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        
R5.0
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]3.9 2.50 1 6.34 1 0.04 2 5.24 1 9.54 2 0.28 1 0.75 1 2.81 3 0.11 1 12.9 3 18.1 3 2.87 4 32.7 2 45.7 2 2.87 3 6.32 4 24.8 4 0.17 3 8.50 11 33.7 10 0.26 5 15.5 4 38.0 4 0.34 18
SoftSplat [169]5.6 2.65 3 7.02 3 0.04 2 6.02 4 11.7 5 0.36 3 0.76 2 2.62 2 0.14 3 12.4 2 17.7 2 2.72 3 34.8 9 48.1 9 2.88 4 6.77 6 26.6 6 0.18 4 8.47 10 34.7 14 0.27 9 15.7 5 38.6 5 0.35 19
EAFI [186]8.1 2.71 4 7.28 5 0.03 1 5.40 2 8.82 1 0.28 1 0.96 5 2.31 1 0.13 2 12.2 1 16.7 1 2.52 1 37.2 24 52.3 26 2.83 2 8.02 21 31.3 22 0.15 1 8.85 13 35.5 17 0.27 9 18.3 15 44.4 16 0.29 4
FGME [158]11.2 2.80 5 7.23 4 0.05 5 7.70 14 13.7 11 0.91 132 1.60 9 4.12 10 0.27 10 14.3 7 18.9 5 3.96 20 31.6 1 44.3 1 2.80 1 5.95 3 23.1 3 0.26 14 7.48 1 29.1 1 0.23 2 14.6 3 36.0 3 0.29 4
SepConv++ [185]11.5 3.29 18 10.0 21 0.07 19 6.76 7 13.3 8 0.41 13 2.12 17 4.53 11 0.40 84 16.3 19 23.0 20 3.53 8 33.4 4 46.2 3 2.91 7 5.17 1 20.4 1 0.15 1 7.67 3 31.3 3 0.26 5 13.4 1 33.3 1 0.28 1
IFRNet [193]11.6 2.62 2 6.53 2 0.07 19 6.16 5 11.2 4 0.71 92 0.94 3 2.89 5 0.17 4 13.6 4 18.8 4 4.05 22 34.9 11 48.6 12 3.39 21 7.01 8 27.5 8 0.22 7 8.36 9 33.7 10 0.22 1 17.2 10 41.8 8 0.30 7
EDSC [173]14.8 3.16 13 9.09 15 0.06 10 7.15 10 14.0 13 0.76 102 1.96 15 4.59 12 0.34 43 16.0 17 22.5 18 3.59 10 34.6 7 47.6 5 3.26 17 6.93 7 27.4 7 0.22 7 7.76 4 31.6 4 0.24 3 17.1 8 41.8 8 0.28 1
BMBC [171]16.4 3.50 24 8.86 13 0.04 2 7.12 9 13.4 9 0.41 13 4.49 32 9.79 31 0.38 74 14.7 9 20.3 8 3.29 7 34.6 7 48.0 8 3.23 16 7.05 9 27.6 9 0.33 22 9.04 15 35.0 15 0.37 24 15.9 6 39.1 6 0.40 25
DistillNet [184]17.6 2.82 7 7.62 7 0.05 5 5.96 3 10.9 3 0.54 53 0.94 3 2.91 6 0.19 5 13.7 5 19.9 7 2.94 5 34.9 11 48.8 14 3.00 9 8.16 23 31.9 23 0.29 17 10.1 103 38.5 25 0.34 21 19.3 20 46.4 22 0.40 25
AdaCoF [165]19.9 3.54 26 10.4 26 0.07 19 7.54 12 14.3 15 0.64 79 2.86 26 5.93 22 0.37 69 17.0 22 23.3 22 3.75 15 37.9 26 51.6 24 3.57 25 6.42 5 25.3 5 0.18 4 7.91 7 32.6 7 0.24 3 16.0 7 39.4 7 0.29 4
ProBoost-Net [191]22.8 3.00 9 8.54 10 0.06 10 8.75 47 15.9 31 1.05 158 1.93 12 4.90 16 0.19 5 16.0 17 21.6 13 4.98 30 37.1 22 50.9 23 3.77 26 7.84 16 30.3 17 0.42 25 8.21 8 33.5 9 0.28 13 18.1 11 44.0 12 0.30 7
TC-GAN [166]23.0 3.27 16 10.0 21 0.07 19 7.97 18 15.3 23 1.01 147 1.94 13 4.87 15 0.33 34 15.5 13 22.3 14 3.56 9 35.3 16 49.0 15 3.18 13 7.85 17 30.7 18 0.30 18 9.41 21 38.2 21 0.28 13 19.5 22 47.1 25 0.31 11
MV_VFI [183]23.1 3.26 15 9.99 20 0.07 19 7.90 17 15.1 21 1.01 147 1.95 14 5.00 17 0.32 29 15.6 15 22.4 16 3.59 10 35.4 18 49.1 16 3.20 14 7.86 19 30.7 18 0.32 19 9.40 19 38.2 21 0.27 9 19.5 22 47.1 25 0.32 15
DSepConv [162]23.4 3.54 26 10.6 28 0.07 19 8.36 32 15.4 25 0.95 142 2.48 22 5.57 20 0.32 29 18.0 46 24.2 26 3.91 19 34.8 9 47.9 6 3.40 22 7.13 12 28.0 11 0.26 14 7.79 5 31.8 5 0.27 9 18.1 11 44.1 13 0.31 11
DAIN [152]23.5 3.36 20 10.3 24 0.06 10 8.05 20 15.2 22 1.00 145 1.92 11 5.22 18 0.33 34 15.5 13 22.3 14 3.63 12 35.4 18 49.1 16 3.27 18 7.85 17 30.7 18 0.32 19 9.40 19 38.3 24 0.28 13 19.5 22 47.1 25 0.31 11
STAR-Net [164]26.2 2.81 6 7.50 6 0.05 5 7.89 16 14.8 18 0.67 85 2.63 24 3.49 9 0.42 93 15.1 11 21.3 11 2.66 2 33.2 3 46.5 4 2.89 6 7.74 15 30.0 16 0.22 7 12.1 186 35.2 16 0.41 30 19.1 19 44.8 17 0.39 23
STSR [170]26.9 3.19 14 9.43 16 0.05 5 6.49 6 12.0 6 0.83 116 2.34 21 5.98 24 0.39 79 14.5 8 20.6 9 4.11 23 40.2 29 55.5 29 3.53 24 8.92 29 34.8 30 0.39 23 9.69 33 39.4 29 0.31 18 20.0 28 48.5 29 0.33 17
MAF-net [163]27.1 2.92 8 8.49 9 0.06 10 8.09 22 15.4 25 1.02 151 2.12 17 5.68 21 0.37 69 16.3 19 22.4 16 4.94 29 39.6 28 54.0 28 3.79 27 8.35 25 32.3 25 0.44 26 8.53 12 34.6 13 0.30 17 18.9 18 46.1 20 0.32 15
FRUCnet [153]27.7 3.63 28 10.4 26 0.09 29 7.97 18 14.6 16 0.90 130 2.48 22 6.05 25 0.51 126 18.1 55 24.7 27 3.76 16 35.2 15 48.7 13 2.88 4 7.06 10 27.7 10 0.32 19 9.00 14 33.4 8 0.32 19 18.2 13 44.3 15 0.30 7
ADC [161]30.5 4.18 33 12.4 33 0.09 29 8.29 31 14.9 19 0.83 116 3.92 31 7.64 28 0.40 84 18.9 119 25.4 30 4.04 21 37.1 22 50.6 22 3.48 23 7.11 11 28.0 11 0.23 11 7.88 6 32.5 6 0.26 5 18.5 16 45.1 18 0.30 7
MEMC-Net+ [160]30.8 3.38 21 9.77 17 0.06 10 8.14 23 14.9 19 1.03 154 2.33 20 5.37 19 0.47 115 17.0 22 22.8 19 3.73 14 37.3 25 51.6 24 3.20 14 8.64 27 33.4 27 0.26 14 9.79 50 38.2 21 0.29 16 19.5 22 47.5 28 0.35 19
GDCN [172]32.3 3.35 19 10.3 24 0.06 10 10.0 111 17.8 61 0.86 123 1.87 10 4.70 13 0.55 137 18.1 55 23.0 20 3.87 18 35.0 13 48.4 11 3.38 20 7.51 14 29.5 14 0.40 24 9.10 16 34.2 12 0.34 21 17.1 8 42.4 10 0.31 11
DAI [168]35.3 3.27 16 8.01 8 0.55 191 8.25 27 14.7 17 1.66 190 1.06 6 3.37 7 0.30 21 13.8 6 19.0 6 4.69 26 38.6 27 53.2 27 3.04 11 8.51 26 33.0 26 0.24 13 10.0 88 37.6 20 0.32 19 19.5 22 46.9 24 0.39 23
IDIAL [192]35.8 3.05 10 8.64 11 0.05 5 7.42 11 14.1 14 0.73 96 1.56 8 3.48 8 0.34 43 15.7 16 21.5 12 3.19 6 34.3 5 47.9 6 3.16 12 8.15 22 31.2 21 0.21 6 12.1 186 36.4 18 0.55 144 19.4 21 45.4 19 0.54 160
OFRI [154]35.9 3.15 12 8.69 12 0.09 29 7.77 15 13.9 12 0.98 144 1.45 7 2.88 4 0.33 34 14.9 10 20.8 10 3.70 13 35.3 16 49.1 16 3.31 19 8.88 28 33.4 27 0.44 26 15.2 198 39.3 28 0.50 118 20.4 31 46.6 23 0.43 29
CyclicGen [149]37.9 3.50 24 9.95 18 0.13 38 7.67 13 12.9 7 1.52 188 3.74 29 10.6 32 0.48 120 19.1 133 25.7 31 5.85 162 36.7 21 49.3 19 3.80 28 5.69 2 21.5 2 0.50 28 7.53 2 30.4 2 0.26 5 13.5 2 33.4 2 0.28 1
FeFlow [167]37.9 3.10 11 8.86 13 0.06 10 8.07 21 15.6 28 1.13 163 2.03 16 4.86 14 0.36 62 16.5 21 23.3 22 3.78 17 34.4 6 48.3 10 3.03 10 8.34 24 32.2 24 0.23 11 11.6 177 36.7 19 0.51 128 19.5 22 46.2 21 0.48 60
