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        
R2.5
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]4.8 7.52 1 20.8 1 0.72 2 17.0 1 25.2 2 1.54 2 3.53 1 10.6 3 0.64 3 54.4 4 60.3 4 34.6 5 72.3 2 82.0 2 31.2 5 29.2 3 55.2 4 18.5 6 31.7 26 59.7 14 3.90 8 35.2 7 71.4 6 2.15 4
SoftSplat [169]4.9 8.60 3 23.7 4 1.22 12 18.0 3 27.0 3 1.73 3 3.66 2 10.3 2 0.59 1 53.3 2 59.3 2 33.7 2 73.6 5 83.2 7 31.5 6 29.5 4 56.5 6 18.4 5 30.8 8 60.0 16 3.83 3 35.2 7 71.9 8 2.07 3
EAFI [186]6.7 8.16 2 22.3 2 0.84 5 17.7 2 24.6 1 1.43 1 4.46 5 9.75 1 0.60 2 52.6 1 57.9 1 33.0 1 74.5 16 84.7 23 29.9 1 31.1 13 60.4 17 18.3 3 31.3 12 59.3 12 3.84 4 36.8 15 74.1 15 2.19 6
IFRNet [193]9.4 8.96 6 23.3 3 1.29 14 18.9 4 27.3 4 2.39 7 3.98 3 11.1 4 0.66 4 55.3 6 60.5 6 37.8 17 74.5 16 84.1 17 35.0 19 30.8 10 57.2 9 20.0 21 31.1 9 59.2 11 3.84 4 36.0 11 72.8 10 2.34 11
SepConv++ [185]9.5 10.9 18 30.2 20 1.67 34 20.6 10 31.1 11 2.66 23 6.24 12 15.6 11 1.39 13 57.3 16 63.0 15 36.6 14 73.2 4 82.5 3 32.6 11 27.6 1 51.0 1 17.8 2 29.5 1 55.7 3 3.68 1 31.7 1 66.0 1 1.90 1
EDSC [173]13.2 10.1 13 28.2 15 1.11 9 20.5 8 31.0 9 2.77 49 7.15 16 16.0 14 1.44 19 57.3 16 63.0 15 37.3 16 73.8 10 83.1 5 34.3 18 30.2 6 56.9 8 19.2 13 30.1 5 56.4 5 4.16 16 35.2 7 71.8 7 2.55 18
FGME [158]15.5 8.82 5 23.7 4 0.69 1 21.6 13 30.8 7 3.50 133 8.22 21 16.0 14 1.51 33 57.2 15 61.4 8 40.0 25 72.2 1 81.7 1 32.2 9 30.6 8 53.5 2 21.1 24 30.7 7 54.6 1 4.26 18 33.3 3 68.0 3 2.54 17
DistillNet [184]20.4 9.46 8 26.7 8 1.01 6 19.5 6 29.3 6 2.01 4 4.11 4 11.6 5 0.78 5 54.2 3 60.4 5 34.1 3 73.6 5 83.6 10 30.8 2 31.5 15 61.2 23 18.8 9 34.1 180 63.2 30 3.87 7 39.5 106 77.0 25 2.43 15
AdaCoF [165]21.6 11.9 25 31.3 26 2.21 136 21.9 14 32.2 16 2.99 87 10.7 26 19.7 24 1.47 26 57.0 14 62.4 11 36.3 12 76.0 26 84.7 23 37.2 25 29.1 2 55.3 5 18.3 3 29.6 2 56.1 4 3.71 2 33.7 4 70.4 4 2.02 2
STSR [170]22.7 9.47 9 27.4 11 1.22 12 19.4 5 29.2 5 2.25 5 8.48 22 18.7 22 1.28 11 55.7 7 61.4 8 37.9 18 76.7 28 86.2 29 36.1 23 32.9 24 62.4 27 21.0 23 33.2 156 62.4 24 4.27 19 37.5 16 77.0 25 2.48 16
DSepConv [162]22.9 10.9 18 30.0 19 1.48 16 23.3 23 34.3 25 3.74 139 9.22 24 18.6 21 1.56 46 58.8 22 64.3 22 38.2 20 74.2 12 83.3 8 35.8 22 30.6 8 56.8 7 19.8 19 30.4 6 56.4 5 4.36 22 36.3 12 73.3 12 2.69 22
TC-GAN [166]26.2 10.8 17 30.3 21 1.87 87 22.7 20 34.3 25 3.38 123 6.03 10 15.8 12 1.16 8 56.2 12 62.8 14 35.5 8 74.3 13 83.9 14 33.5 13 31.5 15 60.4 17 19.5 16 32.1 85 62.6 27 3.97 13 38.6 24 77.2 27 2.31 7
MV_VFI [183]26.3 10.9 18 30.4 23 1.86 81 22.7 20 34.2 24 3.39 124 6.05 11 15.8 12 1.15 7 56.1 11 62.7 13 35.5 8 74.3 13 83.9 14 33.7 15 31.6 18 60.3 16 19.7 18 32.1 85 62.5 26 3.96 11 38.7 28 77.3 29 2.31 7
DAIN [152]28.2 11.1 22 30.7 24 2.01 110 23.2 22 34.6 27 3.46 132 6.24 12 16.0 14 1.19 9 56.0 10 63.0 15 35.4 7 74.5 16 84.0 16 34.1 17 31.5 15 60.4 17 19.6 17 32.0 70 62.4 24 3.96 11 38.7 28 77.3 29 2.38 14
BMBC [171]28.3 11.6 23 28.6 16 1.73 53 22.5 18 31.6 14 3.44 130 17.4 34 27.0 31 2.50 166 55.7 7 61.0 7 35.8 10 73.6 5 83.1 5 31.5 6 30.4 7 57.8 11 19.0 10 32.1 85 59.4 13 3.90 8 34.7 5 71.0 5 2.34 11
ProBoost-Net [191]29.2 9.66 10 27.3 10 0.79 3 22.4 16 32.4 17 3.10 101 7.83 19 16.9 20 1.45 22 58.9 28 63.7 19 42.3 114 75.7 23 84.5 20 38.9 27 33.8 27 60.1 15 23.2 27 31.2 10 58.2 8 4.76 105 36.6 13 73.2 11 2.98 35
IDIAL [192]29.6 10.4 16 28.9 17 1.03 7 22.2 15 31.9 15 2.27 6 5.36 7 13.0 9 1.25 10 56.5 13 62.4 11 35.3 6 73.6 5 83.5 9 32.2 9 32.0 20 60.7 22 18.7 8 38.4 193 62.2 21 4.33 21 42.6 193 76.4 20 3.07 58
STAR-Net [164]30.8 10.2 15 27.0 9 1.62 26 22.4 16 31.0 9 3.18 109 6.65 14 11.8 6 1.35 12 55.9 9 61.8 10 34.3 4 72.8 3 82.8 4 30.8 2 31.2 14 59.3 14 18.6 7 38.9 195 61.0 17 4.00 14 42.1 190 75.9 19 2.61 20
GDCN [172]31.3 11.0 21 30.8 25 1.29 14 25.8 109 36.7 52 3.33 118 5.80 9 14.9 10 1.67 75 58.8 22 64.0 20 36.6 14 74.5 16 83.8 13 35.7 21 31.6 18 59.1 13 20.6 22 32.2 107 59.7 14 4.23 17 35.0 6 72.2 9 2.31 7
MEMC-Net+ [160]34.9 12.4 28 32.3 31 2.16 125 24.1 26 34.1 22 3.39 124 7.37 17 16.6 19 1.59 54 57.6 19 63.0 15 35.8 10 75.4 21 84.9 25 33.9 16 32.2 21 62.7 30 19.2 13 32.6 136 62.2 21 3.92 10 38.3 20 77.2 27 2.31 7
DAI [168]35.3 10.1 13 25.7 7 2.27 141 21.1 12 30.8 7 3.41 128 4.76 6 12.0 7 1.10 6 54.4 4 59.8 3 36.4 13 75.8 25 85.4 27 32.6 11 32.3 22 61.8 25 19.3 15 34.3 183 61.5 18 4.00 14 39.7 123 76.4 20 2.55 18
ADC [161]35.9 13.4 37 34.4 32 2.33 145 24.4 33 34.6 27 4.50 155 12.7 28 22.5 27 1.73 86 59.8 104 65.4 28 38.1 19 75.6 22 84.5 20 36.4 24 30.1 5 57.2 9 19.1 11 29.7 3 56.6 7 3.84 4 35.9 10 74.0 13 2.36 13
MAF-net [163]36.6 8.73 4 25.0 6 0.81 4 20.9 11 31.1 11 2.87 70 6.82 15 16.4 18 1.74 93 59.1 41 64.6 23 42.5 134 76.9 29 85.6 28 38.9 27 33.7 26 60.6 21 22.8 26 31.5 14 58.6 9 4.90 143 36.7 14 74.0 13 3.19 98
NNF-Local [75]41.5 13.4 37 36.1 42 1.56 19 24.2 27 35.7 34 2.60 13 18.4 54 30.4 37 1.43 16 59.2 48 68.4 91 41.6 48 79.1 45 87.3 38 43.1 59 36.4 49 66.6 53 25.0 60 31.7 26 63.5 37 4.66 44 38.9 36 78.4 43 3.01 41
PH-Flow [99]44.7 13.7 59 37.1 73 1.77 60 24.3 30 35.5 33 2.58 10 18.5 59 30.6 41 1.54 40 58.8 22 66.8 33 41.6 48 79.0 38 87.2 36 42.9 44 36.3 39 67.1 102 24.6 39 31.6 15 63.7 47 4.64 35 39.0 43 78.6 53 3.10 73
NN-field [71]46.0 13.5 43 36.9 66 1.67 34 24.2 27 35.4 32 2.54 8 18.7 76 30.6 41 1.52 36 59.3 63 68.5 96 41.7 57 79.1 45 87.3 38 43.2 78 36.4 49 66.2 38 25.0 60 31.6 15 63.6 40 4.64 35 38.9 36 78.1 38 3.05 52
MS_RAFT+_RVC [195]46.6 13.6 52 36.3 49 1.85 76 24.8 55 37.7 69 2.68 25 18.4 54 30.4 37 1.45 22 59.0 36 67.4 45 41.5 40 79.3 98 87.3 38 43.5 123 36.3 39 65.9 37 24.9 49 31.4 13 62.8 28 4.66 44 38.6 24 78.3 41 2.85 25
