Optical flow evaluation results Statistics:     Average   SD   R0.5   R1.0   R2.0   A90   A95   A99  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
R1.0
normalized 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]4.3 3.70 4 4.58 2 5.11 6 3.40 2 6.14 2 4.18 2 2.66 4 4.34 4 4.18 4 18.0 3 14.0 3 35.6 5 20.2 3 16.8 3 33.1 5 20.1 4 9.81 1 27.5 6 5.45 9 9.26 3 9.08 16 4.65 2 8.49 2 5.61 9
EAFI [186]4.5 4.11 7 4.22 1 5.79 8 3.10 1 4.97 1 3.86 1 2.37 1 3.26 1 3.86 1 17.3 1 12.9 1 34.1 1 22.2 13 20.3 22 31.5 1 19.8 2 10.4 3 26.7 2 5.27 4 10.2 12 8.18 4 5.13 8 9.70 9 5.28 3
SoftSplat [169]5.9 5.14 13 5.80 8 7.17 15 4.15 4 7.88 5 4.78 3 2.48 2 3.73 2 3.96 2 17.6 2 13.6 2 34.8 2 21.9 10 19.0 14 33.3 7 20.1 4 10.1 2 27.4 4 5.48 11 9.91 9 8.71 9 4.72 3 8.83 3 5.34 5
DistillNet [184]6.8 4.83 10 5.67 6 6.70 13 3.99 3 6.94 3 5.09 4 2.80 5 4.37 6 4.36 5 18.0 3 14.0 3 35.1 4 20.9 5 18.0 7 32.5 4 20.8 10 12.1 14 27.9 9 5.39 7 10.0 10 8.13 3 5.47 13 10.6 13 5.25 2
IDIAL [192]9.0 4.46 9 6.20 10 5.87 9 5.54 8 9.93 9 5.76 7 3.84 7 5.54 8 5.43 14 19.2 9 15.5 10 36.0 6 21.0 6 17.9 5 33.5 8 20.6 8 11.5 10 27.7 8 5.62 12 10.3 14 8.56 7 5.44 12 10.4 12 5.57 8
IFRNet [193]10.8 5.35 16 5.60 4 7.55 17 4.21 5 7.23 4 5.47 6 2.60 3 3.77 3 4.15 3 19.0 7 14.6 7 38.0 17 22.8 17 19.5 17 37.1 19 21.8 19 11.6 11 29.8 19 5.36 6 9.78 7 8.97 13 5.34 10 9.92 11 6.07 17
SepConv++ [185]18.3 6.74 27 8.41 23 9.06 119 5.55 9 9.95 10 6.90 100 4.36 12 6.59 15 5.22 10 20.1 17 16.8 19 37.3 13 21.6 8 18.2 8 34.6 11 19.8 2 10.6 4 26.8 3 5.26 3 9.59 5 8.57 8 4.83 4 9.15 5 5.34 5
STSR [170]18.4 5.32 15 6.98 15 7.21 16 4.41 6 8.12 6 5.14 5 4.37 13 6.89 18 5.31 11 19.6 13 15.5 10 38.4 18 26.1 28 23.4 28 37.9 22 23.3 24 14.1 26 31.1 23 6.31 23 13.3 32 9.60 17 6.57 25 12.8 30 6.26 18
DAI [168]19.2 6.26 19 5.64 5 9.04 118 5.89 11 10.2 12 6.77 92 2.92 6 4.35 5 4.68 6 18.7 5 14.4 5 37.7 15 24.0 23 21.4 26 33.9 9 21.2 11 12.0 13 28.4 11 5.41 8 10.8 19 8.33 5 5.89 14 11.6 19 5.33 4
STAR-Net [164]19.5 6.45 20 6.77 12 9.14 125 6.55 44 10.8 23 7.59 126 4.45 14 5.19 7 5.60 28 18.9 6 15.2 9 35.0 3 19.7 1 16.5 2 31.8 2 20.5 7 11.8 12 27.4 4 5.10 2 9.29 4 7.77 1 5.05 6 9.62 8 5.10 1
MV_VFI [183]22.7 6.51 21 8.23 21 8.77 88 6.20 21 11.0 26 7.82 131 3.84 7 6.31 12 5.13 7 19.4 11 16.5 14 36.6 8 22.2 13 18.7 11 35.5 14 21.7 16 12.5 17 29.3 17 5.64 13 10.8 19 8.91 12 5.94 16 11.6 19 5.65 11
TC-GAN [166]23.6 6.54 22 8.26 22 8.83 103 6.21 22 11.1 28 7.78 130 3.84 7 6.25 11 5.16 8 19.4 11 16.5 14 36.5 7 22.1 11 18.7 11 35.3 13 21.5 15 12.4 16 28.9 15 5.70 15 10.9 21 9.00 14 5.95 17 11.7 21 5.68 13
DAIN [152]28.2 6.97 47 8.45 24 9.50 146 6.38 30 11.3 31 7.99 136 3.89 10 6.48 14 5.20 9 19.3 10 16.5 14 36.6 8 22.4 15 18.9 13 35.9 17 21.7 16 12.5 17 29.2 16 5.66 14 10.9 21 9.00 14 5.98 18 11.7 21 5.81 15
AdaCoF [165]31.7 7.91 147 9.01 28 10.6 172 6.32 27 10.6 20 7.50 125 5.57 19 7.05 19 5.49 18 20.5 19 16.8 19 37.0 12 25.1 26 21.1 24 39.4 25 20.3 6 10.7 5 27.6 7 5.32 5 9.82 8 8.53 6 5.05 6 9.47 7 5.62 10
MEMC-Net+ [160]32.8 7.02 54 7.74 18 9.49 145 6.69 54 10.8 23 8.04 137 4.78 15 7.18 22 5.85 70 19.9 14 15.8 12 36.9 11 23.2 21 19.9 20 35.6 15 21.4 13 12.8 21 28.5 12 5.72 17 11.8 24 8.81 10 6.02 20 11.9 24 5.77 14
GDCN [172]32.8 5.00 12 7.91 20 6.20 10 8.17 124 13.5 90 7.76 127 4.25 11 6.70 16 5.84 65 21.5 48 17.1 22 37.6 14 22.8 17 19.0 14 37.6 21 22.8 22 13.4 24 30.6 22 5.90 21 10.5 18 9.88 18 5.90 15 11.3 16 6.46 20
BMBC [171]35.7 6.92 45 7.27 17 9.23 136 6.31 26 9.36 8 9.14 153 8.62 167 9.71 34 8.62 178 19.0 7 14.5 6 36.6 8 21.6 8 18.4 10 33.2 6 20.6 8 10.8 7 28.1 10 5.07 1 9.03 2 8.11 2 4.85 5 9.19 6 5.40 7
EDSC [173]36.7 4.84 11 7.00 16 6.26 11 5.80 10 10.3 14 7.30 117 4.96 16 6.43 13 7.36 164 20.2 18 16.8 19 37.8 16 22.7 16 19.3 16 36.4 18 21.7 16 12.1 14 29.3 17 5.75 18 9.63 6 10.6 133 6.00 19 10.6 13 7.93 169
FGME [158]37.3 2.91 1 4.69 3 3.52 1 6.52 42 9.99 11 8.75 144 5.74 22 6.11 10 8.51 176 20.0 15 14.9 8 40.0 24 19.9 2 16.3 1 34.6 11 23.2 23 11.1 8 31.9 24 5.70 15 8.24 1 11.0 160 5.35 11 8.89 4 8.58 179
MDP-Flow2 [68]41.0 6.71 24 9.78 34 8.39 31 6.36 29 11.5 39 6.23 21 7.12 30 9.73 35 5.42 13 21.2 28 18.8 41 41.2 38 30.1 39 26.5 36 45.6 90 27.7 54 19.5 63 36.0 53 6.48 30 13.8 41 10.3 26 8.19 66 16.4 57 7.11 67
PMMST [112]44.1 6.84 37 9.80 35 8.50 43 6.74 55 11.7 44 6.36 45 7.10 29 9.45 30 5.41 12 21.1 23 18.6 34 41.1 29 30.2 44 26.5 36 45.7 108 27.3 32 18.1 37 36.0 53 6.51 36 13.9 47 10.3 26 8.22 72 16.5 67 7.15 84
CoT-AMFlow [174]44.6 6.73 26 9.84 36 8.38 30 6.40 31 11.6 41 6.29 32 7.23 37 10.2 45 5.46 16 21.1 23 18.7 37 41.1 29 30.3 54 26.6 42 45.6 90 27.7 54 19.7 75 36.1 68 6.50 34 13.8 41 10.2 19 8.19 66 16.5 67 7.14 78
NNF-Local [75]45.0 6.74 27 10.1 39 8.30 22 5.97 13 10.3 14 6.14 11 7.09 28 9.63 33 5.44 15 21.7 68 20.5 109 41.2 38 30.3 54 26.6 42 45.4 61 27.9 78 20.6 111 36.0 53 6.51 36 13.8 41 10.3 26 8.04 50 16.1 45 7.10 65
FeFlow [167]45.0 4.28 8 6.79 13 5.43 7 7.25 85 11.8 48 9.22 156 5.71 20 7.22 23 9.27 185 20.5 19 16.5 14 38.9 21 21.0 6 17.9 5 34.0 10 22.3 20 12.5 17 30.1 20 6.31 23 10.3 14 10.9 155 6.32 23 11.4 17 8.05 171
DSepConv [162]45.6 6.14 18 8.45 24 7.88 18 7.10 76 11.8 48 8.91 149 5.82 24 7.06 20 7.53 168 21.5 48 18.0 26 38.6 19 23.1 20 19.5 17 38.0 23 22.3 20 12.8 21 30.1 20 5.79 20 10.2 12 10.5 98 6.42 24 11.9 24 7.63 158
PH-Flow [99]46.2 7.05 60 10.9 55 8.50 43 6.10 16 10.6 20 6.14 11 7.18 33 9.83 37 5.55 25 21.1 23 18.5 32 41.1 29 30.1 39 26.6 42 45.2 48 27.9 78 21.7 146 35.7 41 6.60 53 14.3 65 10.3 26 8.11 56 16.3 53 7.14 78