CtxSyn [134]42.2 3.42 23 9.96 19 0.08 26 6.79 8 13.5 10 0.50 47 2.17 19 5.94 23 0.43 99 15.1 11 23.3 22 4.57 24 42.2 34 56.7 34 4.54 33 10.0 34 36.5 33 0.63 30 13.5 194 44.0 160 0.40 28 21.1 39 49.2 33 0.43 29
PMMST [112]44.2 4.93 35 13.9 35 0.13 38 8.97 63 17.1 44 0.43 21 6.00 45 13.4 37 0.27 10 17.6 26 26.2 38 5.24 56 43.0 48 57.7 42 5.17 55 10.3 37 39.1 41 0.87 50 9.75 42 41.0 50 0.44 51 21.5 71 51.9 81 0.47 45
MDP-Flow2 [68]45.1 4.89 34 14.4 36 0.12 36 8.58 38 16.9 41 0.39 9 5.95 40 13.6 39 0.28 13 17.7 29 26.7 47 5.32 75 42.9 40 57.6 38 5.13 49 10.6 56 40.1 63 0.92 62 9.75 42 41.0 50 0.43 41 21.6 85 51.9 81 0.46 39
SepConv-v1 [125]46.2 3.41 22 11.0 29 0.08 26 8.39 33 16.7 39 1.04 156 2.81 25 7.63 27 0.74 162 18.0 46 25.2 29 5.82 159 42.9 40 57.4 35 4.74 35 9.03 30 34.1 29 0.60 29 9.34 18 38.6 26 0.42 34 20.1 30 48.6 31 0.35 19
SuperSlomo [130]47.0 3.75 29 10.1 23 0.19 110 8.96 62 16.5 35 1.31 174 3.32 28 8.42 29 0.29 19 17.7 29 24.1 25 5.32 75 41.4 30 55.9 30 4.24 30 9.50 32 35.3 32 0.67 31 10.8 157 40.3 33 0.37 24 20.4 31 48.7 32 0.42 27
CoT-AMFlow [174]47.6 4.96 37 14.7 42 0.13 38 8.63 39 17.1 44 0.40 11 6.04 50 13.8 41 0.28 13 17.6 26 26.2 38 5.20 43 43.1 60 57.7 42 5.19 61 10.7 64 40.4 81 0.96 81 9.80 54 41.1 56 0.42 34 21.5 71 51.8 72 0.47 45
NNF-Local [75]50.3 5.11 47 15.7 60 0.11 32 8.18 25 15.8 30 0.39 9 6.01 48 13.5 38 0.27 10 18.3 70 28.3 92 5.29 67 43.0 48 57.6 38 5.11 47 10.8 84 40.9 102 1.01 93 9.67 32 40.7 40 0.46 71 21.2 41 51.2 45 0.46 39
NN-field [71]50.4 5.14 52 16.1 84 0.13 38 8.21 26 15.7 29 0.38 8 6.39 86 13.6 39 0.30 21 18.4 76 28.7 112 5.33 80 42.9 40 57.6 38 5.08 44 10.7 64 40.2 69 0.94 71 9.62 27 40.5 36 0.44 51 21.2 41 51.2 45 0.45 32
MPRN [151]55.4 4.10 32 11.9 31 0.06 10 9.67 96 16.8 40 0.78 106 7.31 164 18.6 172 0.47 115 18.0 46 25.8 32 4.76 27 41.6 32 56.1 31 4.34 32 9.29 31 34.9 31 0.68 32 10.3 124 40.9 45 0.34 21 20.0 28 48.5 29 0.36 22
Layers++ [37]56.0 5.25 71 15.9 68 0.17 86 8.27 28 15.5 27 0.37 5 6.16 62 14.3 50 0.38 74 18.0 46 26.9 52 5.32 75 43.1 60 57.9 58 5.24 80 10.7 64 40.6 94 0.97 86 9.70 35 40.7 40 0.39 26 21.3 49 51.3 49 0.48 60
GMFlow_RVC [196]56.9 5.25 71 17.2 132 0.12 36 8.72 44 17.7 58 0.37 5 6.07 52 13.8 41 0.28 13 17.9 38 27.5 67 5.26 61 43.3 97 58.0 75 5.24 80 10.7 64 40.8 100 0.82 40 9.78 48 41.2 60 0.43 41 21.3 49 51.5 54 0.46 39
TOF-M [150]57.8 3.92 30 11.5 30 0.08 26 8.90 57 17.4 50 1.19 168 3.87 30 8.82 30 0.52 131 17.9 38 25.1 28 5.20 43 42.1 33 56.6 33 4.68 34 10.0 34 36.7 34 0.69 34 12.8 193 41.1 56 0.47 91 21.8 114 50.8 39 0.45 32
MS_RAFT+_RVC [195]58.1 5.21 66 16.4 97 0.13 38 8.81 50 18.1 68 0.42 17 5.80 36 13.2 35 0.26 8 17.6 26 26.0 36 5.05 32 43.3 97 57.9 58 5.43 152 10.3 37 38.9 38 0.68 32 9.50 22 40.0 30 0.44 51 21.6 85 52.6 124 0.54 160
PH-Flow [99]59.4 5.32 86 16.4 97 0.16 75 8.28 29 15.9 31 0.44 24 6.12 58 13.9 45 0.33 34 17.5 24 25.8 32 5.15 40 42.8 38 57.5 36 5.03 41 11.0 114 41.6 138 1.09 121 9.71 36 41.0 50 0.46 71 21.3 49 51.4 52 0.50 105
nLayers [57]62.1 5.26 75 15.8 65 0.16 75 8.54 36 16.6 37 0.45 28 5.89 37 13.1 34 0.30 21 18.1 55 27.1 57 5.35 87 43.3 97 58.0 75 5.36 122 10.8 84 40.9 102 1.11 125 9.65 31 40.1 31 0.48 100 21.2 41 51.1 43 0.45 32
COFM [59]62.4 5.08 45 15.1 45 0.19 110 8.86 53 17.4 50 0.48 38 6.37 82 14.2 49 0.40 84 17.7 29 26.2 38 5.11 33 42.9 40 57.8 47 5.02 40 10.9 98 41.6 138 1.11 125 9.24 17 38.8 27 0.50 118 21.5 71 51.9 81 0.46 39
Sparse-NonSparse [56]62.9 5.31 85 16.3 95 0.17 86 8.74 45 17.2 49 0.48 38 6.19 63 14.7 63 0.34 43 17.9 38 26.3 41 5.23 53 43.1 60 57.8 47 5.25 86 11.0 114 41.2 115 1.04 102 9.71 36 40.9 45 0.46 71 21.2 41 51.3 49 0.47 45
IROF++ [58]64.7 5.37 99 16.8 116 0.14 48 8.87 55 17.4 50 0.45 28 6.41 93 14.6 60 0.43 99 17.5 24 25.8 32 5.22 48 42.9 40 57.8 47 5.19 61 10.5 46 39.4 48 0.87 50 10.0 88 42.4 110 0.47 91 21.4 61 51.5 54 0.50 105
TV-L1-MCT [64]65.9 5.74 158 18.1 159 0.18 101 9.50 87 19.1 85 0.58 62 5.73 34 14.5 57 0.38 74 17.8 34 26.0 36 5.28 65 43.0 48 57.9 58 5.22 73 10.4 40 39.1 41 0.94 71 9.78 48 41.1 56 0.44 51 21.2 41 51.1 43 0.48 60
HAST [107]66.7 5.12 49 15.2 47 0.16 75 8.74 45 17.1 44 0.43 21 6.62 122 15.3 90 0.39 79 17.7 29 26.4 43 4.98 30 43.0 48 58.0 75 5.05 42 11.0 114 41.4 125 1.06 110 9.53 23 40.4 34 0.42 34 22.0 140 52.8 137 0.47 45
ComponentFusion [94]67.9 5.15 53 16.1 84 0.14 48 8.86 53 17.9 64 0.41 13 6.38 83 15.4 91 0.33 34 17.8 34 27.0 55 5.15 40 43.2 85 58.0 75 5.24 80 10.6 56 39.8 52 0.94 71 10.0 88 42.7 130 0.57 153 21.5 71 51.8 72 0.47 45
ProbFlowFields [126]68.8 5.03 40 15.6 58 0.17 86 8.55 37 17.1 44 0.41 13 6.00 45 14.4 53 0.32 29 18.1 55 27.1 57 5.38 95 43.3 97 58.1 97 5.49 170 10.9 98 41.2 115 1.20 144 9.61 26 40.7 40 0.47 91 21.0 38 50.8 39 0.49 84
FMOF [92]69.0 5.62 143 17.2 132 0.21 123 8.71 43 17.0 42 0.44 24 6.38 83 14.7 63 0.46 110 18.6 91 28.0 77 5.31 72 43.1 60 57.9 58 5.15 52 10.8 84 40.5 89 0.87 50 9.60 25 40.4 34 0.40 28 21.5 71 51.7 63 0.46 39
MS-PFT [159]71.4 3.98 31 12.0 32 0.07 19 9.28 78 16.4 34 0.86 123 3.12 27 7.20 26 0.98 173 22.4 184 32.6 183 4.80 28 36.3 20 50.4 21 4.00 29 7.91 20 29.9 15 0.77 36 15.0 197 41.7 77 0.86 184 18.6 17 44.1 13 0.53 146
RAFT-it+_RVC [198]72.9 5.19 59 17.0 124 0.11 32 8.66 41 17.5 55 0.37 5 6.14 59 15.1 82 0.26 8 18.1 55 28.0 77 5.18 42 43.3 97 58.0 75 5.28 100 13.2 196 42.0 152 4.13 198 9.69 33 40.9 45 0.45 61 20.7 34 50.2 35 0.49 84
VCN_RVC [178]73.5 5.47 118 18.2 162 0.15 58 8.99 65 18.3 73 0.44 24 6.54 104 17.0 141 0.35 56 18.2 65 28.5 102 5.35 87 43.1 60 57.9 58 5.20 65 10.7 64 40.4 81 0.80 38 9.97 84 41.7 77 0.44 51 20.9 35 50.5 36 0.48 60
