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
SoftSplat [169]3.4 2.65 1 7.02 1 0.04 1 6.02 1 11.7 1 0.36 1 0.76 1 2.62 1 0.14 1 12.4 1 17.7 1 2.72 2 34.8 6 48.1 6 2.88 2 6.77 4 26.6 4 0.18 1 8.47 8 34.7 11 0.27 7 15.7 3 38.6 3 0.35 14
FGME [158]8.7 2.80 2 7.23 2 0.05 3 7.70 10 13.7 7 0.91 120 1.60 6 4.12 6 0.27 4 14.3 4 18.9 2 3.96 16 31.6 1 44.3 1 2.80 1 5.95 2 23.1 2 0.26 10 7.48 1 29.1 1 0.23 1 14.6 2 36.0 2 0.29 3
EDSC [174]11.4 3.16 9 9.09 11 0.06 7 7.15 6 14.0 9 0.76 91 1.96 10 4.59 8 0.34 35 16.0 13 22.5 13 3.59 7 34.6 4 47.6 3 3.26 12 6.93 5 27.4 5 0.22 4 7.76 3 31.6 3 0.24 3 17.1 6 41.8 6 0.28 1
EAFI [171]12.2 2.94 5 8.53 7 0.07 14 7.39 7 14.0 9 0.89 117 1.37 4 4.19 7 0.18 3 14.7 6 20.2 4 3.42 5 37.3 16 51.6 16 3.12 7 7.45 10 29.3 10 0.21 3 8.28 7 33.7 8 0.23 1 18.1 8 44.0 8 0.32 11
BMBC [172]12.2 3.50 18 8.86 9 0.04 1 7.12 5 13.4 5 0.41 9 4.49 26 9.79 25 0.38 63 14.7 6 20.3 6 3.29 4 34.6 4 48.0 5 3.23 11 7.05 6 27.6 6 0.33 16 9.04 11 35.0 12 0.37 18 15.9 4 39.1 4 0.40 20
AdaCoF [165]15.4 3.54 20 10.4 20 0.07 14 7.54 8 14.3 11 0.64 70 2.86 20 5.93 16 0.37 59 17.0 16 23.3 16 3.75 11 37.9 19 51.6 16 3.57 19 6.42 3 25.3 3 0.18 1 7.91 6 32.6 6 0.24 3 16.0 5 39.4 5 0.29 3
TC-GAN [166]17.9 3.27 11 10.0 16 0.07 14 7.97 13 15.3 18 1.01 135 1.94 9 4.87 11 0.33 27 15.5 11 22.3 10 3.56 6 35.3 10 49.0 10 3.18 8 7.85 13 30.7 14 0.30 13 9.41 16 38.2 16 0.28 9 19.5 15 47.1 18 0.31 7
DAIN [152]18.3 3.36 14 10.3 18 0.06 7 8.05 15 15.2 17 1.00 133 1.92 8 5.22 12 0.33 27 15.5 11 22.3 10 3.63 8 35.4 12 49.1 11 3.27 13 7.85 13 30.7 14 0.32 14 9.40 15 38.3 18 0.28 9 19.5 15 47.1 18 0.31 7
DSepConv [162]18.8 3.54 20 10.6 22 0.07 14 8.36 27 15.4 20 0.95 130 2.48 16 5.57 14 0.32 23 18.0 38 24.2 20 3.91 15 34.8 6 47.9 4 3.40 16 7.13 9 28.0 8 0.26 10 7.79 4 31.8 4 0.27 7 18.1 8 44.1 9 0.31 7
STSR [170]21.2 3.19 10 9.43 12 0.05 3 6.49 3 12.0 3 0.83 105 2.34 15 5.98 18 0.39 68 14.5 5 20.6 7 4.11 18 40.2 22 55.5 22 3.53 18 8.92 22 34.8 23 0.39 17 9.69 26 39.4 23 0.31 13 20.0 20 48.5 22 0.33 13
MAF-net [163]21.3 2.92 4 8.49 6 0.06 7 8.09 17 15.4 20 1.02 138 2.12 12 5.68 15 0.37 59 16.3 14 22.4 12 4.94 23 39.6 21 54.0 21 3.79 20 8.35 17 32.3 17 0.44 19 8.53 9 34.6 10 0.30 12 18.9 13 46.1 14 0.32 11
DCM [185]21.9 2.97 6 8.26 5 0.05 3 6.39 2 11.9 2 0.57 51 0.94 2 2.82 2 0.15 2 14.1 3 20.2 4 3.12 3 37.3 16 51.6 16 3.21 10 8.39 18 32.3 17 0.23 6 11.5 164 39.2 21 0.49 95 20.3 23 48.2 21 0.46 33
STAR-Net [164]21.9 2.81 3 7.50 3 0.05 3 7.89 12 14.8 14 0.67 76 2.63 18 3.49 5 0.42 81 15.1 9 21.3 9 2.66 1 33.2 2 46.5 2 2.89 4 7.74 12 30.0 13 0.22 4 12.1 174 35.2 13 0.41 24 19.1 14 44.8 12 0.39 18
FRUCnet [153]22.5 3.63 22 10.4 20 0.09 22 7.97 13 14.6 12 0.90 118 2.48 16 6.05 19 0.51 113 18.1 47 24.7 21 3.76 12 35.2 9 48.7 9 2.88 2 7.06 7 27.7 7 0.32 14 9.00 10 33.4 7 0.32 14 18.2 10 44.3 11 0.30 5
MEMC-Net+ [160]24.5 3.38 15 9.77 13 0.06 7 8.14 18 14.9 15 1.03 141 2.33 14 5.37 13 0.47 102 17.0 16 22.8 14 3.73 10 37.3 16 51.6 16 3.20 9 8.64 20 33.4 20 0.26 10 9.79 42 38.2 16 0.29 11 19.5 15 47.5 20 0.35 14
ADC [161]25.2 4.18 27 12.4 27 0.09 22 8.29 26 14.9 15 0.83 105 3.92 25 7.64 22 0.40 73 18.9 108 25.4 24 4.04 17 37.1 15 50.6 15 3.48 17 7.11 8 28.0 8 0.23 6 7.88 5 32.5 5 0.26 5 18.5 11 45.1 13 0.30 5
GDCN [173]26.9 3.35 13 10.3 18 0.06 7 10.0 100 17.8 52 0.86 111 1.87 7 4.70 9 0.55 124 18.1 47 23.0 15 3.87 14 35.0 8 48.4 8 3.38 15 7.51 11 29.5 11 0.40 18 9.10 12 34.2 9 0.34 16 17.1 6 42.4 7 0.31 7
DAI [168]29.2 3.27 11 8.01 4 0.55 177 8.25 22 14.7 13 1.66 176 1.06 3 3.37 4 0.30 15 13.8 2 19.0 3 4.69 20 38.6 20 53.2 20 3.04 6 8.51 19 33.0 19 0.24 9 10.0 79 37.6 15 0.32 14 19.5 15 46.9 17 0.39 18
OFRI [154]30.0 3.15 8 8.69 8 0.09 22 7.77 11 13.9 8 0.98 132 1.45 5 2.88 3 0.33 27 14.9 8 20.8 8 3.70 9 35.3 10 49.1 11 3.31 14 8.88 21 33.4 20 0.44 19 15.2 184 39.3 22 0.50 108 20.4 24 46.6 16 0.43 23
FeFlow [167]31.8 3.10 7 8.86 9 0.06 7 8.07 16 15.6 23 1.13 149 2.03 11 4.86 10 0.36 52 16.5 15 23.3 16 3.78 13 34.4 3 48.3 7 3.03 5 8.34 16 32.2 16 0.23 6 11.6 165 36.7 14 0.51 118 19.5 15 46.2 15 0.48 55
CyclicGen [149]32.6 3.50 18 9.95 14 0.13 29 7.67 9 12.9 4 1.52 174 3.74 23 10.6 26 0.48 107 19.1 122 25.7 25 5.85 148 36.7 14 49.3 13 3.80 21 5.69 1 21.5 1 0.50 21 7.53 2 30.4 2 0.26 5 13.5 1 33.4 1 0.28 1
