.2 37 21.1 34 2.71 12 13.8 23 19.7 27 3.65 29 10.3 21 19.2 31 2.71 4 16.8 22 30.8 49 7.53 46 41.1 31 51.1 33 10.0 43 24.6 28 43.0 32 4.93 41 34.2 40 70.9 42 4.04 32 28.8 39 45.4 51 3.42 34
MDP-Flow2 [68]32.8 11.0 29 20.7 31 2.71 12 13.9 27 19.9 30 3.46 3 10.3 21 20.3 38 3.00 12 16.7 20 30.0 39 7.35 17 41.0 30 50.7 30 10.1 56 27.1 67 44.9 46 4.97 50 33.6 30 70.1 35 3.92 24 29.2 43 47.0 62 3.42 34
GDCN [173]34.0 9.04 11 15.1 16 2.65 8 16.0 82 20.4 39 4.55 110 8.35 7 11.7 10 3.37 105 21.2 118 23.7 21 8.16 132 31.3 13 39.5 14 8.16 4 19.8 14 35.3 13 4.43 17 24.4 9 54.7 11 3.79 18 23.9 17 35.8 18 3.11 10
DAI [168]34.6 9.42 18 13.1 8 3.37 151 14.7 50 19.1 23 8.35 181 5.29 3 10.3 5 2.71 4 12.4 3 17.6 4 12.6 178 36.4 20 44.6 20 8.50 14 21.7 19 37.7 19 4.24 10 28.8 21 64.1 24 3.70 11 24.1 18 34.7 16 3.11 10
FeFlow [167]34.7 9.00 10 14.6 12 2.58 5 14.4 39 19.0 22 5.74 154 8.35 7 10.7 8 3.11 96 15.2 12 21.1 12 8.91 159 29.5 4 35.8 3 8.54 16 20.2 17 35.2 12 4.20 3 26.1 13 54.4 8 4.08 69 24.2 19 39.3 27 3.56 105
UnDAF [184]36.2 11.0 29 20.7 31 2.71 12 14.0 28 20.1 35 3.51 5 10.7 26 24.1 83 3.00 12 16.9 25 30.2 41 7.35 17 41.4 34 51.5 37 10.1 56 26.7 58 45.0 47 4.97 50 33.8 33 70.2 36 3.92 24 29.7 60 47.5 68 3.37 23
CoT-AMFlow [175]36.7 11.1 34 21.0 33 2.71 12 14.0 28 20.0 31 3.56 6 10.7 26 24.0 79 3.00 12 16.8 22 30.0 39 7.35 17 41.4 34 51.1 33 10.1 56 26.7 58 45.3 50 4.97 50 34.0 36 70.0 34 4.04 32 29.5 51 47.8 73 3.42 34
MPRN [151]38.1 10.0 26 16.4 24 2.71 12 15.9 79 19.8 29 4.24 91 11.7 77 21.7 53 3.46 124 17.5 36 24.3 23 7.62 69 38.3 22 47.6 23 8.98 24 22.6 21 39.0 23 4.76 23 30.9 26 64.5 26 3.83 19 24.9 25 36.8 21 3.16 18
SuperSlomo [130]41.0 9.66 23 16.1 21 3.37 151 15.4 64 20.4 39 6.06 165 8.43 10 14.4 24 3.00 12 17.1 27 23.8 22 8.58 148 38.5 23 47.8 24 8.76 20 23.1 25 40.8 26 4.80 26 30.2 23 62.5 21 3.87 20 25.2 26 37.4 25 3.32 20
NNF-Local [75]43.9 11.4 43 21.6 37 2.71 12 12.8 10 18.4 18 3.56 6 10.4 24 20.0 36 3.00 12 19.8 91 37.3 126 7.35 17 41.5 38 51.4 35 10.0 43 28.2 99 47.3 71 5.07 83 34.5 43 71.9 55 4.04 32 29.1 42 46.1 57 3.37 23
TOF-M [150]45.9 10.2 27 16.8 25 2.71 12 15.9 79 20.5 44 5.74 154 11.1 52 14.0 22 3.70 129 17.7 40 24.3 23 7.94 114 39.4 26 49.1 26 9.11 26 23.0 24 38.8 22 4.80 26 29.5 22 63.4 22 4.04 32 25.8 27 37.1 23 3.56 105
SepConv-v1 [125]47.2 9.68 24 19.1 27 2.52 3 15.4 64 20.1 35 5.26 145 11.0 36 16.7 26 3.87 145 20.4 105 26.8 27 9.59 168 41.9 40 52.5 45 9.00 25 24.7 29 42.4 29 4.69 22 30.7 25 67.4 27 3.92 24 24.7 23 35.8 18 3.32 20
NN-field [71]47.2 11.5 51 22.9 50 2.71 12 13.0 14 18.6 19 3.42 2 12.3 114 19.7 32 3.00 12 21.1 117 39.8 143 7.44 32 41.4 34 51.4 35 10.0 43 27.5 78 46.4 60 4.97 50 33.8 33 71.0 44 4.04 32 29.3 45 46.2 58 3.37 23
MS-PFT [159]48.1 9.49 19 15.8 20 2.71 12 14.2 34 20.3 37 4.55 110 11.9 91 13.7 21 5.00 159 16.8 22 22.6 17 9.20 166 29.3 3 35.9 4 8.87 22 16.8 5 32.2 6 4.80 26 27.4 16 56.8 14 4.69 170 23.4 11 35.2 17 3.70 153
NNF-EAC [101]53.6 11.5 51 21.7 38 3.11 116 14.5 47 21.0 57 3.70 32 12.3 114 22.6 63 3.00 12 17.7 40 32.4 69 7.55 54 43.2 69 55.1 75 10.1 56 25.1 32 43.8 35 4.90 34 34.0 36 70.5 38 4.08 69 29.4 48 47.5 68 3.42 34
PH-Flow [99]56.1 11.9 84 25.7 97 2.83 44 13.3 20 19.7 27 3.56 6 10.7 26 22.7 64 3.00 12 16.5 19 30.2 41 7.33 9 42.3 47 52.1 41 10.1 56 28.7 116 50.9 131 5.20 111 35.6 68 77.0 96 4.04 32 29.6 55 47.0 62 3.51 82
DeepFlow2 [106]57.1 11.4 43 23.5 54 3.00 100 16.7 100 23.0 103 4.04 74 11.0 36 20.3 38 3.00 12 19.0 75 29.8 37 7.53 46 42.7 54 54.0 56 10.3 86 25.0 30 43.0 32 4.93 41 35.2 60 73.8 70 4.04 32 28.9 40 44.9 46 3.56 105
DeepFlow [85]57.2 11.3 41 24.2 67 3.00 100 16.6 99 23.0 103 4.32 95 11.0 36 20.3 38 3.00 12 19.3 79 28.1 31 7.59 62 42.7 54 54.5 61 10.2 79 25.2 34 44.1 36 5.00 76 32.9 28 68.2 28 4.04 32 28.4 35 44.6 42 3.56 105
CombBMOF [111]57.8 12.0 91 24.3 68 2.83 44 14.3 37 20.6 46 3.56 6 11.3 55 25.7 93 3.00 12 20.3 104 34.9 99 7.55 54 43.2 69 54.0 56 10.1 56 26.4 50 47.7 78 4.90 34 36.2 91 71.4 48 4.08 69 29.5 51 45.7 54 3.37 23
DF-Auto [113]60.3 10.9 28 19.2 28 3.11 116 17.2 112 23.4 114 4.43 103 10.4 24 20.6 46 3.00 12 18.1 53 29.7 34 7.55 54 41.4 34 52.1 41 10.0 43 26.2 45 47.2 68 4.97 50 35.2 60 79.3 110 4.08 69 29.6 55 44.7 43 3.56 105
LME [70]62.0 11.4 43 22.0 43 2.71 12 15.1 58 21.8 69 3.87 63 11.3 55 36.0 165 3.00 12 17.4 31 32.0 66 7.48 36 44.5 97 57.0 95 11.4 173 27.6 80 47.2 68 4.97 50 33.6 30 69.7 31 4.04 32 30.0 63 48.6 82 3.42 34
IROF++ [58]63.1 11.9 84 24.1 65 2.83 44 14.7 50 21.3 59 3.56 6 12.1 110 29.0 124 3.00 12 16.3 18 27.9 29 7.35 17 43.9 83 56.0 84 11.1 133 26.4 50 47.0 67 4.93 41 34.5 43 72.3 57 4.08 69 30.3 73 49.3 91 3.56 105
CBF [12]63.3 11.0 29 19.8 29 3.00 100 17.1 108 22.9 99 4.24 91 12.0 93 19.0 28 3.00 12 17.8 46 28.0 30 7.85 108 40.6 29 49.9 28 9.97 35 26.2 45 44.6 41 4.97 50 36.3 93 76.3 88 4.12 125 27.9 30 41.2 30 3.70 153
WLIF-Flow [91]63.6 11.5 51 22.1 45 2.83 44 15.2 59 21.6 65 3.79 53 11.3 55 26.4 102 3.00 12 17.4 31 30.3 44 7.59 62 42.5 50 53.5 51 10.4 96 29.0 123 51.1 134 5.29 130 34.8 49 69.7 31 4.04 32 30.0 63 48.4 78 3.46 67
FMOF [92]64.0 12.2 114 24.5 77 2.94 82 14.0 28 20.0 31 3.56 6 12.3 114 27.7 111 3.00 12 19.8 91 35.4 104 7.70 88 42.4 48 52.1 41 10.1 56 28.1 95 49.1 95 4.93 41 34.6 46 72.7 62 3.87 20 30.2 69 47.6 72 3.42 34
Aniso. Huber-L1 [22]64.1 11.4 43 21.7 38 3.11 116 19.7 152 24.7 151 4.55 110 12.0 93 19.7 32 3.11 96 18.4 60 29.8 37 7.55 54 42.5 50 54.4 60 9.98 40 25.2 34 42.2 28 4.83 29 35.6 68 71.5 49 4.04 32 27.9 30 42.0 32 3.56 105
CLG-TV [48]66.5 11.1 34 21.8 41 3.11 116 18.8 135 24.0 131 4.43 103 11.3 55 20.0 36 3.70 129 18.6 66 28.9 32 7.72 94 42.8 57 55.0 74 10.0 43 25.0 30 42.9 31 4.93 41 36.0 83 71.6 50 4.04 32 29.0 41 44.0 38 3.56 105
IROF-TV [53]67.3 11.7 64 24.7 84 3.00 100 15.5 68 22.0 80 3.70 32 11.0 36 23.7 74 3.00 12 17.3 29 31.3 53 7.57 61 43.8 81 56.0 84 11.2 142 27.6 80 48.4 86 4.97 50 35.9 81 74.5 79 4.08 69 28.0 32 42.6 34 3.56 105
nLayers [57]67.9 11.8 72 22.9 50 2.83 44 14.1 32 20.4 39 3.56 6 11.0 36 19.7 32 3.00 12 18.3 57 34.2 91 7.39 26 46.7 154 60.1 150 11.0 126 27.9 88 50.1 105 5.20 111 35.5 66 72.6 61 4.08 69 30.8 78 49.3 91 3.42 34
Brox et al. [5]68.0 11.4 43 24.9 89 2.94 82 15.9 79 22.2 83 4.04 74 11.3 55 21.0 47 3.37 105 18.4 60 27.0 28 7.59 62 42.2 45 53.3 49 10.0 43 28.2 99 51.5 138 5.00 76 36.8 97 88.0 143 4.04 32 28.4 35 42.3 33 3.42 34
ALD-Flow [66]68.4 12.0 91 28.4 130 3.11 116 16.3 90 22.8 95 3.83 58 11.0 36 21.7 53 3.00 12 17.9 49 33.6 82 7.39 26 43.4 75 54.6 65 10.8 118 25.8 39 44.8 45 5.00 76 34.1 38 70.4 37 4.04 32 31.9 108 50.3 103 3.46 67
