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        
A95
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
SoftsplatAug [190]2.7 3.16 1 5.69 1 1.73 1 5.07 1 7.05 2 1.83 2 2.16 1 3.70 2 1.41 1 6.88 3 8.29 3 4.43 4 12.7 2 16.6 2 4.24 3 5.89 4 14.0 4 3.37 5 6.78 8 23.8 3 2.38 1 9.85 3 14.9 3 2.16 4
SoftSplat [169]5.1 3.37 2 6.06 3 1.91 11 5.48 4 8.37 7 1.83 2 2.16 1 3.70 2 1.41 1 6.78 2 8.19 2 4.40 2 13.7 18 18.1 19 4.24 3 6.24 6 14.9 6 3.37 5 6.98 11 25.4 5 2.38 1 9.88 5 14.9 3 2.08 1
IFRNet [193]7.3 3.42 4 5.80 2 1.91 11 5.51 5 7.87 4 1.91 4 2.38 3 3.70 2 1.41 1 7.00 4 8.43 5 4.80 20 13.2 7 17.3 6 4.55 22 6.45 8 16.7 11 3.42 16 6.83 9 26.1 8 2.38 1 10.9 9 16.4 9 2.16 4
EAFI [186]7.8 3.37 2 6.16 5 1.83 6 5.20 2 6.68 1 1.73 1 2.38 3 3.46 1 1.41 1 6.68 1 7.87 1 4.32 1 16.0 27 21.3 27 4.20 1 7.33 22 18.3 22 3.32 1 7.23 16 27.1 15 2.38 1 11.6 15 17.1 11 2.16 4
DistillNet [184]9.2 3.56 5 6.16 5 1.91 11 5.45 3 7.55 3 1.91 4 2.38 3 3.79 5 1.41 1 7.16 7 9.04 7 4.43 4 13.6 17 18.0 18 4.24 3 7.51 24 18.6 24 3.37 5 7.87 18 29.0 20 2.38 1 11.6 15 17.4 13 2.16 4
IDIAL [192]10.8 3.74 10 6.68 10 1.83 6 6.22 12 9.81 19 1.91 4 2.71 7 4.08 8 1.73 6 7.72 14 9.81 13 4.55 6 13.3 8 17.6 9 4.32 12 7.26 21 17.0 12 3.37 5 8.58 32 28.0 17 2.38 1 11.5 12 17.1 11 2.16 4
SepConv++ [185]11.0 3.87 15 7.35 18 2.00 18 5.83 8 9.04 9 2.16 88 2.83 12 4.83 11 1.73 6 7.94 20 11.0 24 4.65 8 12.8 3 16.9 4 4.24 3 5.16 1 12.6 2 3.32 1 6.45 3 23.9 4 2.38 1 9.15 2 14.6 2 2.08 1
EDSC [173]13.6 3.79 13 6.98 16 1.83 6 6.06 10 9.63 14 2.16 88 3.00 14 5.00 13 1.73 6 7.83 15 10.7 19 4.69 12 13.1 6 17.4 7 4.43 16 6.48 10 17.6 17 3.37 5 6.56 4 25.7 7 2.38 1 11.3 10 17.4 13 2.16 4
FGME [158]15.5 3.56 5 6.06 3 1.73 1 6.40 15 9.56 13 2.16 88 3.00 14 4.69 10 2.00 126 7.07 5 8.39 4 4.80 20 12.4 1 16.4 1 4.24 3 5.60 3 13.8 3 3.46 22 6.19 1 21.3 2 2.45 21 9.85 3 15.4 5 2.16 4
STAR-Net [164]17.8 3.70 8 6.16 5 2.08 97 6.58 30 10.9 37 2.16 88 3.00 14 4.08 8 1.73 6 7.62 13 9.59 11 4.40 2 12.9 4 17.0 5 4.20 1 7.05 16 17.4 16 3.37 5 8.35 26 26.4 11 2.38 1 11.3 10 16.9 10 2.16 4
STSR [170]18.2 3.74 10 7.35 18 1.91 11 5.74 6 8.29 5 1.91 4 3.37 22 5.69 22 1.73 6 7.26 8 9.42 10 4.80 20 16.8 31 22.5 31 4.55 22 8.29 30 21.3 33 3.51 24 8.27 25 32.7 30 2.38 1 12.8 32 19.1 31 2.16 4
DAI [168]19.4 3.83 14 6.45 8 2.08 97 6.76 43 10.2 28 2.08 8 2.38 3 4.00 7 1.73 6 7.14 6 8.81 6 4.93 24 15.9 26 21.2 26 4.24 3 7.77 26 19.7 26 3.37 5 7.85 17 31.2 28 2.38 1 12.3 26 18.5 27 2.16 4
MV_VFI [183]20.8 3.87 15 7.35 18 2.08 97 6.38 14 9.75 17 2.16 88 2.71 7 5.00 13 1.73 6 7.87 18 10.7 19 4.65 8 13.5 12 17.9 14 4.43 16 7.12 18 17.3 13 3.42 16 7.87 18 30.7 24 2.38 1 12.1 22 18.2 20 2.16 4
TC-GAN [166]21.0 3.87 15 7.35 18 2.08 97 6.40 15 9.83 20 2.16 88 2.71 7 5.00 13 1.73 6 7.87 18 10.7 19 4.65 8 13.5 12 17.9 14 4.40 14 7.12 18 17.3 13 3.42 16 7.87 18 30.7 24 2.38 1 12.1 22 18.3 23 2.16 4
DAIN [152]22.2 3.92 21 7.44 24 2.08 97 6.45 21 9.88 22 2.16 88 2.83 12 5.10 18 1.73 6 7.85 16 10.7 19 4.65 8 13.5 12 17.9 14 4.43 16 7.07 17 17.3 13 3.42 16 7.87 18 30.9 27 2.38 1 12.1 22 18.2 20 2.16 4
BMBC [171]22.5 4.08 23 6.68 10 2.08 97 6.03 9 9.04 9 2.16 88 5.00 33 7.05 31 2.00 126 7.39 10 9.33 9 4.55 6 13.5 12 17.7 10 4.32 12 6.35 7 14.9 6 3.37 5 7.14 14 25.4 5 2.38 1 10.3 6 15.8 7 2.16 4
AdaCoF [165]23.2 4.08 23 7.39 23 2.16 136 6.22 12 9.49 12 2.16 88 4.00 27 5.69 22 1.73 6 8.43 50 11.3 25 4.69 12 14.8 23 19.7 23 4.65 25 5.97 5 15.3 8 3.32 1 6.68 7 26.9 13 2.38 1 10.5 7 16.0 8 2.08 1
DSepConv [162]23.8 4.08 23 7.75 28 2.00 18 6.68 32 9.93 25 2.16 88 3.37 22 5.35 19 1.73 6 8.76 88 12.0 32 4.76 18 13.3 8 17.7 10 4.51 20 6.68 12 18.1 20 3.42 16 6.58 5 26.1 8 2.45 21 12.0 20 18.5 27 2.16 4
MEMC-Net+ [160]25.3 4.08 23 7.05 17 2.16 136 6.48 25 9.83 20 2.16 88 3.00 14 5.35 19 1.73 6 8.19 22 10.2 16 4.69 12 14.8 23 19.7 23 4.40 14 7.68 25 18.0 18 3.37 5 8.19 24 30.0 23 2.38 1 12.3 26 18.3 23 2.16 4
GDCN [172]27.5 4.00 22 7.53 26 1.91 11 7.62 113 11.5 59 2.16 88 2.71 7 4.83 11 1.73 6 8.96 123 10.2 16 4.76 18 13.5 12 17.9 14 4.51 20 6.95 15 18.0 18 3.46 22 7.07 13 26.5 12 2.38 1 11.5 12 18.0 18 2.16 4
FeFlow [167]31.0 3.74 10 6.78 13 1.83 6 6.73 41 10.5 31 2.16 88 3.00 14 5.00 13 2.00 126 8.04 21 10.5 18 4.69 12 13.4 10 17.7 10 4.24 3 7.44 23 18.4 23 3.42 16 8.54 29 28.0 17 2.45 21 11.8 18 18.1 19 2.38 163
ADC [161]33.5 4.51 33 7.96 30 2.16 136 6.56 27 9.63 14 2.38 146 4.36 28 6.35 27 1.73 6 9.11 135 12.1 35 4.80 20 14.4 22 19.3 22 4.55 22 6.68 12 18.1 20 3.37 5 6.66 6 26.1 8 2.38 1 12.0 20 18.4 25 2.16 4
FRUCnet [153]34.1 4.20 27 7.51 25 2.65 192 6.40 15 9.75 17 2.52 169 3.56 25 5.69 22 2.00 126 8.19 22 10.9 23 4.69 12 13.8 20 18.2 21 4.24 3 6.45 8 16.5 10 3.37 5 7.05 12 27.0 14 2.45 21 11.5 12 17.4 13 2.16 4
PMMST [112]34.2 5.00 35 9.68 44 2.00 18 6.88 55 11.0 41 2.08 8 5.69 37 9.00 35 1.73 6 8.21 27 12.0 32 5.07 32 17.4 36 23.4 36 5.07 43 9.29 38 22.6 36 3.74 56 8.66 38 37.1 52 2.45 21 13.9 46 21.3 45 2.16 4
ProBoost-Net [191]34.8 3.70 8 6.73 12 1.73 1 7.33 84 11.5 59 2.16 88 3.00 14 5.00 13 2.00 126 7.57 12 9.76 12 5.00 29 14.9 25 20.1 25 4.65 25 7.14 20 18.8 25 3.56 26 6.86 10 27.6 16 2.45 21 11.9 19 18.2 20 2.31 144
MAF-net [163]35.2 3.56 5 6.78 13 1.73 1 6.78 46 10.9 37 2.16 88 3.00 14 5.48 21 2.00 126 7.85 16 10.1 15 5.00 29 16.2 28 21.8 28 4.69 27 7.79 27 20.6 29 3.56 26 7.14 14 29.3 21 2.45 21 12.3 26 18.4 25 2.38 163
MDP-Flow2 [68]36.8 4.97 34 9.42 39 2.00 18 6.68 32 11.0 41 2.08 8 5.69 37 9.04 40 1.73 6 8.19 22 12.0 32 5.10 61 17.5 38 23.5 39 5.07 43 9.95 71 24.7 72 3.74 56 8.60 34 36.4 41 2.45 21 13.9 46 21.5 47 2.16 4
CoT-AMFlow [174]38.1 5.00 35 9.68 44 2.00 18 6.68 32 11.1 45 2.08 8 5.69 37 9.38 49 1.73 6 8.23 28 12.2 37 5.07 32 17.6 41 23.6 40 5.07 43 9.98 79 24.5 67 3.74 56 8.70 45 37.0 50 2.45 21 13.9 46 21.6 51 2.16 4
CyclicGen [149]40.6 4.20 27 6.86 15 2.45 187 6.06 10 8.29 5 3.42 195 4.36 28 7.62 32 2.00 126 8.74 84 11.6 27 5.26 153 13.4 10 17.4 7 4.69 27 5.35 2 11.3 1 3.70 28 6.24 2 19.7 1 2.38 1 8.89 1 13.0 1 2.16 4