2DHMM-SAS [90]73.6 5.62 143 17.6 150 0.18 101 10.1 114 19.7 104 0.64 79 5.73 34 14.4 53 0.37 69 17.7 29 25.9 35 5.30 69 43.0 48 57.8 47 5.26 90 10.7 64 40.0 61 0.82 40 9.83 57 41.3 63 0.48 100 21.6 85 52.0 86 0.47 45
RAFT-it [194]73.7 5.16 54 16.5 101 0.14 48 8.47 35 17.0 42 0.36 3 5.98 43 14.0 46 0.25 7 17.9 38 27.5 67 5.12 36 43.3 97 57.9 58 5.22 73 13.1 195 40.4 81 3.83 197 9.62 27 40.6 37 0.41 30 22.3 164 53.8 169 0.51 120
RAFT-TF_RVC [179]73.7 5.24 70 17.0 124 0.11 32 8.75 47 17.8 61 0.42 17 6.09 54 14.5 57 0.34 43 18.3 70 28.6 109 5.33 80 43.4 120 58.1 97 5.25 86 13.0 194 40.4 81 3.31 196 9.63 29 40.7 40 0.41 30 20.9 35 50.6 37 0.48 60
CombBMOF [111]74.2 5.46 115 16.2 93 0.22 135 8.89 56 18.0 66 0.45 28 6.29 70 14.7 63 0.40 84 18.5 86 28.0 77 5.24 56 43.0 48 57.7 42 5.08 44 10.8 84 40.2 69 0.82 40 11.7 181 42.9 138 0.47 91 21.2 41 50.9 41 0.45 32
LSM [39]74.8 5.49 121 17.4 143 0.18 101 8.93 59 17.7 58 0.48 38 6.32 75 15.4 91 0.35 56 18.1 55 27.1 57 5.22 48 43.1 60 57.9 58 5.28 100 11.0 114 41.3 121 1.03 100 9.72 39 40.9 45 0.46 71 21.4 61 51.7 63 0.48 60
Ramp [62]76.7 5.46 115 17.1 129 0.18 101 8.84 51 17.4 50 0.58 62 6.14 59 14.7 63 0.34 43 17.8 34 26.4 43 5.23 53 43.2 85 58.0 75 5.27 95 11.2 140 42.0 152 1.15 134 9.72 39 40.9 45 0.42 34 21.6 85 52.1 93 0.48 60
NNF-EAC [101]77.6 5.52 125 15.7 60 0.34 177 9.27 77 18.1 68 0.48 38 6.53 103 13.8 41 0.40 84 18.2 65 27.0 55 5.71 148 43.0 48 57.7 42 5.11 47 10.4 40 39.1 41 0.83 44 9.89 66 41.6 73 0.52 134 21.7 100 52.2 102 0.49 84
DeepFlow [85]78.2 5.06 44 14.6 38 0.19 110 9.80 103 19.5 93 0.75 101 6.45 96 16.6 129 0.35 56 18.7 102 27.6 69 5.41 104 43.4 120 58.0 75 5.37 125 10.3 37 38.3 36 0.99 88 9.83 57 41.8 83 0.43 41 21.3 49 51.6 61 0.48 60
LME [70]78.3 5.13 51 15.8 65 0.14 48 9.15 73 18.4 80 0.51 48 6.32 75 15.7 99 0.34 43 17.9 38 27.1 57 5.34 83 43.8 176 58.8 174 5.79 190 10.8 84 41.2 115 0.93 66 9.86 62 41.3 63 0.43 41 21.3 49 51.5 54 0.47 45
DeepFlow2 [106]78.5 5.16 54 14.9 44 0.21 123 9.81 104 19.7 104 0.65 82 6.38 83 16.3 117 0.34 43 18.6 91 28.1 83 5.29 67 43.4 120 58.0 75 5.37 125 10.2 36 38.4 37 0.85 47 9.96 82 42.1 100 0.44 51 21.4 61 51.8 72 0.49 84
PRAFlow_RVC [177]78.6 5.29 80 16.9 120 0.11 32 9.02 69 18.2 71 0.48 38 5.95 40 13.8 41 0.29 19 18.6 91 28.9 122 5.50 125 43.3 97 58.0 75 5.39 133 10.4 40 39.2 44 0.87 50 9.71 36 41.2 60 0.46 71 22.1 149 52.6 124 0.54 160
PGM-C [118]78.7 5.18 58 16.0 76 0.15 58 8.97 63 18.2 71 0.46 35 6.51 99 16.4 123 0.33 34 18.4 76 28.5 102 5.36 91 43.4 120 58.1 97 5.40 141 10.7 64 40.5 89 0.96 81 9.92 70 41.9 87 0.45 61 21.4 61 51.8 72 0.48 60
FlowFields+ [128]79.1 5.23 69 16.6 107 0.15 58 8.91 58 18.3 73 0.45 28 6.28 69 15.9 103 0.34 43 18.2 65 28.1 83 5.34 83 43.4 120 58.2 111 5.35 118 10.9 98 41.6 138 1.10 123 9.79 50 41.5 68 0.46 71 21.3 49 51.5 54 0.48 60
WLIF-Flow [91]79.3 5.25 71 16.0 76 0.15 58 9.14 72 18.1 68 0.59 68 6.29 70 14.3 50 0.34 43 17.9 38 26.3 41 5.65 143 43.1 60 57.9 58 5.26 90 11.2 140 41.9 151 1.22 150 9.82 56 41.3 63 0.44 51 21.7 100 52.2 102 0.49 84
HCFN [157]79.7 5.11 47 16.0 76 0.15 58 9.40 85 19.6 99 0.48 38 6.30 74 15.5 95 0.36 62 18.0 46 27.6 69 5.26 61 43.0 48 57.8 47 5.17 55 12.5 191 40.5 89 3.11 195 10.0 88 42.1 100 0.49 106 21.4 61 51.7 63 0.48 60
EAI-Flow [147]80.1 5.33 93 15.9 68 0.17 86 9.73 101 19.6 99 0.71 92 6.61 116 16.3 117 0.36 62 18.3 70 28.1 83 5.11 33 43.1 60 57.9 58 5.31 104 10.7 64 39.9 57 0.98 87 10.1 103 42.7 130 0.51 128 21.1 39 50.9 41 0.44 31
Classic+NL [31]80.5 5.56 133 17.4 143 0.22 135 8.99 65 17.6 57 0.54 53 6.02 49 14.7 63 0.36 62 18.1 55 26.8 48 5.41 104 43.1 60 58.0 75 5.23 77 11.1 135 41.5 131 1.06 110 9.72 39 41.0 50 0.46 71 21.6 85 52.0 86 0.47 45
FlowFields [108]80.7 5.22 67 16.5 101 0.16 75 8.95 60 18.3 73 0.42 17 6.29 70 15.9 103 0.35 56 18.4 76 28.5 102 5.41 104 43.4 120 58.1 97 5.33 108 10.9 98 41.3 121 1.08 116 9.79 50 41.5 68 0.45 61 21.3 49 51.6 61 0.49 84
JOF [136]81.6 5.53 129 16.9 120 0.21 123 8.65 40 16.6 37 0.48 38 6.08 53 14.0 46 0.34 43 18.1 55 26.8 48 5.59 135 43.4 120 58.2 111 5.45 160 11.1 135 41.4 125 1.04 102 9.64 30 40.6 37 0.43 41 21.6 85 52.0 86 0.48 60
FC-2Layers-FF [74]82.3 5.40 104 17.0 124 0.17 86 8.15 24 15.3 23 0.42 17 6.14 59 14.9 71 0.35 56 18.1 55 27.2 62 5.31 72 43.3 97 58.2 111 5.36 122 11.2 140 42.2 157 1.20 144 9.75 42 41.0 50 0.49 106 21.7 100 52.1 93 0.48 60
SegFlow [156]82.6 5.19 59 16.1 84 0.15 58 9.01 68 18.4 80 0.48 38 6.40 89 16.0 107 0.30 21 18.3 70 28.3 92 5.37 93 43.3 97 58.1 97 5.41 145 10.8 84 41.0 108 1.14 131 10.0 88 42.4 110 0.46 71 21.4 61 51.8 72 0.48 60
S2F-IF [121]82.7 5.22 67 16.5 101 0.15 58 8.84 51 18.0 66 0.44 24 6.27 68 15.7 99 0.33 34 18.3 70 28.3 92 5.14 39 43.4 120 58.2 111 5.41 145 11.0 114 41.5 131 1.11 125 9.91 69 41.9 87 0.47 91 21.3 49 51.5 54 0.51 120
OFLAF [78]83.0 5.16 54 15.9 68 0.14 48 8.28 29 16.1 33 0.40 11 6.34 80 14.9 71 0.30 21 18.0 46 27.3 63 5.11 33 43.3 97 58.1 97 5.39 133 11.2 140 42.4 159 1.21 147 10.1 103 42.4 110 0.60 161 21.9 131 52.6 124 0.45 32
DF-Auto [113]83.3 5.03 40 13.8 34 0.17 86 10.2 117 19.3 89 0.79 108 6.09 54 14.4 53 0.34 43 18.7 102 28.1 83 5.24 56 43.2 85 57.9 58 5.31 104 10.4 40 39.3 45 0.93 66 10.1 103 42.3 106 0.49 106 21.9 131 52.9 144 0.53 146
AGIF+OF [84]83.4 5.60 139 17.4 143 0.15 58 8.95 60 17.7 58 0.59 68 6.20 65 14.5 57 0.43 99 17.9 38 26.6 46 5.22 48 43.4 120 58.3 135 5.38 131 11.1 135 42.0 152 1.01 93 9.87 65 40.7 40 0.42 34 21.5 71 52.0 86 0.48 60