MDP-Flow2 [68]47.7 13.3 33 35.1 35 1.62 26 24.6 41 36.5 43 2.63 19 18.5 59 30.5 39 1.42 15 59.0 36 67.8 60 41.4 30 79.1 45 87.3 38 43.4 106 36.5 56 66.4 44 25.0 60 32.0 70 63.9 55 4.64 35 39.3 77 78.7 60 3.08 63
CoT-AMFlow [174]49.0 13.3 33 35.0 33 1.63 31 24.6 41 36.5 43 2.66 23 18.6 70 30.9 48 1.43 16 58.9 28 67.5 50 41.4 30 79.2 68 87.3 38 43.5 123 36.5 56 66.6 53 25.0 60 31.9 54 63.8 49 4.63 30 39.2 68 78.8 67 3.08 63
PMMST [112]49.2 13.4 37 35.0 33 1.70 44 25.1 68 37.1 59 2.73 35 18.5 59 30.5 39 1.39 13 58.9 28 67.4 45 41.5 40 79.2 68 87.4 48 43.4 106 36.3 39 66.2 38 24.9 49 31.8 39 63.8 49 4.67 49 39.2 68 78.7 60 3.09 69
COFM [59]50.0 13.6 52 36.0 40 1.89 90 24.6 41 36.4 41 2.71 31 18.5 59 30.3 35 1.59 54 58.8 22 66.8 33 41.1 28 79.0 38 87.4 48 42.6 38 35.8 32 67.2 112 24.1 29 31.2 10 61.6 19 4.89 141 38.5 22 78.1 38 3.34 146
FeFlow [167]50.8 9.85 12 27.9 13 1.17 11 22.5 18 33.7 20 3.61 135 7.73 18 16.2 17 1.94 124 58.5 20 64.7 24 38.2 20 73.6 5 83.6 10 32.1 8 33.0 25 62.0 26 19.9 20 37.0 190 62.1 20 4.86 136 41.1 180 76.7 23 3.33 144
Layers++ [37]51.2 14.0 95 37.5 85 1.91 94 24.3 30 35.3 31 2.75 40 18.3 52 31.0 53 1.56 46 59.2 48 67.5 50 41.7 57 79.2 68 87.4 48 43.1 59 36.4 49 66.5 50 25.0 60 31.6 15 63.2 30 4.60 25 38.7 28 77.7 35 3.12 80
AGIF+OF [84]52.2 13.9 86 37.5 85 1.67 34 24.6 41 36.5 43 2.68 25 18.1 47 31.0 53 1.61 62 58.9 28 66.9 35 41.4 30 79.2 68 87.5 82 43.1 59 36.6 69 67.2 112 25.0 60 31.8 39 63.6 40 4.60 25 39.0 43 78.6 53 2.98 35
HAST [107]53.2 13.7 59 36.2 47 1.93 101 24.7 50 37.0 57 2.77 49 18.8 79 32.2 84 1.66 74 59.1 41 67.9 68 41.4 30 79.0 38 87.4 48 42.6 38 36.3 39 66.9 78 24.6 39 31.6 15 63.3 33 4.71 68 39.0 43 78.4 43 3.06 55
nLayers [57]53.4 13.9 86 36.7 61 1.85 76 24.5 36 36.1 38 2.76 43 17.7 38 30.0 34 1.44 19 59.2 48 67.6 53 41.6 48 79.3 98 87.5 82 43.3 88 36.4 49 66.8 71 25.1 78 31.7 26 63.2 30 4.72 75 38.7 28 77.6 33 3.03 44
Sparse-NonSparse [56]53.5 13.8 74 37.3 78 1.81 65 24.4 33 36.0 37 2.61 14 18.0 45 31.2 59 1.52 36 59.0 36 67.1 40 42.0 87 79.2 68 87.4 48 43.1 59 36.7 90 66.7 60 25.3 110 31.7 26 63.6 40 4.63 30 38.9 36 78.5 50 3.08 63
FRUCnet [153]57.0 14.5 142 31.5 29 5.94 192 24.5 36 34.1 22 5.10 170 10.4 25 20.2 25 2.68 171 61.6 176 66.9 35 39.4 23 74.3 13 83.7 12 33.5 13 30.8 10 58.8 12 19.1 11 33.3 160 58.8 10 4.44 23 37.7 18 74.6 16 2.74 23
CyclicGen [149]57.4 13.7 59 31.4 28 4.62 187 26.2 124 34.0 21 12.3 197 13.8 30 27.5 32 2.63 170 61.2 168 65.1 25 44.0 172 76.0 26 84.3 19 39.2 29 32.3 22 53.7 3 24.3 32 29.7 3 55.6 2 4.29 20 31.7 1 66.4 2 2.16 5
ProbFlowFields [126]57.6 13.5 43 36.6 55 1.82 68 24.4 33 36.4 41 2.68 25 18.5 59 31.2 59 1.49 30 59.2 48 67.2 41 42.1 93 79.3 98 87.5 82 43.6 145 36.5 56 67.0 89 25.2 90 31.6 15 63.5 37 4.64 35 39.0 43 78.4 43 3.06 55
2DHMM-SAS [90]58.6 14.1 105 38.9 137 1.82 68 25.5 93 38.0 78 2.77 49 17.2 32 30.9 48 1.56 46 58.9 28 66.5 30 41.7 57 79.1 45 87.4 48 42.9 44 36.5 56 66.6 53 24.9 49 31.7 26 63.9 55 4.68 57 39.2 68 79.0 76 3.07 58
OFLAF [78]58.8 13.5 43 36.1 42 1.62 26 24.3 30 35.8 35 2.62 18 18.7 76 31.5 68 1.47 26 59.1 41 67.8 60 41.2 29 79.3 98 87.4 48 43.4 106 36.6 69 67.4 129 25.0 60 31.9 54 64.3 69 4.79 115 38.9 36 78.7 60 3.10 73
LSM [39]59.3 13.9 86 38.0 105 1.78 62 24.6 41 36.5 43 2.61 14 18.1 47 32.0 78 1.55 44 59.2 48 67.6 53 42.1 93 79.2 68 87.4 48 43.1 59 36.7 90 66.9 78 25.3 110 31.7 26 63.6 40 4.65 43 38.9 36 78.6 53 3.07 58
FMOF [92]61.1 14.2 115 38.6 122 1.91 94 24.5 36 36.2 39 2.70 30 18.4 54 31.2 59 1.77 100 59.5 77 68.0 72 41.5 40 79.2 68 87.4 48 43.1 59 36.6 69 66.8 71 25.0 60 31.6 15 63.3 33 4.61 28 39.1 55 78.4 43 3.11 79
SepConv-v1 [125]62.2 9.23 7 28.0 14 1.08 8 20.5 8 32.4 17 3.35 119 8.95 23 20.5 26 2.08 138 60.8 155 66.9 35 44.2 174 79.1 45 87.1 34 43.2 78 35.6 30 62.4 27 25.1 78 32.2 107 62.3 23 5.34 178 37.6 17 76.4 20 3.28 133
CombBMOF [111]63.3 13.6 52 36.4 52 1.71 47 24.5 36 36.9 55 2.58 10 18.1 47 31.5 68 1.81 109 59.5 77 68.2 79 41.6 48 79.1 45 87.3 38 43.0 51 36.8 104 66.5 50 25.0 60 33.9 176 65.2 131 4.68 57 39.1 55 78.4 43 2.92 29
ComponentFusion [94]63.6 13.4 37 36.1 42 1.72 51 24.6 41 36.8 53 2.57 9 18.9 89 32.9 99 1.69 78 59.1 41 67.8 60 41.4 30 79.2 68 87.4 48 43.6 145 36.5 56 66.3 40 25.1 78 32.0 70 64.8 98 4.76 105 39.1 55 78.7 60 3.10 73
MPRN [151]64.3 12.4 28 32.0 30 1.81 65 26.3 127 36.9 55 3.69 136 21.6 187 37.6 182 2.47 164 58.8 22 65.1 25 40.0 25 78.3 30 86.6 30 41.3 30 35.8 32 63.1 31 24.8 46 32.8 145 63.8 49 4.48 24 38.5 22 78.0 37 2.68 21
IROF++ [58]64.4 13.8 74 37.8 97 1.72 51 24.6 41 36.6 49 2.61 14 18.6 70 31.3 64 1.64 70 58.8 22 66.7 32 41.8 67 79.0 38 87.3 38 42.7 41 36.5 56 66.6 53 25.0 60 32.0 70 65.0 109 4.74 92 39.5 106 79.2 94 3.30 137
GMFlow_RVC [196]65.1 13.3 33 36.7 61 1.71 47 24.8 55 37.8 70 2.71 31 18.5 59 31.2 59 1.46 24 59.2 48 68.6 108 41.9 74 79.4 141 87.5 82 43.5 123 36.3 39 66.6 53 24.7 44 32.1 85 64.4 80 4.75 99 39.1 55 78.7 60 2.94 32
RAFT-it [194]65.1 13.2 31 35.7 36 1.61 21 24.5 36 36.8 53 2.58 10 18.5 59 31.0 53 1.46 24 59.2 48 68.3 86 41.5 40 79.3 98 87.5 82 43.4 106 41.3 193 66.6 53 31.9 194 31.7 26 63.6 40 4.69 60 39.4 92 79.2 94 2.91 28
OFRI [154]66.2 11.9 25 29.6 18 2.70 160 24.0 25 33.6 19 4.57 160 5.54 8 12.5 8 1.52 36 57.5 18 64.0 20 38.7 22 74.6 20 84.2 18 35.1 20 34.0 28 62.6 29 21.3 25 43.5 198 65.4 137 5.73 191 43.3 196 76.7 23 3.87 184
Ramp [62]66.9 14.1 105 38.7 127 1.92 99 24.6 41 36.6 49 2.69 28 17.9 42 31.0 53 1.47 26 58.9 28 67.0 39 41.9 74 79.2 68 87.5 82 43.1 59 37.0 124 67.4 129 25.5 127 31.6 15 63.5 37 4.63 30 39.1 55 78.9 71 3.19 98