CombBMOF [111]47.2 6.93 46 9.87 38 8.43 36 6.33 28 11.4 34 6.22 20 7.60 82 10.3 47 6.25 120 21.5 48 19.4 58 41.2 38 30.2 44 26.6 42 45.3 55 27.7 54 19.2 54 36.1 68 6.57 45 14.1 53 10.3 26 7.67 32 15.4 37 6.82 28
ADC [161]48.6 8.06 152 9.07 30 10.5 169 7.46 95 11.4 34 10.1 170 6.38 25 8.35 25 6.04 102 22.0 102 18.2 27 38.7 20 24.7 24 21.2 25 38.2 24 21.3 12 12.6 20 28.5 12 5.46 10 10.3 14 8.81 10 6.26 22 12.1 26 6.00 16
NN-field [71]50.8 6.88 39 10.8 50 8.48 40 5.99 14 10.3 14 6.13 10 7.65 91 9.54 31 5.81 59 21.9 88 21.0 134 41.4 57 30.2 44 26.6 42 45.4 61 27.8 67 20.0 84 36.0 53 6.48 30 13.7 39 10.3 26 8.02 47 16.1 45 7.04 55
ProBoost-Net [191]54.5 3.26 3 5.79 7 3.86 3 7.23 83 12.0 53 7.87 134 5.78 23 7.06 20 8.58 177 21.3 34 17.1 22 42.2 133 24.7 24 20.7 23 41.3 27 25.7 27 13.9 25 35.0 28 6.36 25 11.0 23 11.8 182 6.61 27 11.5 18 9.07 187
GMFlow_RVC [196]54.6 6.88 39 10.9 55 8.53 52 6.17 20 11.1 28 6.31 35 7.16 32 9.82 36 5.48 17 21.3 34 19.4 58 41.5 61 30.7 123 27.1 90 45.8 128 27.8 67 20.6 111 35.8 44 6.49 33 13.6 35 10.5 98 7.94 42 16.0 42 6.84 30
MS_RAFT+_RVC [195]59.0 6.98 49 10.4 44 8.70 75 6.30 25 11.6 41 6.27 25 7.04 27 9.31 28 5.50 19 21.0 22 18.3 29 41.2 38 30.5 79 26.8 55 45.9 156 27.6 47 18.9 46 36.0 53 6.42 27 13.3 32 10.5 98 9.98 186 21.4 192 6.79 23
Layers++ [37]59.2 7.17 75 11.1 64 8.79 94 6.14 19 10.3 14 6.41 50 7.34 51 10.3 47 5.69 44 21.3 34 19.0 47 41.3 46 30.5 79 27.1 90 45.4 61 28.1 100 21.1 128 36.2 82 6.51 36 13.8 41 10.2 19 8.20 69 16.4 57 7.13 75
IROF++ [58]59.7 7.07 63 11.3 70 8.50 43 6.64 49 12.0 53 6.19 16 7.54 72 10.6 63 5.84 65 21.2 28 18.6 34 41.5 61 30.2 44 26.9 61 45.0 41 27.6 47 18.8 43 36.2 82 6.69 77 14.7 81 10.5 98 8.17 62 16.4 57 7.33 122
CtxSyn [134]60.4 3.84 5 6.67 11 4.59 4 5.06 7 9.01 7 6.57 71 5.42 17 6.73 17 8.44 174 20.9 21 16.7 18 42.3 137 28.9 33 24.9 33 45.0 41 27.5 39 15.3 30 37.0 152 7.55 173 13.2 30 12.1 186 7.09 29 12.4 27 9.27 188
MAF-net [163]60.7 3.10 2 6.12 9 3.64 2 6.51 41 11.4 34 7.43 121 5.54 18 8.03 24 8.78 179 22.2 119 18.2 27 42.5 150 27.0 29 23.6 29 41.4 29 25.7 27 15.1 29 34.5 26 6.80 103 12.3 26 12.0 184 7.11 30 12.5 28 9.46 190
VCN_RVC [178]60.8 7.09 64 12.0 105 8.52 50 6.46 35 11.8 48 6.27 25 7.68 97 12.5 130 5.77 56 21.7 68 20.3 95 41.9 111 30.4 64 26.9 61 45.2 48 27.3 32 19.6 67 35.5 32 6.58 47 14.2 59 10.4 58 7.87 40 16.0 42 6.80 25
MPRN [151]60.9 6.90 42 9.11 31 9.02 117 7.48 98 12.5 68 8.49 141 8.65 169 13.9 167 6.98 155 21.3 34 18.4 30 40.1 25 28.4 31 24.5 32 43.6 30 26.5 29 14.3 27 36.1 68 6.39 26 13.2 30 10.3 26 6.59 26 12.8 30 6.84 30
nLayers [57]61.2 7.15 73 10.4 44 8.81 99 6.44 34 11.4 34 6.42 51 7.23 37 9.30 27 5.65 36 21.4 42 19.1 50 41.5 61 30.7 123 27.4 136 45.6 90 28.0 89 20.8 117 36.2 82 6.54 43 13.6 35 10.3 26 8.07 51 16.3 53 6.91 36
RAFT-it+_RVC [198]62.0 6.68 23 10.5 47 8.23 19 6.08 15 10.9 25 6.17 14 7.23 37 10.3 47 5.52 20 21.4 42 19.6 66 41.3 46 30.5 79 26.9 61 45.8 128 31.0 188 21.4 138 40.2 190 6.50 34 13.6 35 10.6 133 7.84 36 15.9 40 6.80 25
FRUCnet [153]63.5 12.7 191 9.11 31 18.5 195 7.86 109 11.2 30 11.5 178 7.31 47 8.52 26 11.0 194 21.9 88 17.9 24 39.6 22 22.9 19 19.6 19 35.8 16 21.4 13 12.9 23 28.8 14 5.97 22 10.4 17 10.4 58 6.10 21 11.1 15 7.58 152
PRAFlow_RVC [177]65.1 6.83 34 10.1 39 8.40 32 6.48 37 11.7 44 6.44 55 7.20 36 10.1 41 5.53 21 21.6 56 19.7 72 41.8 96 30.5 79 26.7 50 45.9 156 27.8 67 19.5 63 36.3 97 6.52 42 13.9 47 10.4 58 8.65 130 17.5 132 7.14 78
ProbFlowFields [126]65.2 7.03 56 11.8 95 8.66 71 6.41 32 11.7 44 6.31 35 7.18 33 10.3 47 5.58 26 21.7 68 19.6 66 41.8 96 30.7 123 27.1 90 46.0 168 27.9 78 20.5 102 36.2 82 6.51 36 13.8 41 10.3 26 7.80 35 15.6 38 7.14 78
Sparse-NonSparse [56]65.4 7.09 64 11.3 70 8.57 55 6.53 43 11.8 48 6.21 18 7.40 60 10.5 59 5.64 32 21.5 48 19.0 47 41.7 87 30.4 64 27.0 76 45.4 61 28.3 116 21.5 142 36.4 110 6.66 67 14.4 68 10.3 26 8.23 74 16.6 72 7.09 62
2DHMM-SAS [90]66.2 7.27 91 12.0 105 8.59 59 7.82 108 14.2 105 6.36 45 7.25 40 10.5 59 5.74 50 21.4 42 18.7 37 41.4 57 30.3 54 26.9 61 45.2 48 27.9 78 20.3 93 36.0 53 6.64 64 14.4 68 10.3 26 8.41 95 17.0 92 7.08 59
RAFT-TF_RVC [179]66.5 6.79 32 10.8 50 8.23 19 6.26 23 11.5 39 6.27 25 7.26 41 10.3 47 5.67 40 21.5 48 19.9 78 41.5 61 30.6 101 26.9 61 45.8 128 32.4 193 20.4 97 42.1 193 6.48 30 13.7 39 10.4 58 8.27 78 17.0 92 6.78 22
AGIF+OF [84]66.7 7.11 68 11.3 70 8.46 37 6.68 53 12.2 58 6.27 25 7.38 56 10.1 41 5.71 48 21.2 28 18.6 34 41.1 29 30.8 138 27.6 161 45.4 61 28.3 116 22.2 165 36.0 53 6.67 69 14.0 50 10.3 26 8.34 86 17.0 92 6.91 36
NNF-EAC [101]66.7 7.35 103 11.1 64 8.79 94 6.92 68 12.5 68 6.29 32 7.52 71 10.1 41 5.76 53 21.8 78 19.5 64 42.8 160 30.2 44 26.6 42 45.4 61 27.5 39 18.9 46 36.0 53 6.58 47 14.2 59 10.4 58 8.32 83 16.8 79 7.19 94
RAFT-it [194]67.0 6.75 30 10.7 48 8.27 21 5.94 12 10.5 19 6.12 9 7.15 31 9.95 39 5.53 21 21.2 28 19.1 50 41.3 46 30.4 64 26.7 50 45.7 108 32.4 193 20.6 111 42.4 194 6.46 29 13.5 34 10.4 58 10.0 188 21.4 192 6.89 34
FMOF [92]67.7 7.36 105 12.0 105 8.73 83 6.42 33 11.3 31 6.30 34 7.63 87 10.4 54 6.02 100 21.8 78 19.9 78 41.2 38 30.5 79 27.0 76 45.4 61 28.0 89 20.5 102 36.1 68 6.51 36 13.8 41 10.2 19 8.30 81 16.7 77 7.12 69
FlowFields [108]67.8 7.02 54 11.5 80 8.54 53 6.66 52 12.5 68 6.44 55 7.45 64 11.5 98 5.64 32 21.9 88 20.5 109 41.8 96 30.6 101 27.0 76 45.5 77 27.7 54 20.2 88 36.0 53 6.59 50 14.3 65 10.4 58 8.00 46 16.2 50 7.08 59
FlowFields+ [128]68.6 6.99 50 11.4 77 8.47 39 6.61 48 12.3 60 6.48 59 7.42 62 11.5 98 5.67 40 21.7 68 20.3 95 41.6 74 30.7 123 27.2 107 45.6 90 27.8 67 20.3 93 36.1 68 6.61 55 14.4 68 10.4 58 7.99 45 16.2 50 7.03 53