PRAFlow_RVC [178]68.4 12.6 139 29.8 141 2.71 12 14.7 50 20.4 39 3.70 32 10.7 26 21.7 53 3.00 12 19.2 77 34.7 95 7.75 99 41.7 39 51.6 38 10.2 79 27.1 67 49.6 99 4.93 41 33.1 29 68.9 30 4.04 32 34.5 156 54.9 151 3.56 105
Layers++ [37]69.9 11.4 43 21.7 38 2.94 82 12.8 10 18.2 17 3.46 3 11.0 36 26.7 105 3.00 12 17.7 40 32.9 74 7.53 46 46.6 152 60.9 162 10.6 110 30.9 164 60.2 173 5.00 76 34.9 55 72.7 62 3.87 20 29.9 62 47.5 68 3.46 67
HCFN [157]70.2 12.0 91 27.4 119 2.71 12 15.5 68 21.9 76 3.70 32 11.3 55 23.9 78 3.00 12 17.9 49 34.4 92 7.33 9 43.1 65 53.9 55 10.2 79 26.4 50 46.2 57 6.68 182 37.4 104 76.8 93 4.08 69 31.6 99 50.5 106 3.42 34
MDP-Flow [26]70.4 11.2 37 21.2 35 2.71 12 14.2 34 20.5 44 3.70 32 10.7 26 19.0 28 3.00 12 19.7 89 32.4 69 7.70 88 44.2 88 57.0 95 11.2 142 30.0 149 51.4 137 5.51 161 36.1 88 72.9 65 4.08 69 30.8 78 48.4 78 3.42 34
JOF [136]70.7 12.0 91 23.6 56 3.11 116 14.0 28 20.0 31 3.70 32 11.0 36 23.8 77 3.00 12 18.1 53 31.5 58 7.35 17 44.7 100 57.6 104 11.3 162 29.5 139 50.1 105 5.07 83 34.5 43 71.6 50 4.04 32 31.2 86 50.3 103 3.51 82
p-harmonic [29]73.3 11.4 43 23.5 54 2.83 44 19.1 140 24.3 140 4.80 126 11.3 55 22.0 57 3.70 129 20.9 115 31.7 60 7.62 69 42.6 53 54.2 58 10.1 56 25.7 38 43.5 34 5.07 83 36.1 88 71.8 52 4.08 69 29.6 55 46.5 59 3.51 82
COFM [59]73.4 11.8 72 24.3 68 2.94 82 14.5 47 20.9 54 3.65 29 11.0 36 26.4 102 3.00 12 17.4 31 32.3 67 7.35 17 44.2 88 55.1 75 10.1 56 30.0 149 54.4 158 5.20 111 35.8 76 79.3 110 4.08 69 31.2 86 48.8 85 3.51 82
LDOF [28]73.5 11.4 43 22.5 47 3.56 165 16.1 84 21.4 64 6.35 170 12.0 93 20.3 38 3.70 129 19.0 75 29.7 34 7.94 114 41.2 32 50.9 31 10.1 56 26.8 60 50.2 108 4.90 34 34.8 49 80.2 114 4.08 69 29.4 48 44.5 40 3.46 67
Second-order prior [8]74.0 11.3 41 22.0 43 3.11 116 19.0 139 24.2 138 4.32 95 13.3 129 27.7 111 3.70 129 18.8 70 31.6 59 7.51 40 42.9 60 54.7 68 10.0 43 26.2 45 45.0 47 4.97 50 35.6 68 71.2 45 4.04 32 29.5 51 45.4 51 3.56 105
ProbFlowFields [126]74.4 11.6 56 25.4 93 2.83 44 14.4 39 21.1 58 3.56 6 10.7 26 23.7 74 3.00 12 18.4 60 33.4 79 7.59 62 46.2 141 59.2 136 11.2 142 28.5 112 50.7 125 5.32 136 34.7 47 76.9 94 4.08 69 29.4 48 46.5 59 3.46 67
VCN_RVC [179]74.4 13.1 151 36.7 162 2.71 12 14.4 39 20.6 46 3.56 6 12.1 110 29.5 133 3.00 12 20.8 114 45.5 163 7.53 46 44.2 88 55.1 75 10.1 56 26.4 50 46.9 65 4.83 29 35.2 60 73.6 69 4.04 32 32.4 123 50.7 111 3.42 34
SIOF [67]74.8 11.7 64 23.1 52 3.11 116 19.4 147 24.8 154 4.76 123 11.3 55 25.7 93 3.11 96 18.4 60 31.4 55 8.04 122 40.3 28 50.3 29 9.95 33 25.8 39 45.3 50 4.97 50 33.9 35 71.2 45 4.08 69 30.0 63 47.4 65 3.70 153
FlowFields [108]75.0 11.8 72 25.6 96 2.83 44 14.4 39 20.9 54 3.56 6 11.3 55 24.3 85 3.00 12 20.0 97 38.1 131 7.51 40 43.6 77 54.5 61 11.0 126 28.2 99 50.7 125 5.16 105 34.8 49 75.1 83 4.04 32 32.0 114 52.0 131 3.46 67
Local-TV-L1 [65]75.9 11.2 37 21.5 36 3.56 165 19.6 150 24.4 143 5.57 153 11.0 36 19.1 30 3.00 12 18.3 57 30.4 47 7.87 112 42.8 57 54.5 61 10.2 79 26.2 45 44.7 42 5.45 149 34.2 40 76.1 86 4.08 69 28.0 32 42.8 36 3.65 148
EAI-Flow [147]76.2 12.5 135 26.8 111 2.83 44 15.8 77 21.8 69 4.20 88 12.3 114 30.4 144 3.00 12 19.3 79 34.0 88 7.39 26 44.9 107 57.1 99 11.1 133 26.1 44 46.0 54 5.00 76 36.0 83 72.4 59 4.08 69 29.3 45 45.2 49 3.37 23
TV-L1-MCT [64]78.0 12.4 130 24.7 84 2.83 44 16.4 91 23.1 105 3.83 58 11.9 91 32.7 154 3.00 12 17.6 37 31.7 60 7.53 46 47.0 163 61.2 163 11.0 126 25.5 36 44.7 42 4.97 50 36.0 83 80.7 118 4.04 32 28.4 35 44.8 45 3.46 67
HAST [107]79.2 11.7 64 23.6 56 2.94 82 13.8 23 19.6 25 3.56 6 12.0 93 31.7 150 3.00 12 17.8 46 31.7 60 7.14 6 45.3 115 57.0 95 9.97 35 33.7 176 62.8 179 5.10 100 38.4 120 88.4 145 4.04 32 33.0 135 51.0 113 3.42 34
Sparse-NonSparse [56]79.5 12.0 91 24.3 68 2.83 44 15.0 56 21.3 59 3.56 6 11.7 77 29.0 124 3.00 12 17.6 37 29.7 34 7.39 26 45.7 125 59.3 137 11.0 126 28.8 117 48.7 91 5.07 83 38.6 125 90.1 154 4.04 32 32.4 123 51.8 127 3.42 34
SegFlow [156]79.7 11.9 84 28.2 127 2.83 44 14.4 39 20.6 46 3.70 32 11.3 55 22.4 61 3.00 12 20.4 105 42.0 154 7.62 69 45.9 134 58.7 131 11.2 142 27.2 69 46.8 64 5.23 119 35.1 59 70.8 40 4.08 69 30.8 78 50.1 97 3.51 82
RAFT-TF_RVC [180]80.2 12.9 144 33.5 156 2.71 12 14.4 39 20.7 51 3.56 6 10.7 26 25.7 93 3.00 12 19.5 85 36.1 114 7.62 69 42.8 57 52.7 46 10.0 43 29.7 142 56.4 163 6.81 184 34.1 38 73.2 66 3.92 24 37.5 165 59.3 167 3.37 23
CPM-Flow [114]81.1 11.8 72 27.3 115 2.83 44 14.4 39 20.4 39 3.70 32 11.7 77 24.0 79 3.00 12 21.4 127 40.1 146 7.77 100 45.5 121 58.1 115 11.2 142 26.6 57 48.0 82 5.07 83 36.0 83 72.3 57 4.04 32 30.9 82 50.4 105 3.56 105
OAR-Flow [123]81.2 12.0 91 24.9 89 3.00 100 16.4 91 22.4 86 4.08 79 11.0 36 20.5 45 3.00 12 17.4 31 33.6 82 7.33 9 46.2 141 60.0 149 11.3 162 27.0 63 47.6 75 5.23 119 37.6 107 74.0 73 4.08 69 31.0 84 49.2 89 3.46 67
FlowFields+ [128]81.5 11.8 72 26.1 106 2.71 12 14.1 32 20.6 46 3.70 32 11.2 54 24.8 89 3.00 12 20.1 99 40.2 148 7.53 46 45.5 121 58.0 112 11.2 142 28.6 115 50.6 120 5.20 111 35.6 68 77.5 101 4.04 32 32.2 118 52.5 135 3.42 34
AGIF+OF [84]82.1 12.2 114 24.3 68 2.71 12 15.2 59 21.8 69 3.70 32 11.7 77 27.7 111 3.00 12 18.0 51 33.0 76 7.55 54 45.8 129 58.8 133 11.2 142 30.0 149 53.4 152 5.07 83 35.4 63 74.8 81 3.92 24 32.2 118 52.6 139 3.37 23
ComponentFusion [94]82.6 12.0 91 29.6 139 2.71 12 14.5 47 21.3 59 3.56 6 11.0 36 22.0 57 3.00 12 18.8 70 36.2 119 7.33 9 45.5 121 58.2 121 10.7 115 27.2 69 46.3 58 4.97 50 40.5 150 93.3 164 4.12 125 34.4 153 58.3 165 3.42 34
2DHMM-SAS [90]83.0 12.2 114 24.5 77 2.83 44 17.9 122 24.1 135 3.87 63 12.0 93 28.7 121 3.00 12 17.3 29 31.4 55 7.51 40 45.1 111 58.2 121 11.2 142 27.9 88 49.0 93 4.83 29 37.0 99 76.1 86 4.08 69 31.9 108 50.5 106 3.42 34
BlockOverlap [61]83.0 11.1 34 20.1 30 3.56 165 19.3 144 23.7 123 6.16 166 11.3 55 20.4 44 3.70 129 18.4 60 29.6 33 8.72 153 43.1 65 54.5 61 10.2 79 27.4 75 48.6 89 5.35 143 34.8 49 72.8 64 4.08 69 27.2 29 40.9 29 3.56 105
Modified CLG [34]84.7 11.0 29 21.9 42 3.11 116 19.6 150 23.9 127 5.94 161 12.4 120 26.3 100 3.87 145 19.8 91 30.8 49 8.12 129 42.1 42 52.9 47 10.1 56 27.0 63 48.1 84 5.23 119 34.7 47 70.8 40 4.08 69 29.5 51 45.3 50 3.56 105
TC/T-Flow [77]84.8 12.4 130 26.4 108 2.83 44 16.5 97 23.1 105 3.83 58 11.0 36 22.4 61 3.00 12 18.9 72 34.5 93 7.33 9 45.5 121 58.1 115 11.4 173 27.3 74 47.6 75 4.93 41 41.1 153 80.4 116 4.20 141 30.9 82 49.7 95 3.37 23