S2F-IF [121]68.6 13.5 43 36.6 55 1.70 44 24.9 61 37.9 74 2.77 49 18.8 79 32.7 95 1.54 40 59.1 41 67.7 57 41.6 48 79.3 98 87.5 82 43.3 88 36.5 56 67.1 102 25.0 60 31.9 54 64.7 93 4.74 92 39.3 77 79.1 86 3.10 73
RAFT-it+_RVC [198]68.8 13.1 30 35.7 36 1.54 17 24.8 55 37.8 70 2.61 14 18.8 79 32.5 92 1.48 29 59.2 48 68.6 108 41.4 30 79.3 98 87.5 82 43.4 106 39.6 187 67.5 138 29.5 190 31.7 26 64.0 62 4.72 75 38.4 21 77.5 32 2.86 26
PRAFlow_RVC [177]69.2 13.5 43 36.3 49 1.61 21 24.9 61 37.6 66 2.73 35 18.4 54 31.2 59 1.43 16 59.5 77 68.8 123 42.4 127 79.3 98 87.4 48 43.5 123 36.4 49 65.8 36 25.2 90 31.6 15 63.9 55 4.73 81 40.0 143 79.4 111 3.13 82
TV-L1-MCT [64]69.6 14.5 142 39.7 163 1.86 81 25.2 73 37.8 70 2.78 53 17.3 33 31.1 58 1.59 54 58.9 28 66.6 31 41.6 48 79.1 45 87.4 48 42.9 44 36.8 104 66.4 44 25.6 134 31.8 39 64.0 62 4.73 81 39.1 55 79.0 76 3.20 105
RAFT-TF_RVC [179]69.8 13.3 33 36.2 47 1.54 17 24.7 50 37.5 65 2.74 39 18.6 70 31.8 72 1.59 54 59.5 77 69.0 134 41.9 74 79.3 98 87.5 82 43.3 88 41.7 194 66.9 78 31.8 193 31.7 26 63.8 49 4.66 44 38.7 28 77.9 36 2.90 27
FlowFields+ [128]70.8 13.5 43 37.0 70 1.69 43 25.0 65 38.2 86 2.78 53 18.9 89 33.3 111 1.55 44 59.1 41 67.6 53 41.9 74 79.3 98 87.5 82 43.3 88 36.6 69 67.2 112 25.1 78 31.8 39 64.5 84 4.67 49 39.3 77 79.2 94 3.07 58
VCN_RVC [178]71.1 13.7 59 37.7 95 1.68 39 25.1 68 38.2 86 2.69 28 19.1 111 35.1 156 1.64 70 59.3 63 68.5 96 42.2 106 79.1 45 87.4 48 43.0 51 36.3 39 66.7 60 24.5 36 32.3 116 64.8 98 4.77 110 39.0 43 78.5 50 2.95 33
RNLOD-Flow [119]71.5 13.9 86 37.9 102 1.86 81 25.2 73 37.9 74 2.78 53 19.0 97 32.1 80 1.78 102 59.2 48 67.8 60 41.5 40 79.1 45 87.4 48 43.1 59 36.7 90 66.8 71 25.2 90 31.9 54 64.2 66 4.75 99 39.2 68 79.0 76 3.06 55
FC-2Layers-FF [74]71.6 14.0 95 38.6 122 1.84 72 24.2 27 35.1 29 2.82 63 17.9 42 31.3 64 1.51 33 59.3 63 67.7 57 42.1 93 79.3 98 87.6 127 43.3 88 36.7 90 67.4 129 25.3 110 31.6 15 63.6 40 4.67 49 39.1 55 78.7 60 3.19 98
Classic+NL [31]71.8 14.2 115 38.8 131 1.98 105 24.6 41 36.5 43 2.65 21 17.7 38 30.9 48 1.51 33 59.2 48 67.5 50 42.2 106 79.2 68 87.5 82 43.3 88 37.0 124 67.1 102 25.5 127 31.7 26 63.6 40 4.67 49 39.2 68 79.0 76 3.18 95
CtxSyn [134]72.8 9.68 11 27.4 11 1.15 10 20.4 7 31.4 13 2.64 20 8.05 20 19.1 23 1.57 51 58.6 21 65.2 27 42.5 134 79.0 38 87.1 34 43.0 51 37.9 163 65.3 34 25.7 145 38.4 193 67.7 174 5.17 167 42.3 191 78.4 43 3.48 167
Classic+CPF [82]73.1 14.1 105 38.3 116 1.74 55 24.9 61 37.1 59 2.73 35 17.6 37 31.4 66 1.60 60 59.0 36 67.3 43 41.4 30 79.3 98 87.6 127 43.3 88 36.9 112 67.9 160 25.2 90 31.9 54 64.3 69 4.64 35 39.3 77 79.2 94 3.04 47
FlowFields [108]74.1 13.6 52 37.1 73 1.74 55 25.0 65 38.1 79 2.75 40 18.8 79 33.2 108 1.53 39 59.4 71 68.0 72 42.3 114 79.3 98 87.5 82 43.2 78 36.5 56 67.0 89 25.0 60 31.8 39 64.7 93 4.69 60 39.4 92 79.3 103 3.13 82
EAI-Flow [147]75.4 13.7 59 36.3 49 1.91 94 25.7 106 39.1 111 3.01 89 19.0 97 33.4 113 1.67 75 58.9 28 67.2 41 41.4 30 79.2 68 87.3 38 43.0 51 36.9 112 66.7 60 25.2 90 32.0 70 65.0 109 4.78 112 39.3 77 79.1 86 3.03 44
HCFN [157]76.7 13.2 31 35.8 39 1.61 21 25.2 73 38.7 102 2.73 35 18.8 79 33.0 103 1.59 54 59.3 63 68.1 78 42.3 114 79.1 45 87.4 48 42.9 44 40.0 190 66.8 71 29.9 191 32.2 107 64.9 105 4.74 92 39.1 55 78.6 53 3.04 47
NNF-EAC [101]77.3 14.2 115 37.3 78 2.09 120 25.3 81 37.6 66 2.76 43 18.9 89 30.6 41 1.61 62 59.8 104 68.5 96 43.3 163 79.1 45 87.3 38 43.1 59 36.5 56 66.5 50 25.0 60 32.1 85 64.3 69 4.73 81 39.4 92 79.0 76 3.14 86
LME [70]77.8 13.5 43 36.1 42 1.62 26 25.3 81 37.8 70 3.44 130 19.0 97 32.8 97 1.63 68 59.0 36 67.8 60 41.5 40 79.7 182 87.9 176 44.4 181 36.5 56 67.0 89 24.9 49 32.0 70 64.2 66 4.66 44 39.0 43 78.6 53 3.09 69
S2D-Matching [83]78.3 14.2 115 38.9 137 1.96 102 25.3 81 37.9 74 2.76 43 17.5 35 31.0 53 1.60 60 59.3 63 67.4 45 42.8 145 79.2 68 87.5 82 43.2 78 36.9 112 67.3 122 25.4 121 31.8 39 63.8 49 4.64 35 39.1 55 78.6 53 3.21 112
WLIF-Flow [91]78.6 13.8 74 37.4 82 1.73 53 24.9 61 37.1 59 2.81 60 18.5 59 30.9 48 1.49 30 59.4 71 67.8 60 42.5 134 79.2 68 87.4 48 43.8 172 37.2 139 67.5 138 25.9 152 31.8 39 63.9 55 4.64 35 39.4 92 78.9 71 3.14 86
FESL [72]81.2 14.4 137 39.1 144 1.83 70 25.0 65 37.4 63 2.76 43 18.2 51 31.6 70 1.70 80 59.7 91 68.5 96 41.7 57 79.3 98 87.6 127 43.3 88 36.9 112 67.9 160 25.2 90 31.8 39 63.8 49 4.61 28 39.3 77 78.8 67 3.04 47
JOF [136]83.6 14.4 137 39.1 144 2.17 126 24.7 50 36.3 40 2.87 70 18.1 47 30.6 41 1.54 40 59.7 91 67.9 68 43.2 161 79.3 98 87.5 82 43.6 145 36.9 112 67.0 89 25.4 121 31.6 15 63.4 36 4.66 44 39.1 55 78.7 60 3.29 134
FF++_ROB [141]83.8 13.5 43 36.6 55 1.68 39 25.4 90 38.6 99 2.89 74 19.1 111 33.5 115 1.74 93 59.3 63 68.0 72 41.8 67 79.3 98 87.5 82 43.4 106 37.1 131 66.9 78 25.9 152 31.7 26 64.3 69 4.73 81 39.3 77 79.1 86 3.20 105
UnDAF [187]84.2 13.6 52 36.9 66 1.67 34 25.2 73 38.1 79 2.72 34 19.2 123 35.0 152 1.54 40 60.0 122 70.9 183 42.0 87 79.2 68 87.4 48 43.4 106 36.6 69 67.0 89 25.1 78 32.1 85 64.5 84 4.75 99 39.4 92 79.1 86 3.10 73
PGM-C [118]86.2 13.8 74 37.7 95 1.85 76 25.1 68 38.1 79 2.90 75 19.1 111 33.6 116 1.59 54 59.3 63 68.2 79 41.9 74 79.3 98 87.5 82 43.5 123 36.6 69 67.2 112 25.2 90 31.9 54 64.8 98 4.67 49 39.5 106 79.4 111 3.22 114
PMF [73]87.0 13.7 59 37.1 73 1.66 33 25.5 93 39.3 115 2.71 31 19.0 97 34.9 149 1.74 93 59.4 71 68.4 91 41.8 67 79.4 141 87.6 127 43.3 88 37.3 143 66.9 78 26.2 162 31.9 54 64.3 69 4.73 81 39.3 77 78.8 67 2.93 30