S2F-IF [121]69.2 7.01 53 11.5 80 8.48 40 6.57 45 12.2 58 6.42 51 7.40 60 11.2 92 5.64 32 21.6 56 20.1 86 41.3 46 30.7 123 27.3 120 45.7 108 27.8 67 20.4 97 36.1 68 6.71 82 14.9 95 10.4 58 7.98 44 16.1 45 7.04 55
LME [70]70.4 6.72 25 9.86 37 8.36 26 6.97 72 12.4 64 7.40 120 7.51 69 11.8 107 5.70 47 21.3 34 19.2 54 41.3 46 31.0 168 27.6 161 46.6 181 27.8 67 20.5 102 36.0 53 6.45 28 13.6 35 10.2 19 8.08 53 16.3 53 7.12 69
LSM [39]71.7 7.17 75 11.8 95 8.58 57 6.64 49 12.1 57 6.17 14 7.49 67 10.9 80 5.69 44 21.6 56 19.6 66 41.6 74 30.5 79 27.1 90 45.4 61 28.3 116 21.6 144 36.3 97 6.68 75 14.6 74 10.2 19 8.35 90 16.9 89 7.03 53
CyclicGen [149]72.1 10.0 184 9.16 33 13.8 188 9.67 162 10.4 18 19.8 197 7.89 120 11.0 84 9.80 187 22.8 150 17.9 24 43.7 171 25.6 27 21.4 26 41.3 27 25.2 26 10.7 5 35.5 32 5.75 18 10.1 11 10.2 19 4.50 1 7.84 1 6.41 19
TV-L1-MCT [64]73.0 7.50 126 12.5 138 8.79 94 7.19 80 13.4 88 6.37 47 7.28 44 10.6 63 5.80 58 21.4 42 18.8 41 41.3 46 30.5 79 27.1 90 45.1 45 27.9 78 18.6 39 36.6 128 6.72 86 15.0 104 10.4 58 7.92 41 15.9 40 7.20 98
ComponentFusion [94]73.2 6.91 43 10.8 50 8.55 54 6.49 40 12.0 53 6.10 8 7.49 67 11.2 92 5.72 49 21.3 34 19.4 58 41.2 38 30.6 101 27.2 107 45.8 128 27.8 67 19.6 67 36.2 82 6.92 127 16.4 153 10.4 58 8.43 99 17.0 92 7.16 89
WLIF-Flow [91]73.5 6.99 50 11.0 61 8.48 40 6.76 56 12.4 64 6.39 48 7.38 56 10.3 47 5.68 43 21.4 42 18.8 41 41.9 111 30.4 64 26.9 61 45.9 156 28.8 155 21.9 154 36.9 148 6.56 44 13.9 47 10.3 26 8.34 86 16.8 79 7.15 84
OFRI [154]73.6 8.13 156 6.88 14 11.7 182 8.13 122 11.3 31 13.9 190 5.71 20 5.92 9 10.4 191 20.0 15 15.9 13 39.7 23 22.1 11 18.3 9 37.4 20 25.1 25 15.9 32 34.0 25 15.7 198 12.1 25 45.2 199 7.85 38 11.7 21 15.4 198
COFM [59]74.2 7.04 57 10.7 48 8.70 75 6.60 46 11.9 52 6.35 42 7.26 41 9.93 38 5.63 31 21.2 28 18.8 41 41.0 27 30.4 64 27.3 120 44.9 40 27.7 54 22.6 169 35.1 29 6.86 119 14.7 81 11.2 167 8.67 134 17.2 113 7.78 164
MDP-Flow [26]75.7 6.83 34 10.8 50 8.50 43 6.65 51 12.4 64 6.51 65 7.46 65 10.6 63 5.88 77 22.1 112 20.6 116 41.7 87 30.4 64 26.8 55 45.6 90 28.2 110 21.9 154 36.3 97 6.69 77 14.8 89 10.4 58 8.15 59 16.6 72 7.10 65
HAST [107]75.8 6.97 47 10.2 41 8.69 73 6.46 35 11.6 41 6.26 24 7.72 104 11.1 88 5.97 93 21.1 23 18.7 37 41.1 29 30.5 79 27.5 146 44.8 38 28.2 110 22.8 175 35.5 32 6.76 97 15.2 116 10.4 58 8.81 141 18.0 150 6.96 43
OFLAF [78]76.0 6.81 33 10.2 41 8.40 32 6.10 16 10.7 22 6.21 18 7.36 53 10.6 63 5.54 24 21.1 23 18.8 41 41.0 27 30.8 138 27.4 136 45.7 108 28.1 100 21.9 154 36.0 53 7.02 140 16.1 149 10.4 58 8.90 149 18.1 158 7.16 89
FLAVR [188]76.7 10.8 187 10.9 55 13.3 186 11.7 180 12.5 68 15.5 192 8.08 140 10.7 71 9.21 182 29.1 194 27.5 195 40.3 26 20.3 4 17.3 4 32.4 3 19.7 1 11.3 9 26.5 1 6.63 59 12.7 27 10.3 26 5.18 9 9.75 10 5.65 11
UnDAF [187]77.0 6.89 41 10.9 55 8.41 35 6.95 70 13.1 81 6.33 38 7.68 97 13.2 153 5.60 28 22.1 112 22.0 160 41.7 87 30.3 54 26.7 50 45.6 90 27.9 78 20.2 88 36.1 68 6.63 59 14.6 74 10.4 58 8.44 101 17.1 101 7.12 69
EAI-Flow [147]77.4 7.33 100 11.6 84 8.83 103 7.42 92 13.7 91 7.00 105 7.69 100 12.0 114 5.85 70 21.6 56 19.9 78 41.2 38 30.5 79 27.0 76 45.5 77 27.7 54 18.8 43 36.2 82 6.76 97 15.0 104 10.5 98 7.67 32 15.3 36 7.01 49
LFNet_ROB [145]77.9 7.27 91 11.6 84 8.82 101 7.96 115 14.9 124 7.11 109 7.95 124 13.8 164 6.10 107 21.8 78 20.6 116 41.3 46 30.1 39 26.6 42 45.1 45 27.9 78 21.0 123 35.9 47 6.51 36 14.1 53 10.3 26 7.84 36 15.7 39 7.00 46
RNLOD-Flow [119]78.1 7.12 70 11.5 80 8.64 68 7.38 90 14.0 100 6.35 42 7.55 73 11.2 92 5.83 63 21.3 34 19.0 47 41.1 29 30.5 79 27.2 107 45.4 61 28.3 116 21.6 144 36.2 82 6.62 56 14.2 59 10.4 58 8.70 137 17.7 137 7.02 51
HCFN [157]79.2 6.85 38 11.1 64 8.34 25 6.92 68 13.2 85 6.33 38 7.38 56 11.2 92 5.66 39 21.5 48 19.7 72 41.8 96 30.3 54 26.9 61 45.3 55 30.8 187 19.4 59 40.5 191 6.82 110 15.3 120 10.5 98 8.34 86 16.9 89 7.12 69
Ramp [62]80.7 7.31 98 12.1 110 8.78 92 6.60 46 12.0 53 6.27 25 7.36 53 10.4 54 5.65 36 21.3 34 18.9 46 41.4 57 30.5 79 27.1 90 45.4 61 28.7 149 22.3 167 36.6 128 6.73 92 14.9 95 10.3 26 8.55 116 17.3 119 7.26 110
SegFlow [156]82.0 7.19 80 12.2 118 8.72 79 6.85 63 13.0 78 6.62 73 7.59 81 11.8 107 5.83 63 21.7 68 20.5 109 41.6 74 30.6 101 27.1 90 45.8 128 27.7 54 19.7 75 36.3 97 6.63 59 14.6 74 10.4 58 8.10 55 16.4 57 7.35 128
FC-2Layers-FF [74]83.2 7.22 84 11.9 102 8.70 75 6.10 16 10.2 12 6.47 58 7.31 47 10.5 59 5.64 32 21.4 42 19.1 50 41.6 74 30.7 123 27.5 146 45.6 90 28.6 143 22.7 172 36.4 110 6.77 100 15.0 104 10.3 26 8.57 120 17.2 113 7.20 98
Second-order prior [8]83.3 7.30 97 11.3 70 8.90 113 8.52 138 15.6 142 6.74 87 8.32 153 13.6 160 6.42 136 21.8 78 20.0 82 41.5 61 30.1 39 26.5 36 45.5 77 27.5 39 19.0 49 36.0 53 6.67 69 14.6 74 10.3 26 8.25 75 16.8 79 7.11 67
PGM-C [118]83.5 7.19 80 12.1 110 8.72 79 6.82 58 12.9 74 6.62 73 7.67 95 12.2 120 5.78 57 21.9 88 20.9 128 41.8 96 30.6 101 27.1 90 45.8 128 27.7 54 19.5 63 36.2 82 6.65 65 14.7 81 10.3 26 8.20 69 16.6 72 7.31 116
Classic+NL [31]85.0 7.44 119 12.3 123 8.86 106 6.78 57 12.3 60 6.28 30 7.32 49 10.4 54 5.69 44 21.6 56 19.4 58 41.8 96 30.5 79 27.1 90 45.5 77 28.6 143 21.8 150 36.6 128 6.72 86 14.7 81 10.3 26 8.50 109 17.2 113 7.24 107
Aniso. Huber-L1 [22]85.3 7.61 133 12.2 118 9.19 132 8.99 150 15.7 145 7.12 111 7.73 106 11.0 84 5.86 74 21.8 78 20.0 82 41.6 74 30.2 44 26.6 42 45.5 77 27.4 34 19.6 67 35.7 41 6.68 75 14.6 74 10.3 26 8.34 86 16.8 79 7.29 115
DeepFlow2 [106]85.4 7.28 93 11.3 70 8.88 109 7.68 103 14.4 113 6.94 103 7.58 79 12.3 124 5.88 77 21.9 88 20.2 91 41.7 87 30.5 79 26.8 55 45.9 156 27.5 39 18.0 36 36.4 110 6.67 69 14.6 74 10.4 58 8.18 63 16.4 57 7.31 116