CtxSyn [134]44.6 3.87 15 7.35 18 1.83 6 5.80 7 8.96 8 2.08 8 3.11 21 5.69 22 2.00 126 7.33 9 9.95 14 4.97 25 17.1 34 22.5 31 4.93 33 8.70 33 20.9 30 3.74 56 10.2 165 33.7 34 2.52 154 12.6 30 18.8 29 2.38 163
OFRI [154]46.1 3.87 15 6.61 9 2.16 136 6.40 15 9.70 16 2.45 161 2.71 7 3.79 5 1.73 6 7.39 10 9.20 8 4.69 12 13.8 20 18.1 19 4.43 16 7.87 28 19.9 27 3.51 24 10.2 165 30.7 24 2.58 179 12.2 25 17.9 17 2.38 163
NNF-Local [75]46.8 5.07 43 10.1 59 2.00 18 6.40 15 10.0 26 2.08 8 5.69 37 9.00 35 1.73 6 8.66 68 14.5 118 5.10 61 17.6 41 23.8 49 5.07 43 10.4 112 25.8 109 3.74 56 8.66 38 37.5 58 2.45 21 13.9 46 21.6 51 2.16 4
PH-Flow [99]47.4 5.20 77 10.7 88 2.00 18 6.45 21 10.3 29 2.08 8 5.69 37 9.38 49 1.73 6 8.19 22 11.9 29 5.07 32 17.7 55 24.0 61 5.03 39 10.6 130 26.5 132 3.70 28 8.68 44 38.8 97 2.45 21 14.0 54 21.7 56 2.16 4
NN-field [71]48.3 5.07 43 10.4 74 2.00 18 6.45 21 10.0 26 2.08 8 5.97 93 9.00 35 1.73 6 8.76 88 15.0 134 5.10 61 17.6 41 23.7 45 5.07 43 10.1 85 25.0 83 3.74 56 8.54 29 36.9 48 2.45 21 13.9 46 21.6 51 2.16 4
MPRN [151]52.2 4.43 31 8.35 32 2.08 97 7.39 92 10.8 36 2.16 88 6.06 144 10.4 121 2.00 126 8.70 77 12.4 41 4.97 25 16.7 29 22.2 29 4.83 31 8.23 29 20.5 28 3.70 28 8.81 54 33.2 32 2.45 21 12.4 29 18.9 30 2.16 4
NNF-EAC [101]52.5 5.35 117 10.0 55 2.08 97 7.05 70 11.6 63 2.08 8 6.00 94 9.35 44 1.73 6 8.35 33 12.4 41 5.23 134 17.7 55 23.9 58 5.07 43 9.47 39 22.9 37 3.70 28 8.83 58 37.0 50 2.45 21 14.0 54 21.6 51 2.16 4
IROF++ [58]53.5 5.23 100 10.8 97 2.00 18 6.88 55 11.5 59 2.08 8 6.00 94 10.0 68 1.73 6 8.19 22 11.9 29 5.07 32 17.9 82 24.4 90 5.10 67 9.49 41 24.2 60 3.74 56 9.09 94 37.2 55 2.45 21 14.0 54 22.1 72 2.16 4
SepConv-v1 [125]56.1 3.87 15 8.50 33 1.73 1 7.05 70 11.4 51 2.16 88 3.46 24 6.56 29 2.00 126 8.58 62 12.6 51 5.26 153 17.5 38 23.6 40 4.97 34 8.35 32 22.4 35 3.70 28 8.08 23 33.3 33 2.52 154 12.8 32 19.1 31 2.38 163
GMFlow_RVC [196]58.4 5.20 77 12.5 160 2.00 18 6.68 32 11.1 45 2.08 8 5.69 37 9.35 44 1.73 6 8.43 50 13.8 94 5.10 61 18.0 93 24.5 98 5.10 67 10.3 104 25.5 98 3.70 28 8.81 54 36.6 44 2.45 21 14.2 87 22.0 71 2.16 4
MS_RAFT+_RVC [195]59.6 5.10 65 11.8 149 2.00 18 6.78 46 11.4 51 2.08 8 5.45 34 8.87 34 1.73 6 8.25 29 12.1 35 5.07 32 18.1 108 24.7 112 5.20 112 9.61 50 23.3 43 3.70 28 8.49 28 35.3 35 2.45 21 16.9 190 30.9 193 2.16 4
SuperSlomo [130]60.0 4.24 29 7.53 26 2.16 136 7.14 76 11.4 51 2.71 178 4.36 28 6.45 28 2.00 126 8.27 30 11.3 25 5.10 61 16.7 29 22.2 29 4.80 30 8.29 30 21.0 31 3.74 56 8.60 34 32.7 30 2.52 154 12.6 30 19.1 31 2.38 163
COFM [59]60.4 5.07 43 10.7 88 2.00 18 6.86 54 11.4 51 2.08 8 5.69 37 9.75 58 1.73 6 8.35 33 12.5 46 5.07 32 18.1 108 24.7 112 5.03 39 11.0 161 27.5 163 3.70 28 8.06 22 39.1 101 2.45 21 14.4 112 22.7 105 2.16 4
DeepFlow2 [106]60.5 5.07 43 9.85 50 2.08 97 7.53 107 13.1 111 2.16 88 5.69 37 10.0 68 1.73 6 8.83 109 13.4 80 5.10 61 17.6 41 23.7 45 5.20 112 9.24 37 23.0 38 3.74 56 9.00 77 37.9 71 2.45 21 13.9 46 21.5 47 2.16 4
DF-Auto [113]61.0 5.03 40 8.87 34 2.16 136 7.72 115 13.1 111 2.38 146 5.69 37 9.20 43 1.73 6 8.68 72 12.5 46 5.10 61 17.4 36 23.4 36 5.16 102 9.47 39 24.0 52 3.74 56 8.98 74 38.4 84 2.45 21 14.0 54 21.8 60 2.16 4
TOF-M [150]61.3 4.24 29 8.10 31 1.91 11 7.33 84 11.6 63 2.52 169 4.36 28 6.95 30 2.00 126 8.43 50 11.7 28 5.07 32 16.9 33 22.6 34 4.97 34 8.74 34 21.2 32 3.74 56 9.47 129 31.8 29 2.58 179 13.2 34 19.7 34 2.38 163
WLIF-Flow [91]62.1 5.10 65 10.2 65 2.00 18 7.00 68 11.9 78 2.08 8 5.69 37 9.68 52 1.73 6 8.29 31 12.2 37 5.23 134 17.8 67 24.0 61 5.10 67 10.6 130 26.6 136 3.83 151 8.83 58 37.5 58 2.45 21 14.1 70 21.9 68 2.16 4
MS-PFT [159]63.0 4.43 31 7.94 29 1.91 11 6.95 61 10.7 33 2.45 161 3.74 26 6.06 26 2.08 189 9.57 161 12.7 56 4.97 25 13.7 18 17.8 13 4.69 27 6.73 14 15.4 9 3.74 56 9.98 159 29.5 22 2.65 191 11.6 15 17.7 16 2.38 163
Layers++ [37]63.1 5.10 65 10.1 59 2.08 97 6.45 21 9.88 22 2.08 8 5.69 37 10.0 68 1.73 6 8.37 40 12.7 56 5.10 61 18.1 108 24.9 140 5.10 67 10.7 142 28.3 177 3.74 56 8.76 47 38.0 75 2.45 21 14.1 70 21.9 68 2.16 4
LME [70]63.3 5.07 43 10.1 59 2.00 18 7.05 70 12.0 81 2.16 88 5.69 37 10.7 125 1.73 6 8.35 33 12.8 60 5.10 61 18.0 93 24.4 90 5.29 190 10.2 96 25.3 92 3.74 56 8.70 45 36.4 41 2.45 21 14.0 54 21.7 56 2.16 4
FLAVR [188]63.4 6.16 185 9.35 36 2.38 181 7.44 102 9.15 11 2.83 185 4.83 32 7.77 33 2.00 126 17.0 196 19.8 186 4.97 25 13.0 5 16.8 3 4.24 3 6.58 11 14.2 5 3.32 1 9.56 137 28.3 19 2.45 21 10.7 8 15.6 6 2.16 4
ProbFlowFields [126]63.6 5.03 40 10.7 88 2.00 18 6.68 32 11.3 48 2.08 8 5.69 37 9.47 51 1.73 6 8.52 58 13.3 79 5.20 98 18.2 138 24.9 140 5.23 171 10.5 117 26.2 124 3.74 56 8.60 34 37.7 66 2.45 21 13.8 42 21.6 51 2.16 4
nLayers [57]63.7 5.16 75 10.5 80 2.00 18 6.66 31 10.9 37 2.08 8 5.69 37 9.00 35 1.73 6 8.49 57 13.0 63 5.10 61 18.3 149 25.2 159 5.20 112 10.4 112 25.6 103 3.74 56 8.66 38 38.5 89 2.45 21 14.2 87 22.4 91 2.16 4
CombBMOF [111]63.7 5.35 117 10.5 80 2.00 18 6.83 52 11.4 51 2.08 8 5.80 89 10.0 68 1.73 6 8.83 109 14.4 111 5.10 61 17.9 82 24.3 83 5.07 43 9.88 64 24.1 56 3.70 28 10.7 177 38.3 79 2.45 21 14.0 54 21.9 68 2.16 4
HCFN [157]64.2 5.07 43 11.0 107 2.00 18 7.14 76 12.4 87 2.08 8 5.69 37 10.0 68 1.73 6 8.39 45 13.1 71 5.07 32 17.8 67 24.2 80 5.07 43 10.2 96 23.8 49 4.51 193 9.06 92 39.9 113 2.45 21 14.2 87 22.6 98 2.16 4
DeepFlow [85]64.7 5.07 43 9.63 43 2.08 97 7.44 102 13.0 105 2.16 88 5.74 85 10.0 68 1.73 6 8.96 123 13.0 63 5.20 98 17.6 41 23.8 49 5.20 112 9.15 36 23.2 40 3.87 161 8.81 54 35.6 36 2.45 21 13.7 38 21.1 40 2.16 4
FMOF [92]65.2 5.42 139 11.0 107 2.00 18 6.76 43 11.0 41 2.08 8 6.00 94 10.3 99 1.73 6 8.83 109 14.1 102 5.10 61 17.8 67 24.1 72 5.07 43 10.0 83 25.6 103 3.74 56 8.58 32 37.7 66 2.45 21 14.3 99 22.4 91 2.16 4