PBOFVI [189]87.7 14.3 129 39.6 161 1.75 58 26.0 115 39.1 111 3.08 96 18.8 79 31.6 70 1.73 86 59.3 63 68.3 86 41.7 57 79.3 98 87.5 82 43.7 162 36.6 69 66.3 40 25.2 90 32.5 131 64.7 93 4.74 92 38.8 33 78.3 41 3.08 63
MDP-Flow [26]88.0 13.4 37 36.1 42 1.67 34 24.8 55 37.2 62 2.79 57 18.8 79 32.0 78 1.70 80 59.8 104 68.9 129 42.1 93 79.3 98 87.6 127 43.5 123 36.7 90 67.7 150 25.2 90 32.5 131 65.5 143 4.77 110 39.1 55 79.0 76 3.09 69
SegFlow [156]89.1 13.7 59 37.6 89 1.86 81 25.1 68 38.2 86 2.90 75 19.0 97 33.2 108 1.62 66 59.2 48 67.9 68 41.9 74 79.3 98 87.5 82 43.5 123 36.7 90 67.4 129 25.4 121 31.9 54 65.0 109 4.70 66 39.5 106 79.5 122 3.23 120
Efficient-NL [60]89.4 14.3 129 38.7 127 1.77 60 25.2 73 37.6 66 2.76 43 19.0 97 31.8 72 2.08 138 59.8 104 68.7 116 41.4 30 79.1 45 87.4 48 43.0 51 36.9 112 68.4 176 24.6 39 32.1 85 64.7 93 4.69 60 40.1 151 79.8 144 3.14 86
SVFilterOh [109]90.0 14.1 105 37.3 78 1.96 102 24.7 50 36.6 49 2.87 70 18.3 52 30.8 46 1.63 68 59.9 116 68.5 96 43.1 160 79.5 173 87.7 155 44.5 183 36.6 69 66.7 60 25.3 110 31.6 15 62.8 28 5.05 158 38.6 24 78.2 40 3.37 153
TC-Flow [46]90.8 13.7 59 36.9 66 1.91 94 25.3 81 38.5 96 3.05 94 19.3 132 34.1 134 1.73 86 59.2 48 67.8 60 42.2 106 79.3 98 87.5 82 43.5 123 37.1 131 68.0 164 25.6 134 31.9 54 64.3 69 4.71 68 39.0 43 79.0 76 3.13 82
MS-PFT [159]92.3 13.7 59 36.6 55 1.56 19 28.1 171 38.1 79 4.52 158 11.2 27 23.0 28 3.22 186 64.4 188 73.4 192 41.6 48 75.7 23 85.3 26 38.3 26 35.3 29 61.3 24 25.2 90 40.9 196 67.8 176 6.03 194 39.0 43 74.8 17 3.45 162
AggregFlow [95]92.8 14.5 142 38.3 116 2.20 134 25.7 106 38.5 96 3.23 112 18.6 70 30.8 46 1.44 19 59.7 91 68.4 91 41.7 57 79.4 141 87.6 127 43.8 172 37.5 149 66.9 78 26.4 167 31.8 39 64.2 66 4.70 66 38.9 36 78.4 43 3.08 63
DMF_ROB [135]93.2 13.9 86 37.0 70 1.98 105 25.8 109 39.0 108 2.96 80 19.8 165 35.0 152 2.12 144 59.7 91 68.2 79 41.9 74 79.3 98 87.4 48 43.7 162 36.3 39 66.4 44 25.0 60 32.1 85 64.4 80 4.93 146 39.2 68 79.1 86 3.07 58
IROF-TV [53]93.4 14.0 95 38.1 107 1.99 107 24.7 50 36.5 43 2.65 21 19.1 111 34.2 136 1.78 102 59.1 41 67.4 45 42.4 127 79.4 141 87.7 155 43.6 145 36.0 34 66.4 44 24.4 33 32.1 85 64.6 89 4.75 99 39.8 133 79.9 150 3.35 149
Second-order prior [8]93.7 14.0 95 37.1 73 2.11 121 26.2 124 39.3 115 2.93 78 19.4 140 35.1 156 2.16 150 59.4 71 67.8 60 41.8 67 79.1 45 87.3 38 43.1 59 36.5 56 66.7 60 25.0 60 32.3 116 65.4 137 4.74 92 39.5 106 79.6 132 3.19 98
SuperSlomo [130]93.7 12.3 27 30.3 21 2.92 171 24.8 55 35.2 30 6.60 185 13.6 29 25.5 30 2.01 133 60.5 147 65.5 29 43.9 170 78.3 30 86.6 30 41.9 32 37.4 147 64.3 32 26.4 167 35.3 189 63.9 55 5.33 177 40.3 160 77.6 33 3.51 170
EPPM w/o HM [86]93.9 13.4 37 36.6 55 1.61 21 25.5 93 39.3 115 2.76 43 19.4 140 35.7 167 1.99 132 59.6 84 69.3 144 41.9 74 79.2 68 87.4 48 43.1 59 37.0 124 67.5 138 25.3 110 32.8 145 65.0 109 4.85 133 39.4 92 79.0 76 3.04 47
PWC-Net_RVC [143]94.4 13.7 59 38.1 107 1.70 44 25.8 109 39.7 128 2.83 65 19.3 132 35.0 152 1.75 97 59.4 71 69.1 141 42.1 93 79.3 98 87.6 127 43.4 106 37.0 124 66.7 60 25.5 127 32.0 70 64.4 80 4.74 92 39.3 77 78.9 71 2.98 35
DeepFlow2 [106]94.7 13.9 86 36.6 55 2.07 118 25.6 101 38.4 92 3.08 96 19.1 111 33.6 116 1.70 80 59.6 84 68.5 96 41.9 74 79.4 141 87.5 82 43.7 162 36.7 90 66.3 40 25.4 121 31.9 54 64.7 93 4.67 49 39.4 92 79.4 111 3.26 129
CPM-Flow [114]94.9 13.8 74 37.8 97 1.87 87 25.1 68 38.2 86 2.93 78 19.0 97 33.4 113 1.61 62 59.6 84 68.7 116 42.1 93 79.3 98 87.5 82 43.5 123 36.8 104 66.9 78 25.5 127 32.0 70 65.2 131 4.68 57 39.5 106 79.5 122 3.25 125
TF+OM [98]95.5 13.7 59 36.5 53 2.17 126 25.2 73 37.4 63 3.76 140 17.9 42 32.7 95 1.76 99 59.8 104 68.5 96 42.3 114 79.3 98 87.5 82 43.7 162 36.9 112 66.7 60 25.7 145 31.8 39 64.3 69 4.79 115 39.3 77 79.3 103 3.47 166
ProFlow_ROB [142]95.7 13.6 52 36.5 53 1.85 76 25.3 81 38.4 92 2.96 80 18.9 89 32.9 99 1.62 66 59.7 91 69.6 162 42.5 134 79.4 141 87.6 127 43.4 106 36.6 69 66.7 60 25.1 78 32.1 85 65.1 120 4.71 68 39.7 123 79.7 140 3.20 105
LiteFlowNet [138]96.6 13.8 74 38.6 122 1.68 39 26.0 115 40.1 140 2.84 66 19.2 123 35.3 163 1.64 70 59.8 104 69.4 150 42.3 114 79.1 45 87.4 48 42.9 44 36.6 69 67.6 145 24.4 33 32.9 149 65.8 150 4.81 125 39.6 116 78.9 71 3.03 44
TriFlow [93]96.8 14.2 115 39.0 141 2.20 134 26.6 134 39.3 115 4.59 161 19.0 97 33.7 119 1.71 85 59.9 116 68.7 116 41.4 30 79.2 68 87.5 82 43.5 123 36.7 90 67.1 102 25.2 90 31.8 39 63.9 55 4.69 60 39.1 55 79.0 76 3.23 120
EpicFlow [100]96.9 13.8 74 37.6 89 1.87 87 25.5 93 38.9 105 2.96 80 18.9 89 33.7 119 1.64 70 59.5 77 68.5 96 42.3 114 79.4 141 87.6 127 43.5 123 36.5 56 67.5 138 24.9 49 32.0 70 65.1 120 4.74 92 39.4 92 79.4 111 3.22 114
SRR-TVOF-NL [89]97.2 14.2 115 37.6 89 2.07 118 26.1 120 39.8 132 3.30 116 19.4 140 33.9 127 1.82 111 59.8 104 68.6 108 41.0 27 79.1 45 87.5 82 42.9 44 36.0 34 66.9 78 24.1 29 32.9 149 64.8 98 4.81 125 39.6 116 79.4 111 3.22 114
DeepFlow [85]97.2 13.7 59 35.7 36 2.03 113 25.6 101 38.2 86 3.30 116 19.2 123 33.9 127 1.74 93 59.7 91 68.0 72 42.2 106 79.4 141 87.5 82 43.7 162 37.3 143 66.4 44 26.2 162 31.8 39 64.8 98 4.63 30 39.3 77 79.3 103 3.26 129
SimpleFlow [49]97.3 14.1 105 38.9 137 1.92 99 25.5 93 37.9 74 2.85 68 19.0 97 32.3 86 2.26 155 59.2 48 67.3 43 42.4 127 79.2 68 87.5 82 43.2 78 36.7 90 67.6 145 25.1 78 32.0 70 66.1 160 5.29 173 39.3 77 79.2 94 3.15 89
CostFilter [40]98.7 13.6 52 37.4 82 1.63 31 25.5 93 39.7 128 2.75 40 19.0 97 36.0 170 1.79 104 59.4 71 68.8 123 42.0 87 79.4 141 87.6 127 43.7 162 38.6 174 67.1 102 28.1 184 31.9 54 64.6 89 4.81 125 39.0 43 78.5 50 3.00 39