SRR-TVOF-NL [89]85.8 7.42 117 11.5 80 8.86 106 7.79 105 14.8 121 7.08 108 7.62 84 11.5 98 5.85 70 21.7 68 19.6 66 41.1 29 30.3 54 27.1 90 45.2 48 27.5 39 20.5 102 35.3 31 6.72 86 14.8 89 10.4 58 8.97 155 18.3 164 7.17 91
PWC-Net_RVC [143]86.8 7.22 84 12.8 151 8.51 49 7.26 86 14.0 100 6.49 62 7.78 111 12.7 138 5.95 89 21.6 56 20.3 95 41.6 74 30.8 138 27.5 146 45.6 90 28.2 110 20.2 88 36.5 119 6.58 47 14.2 59 10.4 58 8.02 47 16.3 53 6.87 33
FF++_ROB [141]87.2 7.00 52 11.4 77 8.50 43 7.08 74 13.3 86 6.62 73 7.67 95 11.9 110 5.93 86 21.9 88 20.6 116 41.5 61 30.8 138 27.4 136 45.7 108 28.4 128 20.5 102 36.9 148 6.67 69 14.6 74 10.4 58 8.08 53 16.4 57 7.09 62
LiteFlowNet [138]87.4 7.24 88 12.4 133 8.60 62 7.17 77 13.7 91 6.52 66 7.70 102 13.1 147 5.84 65 22.5 139 22.5 169 41.9 111 30.4 64 27.0 76 45.2 48 27.8 67 21.3 136 35.5 32 6.90 126 15.6 134 10.4 58 7.86 39 16.0 42 6.80 25
Classic+CPF [82]87.5 7.22 84 11.6 84 8.52 50 6.90 67 12.6 72 6.28 30 7.37 55 10.6 63 5.76 53 21.2 28 18.7 37 41.1 29 31.1 172 27.9 171 45.5 77 28.7 149 23.1 180 36.3 97 6.92 127 15.3 120 10.3 26 8.75 139 17.9 145 6.99 45
FESL [72]87.6 7.36 105 11.7 89 8.65 70 6.82 58 12.6 72 6.33 38 7.51 69 10.7 71 5.89 80 21.6 56 19.6 66 41.3 46 30.9 161 27.5 146 45.7 108 28.4 128 22.1 163 36.2 82 6.70 80 14.8 89 10.2 19 8.59 121 17.4 126 7.08 59
CPM-Flow [114]88.4 7.21 82 12.2 118 8.71 78 6.83 61 12.9 74 6.65 78 7.61 83 11.7 104 5.88 77 22.2 119 21.4 149 41.8 96 30.6 101 27.1 90 45.8 128 27.9 78 19.1 50 36.6 128 6.67 69 14.7 81 10.3 26 8.16 60 16.5 67 7.34 125
DF-Auto [113]89.0 7.54 128 11.1 64 9.32 141 8.42 134 14.5 116 8.82 147 7.35 52 10.3 47 5.65 36 22.0 102 20.2 91 41.5 61 30.4 64 26.7 50 45.8 128 27.5 39 18.7 41 36.1 68 6.82 110 15.3 120 10.5 98 8.43 99 17.1 101 7.20 98
IROF-TV [53]90.3 7.33 100 12.3 123 8.82 101 6.83 61 12.3 60 6.23 21 7.70 102 12.9 144 5.93 86 21.5 48 19.5 64 42.0 122 30.8 138 27.3 120 45.9 156 27.5 39 20.2 88 35.6 38 6.75 95 15.1 113 10.5 98 8.18 63 16.4 57 7.37 131
MS-PFT [159]90.7 5.77 17 8.79 26 7.00 14 8.27 126 12.4 64 11.2 175 7.86 116 10.7 71 11.7 195 23.6 171 22.5 169 41.9 111 23.7 22 20.1 21 40.4 26 26.9 30 14.8 28 36.7 138 7.38 164 14.0 50 13.2 196 6.97 28 12.6 29 9.33 189
S2D-Matching [83]91.2 7.37 108 12.3 123 8.80 97 7.62 102 14.2 105 6.43 54 7.28 44 10.4 54 5.74 50 21.6 56 19.1 50 42.2 133 30.6 101 27.3 120 45.4 61 28.6 143 22.5 168 36.4 110 6.76 97 14.5 72 10.3 26 8.46 103 17.0 92 7.32 119
SepConv-v1 [125]91.4 4.07 6 8.88 27 4.61 5 6.87 65 13.0 78 7.47 122 6.42 26 9.58 32 9.25 184 23.4 168 20.0 82 44.0 175 30.2 44 26.3 35 45.7 108 27.9 78 16.5 34 37.4 164 7.61 176 15.6 134 12.9 192 7.71 34 13.8 33 9.78 192
DeepFlow [85]91.7 7.21 82 11.0 61 8.88 109 7.79 105 14.3 108 7.33 118 7.64 89 12.6 134 5.95 89 22.1 112 20.1 86 42.0 122 30.6 101 26.8 55 46.1 171 28.0 89 17.9 35 37.2 158 6.57 45 14.1 53 10.4 58 8.07 51 16.2 50 7.32 119
EPPM w/o HM [86]91.9 6.77 31 10.4 44 8.32 23 7.00 73 13.4 88 6.16 13 8.19 144 13.6 160 6.26 121 21.7 68 20.3 95 41.5 61 30.5 79 27.2 107 45.5 77 28.5 135 21.8 150 36.5 119 6.84 113 15.6 134 10.6 133 8.41 95 17.1 101 6.95 42
Efficient-NL [60]92.5 7.28 93 11.6 84 8.61 64 7.24 84 13.3 86 6.35 42 8.21 146 10.8 75 6.39 133 21.7 68 19.6 66 41.2 38 30.4 64 27.0 76 45.3 55 28.3 116 22.8 175 35.6 38 6.86 119 15.6 134 10.4 58 9.10 163 18.3 164 7.14 78
Brox et al. [5]92.9 7.28 93 11.4 77 8.76 85 7.86 109 14.6 118 6.92 102 8.03 132 13.1 147 6.34 128 21.9 88 19.9 78 41.4 57 30.6 101 27.0 76 45.8 128 27.7 54 19.5 63 36.2 82 6.80 103 15.4 129 10.4 58 8.16 60 16.5 67 7.19 94
p-harmonic [29]93.4 7.04 57 11.3 70 8.62 66 8.81 145 15.8 148 6.98 104 7.76 109 13.1 147 6.18 117 22.4 134 20.7 121 41.9 111 30.5 79 27.0 76 45.5 77 27.8 67 19.2 54 36.4 110 6.71 82 15.1 113 10.3 26 8.29 80 16.8 79 7.12 69
JOF [136]93.5 7.63 134 12.3 123 9.19 132 6.48 37 11.4 34 6.48 59 7.27 43 10.1 41 5.67 40 21.8 78 19.2 54 42.6 156 30.8 138 27.3 120 45.8 128 28.7 149 22.2 165 36.6 128 6.59 50 14.1 53 10.3 26 8.55 116 17.1 101 7.46 138
ProFlow_ROB [142]93.5 7.15 73 11.3 70 8.77 88 7.31 87 14.3 108 6.72 84 7.57 78 11.5 98 5.76 53 22.0 102 21.2 146 42.2 133 30.8 138 27.4 136 45.6 90 27.6 47 18.7 41 36.1 68 6.81 108 15.3 120 10.3 26 8.55 116 17.3 119 7.31 116
SuperSlomo [130]95.6 6.74 27 9.03 29 8.40 32 9.03 153 13.1 81 12.7 186 8.09 141 10.5 59 9.15 181 22.7 147 18.4 30 43.7 171 28.3 30 24.4 30 44.1 32 28.5 135 15.3 30 38.7 180 7.11 145 12.9 28 12.9 192 7.43 31 13.2 32 9.86 193
PMF [73]96.5 6.83 34 10.3 43 8.37 28 6.96 71 13.1 81 6.19 16 7.86 116 13.1 147 6.03 101 21.5 48 19.4 58 41.3 46 31.0 168 27.7 165 45.8 128 28.7 149 20.5 102 37.2 158 6.80 103 15.0 104 10.5 98 8.87 145 18.2 161 7.00 46
EpicFlow [100]96.8 7.18 77 12.0 105 8.72 79 7.42 92 14.4 113 6.72 84 7.68 97 12.1 117 5.92 84 22.1 112 21.1 139 42.0 122 30.7 123 27.1 90 45.8 128 27.5 39 19.9 82 35.9 47 6.79 102 15.2 116 10.4 58 8.40 94 17.1 101 7.33 122
C-RAFT_RVC [181]96.8 7.93 150 12.5 138 9.36 144 7.47 97 13.9 96 7.47 122 7.80 113 11.9 110 6.06 105 21.9 88 20.5 109 42.1 128 30.4 64 26.7 50 45.7 108 28.1 100 21.2 131 36.0 53 6.59 50 14.0 50 10.5 98 8.18 63 16.6 72 7.15 84
DPOF [18]97.0 7.58 132 13.2 161 9.07 120 6.27 24 11.0 26 6.54 68 8.10 142 10.6 63 6.27 123 22.0 102 20.5 109 41.9 111 30.2 44 26.8 55 45.4 61 28.0 89 21.2 131 35.8 44 6.84 113 15.0 104 10.7 145 8.62 125 17.4 126 7.26 110
TOF-M [150]97.7 5.20 14 7.84 19 6.44 12 8.53 139 13.7 91 11.0 173 7.96 125 10.9 80 10.2 189 22.5 139 18.5 32 43.6 170 29.1 34 25.0 34 45.5 77 28.8 155 16.4 33 38.7 180 7.15 149 13.1 29 12.9 192 8.03 49 14.4 34 10.2 195