RAFT-it+_RVC [198]65.7 5.10 65 12.6 162 2.00 18 6.68 32 11.1 45 2.08 8 5.69 37 9.81 62 1.73 6 8.66 68 15.2 139 5.07 32 17.8 67 24.0 61 5.10 67 10.9 154 26.2 124 4.69 197 8.66 38 36.0 37 2.45 21 14.0 54 22.2 79 2.16 4
Sparse-NonSparse [56]66.0 5.20 77 10.7 88 2.00 18 6.78 46 11.6 63 2.08 8 5.69 37 10.0 68 1.73 6 8.43 50 12.5 46 5.07 32 18.1 108 24.7 112 5.10 67 10.5 117 26.7 139 3.74 56 8.76 47 42.1 151 2.45 21 14.3 99 23.0 123 2.16 4
PRAFlow_RVC [177]66.2 5.20 77 12.1 154 2.00 18 6.95 61 11.6 63 2.08 8 5.69 37 9.15 42 1.73 6 8.72 82 14.4 111 5.20 98 17.7 55 24.0 61 5.20 112 9.81 54 24.7 72 3.74 56 8.76 47 36.0 37 2.45 21 14.8 150 24.2 162 2.16 4
IROF-TV [53]66.2 5.20 77 10.7 88 2.08 97 7.05 70 11.9 78 2.08 8 6.00 94 10.3 99 1.73 6 8.37 40 12.6 51 5.16 86 17.8 67 24.1 72 5.23 171 10.1 85 25.0 83 3.70 28 9.04 87 39.1 101 2.45 21 13.7 38 21.0 38 2.16 4
FlowFields [108]67.1 5.10 65 11.1 119 2.00 18 6.88 55 11.5 59 2.08 8 5.69 37 10.0 68 1.73 6 8.76 88 14.9 129 5.20 98 18.0 93 24.4 90 5.16 102 10.3 104 25.8 109 3.74 56 8.76 47 37.8 68 2.45 21 14.1 70 22.5 96 2.16 4
Aniso. Huber-L1 [22]67.2 5.26 102 10.0 55 2.08 97 8.81 155 14.5 157 2.16 88 6.00 94 9.75 58 1.73 6 8.72 82 13.0 63 5.16 86 17.6 41 23.8 49 5.10 67 9.87 63 23.2 40 3.70 28 9.26 110 37.8 68 2.45 21 13.8 42 21.0 38 2.16 4
TV-L1-MCT [64]67.4 5.48 156 11.4 133 2.00 18 7.35 88 13.1 111 2.08 8 5.48 35 10.3 99 1.73 6 8.35 33 12.4 41 5.07 32 18.3 149 25.3 164 5.10 67 9.49 41 23.5 45 3.79 130 8.81 54 39.2 105 2.45 21 13.7 38 21.1 40 2.16 4
ComponentFusion [94]67.8 5.07 43 11.2 126 2.00 18 6.81 51 11.6 63 2.08 8 5.72 84 9.81 62 1.73 6 8.37 40 13.2 76 5.07 32 18.1 108 24.7 112 5.10 67 9.90 65 24.9 79 3.74 56 9.20 107 44.1 172 2.45 21 14.2 87 23.3 139 2.16 4
SegFlow [156]68.0 5.07 43 11.1 119 2.00 18 6.95 61 11.6 63 2.08 8 5.74 85 10.0 68 1.73 6 8.70 77 15.0 134 5.16 86 18.1 108 24.7 112 5.20 112 10.1 85 24.9 79 3.74 56 9.13 100 37.6 62 2.45 21 14.0 54 22.1 72 2.16 4
Brox et al. [5]68.2 5.20 77 9.83 47 2.00 18 7.62 113 12.6 92 2.16 88 6.00 94 10.2 95 2.00 126 8.76 88 12.6 51 5.07 32 17.5 38 23.6 40 5.16 102 10.1 85 25.3 92 3.74 56 9.00 77 40.1 115 2.45 21 13.8 42 21.3 45 2.16 4
MDP-Flow [26]68.7 5.03 40 9.95 53 2.00 18 6.68 32 11.3 48 2.08 8 5.69 37 9.04 40 1.73 6 8.89 118 13.7 87 5.20 98 17.8 67 24.2 80 5.20 112 11.3 175 27.9 170 3.74 56 9.27 114 39.3 107 2.45 21 14.1 70 22.3 87 2.16 4
JOF [136]69.2 5.35 117 10.8 97 2.08 97 6.68 32 10.9 37 2.08 8 5.69 37 9.68 52 1.73 6 8.39 45 12.5 46 5.20 98 18.1 108 24.7 112 5.20 112 10.6 130 27.1 150 3.74 56 8.66 38 37.6 62 2.45 21 14.3 99 22.5 96 2.16 4
RAFT-it [194]71.8 5.07 43 12.4 157 2.00 18 6.56 27 10.7 33 2.08 8 5.69 37 9.35 44 1.73 6 8.54 61 14.4 111 5.07 32 17.7 55 23.8 49 5.10 67 10.8 150 27.1 150 4.69 197 8.54 29 36.0 37 2.45 21 17.3 192 32.0 194 2.16 4
PGM-C [118]71.9 5.07 43 10.9 104 2.00 18 6.93 59 11.6 63 2.08 8 6.00 94 10.3 99 1.73 6 8.76 88 15.2 139 5.16 86 18.0 93 24.7 112 5.20 112 9.97 77 24.8 77 3.74 56 9.00 77 40.1 115 2.45 21 14.1 70 22.7 105 2.16 4
2DHMM-SAS [90]72.1 5.42 139 11.2 126 2.00 18 7.90 128 13.7 133 2.08 8 5.60 36 9.85 64 1.73 6 8.35 33 12.2 37 5.10 61 18.0 93 24.6 110 5.10 67 9.93 69 25.7 106 3.74 56 8.96 68 39.8 112 2.45 21 14.4 112 23.0 123 2.16 4
FlowFields+ [128]72.4 5.10 65 11.1 119 2.00 18 6.78 46 11.3 48 2.08 8 5.69 37 10.0 68 1.73 6 8.70 77 14.9 129 5.16 86 18.2 138 24.9 140 5.20 112 10.4 112 26.3 128 3.74 56 8.79 52 38.6 93 2.45 21 14.1 70 22.7 105 2.16 4
CPM-Flow [114]73.8 5.07 43 10.9 104 2.00 18 6.95 61 11.6 63 2.08 8 5.80 89 10.0 68 1.73 6 9.00 130 15.9 157 5.20 98 18.1 108 24.7 112 5.20 112 9.81 54 24.3 62 3.79 130 9.26 110 38.3 79 2.45 21 14.0 54 22.2 79 2.16 4
HAST [107]73.9 5.07 43 10.5 80 2.00 18 6.68 32 10.7 33 2.08 8 6.00 94 10.3 99 1.73 6 8.29 31 12.4 41 5.00 29 18.4 160 25.3 164 5.03 39 11.0 161 30.7 190 3.70 28 8.60 34 41.8 144 2.45 21 14.9 158 23.9 156 2.16 4
CLG-TV [48]74.3 5.20 77 9.49 40 2.08 97 8.43 145 14.3 151 2.16 88 6.00 94 10.1 91 2.00 126 8.76 88 13.1 71 5.20 98 17.6 41 23.8 49 5.10 67 9.59 49 23.1 39 3.74 56 9.20 107 38.4 84 2.45 21 14.0 54 21.5 47 2.16 4
ALD-Flow [66]74.7 5.20 77 10.7 88 2.08 97 7.35 88 12.9 100 2.16 88 6.00 94 10.1 91 1.73 6 8.39 45 13.0 63 5.16 86 17.9 82 24.3 83 5.20 112 9.56 46 23.5 45 3.79 130 8.79 52 36.8 46 2.45 21 14.5 125 23.0 123 2.16 4
S2F-IF [121]75.1 5.10 65 11.6 144 2.00 18 6.78 46 11.4 51 2.08 8 5.69 37 10.3 99 1.73 6 8.74 84 15.2 139 5.07 32 18.3 149 25.1 154 5.20 112 10.5 117 26.1 119 3.74 56 9.02 85 38.5 89 2.45 21 14.1 70 22.6 98 2.16 4
VCN_RVC [178]75.2 5.35 117 13.3 172 2.00 18 6.88 55 11.4 51 2.08 8 6.00 94 11.5 157 1.73 6 8.70 77 15.5 148 5.16 86 18.1 108 24.7 112 5.10 67 9.95 71 24.2 60 3.70 28 9.00 77 38.0 75 2.45 21 14.1 70 23.0 123 2.16 4
Ramp [62]76.2 5.29 110 10.8 97 2.00 18 6.83 52 11.6 63 2.08 8 5.69 37 10.1 91 1.73 6 8.35 33 12.2 37 5.07 32 18.1 108 24.7 112 5.10 67 10.9 154 27.8 169 3.79 130 8.83 58 43.0 163 2.45 21 14.5 125 23.2 133 2.16 4
Second-order prior [8]76.7 5.20 77 9.83 47 2.08 97 8.43 145 14.5 157 2.08 8 6.35 153 11.0 143 2.00 126 8.83 109 13.8 94 5.07 32 17.7 55 23.8 49 5.07 43 9.70 52 24.1 56 3.74 56 9.33 118 38.4 84 2.45 21 14.0 54 21.8 60 2.16 4
RAFT-TF_RVC [179]76.7 5.10 65 13.0 168 2.00 18 6.76 43 11.4 51 2.08 8 5.69 37 9.68 52 1.73 6 8.68 72 14.6 120 5.10 61 17.9 82 24.3 83 5.10 67 10.7 142 26.8 142 4.55 195 8.66 38 36.8 46 2.45 21 14.7 144 25.3 175 2.16 4
UnDAF [187]77.5 5.20 77 12.6 162 2.00 18 7.16 80 12.5 90 2.08 8 6.00 94 12.7 178 1.73 6 9.47 155 19.4 182 5.20 98 17.6 41 23.7 45 5.07 43 10.1 85 24.5 67 3.74 56 8.96 68 40.1 115 2.45 21 14.2 87 22.2 79 2.16 4
EAI-Flow [147]78.2 5.20 77 11.2 126 2.08 97 7.39 92 12.4 87 2.16 88 6.00 94 10.8 138 1.73 6 8.81 103 14.6 120 5.07 32 18.1 108 24.8 127 5.16 102 9.83 56 24.0 52 3.74 56 9.43 128 38.3 79 2.45 21 13.7 38 21.5 47 2.16 4
DPOF [18]79.2 5.35 117 11.7 146 2.08 97 6.56 27 10.4 30 2.08 8 6.00 94 9.71 57 1.91 121 8.76 88 14.4 111 5.20 98 17.7 55 24.1 72 5.07 43 10.3 104 26.7 139 3.70 28 9.33 118 39.1 101 2.45 21 14.4 112 22.8 111 2.16 4