MDP-Flow [26]84.7 5.03 40 15.4 49 0.14 48 8.68 42 17.4 50 0.47 36 5.97 42 14.3 50 0.32 29 18.9 119 28.5 102 5.50 125 43.2 85 58.0 75 5.39 133 11.2 140 42.6 162 1.31 161 10.3 124 43.1 145 0.49 106 21.4 61 51.7 63 0.47 45
FLAVR [188]86.1 7.34 193 18.1 159 0.06 10 12.1 170 17.5 55 0.85 120 4.63 33 11.8 33 0.63 153 31.2 197 41.5 196 4.66 25 35.1 14 49.5 20 2.95 8 7.41 13 29.1 13 0.22 7 13.9 195 41.6 73 0.69 172 18.2 13 42.5 11 0.60 184
S2D-Matching [83]86.4 5.56 133 17.3 137 0.18 101 9.96 109 19.9 109 0.66 84 5.99 44 14.7 63 0.41 91 17.9 38 26.4 43 5.40 101 43.2 85 58.0 75 5.17 55 11.2 140 42.0 152 1.17 139 9.93 74 41.1 56 0.43 41 21.5 71 51.8 72 0.48 60
TF+OM [98]88.5 4.98 38 14.6 38 0.20 116 9.03 70 17.9 64 0.55 56 6.29 70 16.2 112 0.39 79 18.5 86 28.0 77 5.50 125 43.3 97 58.1 97 5.47 165 10.6 56 39.8 52 1.03 100 9.86 62 42.0 93 0.51 128 21.7 100 52.3 107 0.52 136
ALD-Flow [66]88.6 5.37 99 16.1 84 0.23 143 9.53 88 19.2 88 0.57 60 6.51 99 16.7 133 0.34 43 18.2 65 27.9 73 5.32 75 43.4 120 58.3 135 5.46 163 10.7 64 39.9 57 0.99 88 9.76 47 41.2 60 0.44 51 21.8 114 52.7 133 0.47 45
CPM-Flow [114]88.8 5.20 65 16.1 84 0.16 75 8.99 65 18.3 73 0.47 36 6.42 94 16.0 107 0.30 21 18.8 110 29.2 137 5.43 111 43.4 120 58.2 111 5.44 158 10.6 56 40.1 63 1.02 95 10.0 88 42.6 122 0.45 61 21.4 61 51.8 72 0.53 146
ProFlow_ROB [142]89.0 5.09 46 15.4 49 0.17 86 9.40 85 19.3 89 0.55 56 6.34 80 15.4 91 0.33 34 18.4 76 28.7 112 5.39 99 43.5 148 58.3 135 5.41 145 10.4 40 39.3 45 0.79 37 10.2 116 42.9 138 0.49 106 21.8 114 52.6 124 0.49 84
Brox et al. [5]89.1 5.33 93 15.4 49 0.19 110 10.2 117 20.1 113 0.64 79 6.61 116 17.2 145 0.46 110 18.7 102 28.2 88 5.21 45 43.4 120 58.1 97 5.27 95 10.7 64 40.1 63 0.99 88 9.90 68 42.0 93 0.45 61 21.6 85 52.1 93 0.47 45
DMF_ROB [135]89.8 5.30 83 15.8 65 0.20 116 10.2 117 20.5 121 0.73 96 7.26 160 18.0 163 0.75 163 18.9 119 28.8 117 5.40 101 43.1 60 57.9 58 5.34 114 10.5 46 39.8 52 0.92 62 9.98 86 41.5 68 0.43 41 21.3 49 51.4 52 0.47 45
SVFilterOh [109]89.9 5.32 86 15.7 60 0.21 123 8.78 49 17.1 44 0.49 46 6.40 89 14.6 60 0.38 74 18.4 76 27.1 57 5.80 157 43.8 176 58.6 166 5.65 184 10.9 98 41.0 108 1.04 102 9.54 24 40.1 31 0.43 41 21.7 100 52.2 102 0.50 105
AggregFlow [95]90.0 5.64 146 17.2 132 0.22 135 9.81 104 19.5 93 0.59 68 6.11 57 14.4 53 0.28 13 18.9 119 29.0 127 5.30 69 43.4 120 58.2 111 5.33 108 10.7 64 40.2 69 0.96 81 9.89 66 41.7 77 0.50 118 21.4 61 51.7 63 0.50 105
UnDAF [187]92.6 5.32 86 17.0 124 0.17 86 9.37 82 19.1 85 0.45 28 6.70 126 17.8 160 0.34 43 19.1 133 31.2 175 5.44 114 43.1 60 57.8 47 5.15 52 10.8 84 41.0 108 1.02 95 9.92 70 41.7 77 0.47 91 21.8 114 52.5 122 0.48 60
RNLOD-Flow [119]92.6 5.32 86 16.6 107 0.16 75 9.70 98 19.6 99 0.60 72 6.57 109 15.5 95 0.51 126 18.2 65 27.4 64 5.22 48 43.1 60 58.0 75 5.28 100 11.0 114 41.4 125 1.08 116 9.85 60 41.3 63 0.50 118 21.9 131 52.7 133 0.49 84
Second-order prior [8]93.1 5.29 80 15.3 48 0.27 160 10.8 139 21.1 134 0.78 106 7.14 152 17.8 160 0.62 152 18.6 91 28.3 92 5.21 45 42.9 40 57.7 42 5.16 54 10.5 46 39.6 50 0.93 66 10.2 116 42.8 135 0.44 51 21.6 85 52.3 107 0.49 84
IROF-TV [53]93.8 5.35 98 16.6 107 0.21 123 9.10 71 17.8 61 0.57 60 6.61 116 16.8 135 0.44 103 17.8 34 26.9 52 5.37 93 43.5 148 58.4 150 5.50 173 10.5 46 40.1 63 0.90 59 9.98 86 42.2 103 0.46 71 21.6 85 52.1 93 0.51 120
DPOF [18]94.3 5.51 124 17.9 157 0.22 135 8.45 34 16.5 35 0.43 21 6.87 135 15.1 82 0.59 145 18.9 119 29.5 143 5.43 111 42.9 40 57.8 47 5.05 42 11.0 114 40.9 102 0.84 46 10.3 124 42.5 118 0.45 61 21.9 131 52.8 137 0.48 60
TC-Flow [46]96.8 5.19 59 15.9 68 0.21 123 9.57 89 19.6 99 0.63 75 6.78 132 17.0 141 0.36 62 18.1 55 27.4 64 5.61 139 43.3 97 58.2 111 5.46 163 11.0 114 41.6 138 1.18 140 9.93 74 41.7 77 0.45 61 21.5 71 52.0 86 0.49 84
OAR-Flow [123]97.5 5.28 78 15.5 53 0.18 101 9.71 100 19.5 93 0.67 85 6.43 95 16.3 117 0.28 13 18.0 46 27.6 69 5.23 53 43.5 148 58.4 150 5.48 168 10.9 98 41.3 121 1.13 130 10.2 116 42.9 138 0.51 128 21.7 100 52.3 107 0.45 32
Aniso. Huber-L1 [22]98.5 5.41 106 16.0 76 0.23 143 11.2 150 21.1 134 0.90 130 6.72 127 15.4 91 0.46 110 18.5 86 28.1 83 5.39 99 43.0 48 57.8 47 5.23 77 10.5 46 40.1 63 0.81 39 10.2 116 42.6 122 0.46 71 21.9 131 52.7 133 0.52 136
EpicFlow [100]98.9 5.19 59 16.1 84 0.15 58 9.60 90 19.8 108 0.58 62 6.40 89 16.4 123 0.35 56 18.6 91 29.1 135 5.47 120 43.4 120 58.2 111 5.42 150 10.8 84 41.2 115 1.08 116 10.1 103 42.5 118 0.54 141 21.5 71 52.0 86 0.49 84
ComplOF-FED-GPU [35]99.2 5.30 83 16.1 84 0.19 110 9.39 83 19.3 89 0.58 62 7.21 156 16.9 138 0.66 156 18.4 76 28.6 109 5.32 75 43.1 60 58.0 75 5.27 95 10.8 84 40.9 102 0.99 88 10.1 103 42.8 135 0.47 91 21.8 114 52.3 107 0.50 105
PBOFVI [189]99.8 5.84 163 19.0 173 0.15 58 10.5 131 20.8 127 0.86 123 6.54 104 14.9 71 0.37 69 18.4 76 28.3 92 5.49 123 43.3 97 58.1 97 5.43 152 10.7 64 39.8 52 0.89 57 10.3 124 42.3 106 0.55 144 21.2 41 51.2 45 0.50 105
FF++_ROB [141]99.9 5.19 59 16.1 84 0.13 38 9.36 81 19.0 83 0.51 48 6.52 102 16.2 112 0.46 110 18.6 91 28.8 117 5.41 104 43.4 120 58.2 111 5.44 158 11.3 149 41.2 115 1.71 185 9.85 60 41.8 83 0.49 106 21.3 49 51.5 54 0.57 179
FESL [72]100.4 5.65 149 17.3 137 0.17 86 9.18 74 18.3 73 0.55 56 6.22 66 15.0 78 0.44 103 18.8 110 28.4 97 5.38 95 43.4 120 58.2 111 5.41 145 11.3 149 42.8 166 1.19 142 9.92 70 41.5 68 0.42 34 21.8 114 52.3 107 0.48 60
Classic+CPF [82]101.3 5.59 138 17.3 137 0.16 75 9.22 75 18.3 73 0.58 62 6.00 45 14.9 71 0.40 84 18.0 46 26.8 48 5.22 48 43.5 148 58.5 159 5.38 131 11.4 156 43.0 175 1.15 134 10.1 103 41.9 87 0.45 61 22.0 140 53.1 152 0.49 84