DPOF [18]85.2 12.3 123 29.4 137 3.11 116 13.3 20 19.1 23 3.56 6 15.7 146 25.2 91 3.70 129 19.4 83 37.5 128 7.59 62 43.1 65 54.6 65 10.0 43 29.1 128 49.7 100 4.90 34 36.6 95 77.0 96 4.08 69 31.5 97 50.5 106 3.51 82
F-TV-L1 [15]85.2 12.0 91 26.5 109 3.56 165 19.2 142 24.7 151 4.83 129 11.7 77 21.5 51 4.00 147 19.3 79 32.7 72 7.68 81 43.1 65 55.3 79 9.83 29 25.1 32 42.8 30 5.07 83 34.8 49 74.0 73 4.16 134 28.5 38 42.7 35 3.56 105
AdaConv-v1 [124]85.3 15.0 171 28.2 127 3.70 169 17.6 119 20.7 51 7.68 178 17.4 156 22.0 57 7.00 173 27.5 163 33.7 86 17.0 180 39.9 27 49.8 27 8.19 5 23.8 27 39.5 24 4.76 23 34.2 40 68.5 29 4.12 125 26.9 28 39.5 28 3.42 34
PMF [73]86.7 12.2 114 25.9 100 2.71 12 15.4 64 21.8 69 3.56 6 12.7 122 35.7 163 3.00 12 20.2 102 35.9 111 7.51 40 44.4 95 54.9 72 10.1 56 28.4 104 50.5 118 5.32 136 37.9 113 81.1 121 4.04 32 34.2 150 54.1 146 3.37 23
PGM-C [118]86.8 11.8 72 27.3 115 2.83 44 14.4 39 20.7 51 3.70 32 12.3 114 23.0 68 3.00 12 20.6 110 42.3 155 7.62 69 45.8 129 59.5 143 11.2 142 27.2 69 47.4 72 4.97 50 37.1 101 79.2 107 4.04 32 32.4 123 55.0 153 3.51 82
Ramp [62]87.6 12.0 91 24.6 80 2.94 82 14.8 54 21.3 59 3.70 32 11.7 77 29.4 130 3.00 12 16.9 25 30.3 44 7.39 26 45.4 118 58.5 124 11.0 126 30.2 156 50.9 131 5.23 119 39.8 142 89.6 151 4.04 32 32.4 123 52.5 135 3.42 34
OFLAF [78]88.2 11.7 64 24.5 77 2.71 12 13.6 22 20.3 37 3.56 6 11.0 36 23.0 68 3.00 12 17.6 37 31.3 53 7.39 26 47.3 165 61.7 168 11.2 142 29.6 140 51.9 145 5.32 136 41.8 159 95.6 169 4.16 134 33.6 142 52.1 132 3.42 34
TF+OM [98]88.5 11.6 56 30.1 145 3.11 116 15.0 56 21.6 65 4.04 74 11.7 77 24.0 79 3.00 12 21.3 123 39.0 141 7.68 81 44.3 91 56.7 93 10.3 86 28.8 117 50.4 115 5.07 83 37.7 108 83.5 133 4.08 69 29.2 43 46.0 55 3.56 105
ProFlow_ROB [142]88.6 11.8 72 27.5 120 2.83 44 15.8 77 22.6 90 3.79 53 11.4 73 20.3 38 3.00 12 18.9 72 37.0 123 7.35 17 47.3 165 61.8 171 11.2 142 25.5 36 44.2 37 4.83 29 40.0 147 81.4 123 4.08 69 34.3 152 56.5 159 3.56 105
S2F-IF [121]88.6 12.1 106 29.8 141 2.71 12 14.2 34 20.6 46 3.56 6 11.3 55 26.3 100 3.00 12 20.2 102 40.1 146 7.53 46 45.9 134 58.7 131 11.3 162 28.4 104 50.7 125 5.20 111 35.7 73 76.0 84 4.08 69 32.3 121 53.1 140 3.46 67
AggregFlow [95]89.8 13.7 158 37.1 165 3.11 116 16.2 88 22.6 90 4.04 74 11.0 36 23.3 73 3.00 12 21.8 130 40.7 150 7.66 79 43.2 69 53.5 51 10.3 86 27.0 63 46.0 54 5.00 76 38.0 114 82.4 129 4.08 69 31.9 108 51.9 130 3.42 34
ComplOF-FED-GPU [35]90.0 12.0 91 27.9 124 2.94 82 15.7 74 22.2 83 3.79 53 16.0 147 21.4 49 3.70 129 18.4 60 33.6 82 7.48 36 44.9 107 57.7 105 10.7 115 27.4 75 45.9 53 5.00 76 36.6 95 78.7 106 4.08 69 32.6 133 52.3 133 3.51 82
Ad-TV-NDC [36]90.0 12.2 114 22.5 47 4.32 178 20.6 171 24.8 154 5.80 157 11.7 77 21.6 52 3.37 105 21.6 128 31.8 63 8.04 122 42.5 50 53.4 50 9.97 35 26.4 50 47.6 75 5.16 105 36.8 97 70.9 42 4.08 69 28.3 34 41.8 31 3.70 153
Classic+NL [31]90.5 12.1 106 24.3 68 3.00 100 15.3 62 21.8 69 3.70 32 11.7 77 29.4 130 3.00 12 17.4 31 31.4 55 7.53 46 45.7 125 59.4 139 10.8 118 29.0 123 49.8 103 5.10 100 39.6 139 90.4 156 4.08 69 32.2 118 51.8 127 3.46 67
FC-2Layers-FF [74]91.0 12.1 106 26.0 105 2.83 44 13.0 14 18.7 20 3.56 6 11.4 73 25.7 93 3.00 12 17.8 46 33.5 81 7.48 36 46.5 148 60.3 156 11.2 142 30.4 159 52.3 150 5.32 136 39.8 142 90.0 153 4.08 69 31.8 104 51.6 123 3.46 67
Classic++ [32]91.8 11.6 56 23.7 58 3.11 116 17.8 121 24.4 143 4.08 79 11.7 77 20.3 38 3.37 105 20.1 99 33.8 87 7.62 69 44.7 100 57.8 108 10.0 43 28.0 91 49.7 100 5.35 143 37.4 104 81.4 123 4.08 69 30.7 77 49.5 93 3.56 105
LSM [39]92.0 12.3 123 24.7 84 2.83 44 15.4 64 21.9 76 3.56 6 12.0 93 30.3 142 3.00 12 18.7 68 33.2 78 7.44 32 46.1 140 59.4 139 11.1 133 29.3 132 51.9 145 5.07 83 39.2 132 91.0 159 4.04 32 32.3 121 52.5 135 3.42 34
DMF_ROB [135]92.1 11.9 84 25.4 93 3.00 100 17.1 108 22.8 95 4.08 79 19.4 165 29.7 134 3.70 129 20.4 105 34.5 93 7.68 81 45.3 115 58.1 115 11.1 133 26.4 50 45.6 52 4.97 50 35.7 73 73.8 70 4.08 69 31.2 86 50.2 98 3.42 34
MLDP_OF [87]93.7 11.9 84 24.7 84 2.83 44 17.4 115 23.8 125 3.87 63 10.7 26 24.6 87 3.00 12 20.5 109 33.6 82 8.35 142 44.1 85 56.5 89 10.1 56 29.3 132 50.5 118 5.57 162 35.8 76 73.4 68 4.20 141 31.2 86 50.6 110 3.70 153
C-RAFT_RVC [182]94.4 15.3 172 39.1 170 2.94 82 15.7 74 21.8 69 4.08 79 12.7 122 30.0 139 3.11 96 21.2 118 37.1 125 7.70 88 42.1 42 52.4 44 9.97 35 28.8 117 51.1 134 4.97 50 35.0 58 72.2 56 4.04 32 33.8 146 52.5 135 3.51 82
FlowNetS+ft+v [110]94.8 11.5 51 23.7 58 3.46 162 19.9 157 24.6 149 7.87 180 12.0 93 21.1 48 3.37 105 19.5 85 30.6 48 8.91 159 43.7 79 56.6 92 11.2 142 26.0 41 44.5 40 4.97 50 38.6 125 87.8 141 4.08 69 30.0 63 46.0 55 3.51 82
TCOF [69]95.3 12.0 91 24.7 84 2.83 44 20.3 166 26.4 181 5.07 135 11.1 52 29.0 124 3.00 12 17.7 40 32.4 69 7.68 81 43.2 69 55.5 80 9.97 35 28.8 117 46.3 58 5.07 83 41.2 156 94.9 167 4.08 69 31.8 104 51.3 117 3.70 153
RNLOD-Flow [119]95.4 11.8 72 24.6 80 2.89 78 17.3 114 24.0 131 3.74 49 12.7 122 36.0 165 3.11 96 18.1 53 31.2 52 7.48 36 45.8 129 59.6 144 11.1 133 29.3 132 50.6 120 5.16 105 35.4 63 74.1 76 4.08 69 32.0 114 51.6 123 3.42 34
Fusion [6]95.8 11.6 56 24.3 68 2.89 78 15.6 72 21.9 76 3.83 58 11.0 36 23.7 74 3.37 105 21.0 116 33.4 79 7.62 69 44.1 85 56.3 88 10.1 56 30.3 158 54.1 156 5.45 149 38.0 114 83.7 134 4.08 69 34.0 149 54.7 148 3.56 105
CRTflow [81]96.1 11.7 64 24.4 75 3.32 147 19.5 149 24.9 158 4.51 106 12.0 93 22.7 64 4.00 147 18.1 53 30.3 44 7.68 81 45.0 109 58.1 115 11.3 162 26.0 41 45.1 49 4.97 50 37.7 108 87.9 142 4.08 69 30.8 78 50.2 98 3.56 105
S2D-Matching [83]96.4 12.3 123 25.7 97 2.94 82 17.2 112 23.7 123 4.00 71 11.7 77 28.7 121 3.00 12 17.7 40 31.9 65 7.55 54 46.8 158 60.1 150 10.4 96 30.0 149 51.5 138 5.29 130 37.0 99 77.7 102 4.04 32 31.8 104 50.9 112 3.46 67
RFlow [88]96.5 11.6 56 24.3 68 3.00 100 19.3 144 24.8 154 4.36 98 11.6 76 29.7 134 3.37 105 20.0 97 36.1 114 7.72 94 43.0 61 55.2 78 10.1 56 27.9 88 51.8 144 4.97 50 37.1 101 82.8 131 4.08 69 31.6 99 49.5 93 3.56 105
Sparse Occlusion [54]96.5 11.7 64 25.9 100 3.00 100 18.1 126 24.6 149 3.83 58 11.3 55 22.7 64 3.11 96 18.7 68 34.1 90 7.70 88 45.0 109 58.0 112 11.1 133 28.5 112 44.2 37 5.26 124 39.3 136 83.7 134 3.92 24 31.9 108 51.7 125 3.56 105
SVFilterOh [109]96.8 11.9 84 26.1 106 2.94 82 14.3 37 20.9 54 3.70 32 12.0 93 26.7 105 3.00 12 19.9 95 36.1 114 7.62 69 46.7 154 59.8 147 11.4 173 30.7 163 55.1 159 5.07 83 36.0 83 77.2 98 4.04 32 32.4 123 53.2 142 3.51 82