p-harmonic [29]79.3 5.07 43 9.98 54 2.00 18 8.68 151 14.4 153 2.16 88 6.00 94 10.7 125 1.91 121 9.20 142 13.7 87 5.20 98 17.8 67 24.0 61 5.10 67 9.90 65 23.7 48 3.74 56 9.61 141 38.5 89 2.45 21 14.0 54 21.7 56 2.16 4
CBF [12]79.5 5.00 35 9.40 38 2.08 97 7.77 120 13.0 105 2.16 88 6.00 94 9.68 52 1.73 6 8.68 72 12.5 46 5.35 172 17.6 41 23.4 36 5.20 112 9.85 61 24.3 62 3.74 56 9.11 98 39.3 107 2.52 154 14.0 54 21.1 40 2.38 163
SIOF [67]80.1 5.42 139 10.4 74 2.08 97 8.83 156 15.0 172 2.38 146 5.69 37 10.4 121 1.73 6 8.68 72 13.1 71 5.20 98 17.3 35 23.2 35 5.07 43 9.83 56 23.6 47 3.74 56 9.00 77 36.9 48 2.45 21 14.3 99 22.1 72 2.31 144
OFLAF [78]80.1 5.07 43 10.6 85 2.00 18 6.48 25 10.5 31 2.08 8 5.69 37 10.0 68 1.73 6 8.37 40 12.6 51 5.07 32 18.4 160 25.4 171 5.20 112 10.9 154 27.4 161 3.74 56 9.59 140 44.9 177 2.45 21 15.1 163 24.1 159 2.16 4
ProFlow_ROB [142]80.2 5.07 43 10.9 104 2.00 18 7.33 84 12.7 94 2.16 88 5.69 37 9.98 67 1.73 6 8.60 65 14.1 102 5.20 98 18.3 149 25.2 159 5.20 112 9.52 44 23.4 44 3.70 28 9.49 134 42.0 149 2.45 21 14.5 125 23.6 149 2.16 4
Local-TV-L1 [65]80.6 5.20 77 9.38 37 2.16 136 8.96 160 14.5 157 2.38 146 5.69 37 9.35 44 1.73 6 8.70 77 13.0 63 5.45 179 17.6 41 23.8 49 5.16 102 9.54 45 24.0 52 4.08 186 8.76 47 37.2 55 2.45 21 13.6 37 20.9 37 2.31 144
FC-2Layers-FF [74]80.8 5.26 102 11.0 107 2.00 18 6.40 15 9.88 22 2.08 8 5.69 37 10.3 99 1.73 6 8.39 45 12.8 60 5.10 61 18.2 138 25.0 148 5.20 112 11.0 161 28.1 173 3.79 130 8.91 65 42.8 158 2.45 21 14.5 125 23.0 123 2.16 4
LSM [39]80.8 5.35 117 11.5 138 2.00 18 6.98 65 11.9 78 2.08 8 5.80 89 10.7 125 1.73 6 8.58 62 13.4 80 5.07 32 18.1 108 24.9 140 5.10 67 10.6 130 27.1 150 3.74 56 8.83 58 42.2 153 2.45 21 14.4 112 23.0 123 2.16 4
AGIF+OF [84]81.0 5.42 139 11.1 119 2.00 18 6.98 65 11.8 75 2.08 8 5.69 37 10.0 68 1.73 6 8.43 50 12.8 60 5.07 32 18.5 168 25.2 159 5.20 112 10.8 150 27.6 164 3.74 56 8.98 74 37.9 71 2.45 21 14.7 144 23.4 143 2.16 4
ComplOF-FED-GPU [35]81.1 5.20 77 11.1 119 2.00 18 7.19 82 12.6 92 2.08 8 6.35 153 10.0 68 2.00 126 8.68 72 14.0 101 5.10 61 17.9 82 24.5 98 5.10 67 9.97 77 25.1 86 3.74 56 9.40 123 38.8 97 2.45 21 14.5 125 23.2 133 2.16 4
Classic+NL [31]82.1 5.35 117 11.0 107 2.08 97 6.98 65 11.7 73 2.08 8 5.69 37 10.2 95 1.73 6 8.43 50 12.4 41 5.20 98 18.1 108 24.8 127 5.10 67 10.6 130 26.8 142 3.79 130 8.83 58 42.9 159 2.45 21 14.4 112 22.9 119 2.16 4
LDOF [28]82.2 5.35 117 9.83 47 2.16 136 7.94 129 12.1 82 2.52 169 6.00 94 10.3 99 2.00 126 8.91 121 13.6 85 5.23 134 17.6 41 23.6 40 5.20 112 9.49 41 24.5 67 3.74 56 8.96 68 37.9 71 2.45 21 14.0 54 21.8 60 2.16 4
RNLOD-Flow [119]83.3 5.20 77 11.0 107 2.00 18 7.53 107 13.4 120 2.08 8 6.00 94 11.0 143 1.73 6 8.52 58 13.0 63 5.07 32 18.2 138 25.0 148 5.10 67 10.6 130 26.9 146 3.74 56 8.96 68 38.4 84 2.45 21 14.9 158 23.5 146 2.16 4
OAR-Flow [123]83.5 5.20 77 10.7 88 2.08 97 7.44 102 13.0 105 2.16 88 5.74 85 10.0 68 1.73 6 8.35 33 13.0 63 5.10 61 18.1 108 24.9 140 5.23 171 10.2 96 24.7 72 3.74 56 9.54 136 39.4 110 2.45 21 14.4 112 22.7 105 2.16 4
RFlow [88]83.8 5.07 43 10.2 65 2.08 97 8.58 149 14.7 163 2.08 8 6.00 94 10.3 99 1.73 6 8.91 121 14.4 111 5.20 98 17.7 55 23.9 58 5.10 67 9.95 71 25.4 95 3.70 28 9.13 100 40.4 121 2.45 21 14.3 99 22.6 98 2.31 144
TC/T-Flow [77]84.5 5.45 149 11.5 138 2.00 18 7.42 98 13.0 105 2.08 8 5.69 37 9.76 60 1.73 6 8.60 65 13.7 87 5.16 86 18.3 149 24.9 140 5.20 112 10.1 85 24.9 79 3.74 56 9.75 148 42.6 154 2.45 21 14.5 125 22.6 98 2.16 4
TF+OM [98]85.6 5.00 35 10.2 65 2.08 97 6.93 59 11.7 73 2.16 88 5.69 37 10.5 123 1.73 6 8.81 103 14.6 120 5.20 98 18.0 93 24.4 90 5.20 112 9.95 71 26.1 119 3.79 130 9.09 94 41.0 128 2.45 21 14.1 70 21.8 60 2.38 163
EpicFlow [100]85.7 5.07 43 11.0 107 2.00 18 7.39 92 12.9 100 2.08 8 5.80 89 10.3 99 1.73 6 8.85 115 15.5 148 5.20 98 18.1 108 24.8 127 5.20 112 10.2 96 25.1 86 3.74 56 9.33 118 40.4 121 2.45 21 14.5 125 24.1 159 2.16 4
DMF_ROB [135]87.1 5.20 77 10.8 97 2.08 97 7.85 124 13.4 120 2.08 8 6.35 153 11.6 159 2.00 126 9.02 131 14.5 118 5.16 86 17.8 67 24.4 90 5.20 112 9.83 56 24.3 62 3.74 56 9.04 87 38.3 79 2.45 21 14.1 70 22.4 91 2.16 4
TC-Flow [46]87.2 5.07 43 10.8 97 2.00 18 7.39 92 13.2 116 2.16 88 6.00 94 10.3 99 1.73 6 8.66 68 13.7 87 5.23 134 18.2 138 25.0 148 5.20 112 10.2 96 24.5 67 3.79 130 9.04 87 38.1 77 2.45 21 14.5 125 23.5 146 2.16 4
S2D-Matching [83]87.2 5.35 117 11.2 126 2.00 18 7.75 118 13.5 124 2.08 8 5.69 37 10.0 68 1.73 6 8.37 40 12.6 51 5.20 98 18.3 149 25.2 159 5.07 43 11.0 161 27.7 168 3.79 130 9.09 94 40.3 119 2.45 21 14.4 112 23.0 123 2.16 4
F-TV-L1 [15]88.7 5.35 117 10.3 71 2.16 136 8.83 156 14.6 162 2.16 88 6.00 94 10.3 99 2.00 126 8.76 88 13.2 76 5.26 153 17.6 41 23.8 49 5.03 39 9.57 48 23.2 40 3.79 130 9.18 104 37.6 62 2.45 21 13.8 42 21.2 43 2.31 144
Fusion [6]89.3 5.20 77 10.4 74 2.00 18 7.14 76 11.8 75 2.08 8 5.74 85 9.68 52 1.73 6 9.33 145 14.2 104 5.20 98 18.3 149 24.7 112 5.07 43 11.6 180 28.1 173 3.70 28 9.63 142 41.4 136 2.45 21 15.3 176 24.2 162 2.16 4
LFNet_ROB [145]91.6 5.35 117 13.4 173 2.00 18 7.72 115 12.9 100 2.16 88 6.00 94 11.3 151 1.73 6 8.98 129 15.9 157 5.07 32 18.1 108 24.8 127 5.10 67 11.0 161 28.1 173 3.74 56 9.09 94 37.6 62 2.45 21 14.0 54 22.4 91 2.16 4
Classic++ [32]92.7 5.20 77 10.3 71 2.08 97 7.94 129 13.8 135 2.08 8 6.00 94 10.1 91 1.73 6 8.89 118 13.7 87 5.23 134 18.0 93 24.5 98 5.10 67 10.3 104 25.8 109 3.87 161 9.13 100 40.1 115 2.45 21 14.2 87 22.2 79 2.31 144
Sparse Occlusion [54]93.2 5.26 102 10.5 80 2.08 97 8.04 132 14.4 153 2.08 8 6.00 94 10.0 68 1.73 6 8.83 109 13.7 87 5.20 98 18.1 108 24.7 112 5.20 112 11.0 161 26.5 132 3.74 56 9.42 124 42.0 149 2.45 21 14.4 112 22.8 111 2.16 4
PMF [73]93.2 5.20 77 11.4 133 2.00 18 7.35 88 12.4 87 2.08 8 6.00 94 12.0 168 1.73 6 8.76 88 14.4 111 5.07 32 18.4 160 25.0 148 5.10 67 10.2 96 25.8 109 3.87 161 9.04 87 41.3 134 2.45 21 15.2 172 24.5 167 2.16 4