PMF [73]102.1 5.32 86 16.6 107 0.14 48 9.67 96 19.9 109 0.45 28 6.89 141 18.2 167 0.49 122 18.4 76 27.9 73 5.21 45 43.5 148 58.4 150 5.22 73 11.0 114 40.5 89 1.27 157 9.86 62 41.8 83 0.46 71 22.1 149 53.1 152 0.50 105
Local-TV-L1 [65]104.0 5.29 80 14.6 38 0.35 179 11.5 158 21.1 134 1.23 169 6.39 86 14.9 71 0.37 69 19.0 127 27.9 73 6.64 179 43.3 97 58.3 135 5.33 108 10.9 98 39.0 39 1.58 184 9.79 50 41.6 73 0.48 100 21.3 49 51.5 54 0.53 146
RFlow [88]104.0 5.19 59 16.1 84 0.23 143 10.8 139 21.2 138 0.85 120 6.59 114 16.0 107 0.51 126 18.8 110 28.8 117 5.47 120 43.1 60 58.0 75 5.21 71 10.5 46 40.0 61 0.93 66 10.0 88 42.6 122 0.49 106 22.1 149 53.2 155 0.51 120
PWC-Net_RVC [143]105.0 5.47 118 18.4 167 0.13 38 9.99 110 20.9 130 0.53 51 6.74 128 17.5 154 0.41 91 18.3 70 28.8 117 5.25 60 43.5 148 58.3 135 5.45 160 11.2 140 41.0 108 1.22 150 9.93 74 41.8 83 0.46 71 21.3 49 51.3 49 0.51 120
TriFlow [93]105.9 5.42 107 17.0 124 0.24 149 10.9 142 21.2 138 0.91 132 6.61 116 16.8 135 0.36 62 18.9 119 29.0 127 5.28 65 43.2 85 58.2 111 5.37 125 11.0 114 40.9 102 0.95 76 9.96 82 41.7 77 0.49 106 21.7 100 52.2 102 0.47 45
EPPM w/o HM [86]106.1 5.34 96 17.3 137 0.13 38 9.73 101 20.1 113 0.53 51 7.33 167 18.7 175 0.63 153 18.5 86 29.1 135 5.33 80 43.1 60 58.0 75 5.20 65 11.0 114 41.4 125 0.96 81 10.3 124 42.3 106 0.56 149 21.8 114 52.4 118 0.49 84
Classic++ [32]106.5 5.33 93 16.0 76 0.28 161 10.2 117 20.3 117 0.69 89 6.87 135 16.6 129 0.50 123 18.7 102 27.7 72 5.64 141 43.2 85 58.0 75 5.26 90 11.0 114 40.7 97 1.34 164 9.93 74 41.9 87 0.47 91 21.7 100 52.4 118 0.50 105
CLG-TV [48]106.5 5.32 86 15.7 60 0.26 157 11.0 147 21.2 138 0.83 116 6.75 130 16.6 129 0.56 139 18.9 119 28.4 97 5.50 125 43.3 97 58.1 97 5.25 86 10.5 46 39.8 52 0.87 50 10.1 103 42.5 118 0.44 51 22.0 140 53.1 152 0.51 120
SIOF [67]106.9 5.64 146 16.5 101 0.28 161 11.3 152 21.6 151 0.91 132 6.32 75 15.9 103 0.42 93 18.7 102 28.4 97 5.36 91 43.0 48 57.9 58 5.17 55 10.7 64 40.2 69 0.95 76 10.1 103 42.4 110 0.50 118 22.2 159 53.2 155 0.53 146
Efficient-NL [60]108.0 5.54 131 17.1 129 0.16 75 9.60 90 18.9 82 0.56 59 6.99 147 15.1 82 0.75 163 18.8 110 28.2 88 5.26 61 43.1 60 57.9 58 5.25 86 11.6 162 43.4 184 1.04 102 10.1 103 42.5 118 0.48 100 22.6 172 53.8 169 0.48 60
CostFilter [40]108.8 5.44 109 17.7 152 0.13 38 9.64 93 20.1 113 0.45 28 6.96 145 19.1 178 0.47 115 18.5 86 28.9 122 5.13 38 43.6 165 58.5 159 5.32 107 11.1 135 40.5 89 1.48 176 9.94 79 42.1 100 0.45 61 21.8 114 52.6 124 0.49 84
LDOF [28]108.8 5.53 129 15.6 58 0.32 173 11.1 149 20.3 117 1.45 186 6.89 141 17.3 147 0.59 145 19.0 127 28.9 122 5.63 140 43.4 120 58.2 111 5.40 141 10.4 40 39.0 39 0.83 44 9.92 70 42.4 110 0.46 71 21.6 85 52.3 107 0.46 39
ContinualFlow_ROB [148]108.8 5.85 164 19.2 175 0.16 75 10.4 126 21.5 146 0.82 112 7.31 164 18.8 177 0.51 126 18.7 102 29.7 148 5.52 130 43.1 60 58.1 97 5.33 108 10.5 46 40.3 74 0.86 48 9.97 84 41.6 73 0.43 41 21.5 71 52.1 93 0.55 172
C-RAFT_RVC [181]109.2 6.28 177 20.0 179 0.17 86 10.1 114 21.0 132 0.69 89 6.78 132 16.5 127 0.50 123 19.2 138 30.3 156 5.49 123 43.2 85 57.9 58 5.20 65 11.0 114 41.7 145 0.94 71 10.0 88 42.2 103 0.41 30 21.6 85 51.9 81 0.51 120
Complementary OF [21]109.4 5.28 78 16.7 113 0.15 58 9.39 83 19.5 93 0.58 62 7.53 172 16.3 117 1.10 183 18.7 102 29.0 127 5.35 87 43.2 85 58.2 111 5.26 90 10.9 98 41.2 115 1.16 137 10.3 124 43.4 153 0.55 144 21.5 71 52.2 102 0.51 120
F-TV-L1 [15]109.6 5.56 133 16.0 76 0.36 183 11.4 156 21.5 146 0.94 138 6.88 138 17.0 141 0.66 156 18.7 102 27.9 73 5.79 156 42.6 35 57.8 47 5.01 39 10.6 56 39.3 45 1.02 95 10.0 88 41.9 87 0.55 144 22.0 140 52.8 137 0.51 120
OFH [38]109.9 5.49 121 16.6 107 0.25 153 10.3 123 20.2 116 0.77 104 6.88 138 17.8 160 0.36 62 18.4 76 28.9 122 5.24 56 43.1 60 58.0 75 5.26 90 10.9 98 41.5 131 1.18 140 10.3 124 43.0 142 0.58 156 21.6 85 52.1 93 0.50 105
p-harmonic [29]110.0 5.17 57 15.5 53 0.16 75 11.2 150 21.4 144 0.94 138 6.55 106 17.4 152 0.55 137 19.2 138 28.6 109 5.45 117 43.3 97 58.2 111 5.27 95 10.7 64 40.2 69 1.04 102 10.4 134 43.4 153 0.50 118 21.8 114 52.6 124 0.49 84
HBM-GC [103]110.0 5.52 125 17.1 129 0.22 135 9.64 93 19.3 89 0.59 68 5.93 39 13.2 35 0.31 28 18.8 110 28.0 77 5.83 161 44.3 188 59.2 181 5.71 186 11.5 159 43.3 182 1.32 162 9.75 42 40.6 37 0.39 26 22.0 140 52.9 144 0.50 105
TC/T-Flow [77]110.8 5.73 156 17.3 137 0.22 135 9.66 95 19.7 104 0.63 75 6.24 67 14.9 71 0.32 29 18.6 91 28.7 112 5.38 95 43.5 148 58.4 150 5.50 173 11.0 114 41.4 125 0.89 57 10.2 116 43.0 142 0.58 156 21.9 131 53.0 149 0.45 32
CBF [12]111.3 4.98 38 14.8 43 0.18 101 10.2 117 19.9 109 0.71 92 6.63 124 15.2 87 0.42 93 19.0 127 28.5 102 6.39 175 43.4 120 58.3 135 5.49 170 10.7 64 40.4 81 0.95 76 10.1 103 42.6 122 0.50 118 22.3 164 53.5 165 0.53 146
LFNet_ROB [145]111.7 5.45 112 17.6 150 0.13 38 10.4 126 21.2 138 0.73 96 6.75 130 18.1 165 0.47 115 18.4 76 28.7 112 5.27 64 43.1 60 58.0 75 5.20 65 11.1 135 41.8 148 1.10 123 10.4 134 42.7 130 0.50 118 21.7 100 52.0 86 0.60 184
Steered-L1 [116]112.1 5.12 49 16.0 76 0.17 86 9.62 92 19.5 93 0.88 127 7.15 153 15.6 97 1.00 175 19.4 148 28.5 102 6.39 175 43.5 148 58.5 159 5.19 61 10.8 84 40.8 100 1.20 144 9.95 81 42.6 122 0.52 134 21.7 100 52.6 124 0.48 60
GraphCuts [14]112.8 5.98 170 17.5 148 0.24 149 10.0 111 19.5 93 0.76 102 8.24 185 14.6 60 1.06 178 19.7 154 29.0 127 5.69 146 42.9 40 57.9 58 4.97 37 10.5 46 40.3 74 0.87 50 10.0 88 42.4 110 0.58 156 22.1 149 53.2 155 0.51 120
MLDP_OF [87]113.2 5.44 109 17.2 132 0.17 86 9.84 106 19.9 109 0.62 74 6.19 63 14.8 69 0.28 13 18.6 91 27.4 64 5.71 148 43.3 97 58.2 111 5.34 114 11.9 172 43.3 182 1.57 183 10.4 134 42.6 122 0.56 149 21.7 100 52.3 107 0.59 182