PBOFVI [189]98.4 7.38 112 12.7 149 8.61 64 8.14 123 15.1 129 6.72 84 7.96 125 10.8 75 6.10 107 21.7 68 19.7 72 41.3 46 30.7 123 27.3 120 45.8 128 28.2 110 20.4 97 36.3 97 6.87 122 15.3 120 10.4 58 8.28 79 16.8 79 7.13 75
ComplOF-FED-GPU [35]99.2 7.23 87 11.8 95 8.72 79 7.20 81 13.9 96 6.62 73 8.43 158 12.6 134 6.45 138 21.9 88 20.8 127 42.3 137 30.4 64 26.9 61 45.4 61 27.7 54 20.1 85 36.1 68 6.86 119 15.4 129 10.5 98 8.55 116 17.3 119 7.28 114
DMF_ROB [135]99.6 7.31 98 11.8 95 8.81 99 7.86 109 14.9 124 6.69 82 8.52 161 13.8 164 6.40 135 22.1 112 20.7 121 41.5 61 30.5 79 26.9 61 46.0 168 27.4 34 18.9 46 36.1 68 6.95 134 14.3 65 11.2 167 8.13 57 16.4 57 7.19 94
Sparse Occlusion [54]101.0 7.37 108 12.3 123 8.87 108 8.04 118 15.3 135 6.48 59 7.58 79 10.8 75 5.87 75 22.0 102 20.4 103 41.5 61 30.6 101 27.2 107 45.5 77 28.3 116 21.8 150 36.4 110 6.80 103 15.3 120 10.3 26 8.74 138 17.7 137 7.18 93
TC/T-Flow [77]101.5 7.37 108 11.8 95 8.59 59 7.31 87 14.0 100 6.42 51 7.47 66 11.1 88 5.81 59 21.8 78 20.5 109 41.7 87 30.8 138 27.5 146 45.7 108 28.1 100 20.9 118 36.2 82 7.03 142 16.0 147 10.6 133 8.62 125 17.6 134 7.13 75
AggregFlow [95]103.1 7.71 141 12.6 142 9.11 122 7.50 99 13.9 96 7.06 106 7.19 35 9.98 40 5.53 21 21.9 88 20.4 103 41.6 74 30.8 138 27.3 120 46.1 171 29.0 160 19.7 75 37.9 172 6.75 95 14.7 81 10.5 98 8.32 83 16.8 79 7.40 136
RFlow [88]103.8 7.24 88 12.1 110 8.90 113 8.42 134 15.6 142 6.49 62 7.72 104 12.2 120 6.01 99 22.0 102 20.6 116 41.7 87 30.4 64 27.1 90 45.7 108 27.4 34 19.8 81 35.6 38 6.84 113 15.9 144 10.5 98 8.91 151 18.0 150 7.47 142
CLG-TV [48]103.9 7.52 127 12.3 123 9.14 125 8.67 143 15.8 148 7.11 109 7.97 128 12.7 138 6.26 121 22.1 112 20.3 95 42.0 122 30.5 79 26.9 61 45.7 108 27.6 47 19.1 50 36.2 82 6.71 82 14.9 95 10.4 58 8.53 115 17.3 119 7.24 107
TCOF [69]104.3 7.36 105 12.1 110 8.68 72 9.41 159 16.6 162 7.17 113 7.38 56 10.7 71 5.61 30 21.8 78 20.4 103 41.8 96 30.4 64 27.0 76 45.6 90 28.1 100 21.8 150 35.9 47 6.85 116 15.7 140 10.4 58 9.30 173 19.0 178 7.61 157
LSM_FLOW_RVC [182]104.3 7.83 146 14.1 176 9.11 122 8.56 142 16.3 157 7.76 127 7.99 129 14.5 176 5.91 83 22.2 119 22.1 162 41.5 61 30.4 64 27.0 76 45.3 55 27.6 47 19.7 75 35.8 44 6.80 103 15.3 120 10.5 98 8.22 72 16.6 72 7.14 78
MCPFlow_RVC [197]104.9 7.46 122 11.9 102 8.89 112 6.85 63 12.3 60 7.36 119 7.33 50 11.3 97 5.59 27 21.6 56 19.8 76 41.6 74 30.9 161 27.5 146 46.1 171 28.5 135 23.3 182 36.1 68 6.60 53 14.1 53 10.5 98 13.3 197 30.2 198 7.20 98
SIOF [67]105.1 7.66 138 12.6 142 9.09 121 9.45 160 16.6 162 8.48 140 7.65 91 11.9 110 5.98 94 21.9 88 20.1 86 41.8 96 30.0 37 26.5 36 45.3 55 28.1 100 19.7 75 36.6 128 6.63 59 14.7 81 10.5 98 8.82 142 17.9 145 7.46 138
TC-Flow [46]105.5 7.18 77 11.8 95 8.78 92 7.46 95 14.6 118 6.77 92 7.86 116 12.6 134 5.89 80 21.8 78 20.3 95 41.9 111 30.7 123 27.4 136 45.7 108 28.3 116 21.0 123 36.6 128 6.73 92 14.8 89 10.5 98 8.51 111 17.3 119 7.24 107
3DFlow [133]105.8 7.09 64 11.7 89 8.46 37 6.89 66 13.0 78 6.39 48 8.03 132 10.6 63 5.98 94 21.6 56 19.3 56 41.9 111 30.8 138 27.1 90 47.6 189 29.0 160 23.9 188 36.4 110 7.05 143 16.2 150 10.5 98 8.83 144 18.0 150 7.15 84
CompactFlow_ROB [155]105.8 7.64 136 12.6 142 9.14 125 8.30 131 15.2 131 9.11 152 8.22 147 14.8 177 5.92 84 22.7 147 22.8 174 42.3 137 30.5 79 26.9 61 45.6 90 27.6 47 20.9 118 35.5 32 6.70 80 15.0 104 10.4 58 8.19 66 16.7 77 6.98 44
IAOF [50]106.2 8.70 170 12.9 154 10.3 166 12.4 187 19.2 192 9.77 167 7.74 107 12.0 114 6.21 118 22.8 150 20.2 91 42.0 122 30.2 44 26.5 36 45.5 77 27.7 54 19.6 67 36.1 68 6.67 69 15.0 104 10.3 26 8.41 95 17.1 101 7.12 69
OAR-Flow [123]107.2 7.45 121 11.7 89 8.98 116 7.57 101 14.4 113 6.91 101 7.62 84 12.4 127 5.82 61 21.6 56 20.3 95 41.6 74 30.9 161 27.5 146 45.8 128 28.0 89 20.5 102 36.4 110 6.97 137 15.6 134 10.5 98 8.46 103 17.1 101 7.34 125
ContinualFlow_ROB [148]108.5 7.92 149 13.9 173 9.35 143 8.28 127 15.5 138 8.57 142 8.24 149 14.0 170 6.28 124 21.9 88 21.0 134 41.9 111 30.6 101 27.3 120 45.5 77 27.4 34 20.1 85 35.5 32 6.65 65 14.4 68 10.4 58 8.65 130 17.9 145 6.94 40
SVFilterOh [109]109.9 7.18 77 10.9 55 8.76 85 6.48 37 11.7 44 6.45 57 7.62 84 10.2 45 5.99 97 21.7 68 19.4 58 42.5 150 31.3 178 28.0 177 46.6 181 28.6 143 22.0 159 36.5 119 6.92 127 14.1 53 11.4 174 8.97 155 17.8 142 8.09 172
ALD-Flow [66]109.9 7.54 128 12.1 110 9.14 125 7.43 94 14.3 108 6.85 98 7.66 94 12.5 130 5.87 75 21.8 78 20.4 103 42.3 137 30.8 138 27.4 136 45.9 156 28.1 100 19.9 82 36.6 128 6.62 56 14.2 59 10.5 98 8.68 135 17.5 132 7.46 138
OFH [38]110.7 7.39 114 12.1 110 8.88 109 8.07 119 15.0 128 6.66 80 8.03 132 13.8 164 5.96 92 21.9 88 21.1 139 42.1 128 30.5 79 27.3 120 45.4 61 27.8 67 20.4 97 36.2 82 7.11 145 16.4 153 10.5 98 8.61 124 17.6 134 7.19 94
ResPWCR_ROB [140]112.2 7.34 102 12.4 133 8.76 85 7.92 114 15.1 129 7.28 115 8.37 155 13.4 157 6.22 119 22.7 147 22.2 164 43.1 166 29.7 35 26.5 36 44.6 35 32.9 195 21.5 142 43.1 195 6.66 67 14.9 95 10.3 26 8.50 109 17.4 126 7.00 46
MLDP_OF [87]112.5 7.10 67 11.2 69 8.64 68 7.33 89 13.7 91 6.31 35 7.44 63 10.9 80 5.75 52 22.0 102 19.8 76 42.3 137 30.6 101 27.3 120 46.2 178 31.0 188 22.6 169 40.0 187 6.93 130 15.2 116 11.0 160 8.65 130 17.4 126 7.79 166
Fusion [6]112.5 7.13 72 12.3 123 8.60 62 7.18 79 13.1 81 6.56 69 7.63 87 10.9 80 6.13 113 22.5 139 21.1 139 41.5 61 30.7 123 28.2 182 44.3 33 28.1 100 23.8 186 35.2 30 7.22 156 17.9 168 10.6 133 9.64 181 19.9 185 7.32 119
CostFilter [40]112.5 6.91 43 11.1 64 8.37 28 6.82 58 12.9 74 6.25 23 7.99 129 13.9 167 6.10 107 21.9 88 20.6 116 41.7 87 31.1 172 27.9 171 45.9 156 29.8 174 20.3 93 39.1 183 6.94 132 15.8 141 10.6 133 8.82 142 18.1 158 7.09 62