CtxSyn [134]35.3 3.42 17 9.96 15 0.08 19 6.79 4 13.5 6 0.50 40 2.17 13 5.94 17 0.43 87 15.1 9 23.3 16 4.57 19 42.2 27 56.7 27 4.54 26 10.0 27 36.5 26 0.63 23 13.5 181 44.0 146 0.40 22 21.1 31 49.2 26 0.43 23
PMMST [112]36.7 4.93 29 13.9 29 0.13 29 8.97 54 17.1 38 0.43 15 6.00 36 13.4 29 0.27 4 17.6 20 26.2 31 5.24 46 43.0 41 57.7 35 5.17 48 10.3 30 39.1 33 0.87 41 9.75 34 41.0 41 0.44 44 21.5 61 51.9 72 0.47 40
MDP-Flow2 [68]37.8 4.89 28 14.4 30 0.12 28 8.58 32 16.9 35 0.39 4 5.95 32 13.6 31 0.28 7 17.7 22 26.7 41 5.32 65 42.9 33 57.6 31 5.13 42 10.6 48 40.1 54 0.92 52 9.75 34 41.0 41 0.43 35 21.6 76 51.9 72 0.46 33
UnDAF [184]38.0 4.94 30 14.6 32 0.14 38 8.60 33 17.0 36 0.40 6 6.04 41 13.9 36 0.29 12 17.7 22 26.4 36 5.26 51 43.0 41 57.7 35 5.14 43 10.6 48 40.2 60 0.92 52 9.76 39 41.0 41 0.41 24 21.5 61 51.8 62 0.46 33
SepConv-v1 [125]38.9 3.41 16 11.0 23 0.08 19 8.39 28 16.7 33 1.04 143 2.81 19 7.63 21 0.74 148 18.0 38 25.2 23 5.82 145 42.9 33 57.4 28 4.74 28 9.03 23 34.1 22 0.60 22 9.34 14 38.6 19 0.42 28 20.1 22 48.6 24 0.35 14
SuperSlomo [130]39.3 3.75 23 10.1 17 0.19 97 8.96 53 16.5 29 1.31 160 3.32 22 8.42 23 0.29 12 17.7 22 24.1 19 5.32 65 41.4 23 55.9 23 4.24 23 9.50 25 35.3 25 0.67 24 10.8 144 40.3 26 0.37 18 20.4 24 48.7 25 0.42 21
CoT-AMFlow [175]40.5 4.96 32 14.7 37 0.13 29 8.63 34 17.1 38 0.40 6 6.04 41 13.8 33 0.28 7 17.6 20 26.2 31 5.20 33 43.1 54 57.7 35 5.19 54 10.7 57 40.4 73 0.96 72 9.80 46 41.1 48 0.42 28 21.5 61 51.8 62 0.47 40
NNF-Local [75]42.8 5.11 42 15.7 55 0.11 25 8.18 20 15.8 25 0.39 4 6.01 39 13.5 30 0.27 4 18.3 61 28.3 83 5.29 57 43.0 41 57.6 31 5.11 40 10.8 75 40.9 92 1.01 83 9.67 25 40.7 32 0.46 61 21.2 33 51.2 37 0.46 33
NN-field [71]43.1 5.14 47 16.1 79 0.13 29 8.21 21 15.7 24 0.38 3 6.39 76 13.6 31 0.30 15 18.4 67 28.7 102 5.33 70 42.9 33 57.6 31 5.08 37 10.7 57 40.2 60 0.94 62 9.62 21 40.5 29 0.44 44 21.2 33 51.2 37 0.45 26
MPRN [151]47.5 4.10 26 11.9 25 0.06 7 9.67 85 16.8 34 0.78 95 7.31 150 18.6 158 0.47 102 18.0 38 25.8 26 4.76 21 41.6 25 56.1 24 4.34 25 9.29 24 34.9 24 0.68 25 10.3 113 40.9 37 0.34 16 20.0 20 48.5 22 0.36 17
Layers++ [37]48.4 5.25 63 15.9 63 0.17 74 8.27 23 15.5 22 0.37 2 6.16 52 14.3 41 0.38 63 18.0 38 26.9 46 5.32 65 43.1 54 57.9 51 5.24 72 10.7 57 40.6 85 0.97 77 9.70 27 40.7 32 0.39 20 21.3 40 51.3 40 0.48 55
TOF-M [150]49.8 3.92 24 11.5 24 0.08 19 8.90 48 17.4 44 1.19 154 3.87 24 8.82 24 0.52 118 17.9 32 25.1 22 5.20 33 42.1 26 56.6 26 4.68 27 10.0 27 36.7 27 0.69 26 12.8 180 41.1 48 0.47 81 21.8 104 50.8 31 0.45 26
PH-Flow [99]51.3 5.32 77 16.4 92 0.16 63 8.28 24 15.9 26 0.44 18 6.12 49 13.9 36 0.33 27 17.5 18 25.8 26 5.15 31 42.8 31 57.5 29 5.03 34 11.0 104 41.6 127 1.09 109 9.71 28 41.0 41 0.46 61 21.3 40 51.4 43 0.50 98
nLayers [57]54.0 5.26 66 15.8 60 0.16 63 8.54 30 16.6 31 0.45 22 5.89 29 13.1 27 0.30 15 18.1 47 27.1 51 5.35 77 43.3 90 58.0 66 5.36 111 10.8 75 40.9 92 1.11 113 9.65 24 40.1 24 0.48 89 21.2 33 51.1 35 0.45 26
COFM [59]54.2 5.08 40 15.1 40 0.19 97 8.86 44 17.4 44 0.48 31 6.37 72 14.2 40 0.40 73 17.7 22 26.2 31 5.11 25 42.9 33 57.8 41 5.02 33 10.9 88 41.6 127 1.11 113 9.24 13 38.8 20 0.50 108 21.5 61 51.9 72 0.46 33
Sparse-NonSparse [56]54.7 5.31 76 16.3 90 0.17 74 8.74 38 17.2 43 0.48 31 6.19 53 14.7 54 0.34 35 17.9 32 26.3 34 5.23 43 43.1 54 57.8 41 5.25 76 11.0 104 41.2 104 1.04 91 9.71 28 40.9 37 0.46 61 21.2 33 51.3 40 0.47 40
IROF++ [58]56.2 5.37 89 16.8 108 0.14 38 8.87 46 17.4 44 0.45 22 6.41 83 14.6 51 0.43 87 17.5 18 25.8 26 5.22 38 42.9 33 57.8 41 5.19 54 10.5 38 39.4 40 0.87 41 10.0 79 42.4 97 0.47 81 21.4 51 51.5 45 0.50 98
TV-L1-MCT [64]57.5 5.74 147 18.1 148 0.18 88 9.50 76 19.1 74 0.58 54 5.73 27 14.5 48 0.38 63 17.8 28 26.0 30 5.28 55 43.0 41 57.9 51 5.22 66 10.4 32 39.1 33 0.94 62 9.78 41 41.1 48 0.44 44 21.2 33 51.1 35 0.48 55
HAST [107]58.5 5.12 44 15.2 42 0.16 63 8.74 38 17.1 38 0.43 15 6.62 110 15.3 79 0.39 68 17.7 22 26.4 36 4.98 24 43.0 41 58.0 66 5.05 35 11.0 104 41.4 114 1.06 99 9.53 17 40.4 27 0.42 28 22.0 128 52.8 126 0.47 40
ComponentFusion [94]59.6 5.15 48 16.1 79 0.14 38 8.86 44 17.9 55 0.41 9 6.38 73 15.4 80 0.33 27 17.8 28 27.0 49 5.15 31 43.2 78 58.0 66 5.24 72 10.6 48 39.8 44 0.94 62 10.0 79 42.7 117 0.57 140 21.5 61 51.8 62 0.47 40