AdaConv-v1 [124]113.5 6.72 185 21.8 190 0.25 153 12.8 177 22.4 170 1.80 193 8.18 184 18.4 169 1.46 192 24.3 190 34.7 192 7.39 187 41.5 31 56.1 31 4.28 31 9.57 33 36.9 35 0.71 35 9.75 42 41.0 50 0.60 161 20.5 33 49.7 34 0.42 27
SRR-TVOF-NL [89]114.8 5.70 154 16.9 120 0.23 143 10.3 123 21.0 132 0.88 127 6.57 109 16.1 110 0.39 79 19.2 138 28.7 112 5.12 36 43.2 85 58.3 135 5.27 95 10.8 84 40.9 102 0.86 48 10.6 150 42.3 106 0.46 71 22.5 168 53.8 169 0.54 160
BlockOverlap [61]115.6 5.34 96 14.6 38 0.41 188 11.4 156 20.6 122 1.42 182 6.49 97 14.1 48 0.61 150 18.9 119 26.9 52 7.34 186 44.2 186 58.9 177 5.91 192 11.0 114 39.9 57 1.39 171 9.81 55 41.3 63 0.46 71 21.5 71 51.7 63 0.51 120
Sparse Occlusion [54]116.3 5.43 108 16.8 116 0.23 143 10.3 123 20.8 127 0.63 75 6.51 99 15.0 78 0.44 103 19.0 127 29.0 127 5.42 109 43.4 120 58.2 111 5.41 145 11.3 149 42.9 173 1.14 131 10.1 103 42.2 103 0.42 34 22.1 149 53.2 155 0.49 84
CRTflow [81]117.7 5.48 120 16.5 101 0.34 177 10.7 137 20.7 124 0.86 123 7.25 159 18.6 172 0.60 149 18.8 110 28.8 117 5.98 167 43.4 120 58.2 111 5.43 152 10.7 64 40.4 81 0.95 76 9.93 74 42.0 93 0.49 106 21.7 100 52.3 107 0.49 84
LiteFlowNet [138]118.8 5.61 140 18.9 172 0.15 58 9.94 108 20.9 130 0.65 82 6.33 79 17.5 154 0.39 79 19.2 138 30.9 169 5.94 166 43.1 60 57.9 58 5.36 122 11.3 149 42.2 157 1.06 110 10.7 153 43.5 155 0.62 165 21.2 41 51.2 45 0.54 160
MCPFlow_RVC [197]119.1 6.00 171 19.9 178 0.15 58 9.24 76 19.0 83 0.51 48 6.57 109 16.2 112 0.33 34 18.8 110 29.0 127 5.43 111 43.7 174 58.6 166 5.24 80 11.2 140 42.8 166 1.00 92 10.0 88 42.0 93 0.45 61 23.4 189 57.0 197 0.80 196
AugFNG_ROB [139]120.1 5.68 152 18.7 169 0.15 58 10.9 142 21.8 155 0.93 136 7.28 161 20.6 189 0.48 120 19.3 144 30.7 162 5.40 101 43.6 165 58.6 166 5.47 165 10.6 56 40.1 63 0.82 40 10.5 146 43.0 142 0.50 118 20.9 35 50.7 38 0.48 60
SimpleFlow [49]120.2 5.52 125 17.5 148 0.18 101 10.2 117 19.7 104 0.73 96 7.32 166 15.8 101 1.05 177 18.0 46 26.8 48 5.44 114 43.3 97 58.1 97 5.33 108 11.3 149 42.9 173 1.22 150 10.3 124 44.6 169 1.04 192 21.8 114 52.6 124 0.47 45
IAOF [50]121.3 5.97 169 16.8 116 0.29 166 14.1 192 24.8 192 1.41 181 6.05 51 16.2 112 0.61 150 20.1 162 29.5 143 5.47 120 43.0 48 57.8 47 5.19 61 10.7 64 40.3 74 0.94 71 10.4 134 43.3 150 0.46 71 22.0 140 52.8 137 0.54 160
FlowNet2 [120]121.4 6.90 187 21.5 189 0.25 153 10.6 135 20.7 124 0.82 112 7.10 150 17.3 147 0.54 133 19.4 148 31.8 178 5.57 134 43.4 120 58.3 135 5.39 133 10.7 64 40.3 74 0.90 59 10.0 88 42.0 93 0.46 71 21.6 85 51.9 81 0.51 120
Modified CLG [34]123.3 5.05 43 15.1 45 0.19 110 12.3 173 22.2 164 1.30 173 6.81 134 18.3 168 0.66 156 19.3 144 29.7 148 5.34 83 43.4 120 58.2 111 5.29 103 10.8 84 40.6 94 1.15 134 10.2 116 43.6 156 0.47 91 21.9 131 52.7 133 0.53 146
CompactFlow_ROB [155]124.2 5.67 151 19.0 173 0.14 48 10.4 126 21.6 151 0.77 104 7.21 156 19.2 179 0.46 110 19.3 144 31.0 171 5.65 143 43.2 85 58.0 75 5.24 80 11.0 114 41.8 148 0.87 50 10.6 150 43.3 150 0.49 106 21.8 114 52.3 107 0.53 146
FlowNetS+ft+v [110]124.7 5.40 104 15.5 53 0.29 166 11.7 164 21.7 153 1.62 189 6.88 138 17.1 144 0.56 139 19.0 127 29.2 137 5.73 152 43.5 148 58.4 150 5.56 179 10.5 46 39.9 57 0.95 76 10.1 103 42.9 138 0.52 134 21.8 114 52.5 122 0.48 60
LSM_FLOW_RVC [182]125.2 5.96 168 20.1 181 0.18 101 10.9 142 22.7 172 0.79 108 6.87 135 18.6 172 0.44 103 19.1 133 30.6 159 5.35 87 43.1 60 57.9 58 5.20 65 10.9 98 41.1 114 1.07 115 10.7 153 43.2 147 0.53 138 21.8 114 52.1 93 0.61 188
Occlusion-TV-L1 [63]125.6 5.32 86 16.2 93 0.28 161 11.3 152 21.9 158 0.96 143 6.60 115 16.9 138 0.58 143 19.1 133 28.9 122 5.72 150 43.4 120 58.2 111 5.24 80 10.9 98 40.3 74 1.26 156 10.9 161 42.6 122 0.81 182 21.8 114 52.4 118 0.49 84
EPMNet [131]126.8 6.85 186 22.5 191 0.21 123 10.5 131 20.3 117 0.84 119 7.10 150 17.3 147 0.54 133 19.9 155 33.4 188 5.56 133 43.4 120 58.3 135 5.39 133 11.0 114 41.6 138 0.92 62 10.0 88 42.0 93 0.46 71 21.6 85 51.8 72 0.54 160
Shiralkar [42]127.0 5.73 156 18.1 159 0.21 123 11.6 160 22.0 160 0.88 127 6.74 128 19.9 183 0.73 161 20.3 166 30.1 154 5.46 119 42.6 35 57.5 36 4.99 38 11.3 149 41.5 131 1.35 165 11.0 164 44.9 172 0.67 168 21.5 71 51.7 63 0.48 60
TCOF [69]127.1 5.56 133 16.8 116 0.17 86 11.8 165 22.1 162 1.02 151 6.09 54 15.0 78 0.30 21 19.0 127 29.4 141 5.67 145 43.4 120 58.3 135 5.17 55 11.4 156 43.1 178 1.02 95 11.0 164 43.9 159 0.48 100 23.1 184 55.1 189 0.52 136
HBpMotionGpu [43]127.1 5.80 160 16.3 95 0.42 189 13.1 180 23.8 183 1.34 176 6.32 75 14.9 71 0.38 74 19.9 155 30.4 158 5.80 157 43.1 60 58.3 135 5.39 133 11.3 149 41.0 108 1.21 147 9.94 79 41.9 87 0.43 41 22.1 149 52.9 144 0.53 146
3DFlow [133]128.4 5.58 137 17.4 143 0.16 75 9.35 80 19.1 85 0.61 73 6.93 144 15.0 78 0.44 103 18.6 91 28.4 97 5.54 132 43.4 120 58.2 111 5.40 141 12.1 179 44.7 196 1.35 165 11.3 171 44.6 169 0.57 153 22.4 166 53.7 168 0.50 105
Fusion [6]128.6 5.37 99 16.9 120 0.21 123 9.33 79 18.3 73 0.54 53 6.39 86 15.1 82 0.54 133 20.0 160 29.8 150 5.41 104 43.5 148 59.2 181 5.14 50 11.5 159 43.7 187 1.21 147 10.5 146 44.1 162 0.52 134 23.1 184 55.4 190 0.52 136
CNN-flow-warp+ref [115]129.0 4.95 36 14.4 36 0.22 135 10.9 142 21.2 138 1.23 169 7.43 169 18.0 163 0.79 166 20.9 176 29.8 150 6.84 182 43.5 148 58.3 135 5.57 180 10.7 64 40.3 74 1.22 150 10.3 124 44.4 167 0.67 168 21.6 85 52.1 93 0.47 45
Adaptive [20]129.0 5.50 123 16.7 113 0.30 168 11.8 165 22.2 164 1.02 151 6.58 113 16.5 127 0.53 132 18.6 91 28.0 77 5.60 138 43.5 148 58.3 135 5.21 71 11.0 114 41.3 121 1.09 121 10.4 134 42.8 135 0.46 71 22.2 159 53.5 165 0.54 160