TC-Flow [46]97.6 12.0 91 30.3 147 2.89 78 16.8 102 23.4 114 3.92 69 11.7 77 21.4 49 3.00 12 19.5 85 36.1 114 8.12 129 46.5 148 59.8 147 11.3 162 27.0 63 48.4 86 5.26 124 35.5 66 74.6 80 4.04 32 33.3 139 54.5 147 3.51 82
HBM-GC [103]98.0 11.8 72 23.8 61 3.11 116 16.8 102 24.2 138 3.87 63 10.7 26 18.7 27 3.00 12 18.9 72 32.9 74 7.68 81 46.8 158 60.8 159 11.5 179 34.5 180 61.7 175 5.48 157 37.7 108 81.9 128 4.04 32 30.5 76 47.8 73 3.51 82
3DFlow [133]98.8 12.4 130 27.1 114 2.83 44 15.5 68 22.1 81 3.87 63 13.7 131 24.0 79 3.00 12 19.2 77 38.7 138 7.68 81 44.0 84 56.0 84 10.1 56 31.2 167 53.8 155 5.60 164 39.5 137 79.2 107 4.16 134 31.1 85 48.0 75 3.56 105
Classic+CPF [82]99.1 12.2 114 24.6 80 2.83 44 15.6 72 22.1 81 3.74 49 12.0 93 30.7 145 3.00 12 17.7 40 30.9 51 7.44 32 47.2 164 61.3 164 11.2 142 31.2 167 55.9 160 5.26 124 39.9 144 88.8 148 4.04 32 33.6 142 54.0 145 3.42 34
FESL [72]99.6 12.2 114 25.1 92 2.83 44 14.9 55 21.6 65 3.70 32 12.1 110 33.7 159 3.00 12 19.7 89 35.0 101 7.72 94 46.2 141 60.2 155 11.3 162 29.3 132 50.4 115 5.32 136 39.6 139 88.6 147 3.92 24 32.4 123 51.2 115 3.42 34
CostFilter [40]100.0 13.1 151 33.1 154 2.71 12 15.2 59 21.3 59 3.56 6 14.0 135 42.7 178 3.00 12 22.0 132 44.4 162 7.26 8 45.8 129 57.2 101 10.4 96 27.2 69 48.1 84 5.45 149 39.9 144 89.4 150 4.08 69 35.6 160 56.1 157 3.37 23
Black & Anandan [4]100.6 12.3 123 24.0 63 3.46 162 21.2 174 25.4 166 5.35 147 18.1 160 25.0 90 5.35 163 24.4 152 34.9 99 7.77 100 42.2 45 53.5 51 10.1 56 26.9 62 46.5 61 4.97 50 39.5 137 77.2 98 4.08 69 29.3 45 42.8 36 3.56 105
EpicFlow [100]102.0 11.9 84 27.6 121 2.83 44 16.0 82 22.2 83 3.79 53 11.8 90 21.7 53 3.00 12 21.3 123 42.9 157 7.85 108 46.3 144 59.4 139 11.2 142 27.4 75 47.5 74 5.16 105 38.2 117 76.6 90 4.12 125 35.2 159 58.0 163 3.56 105
Efficient-NL [60]102.2 11.8 72 23.8 61 2.83 44 16.7 100 23.3 110 3.70 32 18.4 162 29.0 124 3.70 129 19.4 83 34.0 88 7.51 40 45.1 111 58.5 124 11.1 133 30.0 149 51.5 138 5.07 83 40.1 148 88.9 149 4.08 69 33.0 135 52.4 134 3.42 34
SRR-TVOF-NL [89]103.2 12.9 144 28.7 131 3.00 100 16.9 106 23.1 105 4.69 120 11.5 75 27.0 109 3.00 12 22.2 134 37.3 126 7.59 62 44.8 105 57.9 110 11.0 126 29.1 128 51.9 145 4.90 34 35.7 73 77.7 102 4.08 69 33.0 135 51.5 122 3.56 105
Bartels [41]104.5 12.2 114 29.9 143 3.37 151 17.4 115 24.3 140 4.83 129 11.3 55 24.7 88 3.70 129 21.2 118 35.4 104 9.15 165 41.3 33 51.0 32 9.87 30 29.7 142 50.2 108 6.32 179 33.7 32 70.7 39 4.20 141 30.2 69 48.4 78 3.79 173
Filter Flow [19]104.5 11.8 72 23.1 52 3.37 151 20.0 159 25.1 160 5.23 144 12.2 113 26.0 97 3.70 129 22.1 133 32.7 72 7.94 114 42.1 42 51.9 39 10.4 96 28.1 95 49.0 93 5.07 83 38.4 120 81.6 125 4.16 134 30.0 63 45.5 53 3.74 170
2D-CLG [1]105.1 11.6 56 24.1 65 3.11 116 19.4 147 23.3 110 6.24 168 18.7 163 24.3 85 4.69 156 22.4 136 31.8 63 8.66 151 43.3 74 56.1 87 10.4 96 26.0 41 44.2 37 5.35 143 40.2 149 91.5 161 4.20 141 29.6 55 44.5 40 3.51 82
Steered-L1 [116]106.2 11.2 37 22.6 49 2.89 78 16.2 88 22.6 90 4.55 110 21.7 166 32.4 153 5.00 159 23.4 146 38.3 133 10.7 171 44.7 100 57.4 102 9.88 31 28.0 91 48.5 88 5.32 136 37.1 101 79.2 107 4.12 125 31.4 93 51.1 114 3.51 82
OFH [38]108.0 12.0 91 27.3 115 3.00 100 18.1 126 23.4 114 4.20 88 12.4 120 32.7 154 3.00 12 18.6 66 35.4 104 7.35 17 46.5 148 60.1 150 10.8 118 27.5 78 47.2 68 5.26 124 41.1 153 81.1 121 4.20 141 35.7 161 56.1 157 3.46 67
EPPM w/o HM [86]108.0 12.7 141 30.9 149 2.71 12 16.1 84 23.1 105 3.70 32 17.7 157 42.4 177 3.70 129 21.3 123 42.5 156 7.70 88 43.0 61 53.1 48 10.3 86 30.2 156 57.1 166 4.97 50 38.5 123 89.6 151 4.12 125 32.4 123 51.3 117 3.42 34
Occlusion-TV-L1 [63]108.4 11.6 56 25.0 91 3.11 116 19.8 155 26.0 176 4.83 129 11.3 55 23.0 68 3.46 124 22.5 139 43.0 159 7.94 114 43.0 61 54.8 71 9.88 31 28.0 91 50.7 125 5.32 136 39.6 139 76.6 90 4.62 168 31.5 97 50.5 106 3.56 105
FF++_ROB [141]109.0 12.1 106 28.2 127 2.71 12 15.5 68 21.6 65 3.74 49 12.0 93 29.4 130 3.00 12 23.3 145 49.1 169 7.83 107 48.1 171 61.6 167 11.3 162 29.1 128 49.5 98 5.94 175 36.5 94 76.4 89 4.08 69 32.1 116 51.3 117 3.65 148
Adaptive [20]109.3 11.6 56 26.7 110 3.11 116 20.2 163 25.9 172 5.07 135 12.0 93 23.0 68 3.37 105 20.4 105 36.6 121 7.77 100 44.3 91 58.5 124 9.98 40 28.3 102 49.1 95 5.16 105 42.5 164 90.6 158 4.08 69 31.6 99 48.8 85 3.65 148
LFNet_ROB [145]109.6 13.4 155 37.5 167 2.71 12 16.1 84 21.8 69 4.08 79 12.0 93 36.3 168 3.37 105 20.7 111 36.0 112 7.94 114 45.4 118 57.8 108 11.6 182 30.6 160 57.4 167 5.20 111 34.9 55 71.8 52 4.08 69 31.3 91 49.9 96 3.70 153
CNN-flow-warp+ref [115]111.6 11.0 29 22.4 46 3.11 116 17.6 119 22.9 99 5.92 160 16.1 148 28.3 120 4.00 147 23.5 147 30.2 41 10.7 171 44.8 105 58.5 124 11.3 162 26.5 56 46.5 61 5.29 130 41.5 157 91.5 161 4.32 156 30.4 74 47.5 68 3.51 82
PWC-Net_RVC [143]111.9 13.5 157 35.8 160 2.71 12 16.4 91 23.3 110 3.74 49 12.0 93 30.3 142 3.00 12 21.3 123 45.6 164 7.51 40 48.8 178 63.0 174 11.2 142 29.7 142 53.0 151 5.29 130 35.8 76 74.9 82 4.08 69 34.2 150 56.0 156 3.51 82
CompactFlow_ROB [155]112.0 14.6 169 39.6 172 2.83 44 16.4 91 22.7 93 4.32 95 14.3 140 38.7 170 3.00 12 31.2 171 71.5 181 8.08 128 43.6 77 54.6 65 10.3 86 29.7 142 55.9 160 4.93 41 37.7 108 83.9 136 4.08 69 33.0 135 51.4 120 3.51 82
TriFlow [93]112.2 12.5 135 36.7 162 3.00 100 18.7 133 24.5 146 4.76 123 11.7 77 28.1 118 3.00 12 21.7 129 41.4 152 7.62 69 46.8 158 60.4 157 11.2 142 29.9 146 51.7 143 4.97 50 37.8 112 76.9 94 4.08 69 31.7 103 48.6 82 3.51 82
Horn & Schunck [3]112.7 12.1 106 23.7 58 3.32 147 21.4 176 25.6 169 5.89 159 17.0 153 28.2 119 5.35 163 27.3 162 37.9 129 8.04 122 42.4 48 54.3 59 10.3 86 26.2 45 44.7 42 5.07 83 40.9 151 81.7 126 4.20 141 30.2 69 44.3 39 3.70 153
IAOF [50]112.8 13.0 148 29.2 135 3.37 151 23.7 182 27.4 184 6.45 172 16.4 150 28.7 121 3.46 124 22.7 140 33.1 77 8.37 143 43.4 75 55.6 82 10.0 43 27.6 80 50.1 105 4.97 50 38.3 118 82.7 130 4.08 69 30.0 63 46.8 61 3.56 105
HBpMotionGpu [43]113.6 12.3 123 32.0 152 3.79 173 20.6 171 25.4 166 6.00 163 11.3 55 26.1 99 3.00 12 23.2 143 44.0 161 7.85 108 44.3 91 56.9 94 10.8 118 29.0 123 53.5 154 5.26 124 34.9 55 69.8 33 4.04 32 31.8 104 51.4 120 3.70 153
TV-L1-improved [17]113.9 11.5 51 25.4 93 3.11 116 20.1 162 26.0 176 5.26 145 16.8 151 19.7 32 4.04 152 19.5 85 32.3 67 7.79 104 43.8 81 56.5 89 10.0 43 28.9 122 51.1 134 5.07 83 43.2 167 98.9 173 4.43 163 31.4 93 50.2 98 3.70 153
Nguyen [33]115.4 12.0 91 25.9 100 3.37 151 21.2 174 24.5 146 6.27 169 12.7 122 28.0 116 3.70 129 23.8 148 34.7 95 8.58 148 43.0 61 54.7 68 10.1 56 27.7 85 50.7 125 4.97 50 43.4 169 93.7 165 4.43 163 30.2 69 47.4 65 3.56 105