FESL [72]93.2 5.42 139 11.0 107 2.00 18 7.05 70 11.8 75 2.08 8 5.69 37 10.7 125 1.73 6 8.81 103 13.5 83 5.20 98 18.4 160 25.1 154 5.20 112 11.0 161 27.0 149 3.74 56 9.06 92 42.9 159 2.45 21 14.8 150 23.7 150 2.16 4
AggregFlow [95]93.3 5.45 149 13.8 177 2.08 97 7.44 102 13.1 111 2.16 88 5.69 37 9.95 66 1.73 6 9.15 139 16.1 159 5.10 61 18.0 93 24.5 98 5.20 112 9.90 65 24.6 71 3.83 151 8.98 74 40.7 124 2.45 21 14.4 112 23.0 123 2.16 4
Classic+CPF [82]93.7 5.35 117 11.3 131 2.00 18 7.07 75 12.1 82 2.08 8 5.69 37 10.5 123 1.73 6 8.43 50 12.7 56 5.07 32 18.7 180 25.7 181 5.20 112 11.2 171 28.7 180 3.74 56 9.42 124 42.9 159 2.45 21 15.1 163 24.2 162 2.16 4
PBOFVI [189]93.8 5.60 164 12.4 157 2.00 18 8.29 140 14.8 170 2.08 8 6.00 94 10.3 99 1.73 6 8.76 88 14.3 106 5.20 98 18.1 108 24.8 127 5.20 112 10.1 85 25.4 95 3.74 56 9.70 147 41.5 139 2.45 21 14.3 99 22.8 111 2.16 4
Modified CLG [34]94.3 5.07 43 9.49 40 2.16 136 9.42 174 14.2 149 2.65 175 6.00 94 11.5 157 2.00 126 9.15 139 14.3 106 5.10 61 17.7 55 23.9 58 5.10 67 10.1 85 24.7 72 3.74 56 9.31 117 37.5 58 2.45 21 14.1 70 21.8 60 2.31 144
FF++_ROB [141]94.9 5.07 43 11.5 138 2.00 18 7.16 80 12.2 84 2.08 8 6.00 94 10.3 99 1.73 6 8.96 123 16.4 163 5.20 98 18.6 174 25.7 181 5.20 112 10.6 130 26.8 142 3.92 176 9.00 77 39.1 101 2.45 21 14.2 87 22.9 119 2.16 4
TCOF [69]96.5 5.35 117 10.7 88 2.00 18 9.27 168 15.4 179 2.16 88 5.69 37 10.2 95 1.73 6 8.74 84 13.1 71 5.23 134 17.7 55 23.8 49 5.07 43 10.7 142 26.6 136 3.70 28 10.0 160 44.7 176 2.45 21 14.6 139 22.9 119 2.38 163
OFH [38]97.1 5.35 117 11.0 107 2.08 97 8.06 135 13.7 133 2.08 8 6.00 94 11.6 159 1.73 6 8.58 62 13.9 99 5.07 32 18.2 138 24.9 140 5.16 102 10.3 104 25.1 86 3.74 56 9.88 155 42.7 156 2.45 21 14.8 150 24.7 169 2.16 4
MCPFlow_RVC [197]97.3 5.74 171 15.4 184 2.00 18 7.00 68 11.6 63 2.16 88 6.00 94 10.3 99 1.73 6 8.87 117 14.7 124 5.20 98 18.1 108 24.5 98 5.10 67 11.2 171 29.1 183 3.74 56 8.91 65 36.0 37 2.45 21 23.5 198 40.0 198 2.16 4
SRR-TVOF-NL [89]97.8 5.45 149 12.1 154 2.08 97 7.77 120 13.5 124 2.16 88 6.00 94 10.3 99 1.73 6 9.26 143 14.7 124 5.07 32 18.1 108 24.6 110 5.10 67 10.4 112 26.6 136 3.70 28 9.42 124 38.5 89 2.45 21 15.1 163 23.9 156 2.16 4
SVFilterOh [109]97.9 5.20 77 10.6 85 2.00 18 6.73 41 11.0 41 2.08 8 6.00 94 10.0 68 1.73 6 8.76 88 13.8 94 5.26 153 18.4 160 25.3 164 5.26 183 10.6 130 28.0 171 3.74 56 8.45 27 39.2 105 2.52 154 14.7 144 23.3 139 2.31 144
C-RAFT_RVC [181]98.3 5.94 179 15.4 184 2.16 136 7.53 107 12.7 94 2.16 88 6.00 94 11.3 151 1.73 6 9.09 134 15.6 150 5.20 98 17.8 67 24.0 61 5.07 43 10.5 117 26.4 129 3.74 56 9.18 104 37.5 58 2.45 21 14.5 125 23.8 153 2.16 4
FlowNetS+ft+v [110]98.5 5.26 102 10.1 59 2.16 136 9.11 164 14.5 157 2.45 161 6.00 94 10.3 99 2.00 126 8.96 123 13.5 83 5.26 153 17.8 67 24.1 72 5.23 171 9.76 53 23.9 51 3.74 56 9.38 122 41.6 140 2.45 21 14.1 70 22.2 79 2.16 4
Efficient-NL [60]98.8 5.35 117 10.7 88 2.00 18 7.42 98 13.0 105 2.08 8 6.35 153 10.7 125 2.00 126 8.81 103 13.4 80 5.10 61 18.1 108 24.7 112 5.10 67 11.2 171 27.6 164 3.70 28 9.47 129 43.6 169 2.45 21 15.1 163 23.8 153 2.16 4
EPPM w/o HM [86]99.3 5.23 100 12.6 162 2.00 18 7.39 92 13.0 105 2.08 8 6.35 153 14.0 189 1.91 121 8.83 109 15.3 144 5.10 61 18.0 93 24.5 98 5.10 67 10.5 117 27.6 164 3.74 56 9.11 98 41.9 145 2.45 21 14.5 125 23.2 133 2.16 4
BlockOverlap [61]99.8 5.20 77 9.29 35 2.16 136 8.74 153 14.1 144 2.65 175 6.00 94 9.35 44 2.00 126 8.52 58 11.9 29 5.60 186 17.8 67 24.0 61 5.32 192 9.83 56 25.0 83 4.04 181 8.83 58 37.1 52 2.52 154 13.5 36 20.6 36 2.38 163
3DFlow [133]100.0 5.42 139 11.5 138 2.00 18 7.14 76 12.3 85 2.08 8 6.22 152 10.0 68 1.73 6 8.66 68 13.6 85 5.23 134 17.9 82 24.5 98 5.20 112 12.3 194 29.0 182 3.79 130 10.6 175 41.7 142 2.45 21 14.8 150 23.2 133 2.16 4
PWC-Net_RVC [143]100.1 5.35 117 13.8 177 2.00 18 7.55 111 13.3 118 2.08 8 6.00 94 11.3 151 1.73 6 8.76 88 15.7 152 5.07 32 18.6 174 25.9 186 5.20 112 10.5 117 26.9 146 3.83 151 9.00 77 38.6 93 2.45 21 14.3 99 23.7 150 2.16 4
CRTflow [81]100.6 5.29 110 10.5 80 2.16 136 8.43 145 14.5 157 2.16 88 6.35 153 11.1 150 2.00 126 8.64 67 13.0 63 5.29 163 18.0 93 24.5 98 5.20 112 9.68 51 23.8 49 3.74 56 9.00 77 40.9 126 2.45 21 14.1 70 22.2 79 2.31 144
MLDP_OF [87]101.4 5.32 114 11.1 119 2.00 18 7.55 111 13.6 130 2.08 8 5.69 37 10.0 68 1.73 6 8.76 88 13.1 71 5.26 153 18.0 93 24.5 98 5.20 112 11.0 161 26.9 146 4.08 186 9.26 110 38.2 78 2.52 154 14.4 112 22.6 98 2.38 163
Steered-L1 [116]102.5 5.07 43 9.81 46 2.00 18 7.35 88 12.8 99 2.16 88 6.35 153 10.3 99 2.00 126 9.31 144 14.3 106 5.35 172 18.2 138 24.7 112 5.07 43 10.2 96 25.7 106 3.79 130 9.33 118 40.4 121 2.45 21 14.6 139 22.8 111 2.31 144
2D-CLG [1]102.6 5.16 75 10.0 55 2.16 136 9.90 180 14.2 149 2.83 185 6.35 153 10.7 125 2.00 126 10.0 170 15.2 139 5.10 61 17.7 55 24.1 72 5.20 112 10.1 85 24.1 56 3.74 56 9.81 149 43.6 169 2.45 21 14.1 70 21.8 60 2.16 4
IAOF [50]103.4 5.60 164 11.0 107 2.16 136 12.0 196 16.9 197 2.52 169 5.69 37 11.0 143 2.00 126 9.76 165 14.3 106 5.20 98 17.7 55 24.0 61 5.07 43 10.0 83 25.2 90 3.74 56 9.47 129 41.4 136 2.45 21 14.2 87 22.1 72 2.16 4
Occlusion-TV-L1 [63]104.2 5.20 77 10.2 65 2.08 97 8.89 158 15.3 177 2.16 88 6.00 94 10.3 99 2.00 126 9.15 139 15.4 145 5.26 153 17.6 41 23.7 45 5.10 67 9.98 79 25.5 98 3.87 161 10.3 169 39.3 107 2.52 154 14.1 70 22.3 87 2.16 4
Complementary OF [21]104.6 5.20 77 12.0 151 2.00 18 7.19 82 12.9 100 2.08 8 6.68 173 10.8 138 2.00 126 8.76 88 14.6 120 5.16 86 18.2 138 25.2 159 5.10 67 10.3 104 25.9 113 3.74 56 9.97 158 42.6 154 2.45 21 15.6 182 28.0 187 2.16 4
CostFilter [40]106.6 5.32 114 13.2 171 2.00 18 7.33 84 12.3 85 2.08 8 6.06 144 13.5 187 1.73 6 8.96 123 16.1 159 5.07 32 18.6 174 25.6 180 5.16 102 9.98 79 24.8 77 4.04 181 9.20 107 43.5 168 2.45 21 15.1 163 24.9 172 2.16 4