FMOF [92]60.5 5.62 132 17.2 122 0.21 110 8.71 37 17.0 36 0.44 18 6.38 73 14.7 54 0.46 97 18.6 81 28.0 69 5.31 62 43.1 54 57.9 51 5.15 46 10.8 75 40.5 80 0.87 41 9.60 19 40.4 27 0.40 22 21.5 61 51.7 53 0.46 33
ProbFlowFields [126]60.6 5.03 35 15.6 53 0.17 74 8.55 31 17.1 38 0.41 9 6.00 36 14.4 44 0.32 23 18.1 47 27.1 51 5.38 85 43.3 90 58.1 86 5.49 157 10.9 88 41.2 104 1.20 132 9.61 20 40.7 32 0.47 81 21.0 30 50.8 31 0.49 78
MS-PFT [159]63.2 3.98 25 12.0 26 0.07 14 9.28 68 16.4 28 0.86 111 3.12 21 7.20 20 0.98 159 22.4 171 32.6 170 4.80 22 36.3 13 50.4 14 4.00 22 7.91 15 29.9 12 0.77 28 15.0 183 41.7 67 0.86 170 18.6 12 44.1 9 0.53 137
2DHMM-SAS [90]64.7 5.62 132 17.6 139 0.18 88 10.1 103 19.7 92 0.64 70 5.73 27 14.4 44 0.37 59 17.7 22 25.9 29 5.30 59 43.0 41 57.8 41 5.26 80 10.7 57 40.0 52 0.82 32 9.83 49 41.3 54 0.48 89 21.6 76 52.0 77 0.47 40
VCN_RVC [179]64.8 5.47 107 18.2 150 0.15 48 8.99 56 18.3 63 0.44 18 6.54 94 17.0 129 0.35 46 18.2 56 28.5 92 5.35 77 43.1 54 57.9 51 5.20 58 10.7 57 40.4 73 0.80 30 9.97 75 41.7 67 0.44 44 20.9 27 50.5 28 0.48 55
RAFT-TF_RVC [180]65.1 5.24 62 17.0 116 0.11 25 8.75 40 17.8 52 0.42 12 6.09 45 14.5 48 0.34 35 18.3 61 28.6 99 5.33 70 43.4 108 58.1 86 5.25 76 13.0 182 40.4 73 3.31 184 9.63 22 40.7 32 0.41 24 20.9 27 50.6 29 0.48 55
CombBMOF [111]65.2 5.46 104 16.2 88 0.22 122 8.89 47 18.0 57 0.45 22 6.29 60 14.7 54 0.40 73 18.5 76 28.0 69 5.24 46 43.0 41 57.7 35 5.08 37 10.8 75 40.2 60 0.82 32 11.7 169 42.9 125 0.47 81 21.2 33 50.9 33 0.45 26
LSM [39]65.6 5.49 110 17.4 132 0.18 88 8.93 50 17.7 50 0.48 31 6.32 65 15.4 80 0.35 46 18.1 47 27.1 51 5.22 38 43.1 54 57.9 51 5.28 90 11.0 104 41.3 110 1.03 89 9.72 31 40.9 37 0.46 61 21.4 51 51.7 53 0.48 55
Ramp [62]67.8 5.46 104 17.1 119 0.18 88 8.84 42 17.4 44 0.58 54 6.14 50 14.7 54 0.34 35 17.8 28 26.4 36 5.23 43 43.2 78 58.0 66 5.27 85 11.2 129 42.0 140 1.15 122 9.72 31 40.9 37 0.42 28 21.6 76 52.1 84 0.48 55
NNF-EAC [101]68.8 5.52 114 15.7 55 0.34 163 9.27 67 18.1 59 0.48 31 6.53 93 13.8 33 0.40 73 18.2 56 27.0 49 5.71 134 43.0 41 57.7 35 5.11 40 10.4 32 39.1 33 0.83 35 9.89 58 41.6 64 0.52 124 21.7 90 52.2 93 0.49 78
DeepFlow [85]69.0 5.06 39 14.6 32 0.19 97 9.80 92 19.5 81 0.75 90 6.45 86 16.6 117 0.35 46 18.7 92 27.6 61 5.41 94 43.4 108 58.0 66 5.37 114 10.3 30 38.3 29 0.99 79 9.83 49 41.8 72 0.43 35 21.3 40 51.6 51 0.48 55
DeepFlow2 [106]69.2 5.16 49 14.9 39 0.21 110 9.81 93 19.7 92 0.65 73 6.38 73 16.3 105 0.34 35 18.6 81 28.1 74 5.29 57 43.4 108 58.0 66 5.37 114 10.2 29 38.4 30 0.85 38 9.96 73 42.1 88 0.44 44 21.4 51 51.8 62 0.49 78
LME [70]69.4 5.13 46 15.8 60 0.14 38 9.15 64 18.4 70 0.51 41 6.32 65 15.7 88 0.34 35 17.9 32 27.1 51 5.34 73 43.8 162 58.8 160 5.79 176 10.8 75 41.2 104 0.93 57 9.86 54 41.3 54 0.43 35 21.3 40 51.5 45 0.47 40
PRAFlow_RVC [178]69.6 5.29 71 16.9 112 0.11 25 9.02 60 18.2 61 0.48 31 5.95 32 13.8 33 0.29 12 18.6 81 28.9 112 5.50 112 43.3 90 58.0 66 5.39 122 10.4 32 39.2 36 0.87 41 9.71 28 41.2 52 0.46 61 22.1 137 52.6 114 0.54 150
PGM-C [118]69.7 5.18 52 16.0 71 0.15 48 8.97 54 18.2 61 0.46 28 6.51 89 16.4 111 0.33 27 18.4 67 28.5 92 5.36 81 43.4 108 58.1 86 5.40 130 10.7 57 40.5 80 0.96 72 9.92 62 41.9 76 0.45 53 21.4 51 51.8 62 0.48 55
FlowFields+ [128]69.8 5.23 61 16.6 100 0.15 48 8.91 49 18.3 63 0.45 22 6.28 59 15.9 92 0.34 35 18.2 56 28.1 74 5.34 73 43.4 108 58.2 99 5.35 107 10.9 88 41.6 127 1.10 111 9.79 42 41.5 59 0.46 61 21.3 40 51.5 45 0.48 55
WLIF-Flow [91]70.5 5.25 63 16.0 71 0.15 48 9.14 63 18.1 59 0.59 60 6.29 60 14.3 41 0.34 35 17.9 32 26.3 34 5.65 129 43.1 54 57.9 51 5.26 80 11.2 129 41.9 139 1.22 138 9.82 48 41.3 54 0.44 44 21.7 90 52.2 93 0.49 78
HCFN [157]70.7 5.11 42 16.0 71 0.15 48 9.40 74 19.6 87 0.48 31 6.30 64 15.5 84 0.36 52 18.0 38 27.6 61 5.26 51 43.0 41 57.8 41 5.17 48 12.5 179 40.5 80 3.11 183 10.0 79 42.1 88 0.49 95 21.4 51 51.7 53 0.48 55
EAI-Flow [147]70.8 5.33 83 15.9 63 0.17 74 9.73 90 19.6 87 0.71 83 6.61 104 16.3 105 0.36 52 18.3 61 28.1 74 5.11 25 43.1 54 57.9 51 5.31 93 10.7 57 39.9 48 0.98 78 10.1 93 42.7 117 0.51 118 21.1 31 50.9 33 0.44 25
FlowFields [108]71.2 5.22 59 16.5 95 0.16 63 8.95 51 18.3 63 0.42 12 6.29 60 15.9 92 0.35 46 18.4 67 28.5 92 5.41 94 43.4 108 58.1 86 5.33 97 10.9 88 41.3 110 1.08 104 9.79 42 41.5 59 0.45 53 21.3 40 51.6 51 0.49 78