Modified CLG [34]115.0 7.63 134 11.6 84 9.65 148 10.7 173 17.2 171 10.7 172 8.25 150 14.3 174 6.60 144 22.4 134 21.1 139 41.8 96 30.6 101 26.9 61 45.8 128 27.7 54 19.2 54 36.3 97 6.69 77 14.9 95 10.4 58 8.41 95 17.0 92 7.35 128
IIOF-NLDP [129]115.8 7.04 57 10.9 55 8.36 26 7.81 107 14.8 121 6.64 77 8.07 139 11.0 84 6.12 110 22.3 128 20.0 82 42.8 160 30.4 64 27.0 76 45.9 156 29.1 165 23.2 181 36.5 119 8.40 193 24.6 195 11.3 170 8.78 140 17.8 142 6.86 32
F-TV-L1 [15]116.3 8.24 159 13.1 158 9.92 158 9.28 155 16.3 157 7.48 124 8.00 131 13.2 153 6.35 130 22.3 128 20.9 128 42.3 137 29.9 36 26.9 61 44.8 38 27.9 78 19.4 59 36.5 119 6.87 122 15.4 129 10.5 98 8.46 103 16.8 79 7.58 152
Complementary OF [21]117.5 7.11 68 12.1 110 8.50 43 7.17 77 14.0 100 6.58 72 8.76 171 12.0 114 6.55 141 22.3 128 21.4 149 42.6 156 30.6 101 27.5 146 45.2 48 28.1 100 20.9 118 36.4 110 7.15 149 16.7 157 10.5 98 9.09 161 18.7 172 7.38 132
FlowNet2 [120]117.5 9.30 175 14.6 179 10.5 169 8.42 134 14.6 118 9.24 158 8.03 132 12.5 130 6.14 115 22.2 119 21.9 158 41.8 96 30.9 161 27.5 146 45.8 128 28.0 89 20.5 102 36.0 53 6.72 86 14.9 95 10.4 58 8.31 82 16.9 89 7.01 49
SimpleFlow [49]117.8 7.37 108 12.4 133 8.74 84 7.88 112 14.3 108 6.50 64 8.59 164 11.5 98 6.51 139 21.6 56 19.3 56 41.8 96 30.6 101 27.3 120 45.5 77 28.5 135 22.9 178 36.2 82 7.66 179 20.5 189 10.8 154 8.89 148 18.2 161 7.15 84
EPMNet [131]117.8 9.02 173 14.8 182 10.2 164 8.29 129 14.1 104 8.78 146 8.03 132 12.5 130 6.15 116 22.8 150 23.9 187 41.7 87 30.9 161 27.5 146 45.8 128 28.0 89 21.4 138 35.9 47 6.72 86 14.9 95 10.4 58 8.21 71 16.8 79 6.83 29
AugFNG_ROB [139]117.8 8.05 151 12.5 138 9.84 157 8.99 150 15.9 153 9.32 162 8.37 155 15.6 182 6.30 125 22.5 139 22.3 165 41.9 111 31.2 176 28.0 177 45.6 90 27.8 67 20.2 88 35.9 47 6.83 112 15.0 104 10.4 58 7.96 43 16.4 57 6.68 21
TF+OM [98]119.9 7.41 115 12.1 110 9.19 132 7.21 82 12.9 74 7.83 132 7.55 73 12.3 124 5.82 61 22.2 119 21.0 134 41.9 111 30.8 138 27.5 146 46.0 168 28.3 116 20.5 102 36.8 143 6.97 137 16.3 151 10.5 98 8.65 130 17.3 119 7.75 162
ROF-ND [105]120.0 7.46 122 11.0 61 8.77 88 7.96 115 15.4 136 6.76 91 7.55 73 11.0 84 5.85 70 23.3 165 23.5 185 41.6 74 30.6 101 27.1 90 45.8 128 28.3 116 22.7 172 35.9 47 7.52 171 17.5 163 11.4 174 9.25 171 18.7 172 7.27 112
LDOF [28]120.2 8.08 153 12.3 123 9.79 155 8.94 148 14.9 124 9.18 155 8.23 148 13.5 159 6.52 140 22.3 128 21.1 139 42.4 148 30.6 101 27.0 76 45.8 128 27.9 78 18.8 43 36.6 128 6.77 100 15.3 120 10.4 58 8.44 101 17.1 101 7.38 132
TriFlow [93]121.5 7.77 143 13.7 170 9.28 137 8.98 149 15.7 145 9.30 161 7.65 91 12.4 127 5.84 65 22.0 102 20.9 128 41.1 29 30.9 161 27.7 165 45.7 108 28.4 128 21.3 136 36.3 97 6.85 116 15.5 133 10.4 58 8.69 136 17.4 126 7.23 106
Local-TV-L1 [65]121.8 8.46 165 12.6 142 10.4 167 9.68 163 16.0 155 8.93 150 7.56 77 11.2 92 5.84 65 23.1 160 20.4 103 46.0 188 30.6 101 27.1 90 45.9 156 30.1 179 19.1 50 39.9 186 6.72 86 14.9 95 10.5 98 8.13 57 16.1 45 7.58 152
Classic++ [32]122.1 7.49 125 12.5 138 9.11 122 8.07 119 15.2 131 6.67 81 7.89 120 12.6 134 6.04 102 22.3 128 20.7 121 42.2 133 30.6 101 27.2 107 45.7 108 29.0 160 21.0 123 37.6 167 6.81 108 15.2 116 10.5 98 8.62 125 17.4 126 7.46 138
Occlusion-TV-L1 [63]122.5 7.44 119 12.3 123 9.14 125 8.91 147 16.5 161 6.85 98 7.83 114 12.8 141 6.32 126 22.6 145 21.5 153 42.5 150 30.5 79 26.9 61 45.8 128 28.4 128 19.6 67 37.1 155 7.15 149 14.8 89 10.7 145 8.51 111 17.1 101 7.34 125
Nguyen [33]123.6 9.74 180 12.6 142 12.4 184 12.3 184 18.6 187 11.1 174 8.27 152 14.8 177 6.69 146 23.4 168 21.7 155 41.8 96 30.3 54 26.8 55 45.3 55 27.4 34 19.6 67 35.7 41 7.24 158 18.3 171 10.5 98 8.37 92 17.0 92 7.22 105
2D-CLG [1]124.0 8.44 163 12.3 123 10.6 172 11.9 182 18.0 181 12.3 184 8.94 174 13.9 167 7.33 163 23.1 160 21.2 146 41.3 46 30.5 79 26.9 61 45.8 128 27.6 47 19.2 54 36.2 82 7.14 147 17.2 161 10.5 98 8.37 92 16.5 67 7.20 98
FlowNetS+ft+v [110]124.9 7.81 145 11.7 89 9.63 147 9.77 165 16.8 164 9.16 154 8.06 137 13.4 157 6.36 131 22.1 112 20.7 121 42.1 128 30.8 138 27.4 136 45.8 128 27.7 54 19.4 59 36.3 97 7.01 139 16.4 153 10.5 98 8.51 111 17.2 113 7.33 122
Adaptive [20]125.5 7.71 141 13.2 161 9.21 135 9.40 158 16.8 164 7.07 107 7.87 119 12.4 127 6.12 110 22.0 102 20.3 95 41.8 96 30.7 123 27.3 120 45.6 90 28.4 128 20.7 116 36.8 143 6.95 134 16.0 147 10.4 58 8.87 145 17.9 145 7.55 149
CVENG22+RIC [199]125.5 7.42 117 12.2 118 8.96 115 7.88 112 15.2 131 6.74 87 7.91 122 13.2 153 6.07 106 22.6 145 22.5 169 42.1 128 30.7 123 27.3 120 45.8 128 28.0 89 20.9 118 36.3 97 6.96 136 15.9 144 10.5 98 9.01 159 18.6 170 7.35 128
Shiralkar [42]125.7 7.48 124 12.8 151 8.80 97 9.00 152 15.8 148 6.65 78 8.52 161 16.1 184 6.84 151 23.4 168 22.3 165 41.6 74 30.0 37 27.0 76 44.5 34 28.7 149 21.1 128 37.1 155 7.49 169 18.7 179 10.6 133 8.64 128 17.7 137 6.93 38
IRR-PWC_RVC [180]128.5 8.49 166 14.9 184 9.74 151 8.53 139 15.2 131 9.29 160 8.39 157 15.9 183 6.13 113 22.8 150 23.4 184 41.5 61 31.1 172 27.8 169 45.7 108 28.2 110 21.7 146 36.1 68 6.73 92 15.1 113 10.3 26 8.64 128 18.0 150 6.79 23
CRTflow [81]131.0 7.69 139 12.6 142 9.28 137 8.45 137 15.5 138 6.81 96 8.55 163 14.0 170 7.29 161 22.4 134 20.7 121 43.8 174 30.7 123 27.2 107 45.7 108 28.1 100 19.6 67 36.7 138 6.87 122 15.8 141 10.6 133 8.59 121 17.2 113 7.65 159
CNN-flow-warp+ref [115]131.0 7.35 103 10.8 50 9.30 139 8.87 146 16.2 156 8.14 139 8.60 165 14.1 172 6.62 145 23.7 174 21.9 158 42.7 158 30.8 138 27.3 120 45.9 156 28.0 89 19.1 50 36.7 138 7.37 163 18.5 176 10.6 133 8.33 85 16.8 79 7.27 112