Adaptive [20]107.0 5.32 114 10.3 71 2.16 136 9.29 171 15.4 179 2.16 88 6.00 94 10.7 125 1.73 6 8.81 103 13.8 94 5.20 98 17.9 82 24.3 83 5.07 43 10.4 112 26.0 115 3.79 130 9.83 150 44.6 174 2.45 21 14.5 125 22.8 111 2.31 144
Ad-TV-NDC [36]108.0 5.66 168 9.88 51 2.52 190 10.1 184 15.1 173 2.71 178 6.00 94 10.7 125 1.73 6 9.49 158 14.2 104 5.35 172 17.7 55 24.0 61 5.20 112 9.56 46 24.0 52 3.87 161 9.56 137 38.6 93 2.45 21 13.9 46 21.2 43 2.38 163
BriefMatch [122]109.5 5.29 110 11.4 133 2.08 97 7.44 102 12.7 94 2.16 88 6.38 171 9.93 65 2.00 126 9.83 167 14.9 129 5.83 193 18.0 93 24.4 90 5.20 112 10.5 117 27.3 158 4.32 191 9.04 87 37.9 71 2.45 21 14.3 99 22.8 111 2.16 4
HBM-GC [103]109.7 5.35 117 10.6 85 2.16 136 7.42 98 13.4 120 2.16 88 5.69 37 9.00 35 1.73 6 8.74 84 13.2 76 5.26 153 18.6 174 25.5 177 5.26 183 11.8 187 31.5 194 3.83 151 8.83 58 41.1 130 2.45 21 14.3 99 22.2 79 2.31 144
Black & Anandan [4]109.8 5.45 149 10.1 59 2.16 136 10.2 187 15.3 177 2.45 161 6.68 173 11.3 151 2.00 126 10.2 172 15.6 150 5.20 98 17.8 67 24.0 61 5.16 102 9.83 56 24.7 72 3.74 56 10.2 165 41.9 145 2.45 21 14.2 87 21.8 60 2.16 4
LiteFlowNet [138]110.3 5.45 149 14.5 181 2.00 18 7.42 98 12.7 94 2.08 8 5.69 37 13.0 181 1.73 6 9.71 164 23.2 193 5.29 163 18.4 160 25.4 171 5.20 112 10.8 150 27.1 150 3.70 28 10.2 165 43.0 163 2.45 21 14.3 99 23.2 133 2.16 4
CNN-flow-warp+ref [115]110.6 5.00 35 9.59 42 2.16 136 8.35 143 13.6 130 2.16 88 6.35 153 11.8 167 2.00 126 10.6 178 15.4 145 5.48 183 17.8 67 24.3 83 5.23 171 9.95 71 24.3 62 3.83 151 9.83 150 44.6 174 2.45 21 14.2 87 22.3 87 2.16 4
LSM_FLOW_RVC [182]113.0 5.74 171 16.9 189 2.08 97 8.12 136 14.0 142 2.16 88 6.00 94 13.0 181 1.73 6 9.38 148 18.9 178 5.16 86 18.2 138 25.1 154 5.10 67 10.5 117 25.5 98 3.74 56 9.63 142 41.1 130 2.45 21 14.4 112 24.0 158 2.16 4
HBpMotionGpu [43]113.5 5.48 156 10.8 97 2.38 181 10.1 184 15.4 179 2.71 178 5.69 37 10.0 68 1.73 6 9.40 150 16.2 162 5.23 134 17.9 82 24.3 83 5.20 112 10.5 117 26.4 129 3.83 151 8.96 68 37.8 68 2.45 21 14.3 99 22.6 98 2.38 163
TriFlow [93]113.5 5.26 102 12.0 151 2.16 136 8.39 144 14.4 153 2.38 146 6.00 94 11.0 143 1.73 6 9.02 131 15.4 145 5.10 61 18.5 168 25.4 171 5.20 112 10.6 130 27.3 158 3.74 56 9.26 110 39.7 111 2.45 21 14.6 139 23.1 131 2.16 4
TVL1_RVC [175]113.8 5.42 139 9.88 51 2.38 181 10.9 190 15.8 192 2.71 178 6.00 94 10.7 125 2.00 126 9.83 167 14.9 129 5.20 98 17.8 67 24.1 72 5.20 112 10.1 85 25.9 113 3.83 151 9.85 152 44.0 171 2.45 21 14.0 54 21.8 60 2.16 4
CVENG22+RIC [199]113.9 5.26 102 11.0 107 2.08 97 7.79 123 13.5 124 2.16 88 6.00 94 11.0 143 1.73 6 9.33 145 17.2 167 5.23 134 18.1 108 24.8 127 5.23 171 10.5 117 26.4 129 3.74 56 9.85 152 42.7 156 2.45 21 15.4 179 27.2 183 2.16 4
CompactFlow_ROB [155]115.2 5.48 156 15.2 183 2.08 97 7.75 118 13.2 116 2.38 146 6.19 151 13.3 185 1.73 6 9.57 161 22.0 192 5.23 134 18.0 93 24.5 98 5.10 67 10.6 130 27.2 154 3.70 28 9.66 145 40.9 126 2.45 21 14.4 112 23.4 143 2.16 4
Nguyen [33]115.8 5.42 139 10.0 55 2.38 181 10.9 190 15.1 173 2.65 175 6.00 94 12.0 168 2.00 126 10.4 177 16.1 159 5.20 98 17.8 67 24.1 72 5.07 43 9.98 79 25.3 92 3.70 28 10.9 181 46.9 183 2.52 154 14.1 70 22.1 72 2.16 4
AdaConv-v1 [124]115.9 6.24 186 14.4 180 2.38 181 9.02 161 12.7 94 3.11 191 7.00 183 11.0 143 2.38 190 13.1 191 18.8 177 5.83 193 16.8 31 22.5 31 4.83 31 8.79 35 22.0 34 3.70 28 8.91 65 36.6 44 2.58 179 13.3 35 20.2 35 2.38 163
FlowNet2 [120]119.5 6.45 191 19.1 195 2.16 136 7.85 124 13.4 120 2.38 146 6.06 144 11.7 161 1.73 6 9.40 150 18.2 173 5.23 134 18.5 168 25.3 164 5.20 112 10.3 104 25.2 90 3.74 56 9.27 114 41.9 145 2.45 21 14.3 99 22.8 111 2.16 4
TV-L1-improved [17]120.2 5.10 65 10.2 65 2.08 97 9.20 167 15.4 179 2.16 88 6.35 153 10.3 99 2.00 126 8.85 115 13.8 94 5.23 134 18.0 93 24.4 90 5.10 67 10.6 130 26.5 132 3.79 130 9.93 157 46.9 183 2.52 154 14.3 99 22.7 105 2.38 163
ResPWCR_ROB [140]120.5 5.35 117 12.5 160 2.00 18 7.94 129 13.6 130 2.16 88 6.68 173 11.3 151 1.91 121 9.42 152 18.1 172 5.29 163 18.1 108 24.8 127 5.07 43 10.6 130 27.3 158 4.40 192 9.56 137 38.4 84 2.45 21 14.7 144 24.7 169 2.16 4
SimpleFlow [49]120.8 5.35 117 11.0 107 2.00 18 8.04 132 13.9 138 2.08 8 6.56 172 11.3 151 2.00 126 8.41 49 12.7 56 5.20 98 18.4 160 25.4 171 5.20 112 11.4 178 28.9 181 3.74 56 10.1 162 53.7 193 2.52 154 15.3 176 26.5 180 2.16 4
Bartels [41]122.4 5.35 117 11.4 133 2.16 136 7.72 115 14.0 142 2.38 146 6.00 94 10.3 99 2.00 126 9.11 135 15.0 134 5.69 188 17.6 41 23.6 40 5.45 196 10.7 142 27.2 154 4.55 195 8.96 68 36.4 41 2.65 191 14.1 70 22.1 72 2.38 163
GraphCuts [14]122.6 5.66 168 11.9 150 2.16 136 7.53 107 12.5 90 2.38 146 7.68 190 10.2 95 2.00 126 9.47 155 14.9 129 5.23 134 18.1 108 24.5 98 5.00 36 10.1 85 25.7 106 3.70 28 9.02 85 42.1 151 2.52 154 15.1 163 24.1 159 2.31 144
ContinualFlow_ROB [148]124.8 5.60 164 14.6 182 2.16 136 7.85 124 13.5 124 2.31 145 6.35 153 12.4 174 2.00 126 8.96 123 16.8 164 5.20 98 18.7 180 26.1 191 5.20 112 9.90 65 24.9 79 3.70 28 9.18 104 41.6 140 2.45 21 15.2 172 27.5 186 2.16 4
AugFNG_ROB [139]125.0 5.48 156 14.1 179 2.16 136 8.27 139 13.5 124 2.38 146 6.35 153 14.0 189 2.00 126 9.47 155 19.5 183 5.20 98 18.7 180 26.0 188 5.23 171 9.85 61 25.5 98 3.70 28 9.85 152 38.7 96 2.45 21 14.2 87 23.1 131 2.16 4
ROF-ND [105]125.2 5.74 171 10.4 74 2.00 18 8.04 132 14.1 144 2.16 88 6.06 144 10.7 125 1.73 6 10.6 178 19.9 187 5.26 153 18.1 108 24.8 127 5.20 112 11.7 183 28.6 178 3.74 56 11.1 183 41.0 128 2.52 154 15.3 176 25.3 175 2.16 4
Filter Flow [19]126.4 5.42 139 10.2 65 2.16 136 9.40 173 14.7 163 2.71 178 6.00 94 10.7 125 2.00 126 9.49 158 13.9 99 5.35 172 18.1 108 24.3 83 5.26 183 10.2 96 25.6 103 3.83 151 9.52 135 41.4 136 2.45 21 14.6 139 22.3 87 2.38 163
IIOF-NLDP [129]126.5 5.45 149 12.0 151 2.00 18 8.12 136 14.7 163 2.08 8 6.06 144 10.0 68 1.73 6 9.13 137 14.8 128 5.32 169 18.1 108 24.8 127 5.10 67 12.2 191 29.1 183 3.87 161 12.0 191 59.6 197 2.65 191 15.2 172 24.6 168 2.16 4