BriefMatch [122]130.8 5.45 112 16.5 101 0.31 172 9.84 106 19.6 99 1.43 183 7.55 174 15.6 97 1.08 180 20.3 166 29.2 137 7.97 194 43.3 97 58.3 135 5.43 152 12.0 176 41.5 131 2.37 191 9.84 59 41.5 68 0.56 149 21.4 61 51.7 63 0.52 136
ResPWCR_ROB [140]130.9 5.54 131 17.8 154 0.20 116 10.6 135 21.5 146 0.80 111 7.77 178 17.7 159 0.44 103 19.4 148 30.7 162 5.93 163 42.7 37 57.6 38 5.10 46 12.4 188 41.7 145 2.49 192 10.9 161 42.7 130 0.58 156 21.7 100 52.3 107 0.52 136
Nguyen [33]132.6 5.63 145 15.9 68 0.23 143 13.8 186 23.8 183 1.37 178 6.89 141 18.7 175 0.59 145 20.8 175 30.8 166 5.44 114 43.1 60 58.1 97 5.14 50 10.6 56 40.4 81 0.93 66 11.9 183 45.9 179 0.73 178 22.0 140 52.8 137 0.52 136
CVENG22+RIC [199]133.0 5.44 109 16.7 113 0.22 135 10.1 114 20.6 122 0.63 75 6.62 122 17.4 152 0.44 103 19.3 144 30.6 159 5.59 135 43.5 148 58.4 150 5.51 176 11.0 114 41.7 145 1.06 110 10.4 134 43.8 158 0.56 149 21.9 131 53.0 149 0.53 146
2D-CLG [1]135.5 5.27 77 15.7 60 0.21 123 13.1 180 22.8 173 1.37 178 7.29 162 17.3 147 0.94 172 20.3 166 30.2 155 5.34 83 43.5 148 58.4 150 5.37 125 10.8 84 40.7 97 1.22 150 10.5 146 44.3 165 0.59 160 22.0 140 52.3 107 0.50 105
TV-L1-improved [17]135.6 5.26 75 16.0 76 0.28 161 11.6 160 22.0 160 1.06 159 7.21 156 16.3 117 0.79 166 18.8 110 28.5 102 5.70 147 43.5 148 58.5 159 5.22 73 11.0 114 41.5 131 1.05 108 10.4 134 44.6 169 0.74 180 22.1 149 53.2 155 0.53 146
IIOF-NLDP [129]135.9 5.65 149 17.8 154 0.15 58 10.5 131 21.5 146 0.72 95 6.98 146 15.2 87 0.42 93 19.5 151 29.3 140 6.15 171 43.1 60 58.0 75 5.20 65 12.2 183 44.1 190 1.54 180 11.9 183 49.2 195 1.34 196 22.2 159 53.0 149 0.50 105
IRR-PWC_RVC [180]135.9 6.21 175 20.0 179 0.20 116 10.4 126 21.3 143 0.85 120 7.49 171 20.5 188 0.47 115 20.1 162 32.1 179 5.45 117 43.6 165 58.6 166 5.53 177 10.9 98 41.5 131 0.96 81 10.4 134 43.1 145 0.46 71 21.7 100 52.4 118 0.49 84
SPSA-learn [13]136.1 5.45 112 15.4 49 0.25 153 11.6 160 21.4 144 1.15 165 7.65 176 16.6 129 1.26 187 20.1 162 28.2 88 5.30 69 43.3 97 58.2 111 5.42 150 10.9 98 41.0 108 1.14 131 11.6 177 50.4 197 1.71 198 22.2 159 53.3 163 0.49 84
SegOF [10]136.5 5.25 71 15.9 68 0.20 116 10.9 142 20.8 127 0.82 112 8.07 183 18.4 169 1.18 185 20.0 160 32.3 180 5.52 130 43.3 97 58.2 111 5.35 118 11.4 156 43.1 178 1.38 170 10.7 153 46.3 180 0.96 190 21.5 71 51.7 63 0.53 146
TriangleFlow [30]138.5 5.85 164 18.2 162 0.26 157 11.0 147 21.8 155 0.79 108 7.17 154 16.3 117 0.58 143 19.6 153 30.7 162 5.74 153 42.8 38 57.8 47 4.95 36 11.6 162 42.8 166 1.05 108 10.8 157 45.8 177 0.73 178 22.8 178 54.3 182 0.51 120
Black & Anandan [4]140.0 5.71 155 15.5 53 0.35 179 12.7 176 22.3 168 1.12 161 7.89 179 18.1 165 1.06 178 20.5 173 30.3 156 5.42 109 43.6 165 58.6 166 5.35 118 10.6 56 39.7 51 0.91 61 10.9 161 44.1 162 0.50 118 22.2 159 52.9 144 0.53 146
Rannacher [23]140.2 5.39 102 16.6 107 0.30 168 11.6 160 22.2 164 1.01 147 7.17 154 16.9 138 0.92 171 18.6 91 28.4 97 5.74 153 43.6 165 58.5 159 5.33 108 11.0 114 41.6 138 1.11 125 10.4 134 44.3 165 0.72 177 21.9 131 52.8 137 0.54 160
ROF-ND [105]140.2 6.15 173 16.4 97 0.14 48 10.4 126 21.1 134 0.70 91 7.09 149 15.9 103 0.40 84 20.7 174 32.9 185 5.82 159 43.4 120 58.2 111 5.37 125 11.6 162 43.4 184 1.16 137 11.6 177 46.4 181 0.55 144 22.6 172 53.8 169 0.54 160
TVL1_RVC [175]140.2 5.69 153 15.5 53 0.35 179 13.7 185 23.9 185 1.38 180 6.66 125 17.5 154 0.67 159 20.4 171 29.6 145 5.50 125 43.6 165 58.5 159 5.43 152 10.8 84 40.3 74 1.08 116 10.5 146 44.4 167 0.65 166 21.8 114 52.6 124 0.49 84
OFRF [132]142.8 6.29 178 18.2 162 0.38 185 11.8 165 22.3 168 1.17 167 6.61 116 17.3 147 0.43 99 19.2 138 29.4 141 5.31 72 43.4 120 58.4 150 5.35 118 11.7 168 42.8 166 1.28 158 10.4 134 43.2 147 0.49 106 22.0 140 53.3 163 0.51 120
Ad-TV-NDC [36]143.2 6.08 172 15.9 68 0.60 192 13.0 178 22.8 173 1.36 177 6.55 106 16.4 123 0.56 139 20.9 176 30.6 159 6.29 173 44.1 182 59.0 179 5.43 152 10.7 64 39.4 48 1.11 125 10.4 134 43.3 150 0.51 128 22.1 149 52.9 144 0.53 146
IAOF2 [51]144.6 6.17 174 18.3 166 0.30 168 12.0 168 23.3 180 0.93 136 5.90 38 16.1 110 0.42 93 20.4 171 31.2 175 5.75 155 43.7 174 58.9 177 5.39 133 11.2 140 42.0 152 1.08 116 10.3 124 42.7 130 0.48 100 22.7 175 54.2 179 0.52 136
Correlation Flow [76]144.8 5.61 140 17.8 154 0.15 58 10.8 139 21.7 153 0.82 112 6.40 89 14.8 69 0.42 93 19.1 133 29.0 127 6.04 169 43.9 178 58.6 166 6.05 194 12.0 176 43.9 188 1.29 160 11.0 164 45.3 174 0.70 174 22.5 168 54.1 177 0.51 120
Filter Flow [19]146.5 5.64 146 16.4 97 0.32 173 12.2 172 22.2 164 1.08 160 6.61 116 16.2 112 0.57 142 20.3 166 29.0 127 6.32 174 44.1 182 59.1 180 5.74 188 10.9 98 40.7 97 1.04 102 10.2 116 43.2 147 0.54 141 22.7 175 54.3 182 0.54 160
Bartels [41]147.9 5.52 125 17.2 132 0.40 187 10.0 111 20.7 124 0.94 138 6.50 98 15.8 101 0.54 133 19.9 155 30.0 153 7.79 191 44.8 192 59.2 181 6.72 197 12.8 193 42.4 159 3.06 194 10.0 88 42.0 93 0.54 141 22.1 149 53.2 155 0.54 160
Dynamic MRF [7]150.0 5.39 102 17.4 143 0.20 116 10.5 131 21.8 155 0.74 100 7.60 175 20.3 187 0.99 174 21.3 179 31.1 173 7.06 184 43.0 48 58.1 97 5.34 114 11.6 162 43.0 175 1.49 177 10.7 153 45.8 177 0.85 183 22.5 168 53.2 155 0.55 172
LocallyOriented [52]150.2 5.79 159 17.9 157 0.26 157 12.1 170 23.2 177 1.01 147 7.05 148 17.6 157 0.51 126 19.9 155 30.9 169 5.72 150 43.3 97 58.2 111 5.23 77 11.9 172 42.6 162 1.52 179 10.8 157 44.0 160 0.53 138 22.5 168 54.0 175 0.52 136
ACK-Prior [27]153.0 5.46 115 17.7 152 0.15 58 9.70 98 20.3 117 0.67 85 7.76 177 16.4 123 1.08 180 19.9 155 31.0 171 6.01 168 44.7 191 59.6 188 5.78 189 12.1 179 44.2 192 1.33 163 10.6 150 44.2 164 0.53 138 23.4 189 56.1 194 0.52 136