OFH [38]99.0 14.1 105 38.2 113 2.03 113 25.6 101 38.4 92 3.01 89 19.4 140 35.1 156 1.79 104 59.5 77 68.8 123 42.3 114 79.1 45 87.4 48 43.1 59 36.7 90 67.6 145 25.2 90 32.1 85 65.1 120 4.79 115 39.2 68 79.2 94 3.15 89
Complementary OF [21]99.4 13.7 59 37.8 97 1.71 47 25.2 73 38.6 99 2.81 60 19.8 165 33.7 119 2.38 160 59.9 116 69.2 143 42.8 145 79.2 68 87.5 82 43.1 59 36.6 69 67.4 129 25.2 90 32.3 116 65.4 137 4.79 115 38.8 33 78.9 71 3.29 134
Aniso. Huber-L1 [22]99.4 14.3 129 38.5 120 2.17 126 26.6 134 39.5 124 3.21 111 19.2 123 32.5 92 1.83 113 59.7 91 68.7 116 41.9 74 79.2 68 87.4 48 43.2 78 36.3 39 67.1 102 24.6 39 32.2 107 64.9 105 4.71 68 39.7 123 79.6 132 3.24 124
DPOF [18]100.0 14.2 115 39.1 144 2.19 133 24.8 55 37.0 57 2.80 58 19.3 132 31.9 74 2.01 133 60.2 137 69.5 157 42.3 114 79.1 45 87.4 48 43.1 59 36.7 90 67.1 102 24.6 39 32.4 125 65.3 135 4.81 125 39.5 106 79.5 122 3.18 95
RFlow [88]100.0 13.8 74 37.8 97 2.02 111 26.0 115 39.1 111 2.85 68 19.0 97 33.1 106 1.86 115 59.7 91 68.4 91 42.2 106 79.2 68 87.6 127 43.4 106 36.1 38 66.8 71 24.5 36 32.2 107 65.1 120 4.82 132 39.7 123 79.8 144 3.34 146
TC/T-Flow [77]100.7 14.3 129 38.8 131 1.84 72 25.3 81 38.6 99 2.81 60 18.9 89 32.4 91 1.58 52 59.9 116 69.5 157 42.1 93 79.3 98 87.5 82 43.5 123 37.1 131 68.0 164 25.2 90 32.1 85 65.2 131 4.81 125 39.2 68 79.4 111 3.00 39
OAR-Flow [123]101.0 14.0 95 36.9 66 2.05 117 25.3 81 38.1 79 3.11 102 19.1 111 34.0 133 1.70 80 59.2 48 68.6 108 41.9 74 79.4 141 87.6 127 43.5 123 36.9 112 67.8 154 25.3 110 32.0 70 65.1 120 4.75 99 39.3 77 79.3 103 3.18 95
Sparse Occlusion [54]101.6 14.2 115 38.6 122 1.99 107 25.8 109 39.2 114 2.78 53 19.3 132 32.3 86 1.80 107 59.8 104 68.8 123 41.7 57 79.3 98 87.5 82 43.2 78 37.1 131 68.4 176 25.3 110 32.1 85 64.4 80 4.60 25 39.7 123 79.6 132 3.15 89
TOF-M [150]101.8 11.7 24 31.3 26 1.68 39 23.9 24 35.8 35 5.13 173 14.0 31 25.4 29 2.53 167 60.9 157 66.9 35 43.8 167 78.9 34 87.0 33 43.4 106 38.3 169 65.3 34 26.7 172 37.9 192 65.0 109 5.51 184 43.2 194 79.5 122 3.94 187
Brox et al. [5]102.0 14.0 95 37.4 82 1.90 92 26.4 129 40.1 140 3.08 96 19.3 132 35.0 152 1.97 128 59.7 91 68.2 79 41.7 57 79.4 141 87.6 127 43.6 145 36.6 69 66.9 78 25.1 78 31.9 54 64.8 98 4.73 81 39.4 92 79.5 122 3.15 89
ContinualFlow_ROB [148]102.3 14.6 148 40.3 170 2.11 121 26.6 134 40.8 156 3.96 144 19.8 165 36.5 178 1.98 129 59.6 84 69.0 134 42.3 114 79.2 68 87.5 82 43.4 106 36.0 34 66.8 71 24.4 33 31.9 54 64.3 69 4.64 35 39.2 68 79.4 111 3.04 47
ComplOF-FED-GPU [35]103.3 14.0 95 38.0 105 1.91 94 25.3 81 38.5 96 2.90 75 20.2 173 34.6 144 2.16 150 59.5 77 68.5 96 42.5 134 79.2 68 87.4 48 43.2 78 36.6 69 67.4 129 25.0 60 32.2 107 65.4 137 4.75 99 39.7 123 79.8 144 3.19 98
LFNet_ROB [145]104.0 13.8 74 37.5 85 1.80 63 27.0 148 41.7 170 3.08 96 19.6 152 35.5 164 1.87 117 59.2 48 67.4 45 41.7 57 79.1 45 87.4 48 42.8 43 36.8 104 67.3 122 24.8 46 33.2 156 65.7 149 4.79 115 40.4 166 80.0 155 3.26 129
GraphCuts [14]104.3 15.1 163 39.3 151 2.68 158 26.4 129 39.4 122 4.50 155 19.2 123 30.7 45 2.69 172 60.7 153 68.6 108 42.8 145 79.0 38 87.4 48 42.5 36 35.6 30 66.7 60 23.7 28 32.0 70 65.0 109 5.04 157 39.0 43 79.2 94 3.48 167
Fusion [6]105.4 13.8 74 38.4 119 1.84 72 25.3 81 38.1 79 2.88 73 19.1 111 32.2 84 1.90 121 60.9 157 69.8 163 41.8 67 79.1 45 87.9 176 42.1 33 36.0 34 67.8 154 24.1 29 32.7 142 66.3 165 4.88 140 39.5 106 80.4 175 3.26 129
Classic++ [32]105.5 14.0 95 38.1 107 2.17 126 25.7 106 38.8 103 2.96 80 19.3 132 33.9 127 1.93 123 59.7 91 67.9 68 42.8 145 79.2 68 87.5 82 43.3 88 37.4 147 67.0 89 26.6 171 31.8 39 64.3 69 4.78 112 39.4 92 79.5 122 3.36 150
DF-Auto [113]106.5 14.2 115 36.7 61 2.25 139 26.5 132 39.0 108 4.23 149 18.8 79 31.4 66 1.58 52 60.1 131 69.3 144 41.6 48 79.3 98 87.5 82 43.6 145 36.6 69 67.0 89 25.1 78 32.3 116 65.1 120 4.81 125 39.9 135 80.1 162 3.22 114
Steered-L1 [116]107.0 13.7 59 37.5 85 1.84 72 25.5 93 38.9 105 3.17 108 19.7 160 33.1 106 2.40 161 60.2 137 68.5 96 42.8 145 79.4 141 87.7 155 43.5 123 36.6 69 67.0 89 25.6 134 31.8 39 64.6 89 4.96 151 38.6 24 79.0 76 3.36 150
ALD-Flow [66]107.5 14.1 105 37.9 102 2.17 126 25.4 90 38.4 92 3.14 104 19.1 111 33.9 127 1.73 86 59.6 84 69.0 134 42.6 142 79.4 141 87.6 127 43.6 145 37.0 124 67.5 138 25.6 134 31.7 26 64.0 62 4.69 60 39.4 92 79.5 122 3.20 105
p-harmonic [29]108.0 13.5 43 36.7 61 1.85 76 26.7 143 39.9 136 3.25 114 19.4 140 35.2 159 2.10 141 60.1 131 68.7 116 42.2 106 79.3 98 87.5 82 43.3 88 36.7 90 66.7 60 25.3 110 32.6 136 65.8 150 4.76 105 39.4 92 79.5 122 3.17 93
FLAVR [188]109.7 20.7 193 45.4 192 3.14 176 37.4 197 46.1 194 7.59 190 17.5 35 30.9 48 2.93 179 68.5 197 76.1 196 39.7 24 74.0 11 84.5 20 31.0 4 30.8 10 60.4 17 17.7 1 41.4 197 69.9 194 4.86 136 40.6 174 75.3 18 2.93 30
Shiralkar [42]111.8 14.2 115 39.0 141 2.02 111 26.8 144 40.3 146 2.98 84 18.5 59 38.0 187 2.48 165 60.1 131 67.7 57 41.8 67 78.8 33 87.2 36 42.3 35 37.7 156 67.2 112 26.2 162 33.2 156 67.1 170 4.94 148 39.4 92 79.3 103 3.10 73
AugFNG_ROB [139]112.4 14.6 148 39.7 163 2.31 143 27.3 158 41.3 163 4.30 153 19.5 147 37.8 184 1.92 122 59.8 104 68.8 123 42.1 93 79.4 141 87.7 155 43.3 88 36.3 39 66.4 44 24.9 49 32.7 142 65.6 147 4.73 81 38.8 33 78.6 53 2.84 24
HBM-GC [103]114.9 14.7 152 39.4 156 2.41 151 25.4 90 38.1 79 3.07 95 18.0 45 29.8 33 1.56 46 59.8 104 68.2 79 42.8 145 80.1 188 88.0 182 45.9 192 37.5 149 68.2 172 26.1 160 31.9 54 63.3 33 4.99 153 39.3 77 79.1 86 3.30 137
C-RAFT_RVC [181]114.9 15.1 163 41.1 175 2.13 123 26.4 129 40.6 154 3.40 126 19.3 132 34.1 134 1.85 114 60.0 122 69.9 165 42.3 114 79.3 98 87.5 82 43.4 106 36.6 69 67.1 102 24.9 49 32.1 85 64.9 105 4.69 60 39.9 135 79.4 111 3.20 105