Classic+NL [31]71.4 5.56 122 17.4 132 0.22 122 8.99 56 17.6 49 0.54 45 6.02 40 14.7 54 0.36 52 18.1 47 26.8 42 5.41 94 43.1 54 58.0 66 5.23 69 11.1 124 41.5 120 1.06 99 9.72 31 41.0 41 0.46 61 21.6 76 52.0 77 0.47 40
JOF [136]72.7 5.53 118 16.9 112 0.21 110 8.65 35 16.6 31 0.48 31 6.08 44 14.0 38 0.34 35 18.1 47 26.8 42 5.59 122 43.4 108 58.2 99 5.45 147 11.1 124 41.4 114 1.04 91 9.64 23 40.6 30 0.43 35 21.6 76 52.0 77 0.48 55
S2F-IF [121]73.3 5.22 59 16.5 95 0.15 48 8.84 42 18.0 57 0.44 18 6.27 58 15.7 88 0.33 27 18.3 61 28.3 83 5.14 30 43.4 108 58.2 99 5.41 134 11.0 104 41.5 120 1.11 113 9.91 61 41.9 76 0.47 81 21.3 40 51.5 45 0.51 112
FC-2Layers-FF [74]73.3 5.40 94 17.0 116 0.17 74 8.15 19 15.3 18 0.42 12 6.14 50 14.9 62 0.35 46 18.1 47 27.2 56 5.31 62 43.3 90 58.2 99 5.36 111 11.2 129 42.2 144 1.20 132 9.75 34 41.0 41 0.49 95 21.7 90 52.1 84 0.48 55
SegFlow [156]73.5 5.19 53 16.1 79 0.15 48 9.01 59 18.4 70 0.48 31 6.40 79 16.0 96 0.30 15 18.3 61 28.3 83 5.37 83 43.3 90 58.1 86 5.41 134 10.8 75 41.0 98 1.14 119 10.0 79 42.4 97 0.46 61 21.4 51 51.8 62 0.48 55
DF-Auto [113]73.8 5.03 35 13.8 28 0.17 74 10.2 105 19.3 77 0.79 97 6.09 45 14.4 44 0.34 35 18.7 92 28.1 74 5.24 46 43.2 78 57.9 51 5.31 93 10.4 32 39.3 37 0.93 57 10.1 93 42.3 94 0.49 95 21.9 120 52.9 133 0.53 137
AGIF+OF [84]74.0 5.60 128 17.4 132 0.15 48 8.95 51 17.7 50 0.59 60 6.20 55 14.5 48 0.43 87 17.9 32 26.6 40 5.22 38 43.4 108 58.3 123 5.38 120 11.1 124 42.0 140 1.01 83 9.87 57 40.7 32 0.42 28 21.5 61 52.0 77 0.48 55
OFLAF [78]74.2 5.16 49 15.9 63 0.14 38 8.28 24 16.1 27 0.40 6 6.34 70 14.9 62 0.30 15 18.0 38 27.3 57 5.11 25 43.3 90 58.1 86 5.39 122 11.2 129 42.4 146 1.21 135 10.1 93 42.4 97 0.60 148 21.9 120 52.6 114 0.45 26
MDP-Flow [26]75.5 5.03 35 15.4 44 0.14 38 8.68 36 17.4 44 0.47 29 5.97 34 14.3 41 0.32 23 18.9 108 28.5 92 5.50 112 43.2 78 58.0 66 5.39 122 11.2 129 42.6 149 1.31 149 10.3 113 43.1 132 0.49 95 21.4 51 51.7 53 0.47 40
S2D-Matching [83]77.0 5.56 122 17.3 126 0.18 88 9.96 98 19.9 97 0.66 75 5.99 35 14.7 54 0.41 79 17.9 32 26.4 36 5.40 91 43.2 78 58.0 66 5.17 48 11.2 129 42.0 140 1.17 127 9.93 65 41.1 48 0.43 35 21.5 61 51.8 62 0.48 55
TF+OM [98]79.0 4.98 33 14.6 32 0.20 103 9.03 61 17.9 55 0.55 47 6.29 60 16.2 101 0.39 68 18.5 76 28.0 69 5.50 112 43.3 90 58.1 86 5.47 152 10.6 48 39.8 44 1.03 89 9.86 54 42.0 82 0.51 118 21.7 90 52.3 98 0.52 127
ALD-Flow [66]79.1 5.37 89 16.1 79 0.23 129 9.53 77 19.2 76 0.57 51 6.51 89 16.7 121 0.34 35 18.2 56 27.9 65 5.32 65 43.4 108 58.3 123 5.46 150 10.7 57 39.9 48 0.99 79 9.76 39 41.2 52 0.44 44 21.8 104 52.7 122 0.47 40
CPM-Flow [114]79.2 5.20 58 16.1 79 0.16 63 8.99 56 18.3 63 0.47 29 6.42 84 16.0 96 0.30 15 18.8 100 29.2 126 5.43 101 43.4 108 58.2 99 5.44 145 10.6 48 40.1 54 1.02 85 10.0 79 42.6 109 0.45 53 21.4 51 51.8 62 0.53 137
Brox et al. [5]79.3 5.33 83 15.4 44 0.19 97 10.2 105 20.1 101 0.64 70 6.61 104 17.2 133 0.46 97 18.7 92 28.2 79 5.21 35 43.4 108 58.1 86 5.27 85 10.7 57 40.1 54 0.99 79 9.90 60 42.0 82 0.45 53 21.6 76 52.1 84 0.47 40
ProFlow_ROB [142]79.3 5.09 41 15.4 44 0.17 74 9.40 74 19.3 77 0.55 47 6.34 70 15.4 80 0.33 27 18.4 67 28.7 102 5.39 89 43.5 136 58.3 123 5.41 134 10.4 32 39.3 37 0.79 29 10.2 105 42.9 125 0.49 95 21.8 104 52.6 114 0.49 78
DMF_ROB [135]80.1 5.30 74 15.8 60 0.20 103 10.2 105 20.5 109 0.73 86 7.26 146 18.0 149 0.75 149 18.9 108 28.8 107 5.40 91 43.1 54 57.9 51 5.34 103 10.5 38 39.8 44 0.92 52 9.98 77 41.5 59 0.43 35 21.3 40 51.4 43 0.47 40
AggregFlow [95]80.2 5.64 135 17.2 122 0.22 122 9.81 93 19.5 81 0.59 60 6.11 48 14.4 44 0.28 7 18.9 108 29.0 117 5.30 59 43.4 108 58.2 99 5.33 97 10.7 57 40.2 60 0.96 72 9.89 58 41.7 67 0.50 108 21.4 51 51.7 53 0.50 98
SVFilterOh [109]80.6 5.32 77 15.7 55 0.21 110 8.78 41 17.1 38 0.49 39 6.40 79 14.6 51 0.38 63 18.4 67 27.1 51 5.80 143 43.8 162 58.6 153 5.65 170 10.9 88 41.0 98 1.04 91 9.54 18 40.1 24 0.43 35 21.7 90 52.2 93 0.50 98
RNLOD-Flow [119]83.0 5.32 77 16.6 100 0.16 63 9.70 87 19.6 87 0.60 64 6.57 98 15.5 84 0.51 113 18.2 56 27.4 58 5.22 38 43.1 54 58.0 66 5.28 90 11.0 104 41.4 114 1.08 104 9.85 52 41.3 54 0.50 108 21.9 120 52.7 122 0.49 78