StereoOF-V1MT [117]154.0 5.94 167 18.8 171 0.20 116 11.3 152 22.6 171 0.94 138 7.95 180 19.6 181 1.00 175 21.6 180 30.7 162 6.76 180 43.3 97 58.3 135 5.37 125 12.1 179 42.6 162 1.82 188 11.6 177 46.7 184 0.90 186 21.8 114 51.8 72 0.50 105
StereoFlow [44]156.7 10.4 198 27.1 198 0.35 179 16.3 197 28.4 198 1.03 154 6.55 106 16.8 135 0.50 123 18.8 110 28.2 88 5.38 95 45.7 197 62.1 197 5.58 181 13.6 197 50.3 198 1.28 158 10.0 88 42.4 110 0.49 106 23.0 180 55.5 191 0.56 177
TI-DOFE [24]156.9 6.39 179 18.7 169 0.36 183 14.8 193 25.5 195 1.66 190 7.45 170 20.2 185 0.78 165 22.8 187 32.5 182 6.04 169 43.2 85 58.4 150 5.17 55 10.9 98 40.4 81 0.92 62 11.2 169 45.6 176 0.65 166 23.2 186 54.2 179 0.65 191
2bit-BM-tele [96]157.4 5.61 140 15.9 68 0.50 190 11.5 158 21.9 158 1.04 156 6.57 109 15.1 82 0.79 166 20.1 162 29.8 150 7.50 188 44.8 192 59.6 188 6.26 195 12.2 183 42.8 166 2.11 190 11.2 169 49.2 195 1.26 194 21.8 114 52.1 93 0.55 172
UnFlow [127]157.9 6.39 179 20.9 183 0.21 123 13.0 178 24.4 191 1.15 165 8.06 182 21.1 190 0.82 169 19.2 138 29.6 145 5.64 141 43.1 60 58.0 75 5.40 141 11.8 170 42.8 166 1.36 168 11.0 164 42.4 110 0.70 174 24.3 197 54.8 187 0.70 193
Horn & Schunck [3]158.5 5.81 161 17.3 137 0.21 123 13.1 180 23.5 181 1.26 172 8.03 181 19.7 182 1.08 180 22.6 185 32.7 184 5.59 135 43.6 165 58.7 172 5.39 133 10.9 98 40.6 94 1.02 95 11.7 181 46.5 182 0.60 161 22.8 178 53.9 173 0.55 172
WRT [146]161.5 5.83 162 18.2 162 0.17 86 11.3 152 21.5 146 0.92 135 8.29 186 15.2 87 1.12 184 19.5 151 29.6 145 5.93 163 43.6 165 58.7 172 5.31 104 12.4 188 45.8 197 1.43 174 12.1 186 51.8 198 1.66 197 22.6 172 54.6 185 0.58 180
WOLF_ROB [144]170.9 6.71 184 21.0 184 0.32 173 12.5 174 23.2 177 1.12 161 7.54 173 17.6 157 0.65 155 20.3 166 33.1 187 6.43 177 43.6 165 58.8 174 5.47 165 11.9 172 42.8 166 1.56 181 12.1 186 46.5 182 0.71 176 22.1 149 52.8 137 0.58 180
NL-TV-NCC [25]172.6 6.44 181 20.3 182 0.24 149 10.7 137 22.1 162 0.68 88 7.38 168 17.2 145 0.59 145 22.2 183 34.7 192 6.82 181 45.5 196 60.2 195 6.68 196 12.3 187 44.6 194 1.19 142 14.4 196 48.1 192 0.67 168 24.0 196 56.4 195 0.55 172
Adaptive flow [45]173.6 7.18 191 19.2 175 0.69 193 15.0 194 25.0 193 2.11 195 7.29 162 16.7 133 0.87 170 22.6 185 31.3 177 7.85 193 44.8 192 60.2 195 5.63 183 11.7 168 43.4 184 1.36 168 10.4 134 43.7 157 0.57 153 23.0 180 54.7 186 0.50 105
HCIC-L [97]173.8 8.84 197 25.2 196 1.06 197 14.0 190 24.1 188 1.43 183 9.42 192 19.3 180 0.69 160 24.3 190 34.1 190 6.48 178 45.1 195 60.1 193 5.86 191 12.1 179 44.1 190 1.06 110 10.2 116 42.6 122 0.51 128 23.6 192 56.0 193 0.51 120
SILK [80]174.0 6.21 175 19.3 177 0.39 186 13.8 186 24.0 186 1.73 192 8.85 189 20.2 185 1.41 189 21.8 181 31.1 173 7.10 185 43.5 148 58.5 159 5.45 160 11.9 172 41.4 125 2.03 189 10.8 157 45.5 175 0.77 181 22.4 166 53.2 155 0.60 184
H+S_RVC [176]175.8 6.49 182 21.0 184 0.14 48 13.5 183 23.2 177 1.23 169 9.69 194 25.4 195 1.25 186 26.6 196 32.3 180 6.22 172 43.9 178 59.3 185 5.49 170 11.8 170 43.0 175 1.23 155 12.3 191 47.9 191 0.92 188 23.8 195 53.9 173 0.59 182
Learning Flow [11]177.5 5.91 166 18.6 168 0.30 168 12.0 168 22.9 175 1.00 145 8.30 187 20.0 184 1.33 188 21.9 182 32.9 185 6.94 183 44.5 190 59.7 191 5.97 193 11.5 159 42.6 162 1.35 165 11.3 171 46.8 185 0.69 172 23.7 193 55.9 192 0.62 189
GroupFlow [9]178.7 7.04 189 22.5 191 0.28 161 12.5 174 24.0 186 1.13 163 9.10 190 22.0 192 1.45 190 21.0 178 33.6 189 5.93 163 44.1 182 59.3 185 5.50 173 12.2 183 44.4 193 1.42 173 11.1 168 45.2 173 0.61 164 22.7 175 54.1 177 0.56 177
SLK [47]180.1 6.55 183 21.1 187 0.32 173 13.5 183 23.1 176 1.44 185 9.16 191 21.2 191 1.49 194 24.9 192 34.2 191 7.81 192 43.5 148 58.8 174 5.34 114 12.2 183 43.1 178 1.45 175 11.9 183 48.9 194 0.96 190 23.0 180 54.0 175 0.64 190
Heeger++ [102]182.4 7.79 195 25.2 196 0.17 86 13.9 189 24.2 189 1.33 175 11.8 196 28.7 197 1.49 194 23.4 188 30.8 166 7.63 189 44.4 189 59.9 192 5.62 182 12.6 192 43.1 178 1.77 187 12.6 192 46.9 186 0.87 185 23.2 186 53.5 165 0.60 184
FFV1MT [104]182.8 6.93 188 22.8 193 0.24 149 14.0 190 23.5 181 1.48 187 11.2 195 27.7 196 1.52 196 23.4 188 30.8 166 7.63 189 44.0 180 59.2 181 5.69 185 12.0 176 41.6 138 1.56 181 12.1 186 47.3 189 0.95 189 23.4 189 54.2 179 0.79 195
FOLKI [16]186.2 7.10 190 21.1 187 0.94 196 15.3 195 25.5 195 2.28 196 8.49 188 22.2 193 1.47 193 26.3 194 35.2 194 10.6 197 44.0 180 59.6 188 5.54 178 11.6 162 41.8 148 1.49 177 11.4 174 47.7 190 0.90 186 23.3 188 54.9 188 0.67 192
Pyramid LK [2]187.6 7.19 192 21.0 184 0.93 195 16.2 196 25.1 194 2.91 197 14.0 197 18.5 171 2.57 197 32.5 198 46.2 198 13.7 198 44.2 186 60.1 193 5.48 168 11.6 162 42.5 161 1.40 172 11.4 174 47.2 188 1.28 195 23.7 193 56.7 196 1.08 197
PGAM+LK [55]188.4 7.51 194 23.5 195 0.73 194 13.8 186 24.2 189 1.92 194 9.44 193 22.7 194 1.45 190 26.4 195 36.9 195 10.5 196 44.1 182 59.5 187 5.72 187 12.4 188 44.0 189 1.75 186 11.3 171 47.0 187 0.68 171 23.0 180 54.5 184 0.76 194
Periodicity [79]195.5 8.05 196 23.2 194 1.34 198 20.5 198 27.4 197 3.39 198 15.2 198 30.5 198 4.22 198 26.2 193 43.5 197 9.47 195 46.4 198 62.7 198 6.92 198 13.7 198 44.6 194 2.88 193 11.4 174 48.3 193 1.18 193 25.7 198 59.2 198 1.29 198
AVG_FLOW_ROB [137]199.0 30.2 199 60.4 199 6.56 199 42.6 199 49.8 199 9.03 199 34.7 199 42.2 199 9.09 199 57.3 199 72.3 199 20.9 199 51.6 199 69.0 199 7.96 199 25.2 199 71.8 199 4.67 199 39.2 199 64.3 199 3.36 199 43.7 199 66.4 199 8.60 199
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.