HBpMotionGpu [43]131.4 9.39 177 14.6 179 11.3 179 11.7 180 18.9 189 11.5 178 7.55 73 11.1 88 6.00 98 23.3 165 22.3 165 43.5 169 30.3 54 27.2 107 45.2 48 28.7 149 20.9 118 37.1 155 6.62 56 14.2 59 10.5 98 8.99 157 17.8 142 8.04 170
Black & Anandan [4]131.5 8.54 167 12.8 151 10.2 164 10.9 175 17.3 174 9.40 163 9.06 176 13.6 160 6.99 156 22.9 157 21.3 148 41.7 87 30.7 123 27.2 107 45.9 156 28.0 89 18.6 39 36.7 138 6.93 130 15.9 144 10.4 58 8.46 103 17.0 92 7.20 98
StereoOF-V1MT [117]131.6 7.65 137 13.5 167 8.77 88 8.69 144 15.9 153 6.52 66 9.43 182 15.4 180 7.23 159 24.4 180 22.3 165 43.2 167 30.5 79 27.2 107 45.0 41 28.9 158 21.2 131 37.2 158 7.77 182 19.4 183 11.0 160 8.26 77 16.4 57 6.93 38
GraphCuts [14]131.8 8.65 169 14.1 176 9.83 156 8.28 127 14.2 105 9.28 159 9.89 186 10.6 63 7.38 165 23.0 158 21.1 139 42.5 150 30.3 54 27.3 120 44.7 37 27.2 31 21.4 138 34.7 27 7.42 167 17.8 166 11.0 160 9.32 174 18.9 176 7.66 160
HBM-GC [103]132.8 7.91 147 12.6 142 9.75 153 7.51 100 13.9 96 6.80 95 7.29 46 9.43 29 5.94 88 22.0 102 19.7 72 42.3 137 32.1 189 28.6 186 48.0 191 30.0 176 24.6 192 37.8 169 7.14 147 14.8 89 11.6 177 8.95 154 17.7 137 8.28 174
CBF [12]133.3 7.41 115 11.9 102 9.31 140 8.07 119 14.9 124 7.14 112 7.69 100 11.1 88 5.95 89 22.8 150 20.7 121 45.1 184 30.8 138 27.3 120 47.0 186 28.2 110 20.6 111 36.5 119 7.17 153 16.6 156 11.2 167 9.16 168 17.9 145 8.83 182
Correlation Flow [76]133.3 7.05 60 11.7 89 8.32 23 8.29 129 15.6 142 6.56 69 7.64 89 10.8 75 5.89 80 22.2 119 20.1 86 42.9 164 31.7 183 27.7 165 49.9 196 29.6 170 23.8 186 37.2 158 7.62 177 19.0 181 11.3 170 9.22 170 18.6 170 7.51 148
Steered-L1 [116]133.5 7.06 62 12.2 118 8.59 59 7.40 91 14.3 108 6.83 97 8.48 160 11.7 104 6.69 146 22.8 150 20.9 128 42.7 158 31.2 176 28.1 180 45.8 128 28.3 116 21.2 131 36.7 138 7.25 159 17.8 166 10.9 155 9.00 158 18.3 164 7.58 152
TriangleFlow [30]133.5 7.79 144 13.0 157 9.16 131 8.36 133 15.5 138 6.69 82 8.20 145 11.9 110 6.59 142 22.5 139 21.0 134 42.5 150 30.1 39 27.0 76 45.0 41 28.9 158 22.6 169 36.5 119 7.42 167 18.3 171 11.0 160 9.49 178 19.3 180 7.47 142
IAOF2 [51]136.8 8.43 162 13.6 169 9.76 154 9.86 167 17.4 175 8.67 143 7.74 107 12.2 120 6.33 127 23.1 160 21.7 155 42.3 137 31.0 168 27.9 171 45.6 90 28.5 135 21.0 123 36.6 128 6.71 82 15.0 104 10.3 26 9.14 166 18.4 167 7.49 146
WRT [146]139.0 7.26 90 11.8 95 8.58 57 8.55 141 14.8 121 6.77 92 9.36 181 10.8 75 6.71 150 22.2 119 20.1 86 42.0 122 31.3 178 28.0 177 46.9 185 29.4 167 25.4 194 36.5 119 9.01 196 28.1 198 11.7 180 9.92 185 21.0 189 6.94 40
BriefMatch [122]139.9 7.38 112 12.0 105 8.85 105 7.71 104 14.5 116 7.86 133 8.77 172 11.7 104 7.25 160 24.2 178 22.0 160 46.2 189 30.8 138 27.4 136 46.1 171 31.8 192 21.7 146 41.3 192 6.85 116 15.3 120 10.7 145 8.51 111 17.1 101 7.56 151
TV-L1-improved [17]142.6 7.55 130 12.9 154 9.15 130 9.36 156 16.9 166 7.19 114 8.63 168 12.2 120 6.92 153 22.2 119 21.0 134 42.3 137 30.8 138 27.5 146 45.6 90 28.5 135 21.4 138 36.8 143 7.38 164 18.6 178 10.7 145 8.94 152 18.0 150 7.75 162
SegOF [10]142.7 8.16 157 12.4 133 10.1 163 9.10 154 15.5 138 8.83 148 9.48 183 14.1 172 7.46 167 22.8 150 23.0 182 41.6 74 30.8 138 27.4 136 45.8 128 28.3 116 22.0 159 36.3 97 7.83 183 21.5 191 11.0 160 8.46 103 17.1 101 7.17 91
BlockOverlap [61]143.5 8.81 171 12.4 133 11.1 177 10.0 170 15.8 148 10.6 171 7.84 115 10.4 54 6.59 142 23.3 165 20.4 103 46.3 190 31.9 186 27.9 171 48.8 194 30.3 183 19.7 75 39.8 185 7.08 144 14.5 72 11.7 180 8.35 90 16.1 45 8.60 180
Dynamic MRF [7]143.6 7.29 96 13.1 158 8.69 73 8.20 125 16.3 157 6.74 87 9.18 178 16.4 187 7.22 158 24.5 182 23.1 183 44.4 178 30.3 54 27.2 107 45.1 45 29.2 166 23.4 184 37.2 158 7.64 178 19.8 186 10.7 145 9.14 166 18.0 150 7.48 145
OFRF [132]143.8 9.30 175 13.4 166 11.0 176 9.59 161 15.7 145 9.07 151 7.92 123 12.7 138 6.05 104 22.3 128 20.2 91 42.8 160 31.0 168 27.9 171 45.4 61 29.6 170 23.3 182 37.4 164 7.34 161 17.7 165 10.5 98 9.09 161 18.8 175 7.05 57
LocallyOriented [52]145.2 8.08 153 13.1 158 9.72 150 9.73 164 17.0 169 7.88 135 8.34 154 12.8 141 6.34 128 23.0 158 22.1 162 43.0 165 30.6 101 27.2 107 45.6 90 30.0 176 21.9 154 38.5 179 7.02 140 15.8 141 10.5 98 9.05 160 18.4 167 7.39 135
AdaConv-v1 [124]145.4 9.81 182 13.9 173 11.6 181 12.1 183 17.6 177 16.0 193 11.4 193 16.1 184 13.1 196 26.5 191 24.4 192 45.3 185 28.4 31 24.4 30 44.6 35 28.4 128 18.1 37 37.7 168 7.74 181 16.3 151 13.1 195 8.25 75 15.1 35 10.1 194
Rannacher [23]146.0 7.69 139 13.2 161 9.32 141 9.37 157 16.9 166 7.28 115 8.67 170 13.0 145 6.91 152 22.2 119 21.1 139 42.4 148 30.8 138 27.5 146 45.7 108 28.5 135 21.2 131 36.9 148 7.35 162 18.5 176 10.7 145 8.90 149 18.0 150 7.78 164
SPSA-learn [13]146.2 8.28 160 12.9 154 9.95 160 9.92 168 16.3 157 9.49 164 9.15 177 12.8 141 7.30 162 23.1 160 20.5 109 41.6 74 30.8 138 27.5 146 45.7 108 28.0 89 20.4 97 36.3 97 8.81 195 27.1 197 11.8 182 10.0 188 21.0 189 7.20 98
ACK-Prior [27]146.8 7.12 70 11.7 89 8.57 55 7.08 74 13.8 95 6.34 41 8.81 173 11.8 107 6.69 146 22.5 139 21.4 149 42.3 137 32.6 193 29.3 192 48.2 192 30.7 186 25.6 195 38.1 175 7.95 186 18.8 180 12.0 184 10.8 194 21.8 194 8.53 178
Ad-TV-NDC [36]147.8 10.8 187 13.9 173 13.4 187 11.6 179 17.6 177 11.2 175 7.77 110 12.3 124 6.12 110 24.0 176 21.6 154 44.4 178 31.1 172 27.6 161 46.1 171 29.0 160 19.3 58 38.0 173 6.87 122 15.4 129 10.5 98 8.59 121 17.0 92 7.71 161
TVL1_RVC [175]148.8 10.1 185 13.7 170 12.4 184 12.6 190 19.1 190 11.9 182 8.06 137 13.6 160 6.43 137 23.6 171 21.4 149 42.3 137 30.8 138 27.4 136 45.8 128 28.6 143 20.1 85 37.0 152 7.25 159 17.6 164 10.6 133 8.49 108 17.1 101 7.38 132