FlowNet2 [120]115.8 15.9 178 41.4 177 2.76 162 27.1 150 40.2 143 4.29 151 19.6 152 34.3 138 1.88 118 60.0 122 70.2 170 42.0 87 79.4 141 87.7 155 43.3 88 36.4 49 66.3 40 24.9 49 32.1 85 64.5 84 4.71 68 39.6 116 79.2 94 3.08 63
CLG-TV [48]116.9 14.3 129 38.8 131 2.17 126 26.6 134 39.8 132 3.24 113 19.5 147 33.9 127 2.11 143 60.0 122 69.0 134 42.4 127 79.3 98 87.6 127 43.5 123 36.6 69 66.9 78 25.1 78 32.1 85 65.1 120 4.71 68 39.9 135 80.0 155 3.20 105
MCPFlow_RVC [197]117.3 14.3 129 39.2 148 1.80 63 25.9 114 39.5 124 3.19 110 19.0 97 33.7 119 1.56 46 59.7 91 68.7 116 41.8 67 79.5 173 87.8 173 43.7 162 36.7 90 68.0 164 25.0 60 32.4 125 65.1 120 4.76 105 39.5 106 80.2 169 3.33 144
MLDP_OF [87]117.4 13.9 86 38.1 107 1.81 65 25.6 101 38.9 105 2.80 58 18.8 79 32.3 86 1.61 62 59.6 84 68.3 86 42.3 114 79.3 98 87.6 127 43.9 175 39.6 187 68.7 182 28.5 186 33.0 154 65.3 135 5.09 161 39.6 116 79.2 94 3.51 170
SIOF [67]117.8 14.7 152 39.5 159 2.23 138 27.1 150 40.3 146 4.25 150 19.1 111 32.9 99 1.82 111 59.8 104 68.6 108 42.1 93 79.1 45 87.4 48 43.0 51 37.1 131 67.1 102 25.5 127 32.4 125 64.9 105 4.79 115 40.1 151 79.9 150 3.40 157
EPMNet [131]117.9 15.7 176 42.3 181 2.55 154 26.9 145 39.5 124 4.05 146 19.6 152 34.3 138 1.88 118 60.1 131 70.4 176 42.0 87 79.4 141 87.7 155 43.3 88 36.5 56 66.9 78 24.9 49 32.1 85 64.5 84 4.71 68 40.0 143 79.3 103 3.05 52
Local-TV-L1 [65]121.2 14.9 157 37.3 78 3.21 177 27.3 158 39.5 124 4.67 162 18.9 89 32.3 86 1.70 80 61.3 170 68.6 108 47.1 190 79.3 98 87.6 127 43.6 145 39.0 179 66.7 60 28.9 188 31.7 26 64.3 69 4.79 115 39.3 77 79.1 86 3.41 160
F-TV-L1 [15]121.8 15.0 158 39.3 151 2.88 169 27.2 154 40.2 143 3.69 136 19.2 123 34.5 143 2.19 152 59.7 91 68.4 91 42.8 145 78.9 34 87.4 48 42.7 41 37.3 143 67.0 89 25.6 134 32.1 85 64.5 84 4.89 141 40.1 151 80.0 155 3.42 161
IAOF [50]122.1 15.5 172 39.2 148 2.93 173 29.4 177 43.0 179 5.18 174 17.8 40 33.0 103 2.04 136 60.8 155 68.9 129 42.2 106 79.2 68 87.4 48 43.3 88 36.8 104 67.2 112 25.1 78 32.7 142 65.6 147 4.67 49 40.0 143 80.0 155 3.20 105
3DFlow [133]122.2 14.1 105 38.7 127 1.71 47 25.2 73 38.2 86 2.84 66 19.0 97 32.3 86 1.69 78 59.9 116 69.0 134 42.4 127 79.6 177 87.6 127 45.1 188 37.7 156 69.2 189 25.4 121 33.7 171 66.7 167 4.86 136 39.9 135 79.8 144 3.12 80
OFRF [132]122.2 16.1 180 39.8 165 3.51 181 27.6 162 40.2 143 4.76 164 18.4 54 34.3 138 1.75 97 60.4 142 68.9 129 43.0 157 79.2 68 87.5 82 43.1 59 38.1 165 68.1 169 26.4 167 32.2 107 65.0 109 4.79 115 39.0 43 79.1 86 3.05 52
TCOF [69]122.5 14.4 137 39.3 151 1.83 70 27.3 158 40.9 159 3.35 119 18.7 76 32.1 80 1.50 32 60.2 137 70.2 170 42.1 93 79.3 98 87.6 127 43.2 78 36.9 112 68.5 178 24.8 46 33.3 160 65.8 150 4.72 75 41.2 181 81.4 188 3.46 164
LSM_FLOW_RVC [182]123.7 14.5 142 40.7 173 2.04 115 27.2 154 42.6 175 3.51 134 19.5 147 36.2 173 1.73 86 59.7 91 69.3 144 41.7 57 79.2 68 87.4 48 43.1 59 37.0 124 67.3 122 24.9 49 33.4 163 66.0 157 4.81 125 40.5 171 79.9 150 3.32 142
BriefMatch [122]125.3 14.0 95 37.0 70 2.17 126 25.6 101 38.8 103 3.98 145 19.7 160 33.0 103 2.69 172 61.1 165 69.0 134 46.4 187 79.3 98 87.6 127 43.8 172 40.5 192 67.9 160 30.6 192 31.8 39 64.0 62 4.94 148 39.0 43 78.8 67 3.34 146
CompactFlow_ROB [155]125.8 14.2 115 39.2 148 1.96 102 27.1 150 41.9 171 4.22 148 20.0 170 37.0 179 1.80 107 60.0 122 69.4 150 42.5 134 79.3 98 87.5 82 43.2 78 36.6 69 67.4 129 24.5 36 33.2 156 65.9 154 4.78 112 40.5 171 80.0 155 3.13 82
Adaptive [20]126.0 14.5 142 39.6 161 2.31 143 27.1 150 40.4 149 3.35 119 18.6 70 33.7 119 1.98 129 59.6 84 68.2 79 42.4 127 79.4 141 87.6 127 43.4 106 37.1 131 67.5 138 25.7 145 32.4 125 64.8 98 4.73 81 40.0 143 80.1 162 3.38 155
IIOF-NLDP [129]126.1 14.1 105 38.2 113 1.62 26 26.1 120 39.9 136 2.98 84 19.3 132 32.1 80 1.77 100 60.6 152 69.4 150 43.2 161 79.3 98 87.5 82 43.6 145 37.8 161 68.6 179 25.6 134 34.1 180 69.5 190 5.66 190 39.9 135 79.6 132 3.01 41
IRR-PWC_RVC [180]126.6 15.0 158 40.8 174 2.39 150 27.2 154 41.3 163 4.51 157 20.2 173 38.0 187 1.86 115 60.4 142 69.8 163 41.9 74 79.4 141 87.6 127 43.4 106 36.6 69 67.0 89 25.0 60 32.6 136 65.5 143 4.72 75 39.7 123 79.5 122 2.99 38
FlowNetS+ft+v [110]127.3 14.7 152 38.1 107 2.80 165 27.5 161 40.6 154 4.81 166 19.6 152 34.9 149 2.07 137 60.1 131 69.5 157 42.2 106 79.4 141 87.7 155 43.4 106 36.6 69 67.1 102 25.2 90 32.0 70 65.4 137 4.73 81 39.6 116 79.7 140 3.21 112
CNN-flow-warp+ref [115]127.8 13.8 74 36.0 40 2.35 147 26.6 134 39.8 132 3.83 141 20.0 170 35.5 164 2.34 157 60.9 157 68.9 129 43.0 157 79.4 141 87.6 127 43.7 162 36.8 104 67.0 89 25.6 134 32.1 85 66.2 162 4.94 148 39.4 92 79.5 122 3.19 98
AdaConv-v1 [124]128.9 16.5 184 42.3 181 4.36 186 30.4 183 43.8 183 9.06 193 20.6 179 36.3 175 4.45 193 64.5 190 71.3 187 45.3 182 78.4 32 86.7 32 42.2 34 36.3 39 64.9 33 25.4 121 32.5 131 63.7 47 5.53 185 38.0 19 77.4 31 3.53 173
CVENG22+RIC [199]129.0 14.2 115 38.7 127 2.04 115 25.8 109 39.3 115 2.99 87 19.1 111 34.8 147 1.81 109 60.1 131 70.1 169 42.5 134 79.4 141 87.7 155 43.6 145 36.9 112 67.8 154 25.3 110 32.3 116 65.9 154 4.79 115 39.8 133 80.0 155 3.30 137
SPSA-learn [13]129.5 14.8 156 37.8 97 2.72 161 27.6 162 40.1 140 4.71 163 20.5 176 33.7 119 2.97 180 60.4 142 67.6 53 41.5 40 79.3 98 87.5 82 43.5 123 36.8 104 67.2 112 25.2 90 33.4 163 70.8 197 6.21 197 39.7 123 79.6 132 3.19 98
CRTflow [81]129.9 14.4 137 38.9 137 2.38 148 26.0 115 39.0 108 3.14 104 20.2 173 36.2 173 2.37 159 60.5 147 69.5 157 44.1 173 79.3 98 87.5 82 43.4 106 37.1 131 67.3 122 25.7 145 32.0 70 64.6 89 4.85 133 39.6 116 79.6 132 3.45 162