Second-order prior [8]83.3 5.29 71 15.3 43 0.27 146 10.8 126 21.1 120 0.78 95 7.14 138 17.8 147 0.62 139 18.6 81 28.3 83 5.21 35 42.9 33 57.7 35 5.16 47 10.5 38 39.6 42 0.93 57 10.2 105 42.8 122 0.44 44 21.6 76 52.3 98 0.49 78
IROF-TV [53]83.9 5.35 88 16.6 100 0.21 110 9.10 62 17.8 52 0.57 51 6.61 104 16.8 123 0.44 91 17.8 28 26.9 46 5.37 83 43.5 136 58.4 138 5.50 160 10.5 38 40.1 54 0.90 49 9.98 77 42.2 91 0.46 61 21.6 76 52.1 84 0.51 112
DPOF [18]84.8 5.51 113 17.9 146 0.22 122 8.45 29 16.5 29 0.43 15 6.87 121 15.1 72 0.59 132 18.9 108 29.5 132 5.43 101 42.9 33 57.8 41 5.05 35 11.0 104 40.9 92 0.84 37 10.3 113 42.5 105 0.45 53 21.9 120 52.8 126 0.48 55
TC-Flow [46]86.9 5.19 53 15.9 63 0.21 110 9.57 78 19.6 87 0.63 67 6.78 118 17.0 129 0.36 52 18.1 47 27.4 58 5.61 125 43.3 90 58.2 99 5.46 150 11.0 104 41.6 127 1.18 128 9.93 65 41.7 67 0.45 53 21.5 61 52.0 77 0.49 78
OAR-Flow [123]87.4 5.28 69 15.5 48 0.18 88 9.71 89 19.5 81 0.67 76 6.43 85 16.3 105 0.28 7 18.0 38 27.6 61 5.23 43 43.5 136 58.4 138 5.48 155 10.9 88 41.3 110 1.13 118 10.2 105 42.9 125 0.51 118 21.7 90 52.3 98 0.45 26
Aniso. Huber-L1 [22]88.2 5.41 96 16.0 71 0.23 129 11.2 137 21.1 120 0.90 118 6.72 113 15.4 80 0.46 97 18.5 76 28.1 74 5.39 89 43.0 41 57.8 41 5.23 69 10.5 38 40.1 54 0.81 31 10.2 105 42.6 109 0.46 61 21.9 120 52.7 122 0.52 127
EpicFlow [100]88.8 5.19 53 16.1 79 0.15 48 9.60 79 19.8 96 0.58 54 6.40 79 16.4 111 0.35 46 18.6 81 29.1 124 5.47 108 43.4 108 58.2 99 5.42 139 10.8 75 41.2 104 1.08 104 10.1 93 42.5 105 0.54 131 21.5 61 52.0 77 0.49 78
ComplOF-FED-GPU [35]89.2 5.30 74 16.1 79 0.19 97 9.39 72 19.3 77 0.58 54 7.21 142 16.9 126 0.66 142 18.4 67 28.6 99 5.32 65 43.1 54 58.0 66 5.27 85 10.8 75 40.9 92 0.99 79 10.1 93 42.8 122 0.47 81 21.8 104 52.3 98 0.50 98
FF++_ROB [141]89.8 5.19 53 16.1 79 0.13 29 9.36 71 19.0 73 0.51 41 6.52 92 16.2 101 0.46 97 18.6 81 28.8 107 5.41 94 43.4 108 58.2 99 5.44 145 11.3 137 41.2 104 1.71 173 9.85 52 41.8 72 0.49 95 21.3 40 51.5 45 0.57 167
FESL [72]90.3 5.65 138 17.3 126 0.17 74 9.18 65 18.3 63 0.55 47 6.22 56 15.0 68 0.44 91 18.8 100 28.4 87 5.38 85 43.4 108 58.2 99 5.41 134 11.3 137 42.8 153 1.19 130 9.92 62 41.5 59 0.42 28 21.8 104 52.3 98 0.48 55
Classic+CPF [82]91.0 5.59 127 17.3 126 0.16 63 9.22 66 18.3 63 0.58 54 6.00 36 14.9 62 0.40 73 18.0 38 26.8 42 5.22 38 43.5 136 58.5 146 5.38 120 11.4 144 43.0 161 1.15 122 10.1 93 41.9 76 0.45 53 22.0 128 53.1 140 0.49 78
PMF [73]91.9 5.32 77 16.6 100 0.14 38 9.67 85 19.9 97 0.45 22 6.89 127 18.2 153 0.49 109 18.4 67 27.9 65 5.21 35 43.5 136 58.4 138 5.22 66 11.0 104 40.5 80 1.27 145 9.86 54 41.8 72 0.46 61 22.1 137 53.1 140 0.50 98
Local-TV-L1 [65]93.7 5.29 71 14.6 32 0.35 165 11.5 145 21.1 120 1.23 155 6.39 76 14.9 62 0.37 59 19.0 116 27.9 65 6.64 165 43.3 90 58.3 123 5.33 97 10.9 88 39.0 31 1.58 172 9.79 42 41.6 64 0.48 89 21.3 40 51.5 45 0.53 137
RFlow [88]93.8 5.19 53 16.1 79 0.23 129 10.8 126 21.2 124 0.85 109 6.59 102 16.0 96 0.51 113 18.8 100 28.8 107 5.47 108 43.1 54 58.0 66 5.21 64 10.5 38 40.0 52 0.93 57 10.0 79 42.6 109 0.49 95 22.1 137 53.2 143 0.51 112
PWC-Net_RVC [143]94.2 5.47 107 18.4 155 0.13 29 9.99 99 20.9 116 0.53 43 6.74 114 17.5 141 0.41 79 18.3 61 28.8 107 5.25 50 43.5 136 58.3 123 5.45 147 11.2 129 41.0 98 1.22 138 9.93 65 41.8 72 0.46 61 21.3 40 51.3 40 0.51 112
TriFlow [93]95.5 5.42 97 17.0 116 0.24 135 10.9 129 21.2 124 0.91 120 6.61 104 16.8 123 0.36 52 18.9 108 29.0 117 5.28 55 43.2 78 58.2 99 5.37 114 11.0 104 40.9 92 0.95 67 9.96 73 41.7 67 0.49 95 21.7 90 52.2 93 0.47 40
CLG-TV [48]95.9 5.32 77 15.7 55 0.26 143 11.0 134 21.2 124 0.83 105 6.75 116 16.6 117 0.56 126 18.9 108 28.4 87 5.50 112 43.3 90 58.1 86 5.25 76 10.5 38 39.8 44 0.87 41 10.1 93 42.5 105 0.44 44 22.0 128 53.1 140 0.51 112
EPPM w/o HM [86]95.9 5.34 86 17.3 126 0.13 29 9.73 90 20.1 101 0.53 43 7.33 153 18.7 161 0.63 140 18.5 76 29.1 124 5.33 70 43.1 54 58.0 66 5.20 58 11.0 104 41.4 114 0.96 72 10.3 113 42.3 94 0.56 137 21.8 104 52.4 109 0.49 78
Classic++ [32]96.2 5.33 83 16.0 71 0.28 147 10.2 105 20.3 105 0.69 80 6.87 121 16.6 117 0.50 110 18.7 92 27.7 64 5.64 127 43.2 78 58.0 66 5.26 80 11.0 104 40.7 88 1.34 152 9.93 65 41.9 76 0.47 81 21.7 90 52.4 109 0.50 98