TVL1_RVC [176]116.0 11.8 72 25.9 100 3.70 169 21.7 177 25.9 172 6.03 164 12.3 114 26.8 108 3.70 129 22.9 142 35.4 104 8.33 139 43.2 69 54.9 72 10.1 56 28.4 104 50.6 120 5.10 100 41.0 152 91.6 163 4.24 152 29.6 55 44.9 46 3.56 105
GraphCuts [14]116.1 13.9 163 30.2 146 3.32 147 16.4 91 22.5 87 4.36 98 33.4 180 24.1 83 5.35 163 22.3 135 34.7 95 7.87 112 44.5 97 57.0 95 9.98 40 28.3 102 50.3 113 4.90 34 38.5 123 88.2 144 4.20 141 33.9 148 53.6 144 3.56 105
BriefMatch [122]117.0 12.1 106 29.2 135 3.11 116 16.5 97 22.5 87 6.61 174 18.0 159 22.7 64 5.69 166 26.2 158 35.5 109 18.2 182 43.7 79 54.7 68 10.4 96 29.6 140 50.2 108 5.94 175 35.8 76 72.5 60 4.16 134 32.1 116 50.2 98 3.56 105
FlowNet2 [120]118.3 19.1 178 47.5 179 3.11 116 17.1 108 24.1 135 4.55 110 14.2 138 29.8 137 3.37 105 23.8 148 42.9 157 8.33 139 45.9 134 58.1 115 10.6 110 27.6 80 49.4 97 4.93 41 39.2 132 81.0 119 4.08 69 31.6 99 49.2 89 3.56 105
TI-DOFE [24]118.8 12.7 141 27.6 121 3.87 177 22.2 180 25.3 162 6.66 175 14.1 137 25.3 92 4.36 154 27.7 164 38.7 138 9.06 164 42.7 54 53.6 54 10.1 56 26.8 60 48.8 92 4.97 50 38.3 118 76.0 84 4.24 152 31.9 108 44.7 43 3.87 176
AugFNG_ROB [139]119.7 13.7 158 36.6 161 3.00 100 17.5 118 22.9 99 4.80 126 14.3 140 36.0 165 3.37 105 27.8 165 64.0 176 7.96 121 48.6 177 63.0 174 11.4 173 28.0 91 51.6 142 4.83 29 36.1 88 76.6 90 4.08 69 31.9 108 47.2 64 3.42 34
ROF-ND [105]120.3 12.4 130 24.4 75 2.83 44 17.9 122 23.9 127 4.08 79 12.0 93 26.6 104 3.00 12 29.5 170 48.9 168 8.72 153 45.4 118 58.6 128 11.1 133 31.1 166 53.4 152 5.26 124 38.9 130 74.2 77 4.20 141 38.0 167 60.3 169 3.56 105
Correlation Flow [76]121.5 12.6 139 28.0 125 2.71 12 20.0 159 25.8 170 4.36 98 11.3 55 22.3 60 3.00 12 20.7 111 38.6 137 7.72 94 45.7 125 59.0 135 10.3 86 33.4 174 60.4 174 5.45 149 45.6 174 99.9 174 4.40 158 33.4 140 54.9 151 3.56 105
NL-TV-NCC [25]122.5 13.7 158 27.3 115 2.94 82 18.5 128 24.7 151 4.04 74 15.0 144 29.0 124 3.70 129 25.6 155 46.4 166 7.94 114 42.0 41 51.9 39 10.4 96 30.6 160 51.9 145 5.29 130 41.9 160 81.7 126 4.40 158 31.3 91 48.6 82 3.79 173
TriangleFlow [30]123.0 12.5 135 25.9 100 3.11 116 18.8 135 24.3 140 4.24 91 13.2 128 29.7 134 3.46 124 21.2 118 35.4 104 7.94 114 44.4 95 57.7 105 9.95 33 29.4 137 48.6 89 5.07 83 43.9 170 99.9 174 4.43 163 42.1 177 69.7 181 3.56 105
Complementary OF [21]123.1 12.4 130 34.5 158 2.83 44 16.4 91 23.5 118 3.79 53 30.7 173 32.2 152 7.05 176 19.9 95 43.9 160 7.44 32 46.9 161 60.4 157 10.7 115 28.1 95 47.7 78 5.23 119 41.1 153 80.3 115 4.12 125 42.0 175 62.0 174 3.56 105
LocallyOriented [52]124.0 12.2 114 28.1 126 3.27 145 20.5 169 25.9 172 5.07 135 14.3 140 30.0 139 3.37 105 24.2 151 41.7 153 7.66 79 44.7 100 57.1 99 10.1 56 28.8 117 47.4 72 5.48 157 42.4 162 80.6 117 4.12 125 32.4 123 51.2 115 3.56 105
IAOF2 [51]124.7 12.7 141 28.7 131 3.32 147 20.4 167 25.9 172 4.76 123 12.7 122 31.7 150 3.11 96 22.4 136 35.8 110 8.06 127 45.9 134 59.6 144 10.8 118 29.9 146 51.5 138 5.10 100 39.0 131 79.7 112 4.08 69 31.2 86 49.0 88 3.56 105
LSM_FLOW_RVC [183]124.9 16.3 174 45.1 177 2.94 82 17.4 115 23.3 110 4.36 98 13.7 131 39.4 172 3.00 12 25.7 156 64.9 178 7.77 100 46.4 147 60.1 150 11.0 126 27.7 85 46.6 63 5.16 105 38.1 116 78.5 105 4.12 125 35.1 158 56.5 159 3.70 153
ContinualFlow_ROB [148]125.9 14.3 166 37.0 164 2.94 82 17.0 107 23.6 120 4.51 106 13.8 134 33.5 158 3.37 105 23.2 143 53.7 172 7.70 88 49.9 179 66.1 180 11.3 162 27.2 69 49.8 103 4.90 34 38.7 128 86.6 139 4.04 32 42.0 175 61.1 171 3.56 105
H+S_RVC [177]126.2 13.7 158 27.7 123 3.11 116 18.5 128 22.5 87 5.74 154 17.7 157 27.7 111 5.74 169 27.2 161 34.7 95 9.04 163 44.1 85 56.5 89 10.4 96 27.7 85 47.9 80 5.35 143 39.2 132 83.4 132 4.80 172 32.5 132 48.8 85 3.83 175
EPMNet [131]127.6 19.3 179 47.9 180 3.11 116 16.8 102 23.2 109 4.55 110 14.2 138 29.8 137 3.37 105 33.0 176 78.1 183 8.29 137 45.9 134 58.1 115 10.6 110 30.0 149 51.9 145 4.97 50 39.2 132 81.0 119 4.08 69 33.8 146 53.1 140 3.51 82
IIOF-NLDP [129]128.6 12.9 144 29.0 134 2.71 12 18.6 132 24.8 154 4.08 79 13.4 130 26.7 105 3.00 12 21.9 131 39.8 143 8.16 132 45.8 129 59.4 139 10.4 96 31.6 170 59.9 171 6.06 178 54.7 183 99.9 174 6.03 182 35.7 161 57.2 162 3.42 34
ACK-Prior [27]129.1 12.5 135 29.7 140 2.83 44 16.1 84 22.7 93 4.00 71 25.6 169 27.7 111 5.72 168 22.4 136 36.0 112 10.7 171 45.7 125 59.3 137 11.4 173 31.8 171 50.6 120 5.35 143 38.8 129 79.9 113 4.16 134 33.5 141 51.7 125 3.70 153
Rannacher [23]129.7 11.7 64 28.7 131 3.16 144 20.4 167 26.3 179 5.07 135 19.0 164 26.0 97 4.80 158 19.8 91 38.1 131 7.79 104 44.5 97 57.4 102 10.1 56 29.0 123 50.3 113 5.20 111 42.6 165 97.0 170 4.40 158 33.7 144 55.9 155 3.70 153
LiteFlowNet [138]130.2 14.1 165 39.6 172 2.71 12 15.7 74 21.9 76 4.00 71 14.0 135 43.0 179 3.00 12 36.3 181 70.9 180 9.02 161 48.3 173 63.2 177 11.5 179 30.1 155 57.7 168 5.10 100 42.1 161 87.4 140 4.24 152 32.4 123 50.2 98 3.51 82
Learning Flow [11]131.9 12.1 106 24.6 80 3.27 145 19.7 152 25.2 161 5.00 133 39.7 182 47.7 183 7.68 178 24.6 153 35.0 101 8.19 135 45.2 114 58.6 128 10.5 109 28.4 104 48.0 82 5.45 149 38.4 120 77.8 104 4.40 158 32.6 133 48.4 78 3.92 178
2bit-BM-tele [96]132.2 11.7 64 27.0 113 3.79 173 20.2 163 26.3 179 5.07 135 12.0 93 23.2 72 4.00 147 21.2 118 36.1 114 8.16 132 45.3 115 58.0 112 10.3 86 34.0 178 61.8 176 5.92 172 54.1 182 99.9 174 5.72 180 29.8 61 47.4 65 3.74 170
SimpleFlow [49]133.9 12.0 91 24.0 63 2.94 82 18.5 128 24.4 143 4.24 91 32.7 176 39.0 171 5.69 166 18.0 51 36.2 119 7.55 54 46.9 161 60.8 159 11.1 133 31.4 169 58.1 169 5.35 143 49.4 178 99.9 174 5.16 178 40.0 171 63.0 177 3.46 67
FOLKI [16]134.4 13.0 148 30.9 149 4.97 182 22.2 180 24.9 158 9.00 182 17.3 155 33.0 156 7.00 173 33.4 177 38.7 138 17.0 180 44.3 91 55.8 83 10.4 96 27.6 80 49.7 100 5.48 157 36.2 91 74.2 77 4.80 172 30.4 74 44.9 46 4.08 180
SILK [80]135.1 13.3 154 30.7 148 3.83 176 22.0 179 25.3 162 7.16 176 34.7 181 40.0 174 7.77 180 26.6 159 36.6 121 8.60 150 45.1 111 57.9 110 10.0 43 28.4 104 50.9 131 6.03 177 34.8 49 71.8 52 4.51 167 31.4 93 48.0 75 3.74 170
ResPWCR_ROB [140]135.8 12.9 144 34.8 159 2.94 82 17.1 108 24.0 131 4.36 98 16.8 151 31.4 149 3.37 105 25.7 156 57.3 174 8.29 137 46.7 154 60.8 159 11.2 142 29.9 146 58.2 170 5.92 172 35.6 68 74.0 73 4.20 141 36.6 164 60.5 170 3.56 105
IRR-PWC_RVC [181]136.2 16.8 175 47.4 178 3.11 116 16.8 102 23.9 127 4.55 110 14.4 143 38.1 169 3.11 96 38.2 182 83.8 185 7.85 108 47.8 169 61.8 171 11.8 184 30.6 160 56.6 164 4.97 50 38.6 125 85.0 138 4.04 32 42.6 178 61.3 172 3.42 34