Shiralkar [42]126.8 5.48 156 12.7 165 2.08 97 9.06 163 14.7 163 2.08 8 6.00 94 12.8 179 2.00 126 10.7 180 19.7 184 5.20 98 18.1 108 24.8 127 5.00 36 10.8 150 26.1 119 3.87 161 10.8 180 47.5 187 2.45 21 14.9 158 25.8 178 2.16 4
EPMNet [131]127.3 6.45 191 19.7 197 2.16 136 7.85 124 13.1 111 2.38 146 6.06 144 11.7 161 1.73 6 10.1 171 24.0 195 5.23 134 18.5 168 25.3 164 5.20 112 10.7 142 27.6 164 3.70 28 9.27 114 41.9 145 2.45 21 14.5 125 23.8 153 2.16 4
Correlation Flow [76]128.1 5.42 139 11.7 146 2.00 18 8.58 149 15.4 179 2.08 8 5.69 37 9.80 61 1.73 6 8.89 118 14.7 124 5.32 169 18.1 108 24.8 127 5.32 192 12.3 194 30.3 189 3.83 151 10.5 173 48.8 189 2.52 154 14.8 150 23.7 150 2.31 144
TriangleFlow [30]128.4 5.60 164 11.6 144 2.16 136 8.50 148 14.4 153 2.08 8 6.35 153 10.7 125 2.00 126 9.42 152 15.8 154 5.23 134 18.0 93 24.5 98 5.00 36 11.1 170 27.2 154 3.74 56 10.4 170 47.2 186 2.52 154 15.6 182 26.7 181 2.16 4
Rannacher [23]129.6 5.26 102 10.8 97 2.16 136 9.27 168 15.5 186 2.16 88 6.35 153 10.9 141 2.00 126 8.76 88 14.4 111 5.23 134 17.9 82 24.4 90 5.20 112 10.5 117 26.7 139 3.79 130 9.90 156 45.9 180 2.52 154 14.4 112 23.5 146 2.38 163
IAOF2 [51]134.3 5.74 171 11.5 138 2.16 136 9.49 175 15.9 195 2.38 146 5.69 37 11.0 143 2.00 126 9.61 163 15.8 154 5.26 153 18.7 180 25.3 164 5.20 112 10.9 154 27.4 161 3.74 56 9.47 129 41.1 130 2.45 21 14.5 125 22.8 111 2.31 144
Horn & Schunck [3]134.8 5.48 156 10.4 74 2.16 136 10.5 189 15.4 179 2.52 169 6.68 173 12.0 168 2.00 126 11.5 186 17.6 171 5.23 134 17.9 82 24.0 61 5.20 112 9.93 69 24.1 56 3.79 130 11.1 183 42.9 159 2.52 154 14.5 125 22.2 79 2.38 163
OFRF [132]136.7 5.80 175 13.7 175 2.16 136 9.15 166 15.1 173 2.45 161 6.00 94 11.7 161 1.73 6 9.13 137 15.1 138 5.10 61 18.7 180 25.9 186 5.16 102 11.3 175 29.1 183 3.87 161 10.1 162 44.5 173 2.45 21 15.4 179 24.9 172 2.16 4
IRR-PWC_RVC [180]136.8 5.83 178 17.8 192 2.16 136 7.77 120 13.3 118 2.38 146 6.35 153 14.3 192 1.73 6 10.2 172 25.2 196 5.20 98 18.7 180 26.0 188 5.23 171 10.7 142 28.0 171 3.74 56 9.63 142 41.3 134 2.45 21 15.5 181 28.0 187 2.16 4
TI-DOFE [24]138.0 5.80 175 11.0 107 2.52 190 11.5 194 15.8 192 3.11 191 6.35 153 12.3 172 2.00 126 11.4 185 17.4 168 5.29 163 17.9 82 24.2 80 5.07 43 9.95 71 24.4 66 3.79 130 10.5 173 39.9 113 2.52 154 14.8 150 22.1 72 2.38 163
LocallyOriented [52]138.1 5.45 149 11.2 126 2.16 136 9.49 175 15.7 190 2.16 88 6.06 144 11.7 161 1.91 121 9.42 152 17.0 165 5.23 134 18.2 138 24.8 127 5.07 43 11.0 161 26.5 132 4.04 181 10.4 170 43.0 163 2.45 21 14.8 150 23.4 143 2.31 144
SegOF [10]139.8 5.10 65 11.4 133 2.16 136 8.29 140 13.9 138 2.38 146 7.00 183 12.1 171 2.00 126 9.81 166 21.0 188 5.20 98 18.2 138 25.1 154 5.20 112 10.9 154 26.1 119 3.79 130 10.4 170 48.4 188 2.58 179 14.7 144 25.1 174 2.16 4
SPSA-learn [13]140.3 5.29 110 10.4 74 2.16 136 9.04 162 14.1 144 2.45 161 6.68 173 11.7 161 2.00 126 10.3 176 15.8 154 5.10 61 18.4 160 25.3 164 5.20 112 10.5 117 26.8 142 3.74 56 12.3 194 58.4 195 2.71 197 17.6 193 35.0 196 2.16 4
StereoOF-V1MT [117]142.4 5.69 170 13.0 168 2.08 97 8.68 151 14.1 144 2.08 8 6.73 182 12.4 174 2.00 126 11.6 187 19.1 181 5.45 179 18.5 168 25.4 171 5.20 112 11.3 175 26.1 119 3.92 176 11.2 185 44.9 177 2.58 179 14.2 87 22.6 98 2.16 4
2bit-BM-tele [96]144.0 5.35 117 10.1 59 2.16 136 8.91 159 15.4 179 2.45 161 6.00 94 10.0 68 2.00 126 9.04 133 14.3 106 5.60 186 18.3 149 24.9 140 5.35 195 11.7 183 31.3 192 4.24 190 12.0 191 58.7 196 2.83 198 13.9 46 21.7 56 2.45 196
ACK-Prior [27]144.2 5.35 117 11.7 146 2.00 18 7.39 92 12.9 100 2.08 8 6.68 173 10.8 138 2.00 126 9.54 160 15.7 152 5.32 169 18.7 180 25.5 177 5.29 190 11.9 189 29.5 186 3.87 161 10.1 162 41.7 142 2.52 154 16.1 186 24.8 171 2.38 163
StereoFlow [44]144.4 8.68 198 20.4 198 2.45 187 10.3 188 16.1 196 2.71 178 6.00 94 10.7 125 1.73 6 8.81 103 13.7 87 5.16 86 22.6 196 31.6 196 5.26 183 14.3 198 35.7 198 3.79 130 9.13 100 38.8 97 2.45 21 15.6 182 25.3 175 2.31 144
Dynamic MRF [7]147.2 5.26 102 11.5 138 2.00 18 8.12 136 14.3 151 2.16 88 6.68 173 12.8 179 2.00 126 10.9 183 18.3 175 5.51 185 18.3 149 25.0 148 5.20 112 11.6 180 28.6 178 3.87 161 10.7 177 45.7 179 2.52 154 14.9 158 23.3 139 2.31 144
UnFlow [127]147.5 5.97 180 15.5 186 2.16 136 9.13 165 14.1 144 2.38 146 6.68 173 13.0 181 2.00 126 9.35 147 17.1 166 5.23 134 18.6 174 25.8 184 5.20 112 11.5 179 29.5 186 3.74 56 9.66 145 37.4 57 2.45 21 16.9 190 28.1 189 2.38 163
WRT [146]148.4 5.57 162 12.1 154 2.00 18 8.74 153 13.9 138 2.16 88 7.35 188 10.3 99 2.00 126 9.38 148 15.0 134 5.29 163 18.7 180 26.0 188 5.16 102 12.7 197 31.4 193 3.83 151 13.6 198 62.2 198 2.65 191 17.8 194 33.8 195 2.16 4
NL-TV-NCC [25]150.2 6.03 182 12.8 167 2.00 18 8.29 140 14.7 163 2.16 88 6.35 153 11.7 161 2.00 126 10.7 180 18.6 176 5.45 179 18.1 108 24.1 72 5.45 196 12.0 190 28.2 176 3.79 130 13.0 196 43.4 167 2.58 179 15.1 163 23.2 133 2.38 163
SILK [80]153.2 5.80 175 12.7 165 2.38 181 11.1 192 15.6 188 2.83 185 7.35 188 13.0 181 2.00 126 10.8 182 17.5 169 5.48 183 18.3 149 24.8 127 5.20 112 10.5 117 26.0 115 4.20 189 10.0 160 37.1 52 2.52 154 14.6 139 22.7 105 2.31 144
Learning Flow [11]153.8 5.57 162 11.1 119 2.16 136 9.27 168 15.1 173 2.16 88 7.00 183 13.3 185 2.00 126 10.2 172 15.2 139 5.45 179 18.5 168 25.1 154 5.32 192 10.7 142 26.2 124 3.87 161 10.6 175 40.8 125 2.52 154 15.1 163 23.3 139 2.38 163
H+S_RVC [176]156.3 6.00 181 13.0 168 2.16 136 9.49 175 13.5 124 2.71 178 7.68 190 13.7 188 2.38 190 13.7 193 17.5 169 5.35 172 18.3 149 24.7 112 5.20 112 10.9 154 25.5 98 3.79 130 11.6 188 41.2 133 2.58 179 14.8 150 22.9 119 2.38 163
WOLF_ROB [144]163.9 6.35 189 18.1 193 2.16 136 10.0 182 15.6 188 2.16 88 6.68 173 12.5 177 2.00 126 9.88 169 19.7 184 5.35 172 18.9 191 26.1 191 5.20 112 11.7 183 29.9 188 4.04 181 12.1 193 51.4 192 2.52 154 15.7 185 27.0 182 2.16 4