LDOF [28]130.0 15.0 158 38.8 131 2.92 171 28.0 169 41.1 161 5.03 169 19.7 160 34.8 147 2.15 148 60.0 122 68.9 129 42.6 142 79.4 141 87.6 127 43.5 123 36.9 112 66.8 71 25.5 127 31.9 54 65.1 120 4.73 81 39.5 106 79.6 132 3.23 120
HBpMotionGpu [43]130.2 15.8 177 40.2 169 3.66 183 29.5 178 42.8 178 6.27 179 18.5 59 31.9 74 1.73 86 61.3 170 69.9 165 43.9 170 79.1 45 87.6 127 43.0 51 37.6 155 67.6 145 25.9 152 32.0 70 64.3 69 4.67 49 40.0 143 79.9 150 3.75 182
ResPWCR_ROB [140]130.3 13.9 86 38.2 113 1.89 90 26.5 132 40.4 149 3.42 129 19.9 169 35.6 166 1.95 126 60.5 147 70.2 170 43.3 163 78.9 34 87.4 48 42.5 36 42.1 195 67.7 150 32.5 195 33.9 176 65.4 137 4.85 133 40.1 151 79.7 140 3.17 93
ROF-ND [105]130.5 15.1 163 37.9 102 1.86 81 26.3 127 40.5 153 3.12 103 19.6 152 32.8 97 1.68 77 60.9 157 71.1 186 41.9 74 79.3 98 87.5 82 43.5 123 37.0 124 68.2 172 24.9 49 34.3 183 68.3 182 5.28 172 40.5 171 80.5 178 3.25 125
Occlusion-TV-L1 [63]130.8 14.3 129 39.1 144 2.21 136 26.6 134 40.0 138 3.14 104 19.2 123 34.2 136 2.15 148 60.0 122 68.5 96 42.8 145 79.3 98 87.5 82 43.6 145 37.5 149 67.0 89 26.2 162 32.9 149 65.1 120 5.16 166 40.0 143 79.8 144 3.30 137
Modified CLG [34]132.3 14.1 105 37.6 89 2.33 145 28.5 174 41.4 168 5.68 175 19.6 152 35.8 169 2.31 156 60.2 137 68.6 108 42.1 93 79.4 141 87.5 82 43.5 123 36.7 90 67.2 112 25.2 90 32.3 116 66.0 157 4.76 105 40.2 157 80.4 175 3.40 157
CBF [12]133.5 13.7 59 37.2 77 2.15 124 26.0 115 39.4 122 3.28 115 19.1 111 32.1 80 1.79 104 61.0 163 70.0 168 45.8 184 79.6 177 87.8 173 44.9 187 36.8 104 67.4 129 25.2 90 32.2 107 65.5 143 5.22 169 40.0 143 80.2 169 3.99 190
TriangleFlow [30]135.1 14.7 152 40.0 168 2.29 142 26.6 134 40.8 156 3.03 92 19.4 140 33.3 111 2.10 141 60.4 142 69.9 165 42.8 145 79.0 38 87.4 48 42.6 38 37.7 156 68.3 175 25.3 110 33.1 155 67.8 176 5.24 171 40.4 166 80.6 180 3.32 142
ACK-Prior [27]136.3 13.8 74 38.1 107 1.74 55 25.5 93 39.3 115 2.82 63 19.6 152 33.8 126 2.45 163 60.5 147 70.3 173 42.3 114 80.2 189 88.0 182 45.8 191 38.2 166 67.8 154 26.9 176 32.6 136 66.2 162 5.35 179 38.9 36 79.7 140 3.60 178
BlockOverlap [61]136.3 15.1 163 37.6 89 3.31 179 27.7 165 39.3 115 5.73 176 18.6 70 30.3 35 2.09 140 60.9 157 68.2 79 47.1 190 80.2 189 87.9 176 46.5 193 39.0 179 67.3 122 28.4 185 31.9 54 63.9 55 5.09 161 39.7 123 79.3 103 3.55 174
2D-CLG [1]136.5 14.5 142 37.6 89 2.76 162 29.8 180 42.4 174 6.69 186 19.7 160 35.2 159 2.74 175 60.7 153 68.7 116 41.5 40 79.4 141 87.7 155 43.5 123 36.6 69 67.0 89 25.1 78 32.5 131 66.7 167 4.90 143 40.2 157 80.1 162 3.25 125
Nguyen [33]136.8 15.6 173 38.5 120 3.62 182 30.1 182 43.2 180 6.04 177 19.6 152 36.3 175 2.25 154 61.1 165 69.4 150 42.0 87 79.2 68 87.5 82 43.1 59 36.4 49 67.2 112 24.7 44 34.3 183 67.4 173 5.00 154 40.2 157 80.3 171 3.29 134
SegOF [10]137.4 14.2 115 36.8 65 2.54 153 27.0 148 40.0 138 4.18 147 21.1 183 36.1 172 3.15 185 60.5 147 70.7 181 41.6 48 79.4 141 87.6 127 43.6 145 36.9 112 68.2 172 25.2 90 32.5 131 68.0 181 5.31 176 39.6 116 79.4 111 3.22 114
IAOF2 [51]138.2 15.6 173 41.3 176 2.58 156 27.6 162 41.4 168 4.29 151 17.8 40 33.6 116 1.94 124 61.2 168 70.8 182 42.8 145 79.4 141 87.7 155 43.3 88 37.2 139 67.5 138 25.6 134 32.3 116 65.0 109 4.63 30 40.6 174 80.4 175 3.40 157
TV-L1-improved [17]139.2 14.2 115 38.8 131 2.25 139 26.9 145 40.3 146 3.40 126 19.5 147 33.9 127 2.44 162 59.9 116 69.0 134 42.7 144 79.4 141 87.7 155 43.5 123 37.2 139 67.6 145 25.8 149 32.1 85 66.1 160 5.05 158 39.9 135 80.0 155 3.46 164
StereoOF-V1MT [117]139.4 14.6 148 39.9 166 2.00 109 27.2 154 41.9 171 3.04 93 20.9 182 37.8 184 2.85 178 61.3 170 68.3 86 43.8 167 79.2 68 87.5 82 42.9 44 38.2 166 67.8 154 26.3 166 33.8 172 68.5 183 5.36 180 40.0 143 79.4 111 3.09 69
Correlation Flow [76]139.6 14.0 95 38.3 116 1.61 21 26.2 124 39.8 132 2.98 84 19.1 111 31.9 74 1.73 86 60.4 142 69.4 150 43.6 166 80.2 189 87.9 176 47.8 196 38.0 164 68.7 182 26.0 157 33.4 163 67.2 171 5.29 173 40.1 151 80.3 171 3.39 156
Dynamic MRF [7]139.9 13.9 86 38.6 122 1.90 92 26.1 120 40.4 149 3.08 96 20.0 170 37.7 183 2.73 174 61.3 170 69.3 144 44.6 177 79.1 45 87.6 127 43.0 51 37.7 156 68.0 164 25.9 152 32.6 136 67.2 171 5.08 160 40.4 166 80.5 178 3.49 169
WRT [146]141.5 14.3 129 39.0 141 1.76 59 26.6 134 39.7 128 3.14 104 20.8 180 31.9 74 2.57 168 60.2 137 69.5 157 42.3 114 79.6 177 87.7 155 44.4 181 37.8 161 69.5 194 25.5 127 34.2 182 71.4 198 6.06 195 39.7 123 79.8 144 2.95 33
Rannacher [23]143.6 14.4 137 39.3 151 2.38 148 26.9 145 40.4 149 3.36 122 19.5 147 34.6 144 2.58 169 59.8 104 68.8 123 42.8 145 79.4 141 87.7 155 43.6 145 37.2 139 67.8 154 25.8 149 32.2 107 66.0 157 5.02 155 39.9 135 79.9 150 3.56 175
Black & Anandan [4]144.4 15.3 168 38.8 131 2.96 174 28.4 172 40.9 159 4.78 165 20.5 176 35.2 159 2.74 175 60.9 157 69.3 144 42.1 93 79.4 141 87.7 155 43.6 145 37.1 131 66.6 53 25.6 134 32.9 149 65.9 154 4.72 75 40.3 160 80.3 171 3.25 125
LocallyOriented [52]146.5 15.0 158 40.3 170 2.53 152 27.7 165 41.3 163 3.86 142 19.4 140 34.4 141 1.95 126 61.1 165 70.6 178 43.3 163 79.2 68 87.5 82 43.3 88 39.1 183 68.1 169 27.6 182 32.9 149 65.8 150 4.72 75 40.6 174 80.6 180 3.37 153
UnFlow [127]148.9 16.0 179 42.8 184 2.87 168 30.6 186 45.2 192 4.52 158 21.3 186 39.4 191 2.81 177 60.0 122 68.3 86 42.1 93 79.2 68 87.4 48 43.5 123 37.5 149 68.0 164 25.2 90 33.8 172 65.1 120 4.98 152 43.2 194 81.8 192 3.67 180
TVL1_RVC [175]152.5 16.2 181 39.4 156 4.14 185 30.4 183 43.4 181 6.38 181 18.9 89 34.9 149 2.12 144 61.3 170 69.1 141 42.9 156 79.4 141 87.7 155 43.6 145 37.5 149 67.2 112 26.0 157 32.3 116 66.2 162 4.91 145 40.1 151 80.3 171 3.31 141