SIOF [67]96.7 5.64 135 16.5 95 0.28 147 11.3 139 21.6 137 0.91 120 6.32 65 15.9 92 0.42 81 18.7 92 28.4 87 5.36 81 43.0 41 57.9 51 5.17 48 10.7 57 40.2 60 0.95 67 10.1 93 42.4 97 0.50 108 22.2 147 53.2 143 0.53 137
Efficient-NL [60]97.4 5.54 120 17.1 119 0.16 63 9.60 79 18.9 72 0.56 50 6.99 133 15.1 72 0.75 149 18.8 100 28.2 79 5.26 51 43.1 54 57.9 51 5.25 76 11.6 150 43.4 170 1.04 91 10.1 93 42.5 105 0.48 89 22.6 159 53.8 157 0.48 55
LDOF [28]98.0 5.53 118 15.6 53 0.32 159 11.1 136 20.3 105 1.45 172 6.89 127 17.3 135 0.59 132 19.0 116 28.9 112 5.63 126 43.4 108 58.2 99 5.40 130 10.4 32 39.0 31 0.83 35 9.92 62 42.4 97 0.46 61 21.6 76 52.3 98 0.46 33
ContinualFlow_ROB [148]98.1 5.85 152 19.2 162 0.16 63 10.4 114 21.5 132 0.82 101 7.31 150 18.8 163 0.51 113 18.7 92 29.7 137 5.52 117 43.1 54 58.1 86 5.33 97 10.5 38 40.3 66 0.86 39 9.97 75 41.6 64 0.43 35 21.5 61 52.1 84 0.55 160
CostFilter [40]98.2 5.44 99 17.7 141 0.13 29 9.64 82 20.1 101 0.45 22 6.96 131 19.1 164 0.47 102 18.5 76 28.9 112 5.13 29 43.6 152 58.5 146 5.32 96 11.1 124 40.5 80 1.48 164 9.94 70 42.1 88 0.45 53 21.8 104 52.6 114 0.49 78
C-RAFT_RVC [182]98.8 6.28 164 20.0 165 0.17 74 10.1 103 21.0 118 0.69 80 6.78 118 16.5 115 0.50 110 19.2 126 30.3 145 5.49 111 43.2 78 57.9 51 5.20 58 11.0 104 41.7 134 0.94 62 10.0 79 42.2 91 0.41 24 21.6 76 51.9 72 0.51 112
Complementary OF [21]99.0 5.28 69 16.7 106 0.15 48 9.39 72 19.5 81 0.58 54 7.53 158 16.3 105 1.10 169 18.7 92 29.0 117 5.35 77 43.2 78 58.2 99 5.26 80 10.9 88 41.2 104 1.16 125 10.3 113 43.4 140 0.55 134 21.5 61 52.2 93 0.51 112
F-TV-L1 [15]99.3 5.56 122 16.0 71 0.36 169 11.4 143 21.5 132 0.94 126 6.88 124 17.0 129 0.66 142 18.7 92 27.9 65 5.79 142 42.6 28 57.8 41 5.01 32 10.6 48 39.3 37 1.02 85 10.0 79 41.9 76 0.55 134 22.0 128 52.8 126 0.51 112
OFH [38]99.3 5.49 110 16.6 100 0.25 139 10.3 111 20.2 104 0.77 93 6.88 124 17.8 147 0.36 52 18.4 67 28.9 112 5.24 46 43.1 54 58.0 66 5.26 80 10.9 88 41.5 120 1.18 128 10.3 113 43.0 129 0.58 143 21.6 76 52.1 84 0.50 98
p-harmonic [29]99.7 5.17 51 15.5 48 0.16 63 11.2 137 21.4 130 0.94 126 6.55 95 17.4 140 0.55 124 19.2 126 28.6 99 5.45 105 43.3 90 58.2 99 5.27 85 10.7 57 40.2 60 1.04 91 10.4 122 43.4 140 0.50 108 21.8 104 52.6 114 0.49 78
HBM-GC [103]99.7 5.52 114 17.1 119 0.22 122 9.64 82 19.3 77 0.59 60 5.93 31 13.2 28 0.31 22 18.8 100 28.0 69 5.83 147 44.3 174 59.2 167 5.71 172 11.5 147 43.3 168 1.32 150 9.75 34 40.6 30 0.39 20 22.0 128 52.9 133 0.50 98
TC/T-Flow [77]100.3 5.73 145 17.3 126 0.22 122 9.66 84 19.7 92 0.63 67 6.24 57 14.9 62 0.32 23 18.6 81 28.7 102 5.38 85 43.5 136 58.4 138 5.50 160 11.0 104 41.4 114 0.89 48 10.2 105 43.0 129 0.58 143 21.9 120 53.0 138 0.45 26
CBF [12]100.8 4.98 33 14.8 38 0.18 88 10.2 105 19.9 97 0.71 83 6.63 111 15.2 76 0.42 81 19.0 116 28.5 92 6.39 161 43.4 108 58.3 123 5.49 157 10.7 57 40.4 73 0.95 67 10.1 93 42.6 109 0.50 108 22.3 152 53.5 153 0.53 137
LFNet_ROB [145]100.8 5.45 101 17.6 139 0.13 29 10.4 114 21.2 124 0.73 86 6.75 116 18.1 151 0.47 102 18.4 67 28.7 102 5.27 54 43.1 54 58.0 66 5.20 58 11.1 124 41.8 136 1.10 111 10.4 122 42.7 117 0.50 108 21.7 90 52.0 77 0.60 172
Steered-L1 [116]101.5 5.12 44 16.0 71 0.17 74 9.62 81 19.5 81 0.88 114 7.15 139 15.6 86 1.00 161 19.4 135 28.5 92 6.39 161 43.5 136 58.5 146 5.19 54 10.8 75 40.8 91 1.20 132 9.95 72 42.6 109 0.52 124 21.7 90 52.6 114 0.48 55
GraphCuts [14]102.0 5.98 158 17.5 137 0.24 135 10.0 100 19.5 81 0.76 91 8.24 171 14.6 51 1.06 164 19.7 141 29.0 117 5.69 132 42.9 33 57.9 51 4.97 30 10.5 38 40.3 66 0.87 41 10.0 79 42.4 97 0.58 143 22.1 137 53.2 143 0.51 112
MLDP_OF [87]102.6 5.44 99 17.2 122 0.17 74 9.84 95 19.9 97 0.62 66 6.19 53 14.8 60 0.28 7 18.6 81 27.4 58 5.71 134 43.3 90 58.2 99 5.34 103 11.9 160 43.3 168 1.57 171 10.4 122 42.6 109 0.56 137 21.7 90 52.3 98 0.59 170
AdaConv-v1 [124]102.8 6.72 172 21.8 176 0.25 139 12.8 163 22.4 156 1.80 179 8.18 170 18.4 155 1.46 178 24.3 177 34.7 179 7.39 173 41.5 24 56.1 24 4.28 24 9.57 26 36.9 28 0.71 27 9.75 34 41.0 41 0.60 148 20.5 26 49.7 27 0.42 21
SRR-TVOF-NL [89]103.9 5.70 143 16.9 112 0.23 129 10.3 111 21.0 118 0.88 114 6.57 98 16.1 99 0.39 68 19.2 126 28.7 102 5.12 28 43.2 78 58.3 123 5.27 85 10.8 75 40.9 92 0.86 39 10.6 137 42.3 94 0.46 61 22.5 155 53.8 157 0.54 150