StereoFlow [44]136.9 22.8 184 48.3 181 3.74 172 20.5 169 26.8 182 5.07 135 11.3 55 29.3 129 3.37 105 20.1 99 37.0 123 7.62 69 59.3 182 75.2 182 10.8 118 39.3 184 71.4 183 5.45 149 35.8 76 73.9 72 4.08 69 35.7 161 55.1 154 3.70 153
StereoOF-V1MT [117]139.2 13.7 158 32.7 153 3.00 100 18.7 133 23.6 120 4.80 126 21.8 168 28.0 116 5.07 162 31.6 172 40.6 149 9.57 167 46.5 148 58.9 134 11.5 179 29.2 131 50.2 108 6.45 181 42.4 162 94.7 166 4.80 172 31.4 93 48.3 77 3.46 67
OFRF [132]139.4 14.4 167 38.4 169 3.70 169 19.9 157 25.3 162 5.48 150 13.0 127 33.0 156 3.11 96 20.7 111 38.4 134 7.79 104 47.8 169 61.4 165 10.9 124 31.9 172 56.8 165 5.29 130 41.5 157 90.5 157 4.08 69 34.4 153 54.7 148 3.42 34
Shiralkar [42]139.5 13.2 153 31.6 151 3.00 100 19.7 152 24.5 146 4.65 118 17.0 153 30.7 145 4.08 153 32.1 174 53.1 171 8.04 122 46.3 144 59.7 146 10.3 86 28.4 104 50.2 108 5.45 149 45.5 173 95.2 168 4.24 152 39.2 170 62.6 175 3.42 34
Dynamic MRF [7]141.6 12.1 106 26.8 111 2.94 82 18.0 125 23.9 127 4.16 87 18.3 161 30.7 145 5.00 159 28.9 167 39.8 143 10.5 170 45.9 134 58.6 128 11.2 142 30.9 164 56.0 162 5.80 171 43.0 166 90.3 155 4.65 169 33.7 144 51.8 127 3.70 153
Adaptive flow [45]142.5 13.4 155 25.8 99 4.51 179 21.8 178 25.4 166 7.26 177 13.7 131 27.5 110 4.69 156 24.1 150 35.2 103 8.76 156 47.3 165 61.5 166 10.2 79 33.8 177 61.9 177 5.45 149 35.9 81 73.2 66 4.20 141 34.7 157 54.7 148 3.70 153
UnFlow [127]146.0 14.9 170 40.2 174 3.11 116 18.5 128 23.4 114 5.48 150 15.3 145 31.3 148 4.36 154 22.8 141 38.0 130 8.45 145 48.3 173 63.0 174 10.9 124 32.4 173 62.0 178 5.72 166 35.4 63 71.2 45 4.32 156 45.5 181 66.0 180 3.87 176
SPSA-learn [13]148.0 12.3 123 33.7 157 3.37 151 19.2 142 23.6 120 5.45 149 30.0 172 39.7 173 7.00 173 26.9 160 41.3 151 8.41 144 46.7 154 60.1 150 10.2 79 29.4 137 50.6 120 5.20 111 53.7 181 99.9 174 8.43 184 51.4 183 72.0 183 3.51 82
SegOF [10]150.6 12.3 123 33.1 154 3.11 116 17.9 122 23.8 125 4.51 106 29.0 171 34.3 161 6.16 170 32.8 175 78.9 184 8.33 139 48.1 171 63.6 178 11.2 142 28.5 112 54.3 157 5.72 166 44.6 171 99.9 174 4.97 176 37.9 166 61.4 173 3.51 82
WRT [146]150.8 13.0 148 29.4 137 2.83 44 18.8 135 23.5 118 4.69 120 32.7 176 30.0 139 6.73 171 24.7 154 39.3 142 9.02 161 47.4 168 61.7 168 10.4 96 34.4 179 63.1 180 5.92 172 57.2 184 99.9 174 7.68 183 49.8 182 72.2 184 3.56 105
HCIC-L [97]151.9 21.0 183 41.8 175 5.07 183 20.2 163 26.1 178 5.80 157 16.3 149 42.3 176 4.00 147 31.7 173 51.0 170 8.50 146 44.7 100 55.5 80 10.4 96 35.2 181 69.8 182 5.07 83 39.9 144 91.2 160 4.16 134 40.4 174 58.0 163 3.65 148
FFV1MT [104]153.5 17.0 176 37.6 168 3.37 151 19.3 144 22.9 99 6.40 171 28.2 170 46.7 182 6.95 172 29.3 168 38.4 134 11.4 175 46.3 144 58.2 121 10.4 96 29.0 123 50.4 115 5.72 166 46.7 175 88.5 146 4.93 175 39.0 169 56.9 161 4.43 182
PGAM+LK [55]153.6 15.5 173 39.4 171 4.55 180 19.8 155 24.0 131 7.68 178 33.1 179 43.4 180 8.00 181 34.5 179 45.7 165 11.2 174 46.6 152 57.7 105 10.6 110 29.3 132 50.8 130 5.74 170 37.4 104 77.2 98 4.43 163 34.4 153 53.3 143 4.24 181
Heeger++ [102]155.0 19.8 180 44.7 176 3.11 116 18.9 138 22.8 95 6.45 172 33.0 178 35.2 162 7.16 177 29.3 168 38.4 134 11.4 175 51.5 180 65.2 179 11.3 162 28.4 104 46.9 65 6.78 183 47.9 177 84.5 137 4.69 170 40.1 172 58.8 166 3.70 153
SLK [47]156.0 13.9 163 29.9 143 3.79 173 20.0 159 22.8 95 6.22 167 32.0 175 33.7 159 7.72 179 33.4 177 46.4 166 16.1 179 48.5 176 61.7 168 10.3 86 28.4 104 47.9 80 5.72 166 43.2 167 97.9 171 4.97 176 38.7 168 59.8 168 4.04 179
WOLF_ROB [144]165.3 19.8 180 50.0 183 3.37 151 21.0 173 25.8 170 5.42 148 21.7 166 43.4 180 3.37 105 28.0 166 54.1 173 8.54 147 48.3 173 62.7 173 11.3 162 33.4 174 60.0 172 5.57 162 49.5 179 99.9 174 4.40 158 40.3 173 64.3 178 3.65 148
Pyramid LK [2]165.8 14.4 167 37.3 166 4.93 181 23.7 182 25.3 162 9.98 184 42.2 183 35.7 163 12.3 183 56.2 184 64.2 177 35.8 184 65.6 183 83.9 183 10.6 110 28.1 95 46.1 56 5.48 157 45.2 172 99.9 174 5.89 181 53.6 184 75.1 185 5.42 183
GroupFlow [9]167.5 19.9 182 49.6 182 3.42 160 19.1 140 24.1 135 5.48 150 31.4 174 40.0 174 8.19 182 36.2 180 61.9 175 12.1 177 55.6 181 71.3 181 11.4 173 36.3 182 67.0 181 5.60 164 46.7 175 98.5 172 4.20 141 43.6 179 62.8 176 3.56 105
Periodicity [79]182.0 17.6 177 55.7 184 5.45 184 26.8 184 27.0 183 9.75 183 49.4 185 51.5 185 17.7 184 51.3 183 70.3 179 27.9 183 66.6 184 86.3 184 11.7 183 38.7 183 82.5 184 6.38 180 51.8 180 99.9 174 5.48 179 44.3 180 65.5 179 5.80 184
AVG_FLOW_ROB [137]184.2 64.1 185 67.2 185 12.2 185 44.0 185 47.3 185 16.5 185 48.3 184 50.5 184 29.0 185 68.4 185 77.2 182 51.4 185 78.9 185 90.3 185 20.4 185 80.7 185 99.9 185 17.7 185 73.1 185 99.9 174 14.0 185 64.2 185 71.2 182 16.7 185
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

Methodtime*framescolor Reference and notes
[1] 2D-CLG 844 2 gray The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences.
[2] Pyramid LK 12 2 color A modification of Bouguet's pyramidal implementation of Lucas-Kanade.
[3] Horn & Schunck 49 2 gray A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data.
[4] Black & Anandan 328 2 gray A modern Matlab implementation of the Black & Anandan method by Deqing Sun.
[5] Brox et al. 18 2 color T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.)
[6] Fusion 2,666 2 color V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008.
[7] Dynamic MRF 366 2 gray B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.)
[8] Second-order prior 14 2 gray W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[9] GroupFlow 600 2 gray X. Ren. Local Grouping for Optical Flow. CVPR 2008.
[10] SegOF 60 2 color L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available.
[11] Learning Flow 825 2 gray D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008.
[12] CBF 69 2 color W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[13] SPSA-learn 200 2 color Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008.
[14] GraphCuts 1,200 2 color T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008.
[15] F-TV-L1 8 2 gray A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008.
[16] FOLKI 1.4 2 gray G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005.
[17] TV-L1-improved 2.9 2 gray A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision.
[18] DPOF 287 2 color C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.)
[19] Filter Flow 34,000 2 color S. Seitz and S. Baker. Filter flow. ICCV 2009.