Adaptive flow [45]164.0 6.24 186 11.3 131 2.71 193 11.2 193 15.7 190 3.42 195 6.35 153 10.9 141 2.00 126 10.2 172 14.7 124 5.72 189 18.7 180 25.4 171 5.23 171 11.7 183 30.8 191 3.87 161 9.42 124 38.8 97 2.58 179 14.9 158 24.3 165 2.38 163
FOLKI [16]164.1 6.14 184 12.4 157 3.11 195 11.5 194 15.5 186 3.32 194 7.00 183 14.7 193 2.38 190 13.5 192 18.2 173 6.27 196 18.6 174 25.0 148 5.23 171 10.3 104 25.1 86 4.04 181 11.0 182 38.3 79 2.58 179 14.7 144 22.4 91 2.38 163
GroupFlow [9]165.8 6.56 193 19.6 196 2.16 136 9.38 172 14.7 163 2.52 169 7.68 190 16.8 196 2.00 126 11.1 184 23.5 194 5.29 163 20.7 195 29.3 195 5.23 171 12.4 196 32.8 196 3.87 161 11.3 187 49.6 191 2.45 21 16.8 189 30.4 192 2.16 4
Heeger++ [102]170.2 7.16 196 18.5 194 2.16 136 9.75 178 13.8 135 2.45 161 9.35 195 16.1 195 2.38 190 13.0 189 18.9 178 5.74 190 19.8 194 27.4 194 5.23 171 12.2 191 26.0 115 3.92 176 13.5 197 46.5 181 2.52 154 16.1 186 27.4 184 2.16 4
SLK [47]174.9 6.03 182 13.6 174 2.45 187 10.1 184 13.8 135 2.89 188 7.68 190 12.4 174 2.38 190 13.8 195 21.0 188 5.77 192 19.1 193 26.4 193 5.20 112 11.2 171 26.2 124 3.87 161 11.8 189 46.9 183 2.58 179 15.2 172 26.1 179 2.38 163
FFV1MT [104]177.5 6.40 190 16.8 188 2.16 136 9.87 179 13.9 138 2.89 188 9.35 195 18.7 197 2.52 196 13.0 189 18.9 178 5.74 190 18.8 189 25.7 181 5.26 183 10.9 154 26.0 115 3.92 176 12.8 195 46.5 181 2.52 154 16.2 188 27.4 184 2.45 196
HCIC-L [97]179.1 7.62 197 17.7 191 3.16 196 9.98 181 14.8 170 3.16 193 7.14 187 14.0 189 2.00 126 12.4 188 21.5 191 5.35 172 18.9 191 25.5 177 5.26 183 11.8 187 31.9 195 3.87 161 9.47 129 43.2 166 2.58 179 18.7 196 30.1 191 2.38 163
PGAM+LK [55]179.5 6.56 193 16.0 187 2.71 193 10.0 182 14.7 163 3.00 190 7.75 194 15.7 194 2.38 190 13.7 193 21.1 190 6.27 196 18.8 189 25.8 184 5.26 183 11.6 180 27.2 154 4.08 186 10.7 177 40.3 119 2.58 179 15.1 163 24.4 166 2.38 163
Pyramid LK [2]181.0 6.24 186 13.7 175 3.16 196 12.7 197 15.8 192 3.79 197 11.8 197 12.3 172 3.00 197 25.5 198 41.4 197 7.14 198 22.9 197 33.6 197 5.20 112 10.7 142 25.4 95 3.92 176 11.2 185 49.2 190 2.65 191 19.6 197 37.8 197 2.38 163
Periodicity [79]195.5 6.81 195 17.5 190 3.27 198 15.3 198 16.9 197 4.24 198 13.7 198 22.7 198 4.36 198 18.0 197 41.4 197 6.16 195 23.9 198 34.4 198 5.60 198 12.2 191 34.5 197 4.51 193 11.8 189 55.6 194 2.65 191 17.9 195 29.7 190 2.71 198
AVG_FLOW_ROB [137]199.0 31.4 199 43.5 199 5.60 199 24.2 199 24.5 199 6.45 199 24.3 199 27.7 199 8.43 199 44.7 199 55.2 199 16.9 199 38.9 199 51.5 199 6.24 199 31.3 199 72.3 199 4.83 199 34.9 199 63.2 199 3.65 199 35.1 199 43.8 199 6.73 199
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 Tan Khoa Mai, Michele Gouiffes, and Samia Bouchafa. Optical flow refinement using iterative propagation under colour, proximity and flow reliability constraints. IET Image Processing 2020.
[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 Bo Yan, Weimin Tan, Chuming Lin, and Liquan Shen. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. IEEE Transactions on Broadcasting, 2020.
[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 Mengshun Hu, Jing Xiao, Liang Liao, Zheng Wang, Chia-Wen Lin, Mi Wang, and Shinichi Satoh. Capturing small, fast-moving objects: Frame interpolation via recurrent motion enhancement. IEEE TCSVT 2021.
[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] BMBC 0.77 2 color Anonymous. (Interpolation results only.) BMBC: Bilateral motion estimation with bilateral cost volume for video interpolation. ECCV 2020 submission 2095.
[172] GDCN 1.0 2 color Anonymous. (Interpolation results only.) Video interpolation via generalized deformable convolution. ECCV 2020 submission 4347.
[173] 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.
[174] 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.
[175] 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.
[176] 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.
[177] PRAFlow_RVC 0.34 2 color Zhexiong Wan, Yuxin Mao, and Yuchao Dai. Pyramid recurrent all-pairs flow. RVC 2020 submission.
[178] VCN_RVC 0.84 2 color Gengshan Yang and Deva Ramanan. Volumetric correspondence networks for optical flow. NeurIPS 2019. RVC 2020 submission.
[179] 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.
[180] 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.
[181] C-RAFT_RVC 0.60 2 color Henrique Morimitsu and Xiangyang Ji. Classification RAFT. RVC 2020 submission.
[182] 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.
[183] MV_VFI 0.23 2 color Zhenfang Wang, Yanjiang Wang, and Baodi Liu. (Interpolation results only.) Multi-view based video interpolation algorithm. ICASSP 2021 submission.
[184] DistillNet 0.12 2 color Anonymous. (Interpolation results only.) A teacher-student optical-flow distillation framework for video frame interpolation. CVPR 2021 submission 7534.
[185] SepConv++ 0.1 2 color Simon Niklaus, Long Mai, and Oliver Wang. (Interpolation results only.) Revisiting adaptive convolutions for video frame interpolation. WACV 2021.
[186] EAFI 0.18 2 color Anonymous. (Interpolation results only.) Error-aware spatial ensembles for video frame interpolation. ICCV 2021 submission 8020.
[187] UnDAF 0.04 2 color Anonymous. UnDAF: A general unsupervised domain adaptation framework for disparity, optical flow or scene flow estimation. CVPR 2021 submission 236.
[188] FLAVR 0.029 all color Anonymous. (Interpolation results only.) FLAVR frame interpolation. NeurIPS 2021 submission 1300.
[189] PBOFVI 150 2 color Zemin Cai, Jianhuang Lai, Xiaoxin Liao, and Xucong Chen. Physics-based optical flow under varying illumination. Submitted to IEEE TCSVT 2021.
[190] SoftsplatAug 0.17 2 color Anonymous. (Interpolation results only.) Transformation data augmentation for sports video frame interpolation. ICCV 2021 submission 3245.
* 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.