BlockOverlap [61]104.8 5.34 86 14.6 32 0.41 174 11.4 143 20.6 110 1.42 168 6.49 87 14.1 39 0.61 137 18.9 108 26.9 46 7.34 172 44.2 172 58.9 163 5.91 178 11.0 104 39.9 48 1.39 159 9.81 47 41.3 54 0.46 61 21.5 61 51.7 53 0.51 112
Sparse Occlusion [54]105.5 5.43 98 16.8 108 0.23 129 10.3 111 20.8 114 0.63 67 6.51 89 15.0 68 0.44 91 19.0 116 29.0 117 5.42 99 43.4 108 58.2 99 5.41 134 11.3 137 42.9 159 1.14 119 10.1 93 42.2 91 0.42 28 22.1 137 53.2 143 0.49 78
CRTflow [81]106.9 5.48 109 16.5 95 0.34 163 10.7 124 20.7 111 0.86 111 7.25 145 18.6 158 0.60 136 18.8 100 28.8 107 5.98 153 43.4 108 58.2 99 5.43 141 10.7 57 40.4 73 0.95 67 9.93 65 42.0 82 0.49 95 21.7 90 52.3 98 0.49 78
LiteFlowNet [138]107.8 5.61 129 18.9 160 0.15 48 9.94 97 20.9 116 0.65 73 6.33 69 17.5 141 0.39 68 19.2 126 30.9 157 5.94 152 43.1 54 57.9 51 5.36 111 11.3 137 42.2 144 1.06 99 10.7 140 43.5 142 0.62 152 21.2 33 51.2 37 0.54 150
AugFNG_ROB [139]109.0 5.68 141 18.7 157 0.15 48 10.9 129 21.8 141 0.93 124 7.28 147 20.6 175 0.48 107 19.3 132 30.7 150 5.40 91 43.6 152 58.6 153 5.47 152 10.6 48 40.1 54 0.82 32 10.5 133 43.0 129 0.50 108 20.9 27 50.7 30 0.48 55
SimpleFlow [49]109.2 5.52 114 17.5 137 0.18 88 10.2 105 19.7 92 0.73 86 7.32 152 15.8 90 1.05 163 18.0 38 26.8 42 5.44 103 43.3 90 58.1 86 5.33 97 11.3 137 42.9 159 1.22 138 10.3 113 44.6 155 1.04 178 21.8 104 52.6 114 0.47 40
FlowNet2 [120]110.0 6.90 174 21.5 175 0.25 139 10.6 122 20.7 111 0.82 101 7.10 136 17.3 135 0.54 120 19.4 135 31.8 165 5.57 121 43.4 108 58.3 123 5.39 122 10.7 57 40.3 66 0.90 49 10.0 79 42.0 82 0.46 61 21.6 76 51.9 72 0.51 112
IAOF [50]110.6 5.97 157 16.8 108 0.29 152 14.1 178 24.8 178 1.41 167 6.05 43 16.2 101 0.61 137 20.1 149 29.5 132 5.47 108 43.0 41 57.8 41 5.19 54 10.7 57 40.3 66 0.94 62 10.4 122 43.3 137 0.46 61 22.0 128 52.8 126 0.54 150
Modified CLG [34]112.1 5.05 38 15.1 40 0.19 97 12.3 159 22.2 150 1.30 159 6.81 120 18.3 154 0.66 142 19.3 132 29.7 137 5.34 73 43.4 108 58.2 99 5.29 92 10.8 75 40.6 85 1.15 122 10.2 105 43.6 143 0.47 81 21.9 120 52.7 122 0.53 137
CompactFlow_ROB [155]113.0 5.67 140 19.0 161 0.14 38 10.4 114 21.6 137 0.77 93 7.21 142 19.2 165 0.46 97 19.3 132 31.0 159 5.65 129 43.2 78 58.0 66 5.24 72 11.0 104 41.8 136 0.87 41 10.6 137 43.3 137 0.49 95 21.8 104 52.3 98 0.53 137
FlowNetS+ft+v [110]113.6 5.40 94 15.5 48 0.29 152 11.7 151 21.7 139 1.62 175 6.88 124 17.1 132 0.56 126 19.0 116 29.2 126 5.73 138 43.5 136 58.4 138 5.56 165 10.5 38 39.9 48 0.95 67 10.1 93 42.9 125 0.52 124 21.8 104 52.5 113 0.48 55
LSM_FLOW_RVC [183]113.9 5.96 156 20.1 167 0.18 88 10.9 129 22.7 158 0.79 97 6.87 121 18.6 158 0.44 91 19.1 122 30.6 148 5.35 77 43.1 54 57.9 51 5.20 58 10.9 88 41.1 103 1.07 103 10.7 140 43.2 134 0.53 128 21.8 104 52.1 84 0.61 175
Occlusion-TV-L1 [63]114.5 5.32 77 16.2 88 0.28 147 11.3 139 21.9 144 0.96 131 6.60 103 16.9 126 0.58 130 19.1 122 28.9 112 5.72 136 43.4 108 58.2 99 5.24 72 10.9 88 40.3 66 1.26 144 10.9 148 42.6 109 0.81 168 21.8 104 52.4 109 0.49 78
EPMNet [131]115.2 6.85 173 22.5 177 0.21 110 10.5 119 20.3 105 0.84 108 7.10 136 17.3 135 0.54 120 19.9 142 33.4 175 5.56 120 43.4 108 58.3 123 5.39 122 11.0 104 41.6 127 0.92 52 10.0 79 42.0 82 0.46 61 21.6 76 51.8 62 0.54 150
Shiralkar [42]115.6 5.73 145 18.1 148 0.21 110 11.6 147 22.0 146 0.88 114 6.74 114 19.9 169 0.73 147 20.3 153 30.1 143 5.46 107 42.6 28 57.5 29 4.99 31 11.3 137 41.5 120 1.35 153 11.0 151 44.9 158 0.67 155 21.5 61 51.7 53 0.48 55
TCOF [69]115.8 5.56 122 16.8 108 0.17 74 11.8 152 22.1 148 1.02 138 6.09 45 15.0 68 0.30 15 19.0 116 29.4 130 5.67 131 43.4 108 58.3 123 5.17 48 11.4 144 43.1 164 1.02 85 11.0 151 43.9 145 0.48 89 23.1 171 55.1 176 0.52 127
HBpMotionGpu [43]116.2 5.80 149 16.3 90 0.42 175 13.1 166 23.8 169 1.34 162 6.32 65 14.9 62 0.38 63 19.9 142 30.4 147 5.80 143 43.1 54 58.3 123 5.39 122 11.3 137 41.0 98 1.21 135 9.94 70 41.9 76 0.43 35 22.1 137 52.9 133 0.53 137
3DFlow [133]116.9 5.58 126 17.4 132 0.16 63 9.35 70 19.1 74 0.61 65 6.93 130 15.0 68 0.44 91 18.6 81 28.4 87 5.54 119 43.4 108 58.2 99 5.40 130 12.1 167 44.7 182 1.35 153 11.3 158 44.6 155 0.57 140 22.4 153 53.7 156 0.50 98