[20] Adaptive 9.2 2 gray A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009.
[21] Complementary OF 44 2 color H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[22] Aniso. Huber-L1 2 2 gray M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision.
[23] Rannacher 0.12 2 gray J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009.
[24] TI-DOFE 260 2 gray C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009.
[25] NL-TV-NCC 20 2 color M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010.
[26] MDP-Flow 188 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010.
[27] ACK-Prior 5872 2 color K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010.
[28] LDOF 122 2 color T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011.
[29] p-harmonic 565 2 gray J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010.
[30] TriangleFlow 4200 2 gray B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010.
[31] Classic+NL 972 2 color D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code.
[32] Classic++ 486 2 gray A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010.
[33] Nguyen 33 2 gray D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011.
[34] Modified CLG 133 2 gray R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010.
[35] ComplOF-FED-GPU 0.97 2 color P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010.
[36] Ad-TV-NDC 35 2 gray M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010.
[37] Layers++ 18206 2 color D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010.
[38] OFH 620 3 color H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011.
[39] LSM 1615 2 color K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011.
[40] CostFilter 55 2 color C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011.
[41] Bartels 0.15 2 gray C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU.
[42] Shiralkar 600 2 gray M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242.
[43] HBpMotionGpu 1000 5 gray S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.)
[44] StereoFlow 7200 2 color G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772.
[45] Adaptive flow 121 2 gray Tarik Arici and Vural Aksakalli. Energy minimization based motion estimation using adaptive smoothness priors. VISAPP 2012.
[46] TC-Flow 2500 5 color S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011.
[47] SLK 300 2 gray T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011.
[48] CLG-TV 29 2 gray M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code.
[49] SimpleFlow 1.7 2 color M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012.
[50] IAOF 57 2 gray D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011.
[51] IAOF2 56 2 gray Duc Dung Nguyen and Jae Wook Jeon. Enhancing accuracy and sharpness of motion field with adaptive scheme and occlusion-aware filter. IET Image Processing 7.2 (2013): 144-153.
[52] LocallyOriented 9541 2 gray Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012.
[53] IROF-TV 261 2 color H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop.
[54] Sparse Occlusion 2312 2 color Alper Ayvaci, Michalis Raptis, and Stefano Soatto. Sparse occlusion detection with optical flow. IJCV 97(3):322-338, 2012.
[55] PGAM+LK 0.37 2 gray A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010.
[56] Sparse-NonSparse 713 2 color Zhuoyuan Chen, Jiang Wang, and Ying Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. CVPR 2012.
[57] nLayers 36150 4 color D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012.
[58] IROF++ 187 2 color H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013.
[59] COFM 600 3 color M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013.
[60] Efficient-NL 400 2 color P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012.
[61] BlockOverlap 2 2 gray Michael Santoro, Ghassan AlRegib, and Yucel Altunbasak. Motion estimation using block overlap minimization. MMSP 2012.
[62] Ramp 1200 2 color A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012.
[63] Occlusion-TV-L1 538 3 gray C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012.
[64] TV-L1-MCT 90 2 color M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012.
[65] Local-TV-L1 500 2 gray L. Raket. Local smoothness for global optical flow. ICIP 2012.
[66] ALD-Flow 61 2 color M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012.
[67] SIOF 234 2 color L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012.
[68] MDP-Flow2 342 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available.
[69] TCOF 1421 all gray J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013.
[70] LME 476 2 color W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013.
[71] NN-field 362 2 color L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[72] FESL 3310 2 color Weisheng Dong, Guangming Shi, Xiaocheng Hu, and Yi Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. IEEE TIP 23(10):4527-4538, 2014.
[73] PMF 35 2 color J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013.
[74] FC-2Layers-FF 2662 4 color D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013.
[75] NNF-Local 673 2 color Zhuoyuan Chen, Hailin Jin, Zhe Lin, Scott Cohen, and Ying Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[76] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[77] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[78] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[79] Periodicity 8000 4 color Georgii Khachaturov, Silvia Gonzalez-Brambila, and Jesus Gonzalez-Trejo. Periodicity-based computation of optical flow. Computacion y Sistemas (CyS) 2014.
[80] SILK 572 2 gray Pascal Zille, Thomas Corpetti, Liang Shao, and Xu Chen. Observation model based on scale interactions for optical flow estimation. IEEE TIP 23(8):3281-3293, 2014.
[81] CRTflow 13 3 color O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013.
[82] Classic+CPF 640 2 gray Zhigang Tu, Nico van der Aa, Coert Van Gemeren, and Remco Veltkamp. A combined post-filtering method to improve accuracy of variational optical flow estimation. Pattern Recognition 47(5):1926-1940, 2014.
[83] S2D-Matching 1200 2 color Marius Leordeanu, Andrei Zanfir, and Cristian Sminchisescu. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013.
[84] AGIF+OF 438 2 gray Zhigang Tu, Ronald Poppe, and Remco Veltkamp. Adaptive guided image filter for warping in variational optical flow computation. Signal Processing 127:253-265, 2016.