Horn & Schunck [3]150.0 8.45 164 13.3 165 10.0 161 11.4 178 18.1 184 9.84 168 9.65 184 16.1 184 7.89 171 24.6 183 22.8 174 42.8 160 30.6 101 27.2 107 45.6 90 28.3 116 19.4 59 36.8 143 7.41 166 18.0 170 10.6 133 8.94 152 17.7 137 7.55 149
UnFlow [127]152.5 9.13 174 15.0 185 10.7 174 10.9 175 18.1 184 9.23 157 9.21 179 16.9 190 7.18 157 22.4 134 21.8 157 41.8 96 30.8 138 27.6 161 45.9 156 28.6 143 22.7 172 36.0 53 6.94 132 15.6 134 10.5 98 10.0 188 19.3 180 7.47 142
StereoFlow [44]152.5 13.8 194 20.2 197 14.0 189 14.1 194 21.3 197 12.0 183 7.79 112 13.3 156 5.98 94 22.4 134 20.9 128 42.1 128 33.7 197 32.3 197 46.1 171 30.5 184 31.8 198 36.3 97 6.63 59 14.7 81 10.4 58 9.98 186 21.0 189 7.42 137
TI-DOFE [24]153.4 11.8 190 14.7 181 14.8 191 13.9 193 20.3 194 13.5 189 9.26 180 16.5 189 7.69 170 25.1 185 22.8 174 43.3 168 30.2 44 27.1 90 45.4 61 28.4 128 19.6 67 36.8 143 7.22 156 17.2 161 10.7 145 9.21 169 18.1 158 7.59 156
WOLF_ROB [144]159.2 8.87 172 16.2 190 9.71 149 9.97 169 16.9 166 7.77 129 8.60 165 13.0 145 6.39 133 23.2 164 23.5 185 43.7 171 30.9 161 27.9 171 45.8 128 30.1 179 22.8 175 38.2 177 7.54 172 19.0 181 10.7 145 9.12 165 18.7 172 7.06 58
Filter Flow [19]160.0 8.30 161 13.2 161 10.0 161 10.8 174 17.1 170 11.7 180 7.96 125 12.1 117 6.38 132 23.7 174 20.9 128 44.5 182 31.5 182 28.2 182 46.7 183 28.8 155 21.0 123 37.3 163 7.15 149 17.0 160 10.7 145 9.54 180 18.9 176 8.47 177
NL-TV-NCC [25]161.5 7.56 131 12.7 149 8.62 66 8.00 117 15.4 136 6.74 87 8.46 159 13.1 147 6.70 149 24.2 178 24.0 190 45.0 183 32.8 194 28.3 185 52.0 199 29.4 167 24.1 189 36.9 148 7.89 185 17.9 168 12.4 190 10.1 191 19.9 185 8.92 183
SILK [80]164.3 9.77 181 15.1 186 11.8 183 12.3 184 18.7 188 11.2 175 10.3 187 16.4 187 8.14 173 25.2 186 22.8 174 45.9 187 30.8 138 27.5 146 45.7 108 30.6 185 20.3 93 40.1 188 7.19 155 16.8 158 10.9 155 8.87 145 17.6 134 7.50 147
Bartels [41]164.6 8.10 155 13.8 172 9.94 159 8.35 132 15.8 148 8.75 144 8.11 143 12.1 117 6.97 154 24.1 177 22.7 172 47.6 192 32.4 190 27.8 169 51.1 198 35.4 197 23.0 179 46.5 198 7.18 154 14.9 95 12.3 189 9.36 176 18.0 150 9.76 191
H+S_RVC [176]165.3 9.43 178 14.2 178 11.2 178 12.3 184 18.0 181 11.8 181 12.2 194 21.7 195 10.9 193 28.4 193 22.8 174 44.0 175 30.7 123 27.7 165 45.6 90 28.5 135 21.1 128 36.5 119 8.15 188 20.3 188 11.3 170 9.37 177 17.2 113 7.81 167
SLK [47]170.8 11.4 189 15.4 187 14.4 190 12.4 187 18.0 181 12.6 185 10.9 191 17.6 192 8.85 180 27.8 192 25.2 193 46.6 191 30.6 101 28.1 180 43.6 30 29.0 160 21.9 154 37.0 152 8.25 190 22.4 192 11.3 170 9.33 175 18.5 169 7.91 168
GroupFlow [9]171.7 10.1 185 16.9 192 11.3 179 10.4 172 17.8 180 10.0 169 10.8 190 17.5 191 9.21 182 23.6 171 23.9 187 42.5 150 31.9 186 29.3 192 46.2 178 30.1 179 24.5 191 37.8 169 7.55 173 18.4 174 10.6 133 9.52 179 19.8 184 6.89 34
Heeger++ [102]172.2 9.81 182 17.3 193 10.4 167 11.3 177 17.2 171 9.67 165 13.6 196 23.8 197 10.2 189 26.3 189 22.8 174 44.4 178 31.8 185 28.9 191 46.3 180 29.6 170 22.0 159 37.5 166 8.17 189 19.8 186 10.9 155 9.10 163 18.2 161 7.02 51
Learning Flow [11]173.9 8.21 158 14.8 182 9.74 151 9.78 166 17.6 177 8.11 138 9.68 185 15.5 181 7.56 169 25.0 184 24.3 191 45.4 186 31.9 186 28.7 189 47.3 187 29.4 167 22.0 159 37.8 169 7.49 169 18.3 171 10.9 155 10.2 192 20.2 187 8.31 175
2bit-BM-tele [96]175.3 8.61 168 13.5 167 10.5 169 10.0 170 17.5 176 9.73 166 8.26 151 11.5 98 7.40 166 24.4 180 22.7 172 48.1 193 32.5 192 28.6 186 50.2 197 34.7 196 24.3 190 44.9 196 9.35 197 26.2 196 13.8 197 9.25 171 17.3 119 10.2 195
FFV1MT [104]180.1 9.53 179 16.7 191 10.7 174 12.6 190 18.2 186 12.8 187 13.3 195 23.5 196 10.5 192 26.3 189 22.8 174 44.4 178 31.4 181 28.2 182 46.1 171 29.8 174 20.6 111 38.1 175 8.32 192 20.5 189 11.0 160 10.5 193 20.4 188 8.45 176
Adaptive flow [45]183.0 13.2 193 15.9 188 16.2 193 14.2 195 19.9 193 16.4 194 9.02 175 13.1 147 8.03 172 26.0 188 22.8 174 48.6 194 32.4 190 29.4 194 47.9 190 30.1 179 24.6 192 38.0 173 7.55 173 16.9 159 12.2 187 9.85 182 19.5 182 8.97 186
FOLKI [16]183.7 15.0 196 17.4 194 19.4 196 14.3 196 20.9 196 14.4 191 10.7 189 19.2 194 9.99 188 29.8 196 26.8 194 53.1 197 31.3 178 28.6 186 45.8 128 30.0 176 21.7 146 38.9 182 7.85 184 19.4 183 11.6 177 9.85 182 19.2 179 8.80 181
Pyramid LK [2]186.3 16.3 197 16.1 189 21.6 197 16.0 197 20.3 194 18.2 196 16.7 197 15.3 179 14.3 197 35.7 198 36.7 198 56.5 198 32.8 194 31.2 196 45.7 108 29.7 173 22.1 163 38.2 177 8.31 191 23.1 193 11.6 177 11.8 195 25.0 195 8.22 173
PGAM+LK [55]187.8 12.7 191 18.1 195 15.3 192 12.4 187 19.1 190 13.0 188 11.1 192 18.6 193 9.33 186 29.2 195 27.5 195 51.6 196 31.7 183 28.8 190 46.7 183 31.3 190 23.7 185 40.1 188 7.67 180 19.4 183 11.4 174 9.89 184 19.5 182 8.95 184
HCIC-L [97]188.6 18.0 198 18.7 196 23.1 198 12.7 192 17.2 171 17.0 195 10.5 188 14.4 175 8.49 175 25.7 187 23.9 187 44.3 177 33.2 196 29.8 195 49.0 195 31.7 191 26.4 197 39.2 184 7.98 187 18.4 174 12.4 190 12.4 196 25.3 197 8.96 185
Periodicity [79]196.2 14.9 195 20.8 198 18.2 194 20.1 198 22.0 198 21.5 198 17.7 198 26.4 198 16.1 198 29.8 196 34.8 197 49.7 195 35.4 198 34.2 198 48.7 193 37.1 198 25.8 196 47.4 199 8.68 194 23.6 194 12.2 187 13.3 197 25.1 196 11.6 197
AVG_FLOW_ROB [137]198.4 46.4 199 51.9 199 42.8 199 44.1 199 40.8 199 44.3 199 39.2 199 37.3 199 32.5 199 57.2 199 58.7 199 63.7 199 41.6 199 42.4 199 47.5 188 46.3 199 59.4 199 45.4 197 25.5 199 33.4 199 16.2 198 33.6 199 39.6 199 34.2 199
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.