Filter Flow [19]153.6 15.0 158 39.4 156 2.78 164 28.4 172 40.8 156 6.31 180 18.5 59 32.9 99 2.14 146 61.7 177 69.3 144 45.3 182 79.7 182 88.0 182 44.5 183 37.3 143 67.7 150 26.1 160 32.1 85 65.2 131 4.93 146 40.3 160 80.7 183 3.97 189
StereoFlow [44]154.7 22.8 197 51.1 198 4.80 188 36.2 196 51.1 198 6.57 184 19.2 123 34.6 144 1.89 120 60.0 122 68.5 96 42.4 127 80.3 192 89.1 197 43.9 175 39.0 179 74.1 198 25.3 110 32.1 85 65.0 109 4.73 81 40.3 160 80.9 184 3.36 150
Ad-TV-NDC [36]160.8 17.2 187 39.9 166 5.26 190 29.6 179 42.1 173 6.18 178 19.2 123 33.7 119 1.98 129 62.4 179 70.3 173 45.2 181 79.6 177 87.9 176 43.9 175 38.3 169 67.3 122 27.2 180 32.3 116 65.5 143 4.80 124 40.3 160 80.1 162 3.58 177
WOLF_ROB [144]160.8 15.6 173 41.7 179 2.64 157 27.8 167 41.3 163 3.72 138 19.7 160 35.2 159 2.02 135 61.3 170 71.8 188 44.5 175 79.4 141 87.8 173 43.7 162 38.8 177 67.9 160 27.5 181 34.4 186 67.7 174 5.09 161 39.9 135 79.6 132 3.22 114
Bartels [41]161.6 14.6 148 39.3 151 2.80 165 26.1 120 39.7 128 4.45 154 19.0 97 33.2 108 2.14 146 62.1 178 70.9 183 48.9 192 80.7 196 88.1 185 49.2 198 43.7 197 69.0 188 34.8 198 32.4 125 65.0 109 5.76 192 40.4 166 80.1 162 4.26 192
TI-DOFE [24]164.2 17.9 190 43.0 185 5.41 191 32.3 192 46.2 195 7.98 191 20.5 176 38.1 189 2.97 180 63.1 186 70.6 178 43.8 167 79.1 45 87.6 127 43.1 59 37.7 156 67.4 129 25.8 149 33.4 163 67.8 176 5.09 161 41.6 185 81.5 190 3.68 181
Horn & Schunck [3]165.3 15.3 168 40.4 172 2.69 159 29.0 175 42.7 176 5.10 170 21.1 183 37.9 186 3.33 187 62.5 181 70.3 173 43.0 157 79.3 98 87.7 155 43.6 145 37.5 149 67.3 122 25.9 152 33.9 176 68.5 183 5.03 156 41.2 181 81.2 187 3.57 176
GroupFlow [9]168.4 16.8 186 43.4 186 3.43 180 29.1 176 43.9 184 5.11 172 22.2 190 39.3 190 3.53 188 61.0 163 70.6 178 42.5 134 79.7 182 88.1 185 44.0 178 39.0 179 69.4 193 26.8 175 32.8 145 66.8 169 4.87 139 40.4 166 80.1 162 3.01 41
2bit-BM-tele [96]169.7 15.3 168 39.5 159 3.22 178 27.8 167 41.2 162 4.90 167 18.8 79 32.5 92 2.34 157 62.4 179 71.0 185 49.0 193 80.6 194 88.2 190 47.9 197 42.8 196 69.3 192 32.9 196 33.4 163 70.0 195 6.77 198 40.3 160 79.4 111 4.33 195
SLK [47]170.7 17.4 188 43.9 189 4.90 189 30.5 185 44.0 185 7.18 188 22.5 191 39.8 192 4.15 192 64.5 190 70.5 177 46.7 188 78.9 34 87.7 155 41.6 31 38.5 172 68.8 184 26.0 157 33.8 172 70.1 196 5.50 183 41.6 185 81.4 188 3.91 186
NL-TV-NCC [25]171.6 15.1 163 41.6 178 1.86 81 26.6 134 41.3 163 3.02 91 20.8 180 35.7 167 2.24 153 63.2 187 73.9 193 45.9 185 81.3 198 88.7 196 49.9 199 38.6 174 69.8 196 25.6 134 37.6 191 69.5 190 5.62 188 42.4 192 82.1 195 4.00 191
SILK [80]171.9 16.3 182 42.0 180 4.01 184 29.9 181 43.5 182 6.44 182 21.6 187 37.4 181 3.55 189 62.6 182 69.4 150 47.0 189 79.3 98 87.7 155 43.6 145 39.9 189 68.1 169 29.2 189 32.8 145 67.8 176 5.14 165 40.6 174 80.6 180 3.52 172
HCIC-L [97]173.2 23.2 198 49.0 197 11.0 198 32.1 191 44.4 186 9.93 194 23.2 193 36.4 177 3.02 182 64.4 188 72.1 189 44.9 178 80.6 194 88.5 194 46.6 194 39.1 183 68.9 186 27.1 178 32.4 125 65.0 109 5.53 185 39.1 55 79.3 103 3.65 179
H+S_RVC [176]175.6 16.5 184 43.8 188 2.91 170 31.7 189 44.6 187 6.50 183 24.3 194 44.2 195 4.80 195 65.7 193 69.4 150 44.5 175 79.4 141 88.2 190 43.1 59 38.5 172 68.6 179 25.6 134 34.8 187 69.4 189 5.55 187 43.5 197 81.6 191 3.89 185
Heeger++ [102]175.7 17.5 189 47.2 196 2.80 165 31.1 188 44.9 190 4.93 168 26.6 196 47.7 197 4.79 194 62.6 182 68.0 72 45.1 179 79.8 186 88.4 193 44.1 179 39.1 183 68.9 186 26.5 170 34.8 187 67.9 180 5.23 170 41.5 184 80.1 162 3.23 120
FFV1MT [104]178.2 16.4 183 44.7 191 3.13 175 31.9 190 44.7 188 7.15 187 25.4 195 45.6 196 5.04 196 62.6 182 68.0 72 45.1 179 79.6 177 87.9 176 44.1 179 38.9 178 67.7 150 27.1 178 34.0 179 68.5 183 5.29 173 41.8 188 81.0 185 4.48 197
Learning Flow [11]178.3 15.3 168 42.7 183 2.55 154 28.0 169 42.7 176 3.95 143 21.1 183 37.0 179 3.03 184 63.0 185 73.3 191 46.2 186 80.0 187 88.2 190 45.1 188 38.2 166 68.6 179 26.7 172 33.8 172 68.5 183 5.21 168 41.9 189 82.3 196 3.95 188
Adaptive flow [45]181.5 19.6 192 44.1 190 6.76 193 32.8 193 45.7 193 10.2 195 19.8 165 34.4 141 3.02 182 64.7 192 72.1 189 49.4 194 80.3 192 88.6 195 45.6 190 38.3 169 69.2 189 26.7 172 32.6 136 66.5 166 5.45 182 41.0 178 81.1 186 3.75 182
Pyramid LK [2]183.9 21.2 196 43.7 187 10.7 197 33.1 195 45.1 191 11.9 196 27.3 197 36.0 170 6.46 197 70.7 198 78.5 198 57.7 198 79.5 173 88.1 185 43.3 88 38.6 174 68.8 184 27.0 177 33.5 169 68.8 187 6.00 193 41.0 178 81.8 192 4.31 194
FOLKI [16]188.3 20.9 194 46.0 193 9.48 196 32.8 193 47.4 196 8.75 192 21.6 187 40.7 193 4.10 191 67.2 196 74.2 195 53.7 197 79.5 173 88.1 185 43.7 162 39.2 186 69.2 189 27.9 183 33.4 163 69.5 190 5.65 189 41.7 187 82.3 196 4.28 193
PGAM+LK [55]188.6 19.4 191 46.4 194 6.81 194 30.9 187 44.8 189 7.52 189 22.7 192 40.9 194 3.99 190 66.6 195 73.9 193 52.4 196 79.7 182 88.1 185 44.5 183 40.2 191 69.7 195 28.8 187 33.3 160 69.3 188 5.42 181 41.4 183 81.8 192 4.36 196
Periodicity [79]195.5 21.0 195 47.0 195 9.32 195 38.1 198 48.1 197 14.7 198 29.8 198 47.9 198 9.27 198 66.0 194 77.1 197 50.7 195 80.8 197 89.3 198 46.8 195 45.1 198 70.6 197 35.5 199 33.5 169 69.6 193 6.07 196 43.5 197 84.0 198 6.51 198
AVG_FLOW_ROB [137]198.2 51.4 199 76.8 199 29.6 199 67.5 199 74.0 199 36.6 199 51.8 199 59.9 199 20.1 199 84.7 199 90.1 199 64.7 199 81.8 199 91.0 199 44.5 183 51.7 199 87.4 199 33.4 197 57.5 199 81.8 199 10.1 199 63.2 199 86.1 199 26.5 199
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.