[85] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[86] EPPM w/o HM 2.5 2 color L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014.
[87] MLDP_OF 165 2 gray M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014.
[88] RFlow 20 2 gray S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014.
[89] SRR-TVOF-NL 32 all color P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014.
[90] 2DHMM-SAS 157 2 color M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission.
[91] WLIF-Flow 700 2 color Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014.
[92] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[93] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[94] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[95] AggregFlow 1642 2 color D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759.
[96] 2bit-BM-tele 124 2 gray R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013.
[97] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[98] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[99] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[100] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[101] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[102] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[103] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[104] FFV1MT 358 5 gray F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015.
[105] ROF-ND 4 2 color S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015.
[106] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[107] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[108] FlowFields 15 2 color C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015.
[109] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[110] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[111] CombBMOF 51 2 color M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.)
[112] PMMST 182 2 color F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015.
[113] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[114] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[115] CNN-flow-warp+ref 1.4 3 color D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016.
[116] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[117] StereoOF-V1MT 343 2 gray Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132.
[118] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[119] RNLOD-Flow 1040 2 gray C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. IEEE TIP 26(8):4055-4067, 2017.
[120] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[121] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[122] BriefMatch 0.068 2 gray G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62.
[123] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[124] AdaConv-v1 2.8 2 color Simon Niklaus, Long Mai, and Feng Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[125] SepConv-v1 0.2 2 color Simon Niklaus, Long Mai, and Feng Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[126] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[127] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[128] FlowFields+ 10.5 2 color C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017.
[129] IIOF-NLDP 150 2 color D.-H. Trinh, W. Blondel, and C. Daul. A general form of illumination-invariant descriptors in variational optical flow estimation. ICIP 2017.
[130] SuperSlomo 0.5 2 color Anonymous. (Interpolation results only.) Super SloMo: High quality estimation of multiple intermediate frames for video interpolation. CVPR 2018 submission 325.
[131] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[132] OFRF 90 2 color T. Mai, M. Gouiffes, and S. Bouchafa. Optical Flow refinement using iterative propagation under color, proximity and flow reliability constraints. Submitted to Signal, Image and Video Processing 2017.
[133] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
[134] CtxSyn 0.07 2 color Simon Niklaus and Feng Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[135] DMF_ROB 10 2 color ROB 2018 baseline submission, based on: P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[136] JOF 657 2 gray C. Zhang, L. Ge, Z. Chen, M. Li, W. Liu, and H. Chen. Refined TV-L1 optical flow estimation using joint filtering. Submitted to IEEE TMM, 2018.
[137] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[138] LiteFlowNet 0.06 2 color T.-W. Hui, X. Tang, and C. C. Loy. LiteFlowNet: A lightweight convolutional neural network for optical flow estimation. CVPR 2018.
[139] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[140] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[141] FF++_ROB 17.43 2 color R. Schuster, C. Bailer, O. Wasenmueller, D. Stricker. FlowFields++: Accurate optical flow correspondences meet robust interpolation. ICIP 2018. Submitted to ROB 2018.
[142] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[143] PWC-Net_RVC 0.069 2 color D. Sun, X. Yang, M.-Y. Liu, and J. Kautz. PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. CVPR 2018. Also RVC 2020 baseline submission.
[144] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[145] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
[146] WRT 9 2 color L. Mei, J. Lai, X. Xie, J. Zhu, and J. Chen. Illumination-invariance optical flow estimation using weighted regularization transform. Submitted to IEEE TCSVT 2018.
[147] EAI-Flow 2.1 2 color Anonymous. Hierarchical coherency sensitive hashing and interpolation with RANSAC for large displacement optical flow. CVIU 2018 submission 17-678.
[148] ContinualFlow_ROB 0.5 all color Michal Neoral, Jan Sochman, and Jiri Matas. Continual occlusions and optical flow estimation. ACCV 2018.
[149] CyclicGen 0.088 2 color Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
[150] TOF-M 0.393 2 color Tianfan Xue, Baian Chen, Jiajun Wu, Donglai Wei, and William Freeman. Video enhancement with task-oriented flow. arXiv 1711.09078, 2017.
[151] MPRN 0.32 4 color Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[152] DAIN 0.13 2 color Wenbo Bao, Wei-Sheng Lai, Chao Ma, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019.
[153] FRUCnet 0.65 2 color Van Thang Nguyen, Kyujoong Lee, and Hyuk-Jae Lee. (Interpolation results only.) A stacked deep MEMC network for frame rate up conversion and its application to HEVC. Submitted to IEEE TCSVT 2019.
[154] OFRI 0.31 2 color Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
[155] CompactFlow_ROB 0.05 2 color Anonymous. CompactFlow: spatially shiftable window revisited. CVPR 2019 submission 1387.
[156] SegFlow 3.2 2 color Jun Chen, Zemin Cai, Jianhuang Lai, and Xiaohua Xie. Efficient segmentation-based PatchMatch for large displacement optical flow estimation. IEEE TCSVT 2018.
[157] HCFN 0.18 2 color Anonymous. Practical coarse-to-fine optical flow with deep networks. ICCV 2019 submission 116.
[158] FGME 0.23 2 color Anonymous. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. ICCV 2019 submission 4327.
[159] MS-PFT 0.44 2 color Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) A multi-scale position feature transform network for video frame interpolation. IEEE TCSVT 2020.
[160] MEMC-Net+ 0.12 2 color Wenbo Bao, Wei-Sheng Lai, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang. (Interpolation results only.) MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement. Submitted to PAMI 2018.
[161] ADC 0.01 2 color Anonymous. (Interpolation results only.) Learning spatial transform for video frame interpolation. ICCV 2019 submission 5424.
[162] DSepConv 0.3 2 color Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) Video frame interpolation via deformable separable convolution. AAAI 2020.
[163] MAF-net 0.3 2 color Anonymous. (Interpolation results only.) MAF-net: Motion attention feedback network for video frame interpolation. AAAI 2020 submission 9862.
[164] STAR-Net 0.049 2 color Anonymous. (Interpolation results only.) Space-time-aware multiple resolution for video enhancement. CPVR 2020 submission 430.
[165] AdaCoF 0.03 2 color Hyeongmin Lee, Taeoh Kim, Tae-young Chung, Daehyun Pak, Yuseok Ban, and Sangyoun Lee. (Interpolation results only.) AdaCoF: Adaptive collaboration of flows for video frame interpolation. CVPR 2020. Code available.
[166] TC-GAN 0.13 2 color Anonymous. (Interpolation results only.) A temporal and contextual generative adversarial network for video frame interpolation. CVPR 2020 submission 111.
[167] FeFlow 0.52 2 color Shurui Gui, Chaoyue Wang, Qihua Chen, and Dacheng Tao. (Interpolation results only.) FeatureFlow: Robust video interpolation via structure-to-texture generation. CVPR 2020. Code available.
[168] DAI 0.23 2 color Anonymous. (Interpolation results only.) Deep animation inbetweening. CVPR 2020 submission 6404.
[169] SoftSplat 0.1 2 color Simon Niklaus and Feng Liu. (Interpolation results only.) Softmax splatting for video frame interpolation. CVPR 2020.
[170] STSR 5.35 2 color Anonymous. (Interpolation results only.) Spatial and temporal video super-resolution with a frequency domain loss. ECCV 2020 submission 2340.
[171] EAFI 0.13 2 color Anonymous. (Interpolation results only.) Fast & small: Error-aware frame interpolation. ECCV 2020 submission 5256.
[172] BMBC 0.77 2 color Anonymous. (Interpolation results only.) BMBC: Bilateral motion estimation with bilateral cost volume for video interpolation. ECCV 2020 submission 2095.
[173] GDCN 1.0 2 color Anonymous. (Interpolation results only.) Video interpolation via generalized deformable convolution. ECCV 2020 submission 4347.
[174] EDSC 0.56 2 color Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) Multiple video frame interpolation via enhanced deformable separable convolution. Submitted to PAMI 2020.
[175] CoT-AMFlow 0.04 2 color Anonymous. CoT-AMFlow: Adaptive modulation network with co-teaching strategy for unsupervised optical flow estimation. CoRL 2020 submission 36.
[176] TVL1_RVC 11.6 2 color RVC 2020 baseline submission by Toby Weed, based on: Javier Sanchez, Enric Meinhardt-Llopis, and Gabriele Facciolo. TV-L1 optical flow estimation. IPOL 3:137-150, 2013.
[177] H+S_RVC 44.7 2 color RVC 2020 baseline submission by Toby Weed, based on: Enric Meinhardt-Llopis, Javier Sanchez, and Daniel Kondermann. Horn-Schunck optical flow with a multi-scale strategy. IPOL 3:151–172, 2013.
[178] PRAFlow_RVC 0.34 2 color Zhexiong Wan, Yuxin Mao, and Yuchao Dai. Pyramid recurrent all-pairs flow. RVC 2020 submission.
[179] VCN_RVC 0.84 2 color Gengshan Yang and Deva Ramanan. Volumetric correspondence networks for optical flow. NeurIPS 2019. RVC 2020 submission.
[180] RAFT-TF_RVC 1.51 2 color 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.
[181] IRR-PWC_RVC 0.18 2 color Junhwa Hur and Stefan Roth. Iterative residual refinement for joint optical flow and occlusion estimation. CVPR 2019. RVC 2020 submission.
[182] C-RAFT_RVC 0.60 2 color Henrique Morimitsu and Xiangyang Ji. Classification RAFT. RVC 2020 submission.
[183] LSM_FLOW_RVC 0.2 2 color Chengzhou Tang, Lu Yuan, and Ping Tan. LSM: Learning subspace minimization for low-level vision. CVPR 2020. RVC 2020 submission.
[184] UnDAF 0.04 2 color Anonymous. UnDAF: A general unsupervised domain adaptation framework for disparity, optical flow or scene flow estimation. AAAI 2021 submission 6648.
[185] DCM 0.13 2 color Anonymous. (Interpolation results only.) Distill from a cheating model for flow-based video frame interpolation. AAAI 2021 submission 4425.
* The "time" column lists the reported runtime in seconds on the "Urban" sequence. Note that these runtimes are not normalized by processor speed or type.