Fusion [6]117.4 5.37 89 16.9 112 0.21 110 9.33 69 18.3 63 0.54 45 6.39 76 15.1 72 0.54 120 20.0 147 29.8 139 5.41 94 43.5 136 59.2 167 5.14 43 11.5 147 43.7 173 1.21 135 10.5 133 44.1 148 0.52 124 23.1 171 55.4 177 0.52 127
Adaptive [20]117.6 5.50 112 16.7 106 0.30 154 11.8 152 22.2 150 1.02 138 6.58 101 16.5 115 0.53 119 18.6 81 28.0 69 5.60 124 43.5 136 58.3 123 5.21 64 11.0 104 41.3 110 1.09 109 10.4 122 42.8 122 0.46 61 22.2 147 53.5 153 0.54 150
CNN-flow-warp+ref [115]117.7 4.95 31 14.4 30 0.22 122 10.9 129 21.2 124 1.23 155 7.43 155 18.0 149 0.79 152 20.9 163 29.8 139 6.84 168 43.5 136 58.3 123 5.57 166 10.7 57 40.3 66 1.22 138 10.3 113 44.4 153 0.67 155 21.6 76 52.1 84 0.47 40
ResPWCR_ROB [140]119.5 5.54 120 17.8 143 0.20 103 10.6 122 21.5 132 0.80 100 7.77 164 17.7 146 0.44 91 19.4 135 30.7 150 5.93 149 42.7 30 57.6 31 5.10 39 12.4 176 41.7 134 2.49 180 10.9 148 42.7 117 0.58 143 21.7 90 52.3 98 0.52 127
BriefMatch [122]119.6 5.45 101 16.5 95 0.31 158 9.84 95 19.6 87 1.43 169 7.55 160 15.6 86 1.08 166 20.3 153 29.2 126 7.97 180 43.3 90 58.3 123 5.43 141 12.0 164 41.5 120 2.37 179 9.84 51 41.5 59 0.56 137 21.4 51 51.7 53 0.52 127
Nguyen [33]121.3 5.63 134 15.9 63 0.23 129 13.8 172 23.8 169 1.37 164 6.89 127 18.7 161 0.59 132 20.8 162 30.8 154 5.44 103 43.1 54 58.1 86 5.14 43 10.6 48 40.4 73 0.93 57 11.9 171 45.9 165 0.73 164 22.0 128 52.8 126 0.52 127
TV-L1-improved [17]124.0 5.26 66 16.0 71 0.28 147 11.6 147 22.0 146 1.06 145 7.21 142 16.3 105 0.79 152 18.8 100 28.5 92 5.70 133 43.5 136 58.5 146 5.22 66 11.0 104 41.5 120 1.05 97 10.4 122 44.6 155 0.74 166 22.1 137 53.2 143 0.53 137
IRR-PWC_RVC [181]124.0 6.21 162 20.0 165 0.20 103 10.4 114 21.3 129 0.85 109 7.49 157 20.5 174 0.47 102 20.1 149 32.1 166 5.45 105 43.6 152 58.6 153 5.53 163 10.9 88 41.5 120 0.96 72 10.4 122 43.1 132 0.46 61 21.7 90 52.4 109 0.49 78
2D-CLG [1]124.0 5.27 68 15.7 55 0.21 110 13.1 166 22.8 159 1.37 164 7.29 148 17.3 135 0.94 158 20.3 153 30.2 144 5.34 73 43.5 136 58.4 138 5.37 114 10.8 75 40.7 88 1.22 138 10.5 133 44.3 151 0.59 147 22.0 128 52.3 98 0.50 98
IIOF-NLDP [129]124.5 5.65 138 17.8 143 0.15 48 10.5 119 21.5 132 0.72 85 6.98 132 15.2 76 0.42 81 19.5 138 29.3 129 6.15 157 43.1 54 58.0 66 5.20 58 12.2 171 44.1 176 1.54 168 11.9 171 49.2 181 1.34 182 22.2 147 53.0 138 0.50 98
SPSA-learn [13]124.7 5.45 101 15.4 44 0.25 139 11.6 147 21.4 130 1.15 151 7.65 162 16.6 117 1.26 173 20.1 149 28.2 79 5.30 59 43.3 90 58.2 99 5.42 139 10.9 88 41.0 98 1.14 119 11.6 165 50.4 183 1.71 184 22.2 147 53.3 151 0.49 78
SegOF [10]124.8 5.25 63 15.9 63 0.20 103 10.9 129 20.8 114 0.82 101 8.07 169 18.4 155 1.18 171 20.0 147 32.3 167 5.52 117 43.3 90 58.2 99 5.35 107 11.4 144 43.1 164 1.38 158 10.7 140 46.3 166 0.96 176 21.5 61 51.7 53 0.53 137
TriangleFlow [30]126.6 5.85 152 18.2 150 0.26 143 11.0 134 21.8 141 0.79 97 7.17 140 16.3 105 0.58 130 19.6 140 30.7 150 5.74 139 42.8 31 57.8 41 4.95 29 11.6 150 42.8 153 1.05 97 10.8 144 45.8 163 0.73 164 22.8 165 54.3 169 0.51 112
Black & Anandan [4]128.3 5.71 144 15.5 48 0.35 165 12.7 162 22.3 154 1.12 147 7.89 165 18.1 151 1.06 164 20.5 160 30.3 145 5.42 99 43.6 152 58.6 153 5.35 107 10.6 48 39.7 43 0.91 51 10.9 148 44.1 148 0.50 108 22.2 147 52.9 133 0.53 137
Rannacher [23]128.3 5.39 92 16.6 100 0.30 154 11.6 147 22.2 150 1.01 135 7.17 140 16.9 126 0.92 157 18.6 81 28.4 87 5.74 139 43.6 152 58.5 146 5.33 97 11.0 104 41.6 127 1.11 113 10.4 122 44.3 151 0.72 163 21.9 120 52.8 126 0.54 150
ROF-ND [105]128.4 6.15 160 16.4 92 0.14 38 10.4 114 21.1 120 0.70 82 7.09 135 15.9 92 0.40 73 20.7 161 32.9 172 5.82 145 43.4 108 58.2 99 5.37 114 11.6 150 43.4 170 1.16 125 11.6 165 46.4 167 0.55 134 22.6 159 53.8 157 0.54 150
TVL1_RVC [176]128.5 5.69 142 15.5 48 0.35 165 13.7 171 23.9 171 1.38 166 6.66 112 17.5 141 0.67 145 20.4 158 29.6 134 5.50 112 43.6 152 58.5 146 5.43 141 10.8 75 40.3 66 1.08 104 10.5 133 44.4 153 0.65 153 21.8 104 52.6 114 0.49 78
OFRF [132]130.8 6.29 165 18.2 150 0.38 171 11.8 152 22.3 154 1.17 153 6.61 104 17.3 135 0.43 87 19.2 126 29.4 130 5.31 62 43.4 108 58.4 138 5.35 107 11.7 156 42.8 153 1.28 146 10.4 122 43.2 134 0.49 95 22.0 128 53.3 151 0.51 112
Ad-TV-NDC [36]131.5 6.08 159 15.9 63 0.60 178 13.0 164 22.8 159 1.36 163 6.55 95 16.4 111 0.56 126 20.9 163 30.6 148 6.29 159 44.1 168 59.0 165 5.43 141 10.7 57 39.4 40 1.11 113 10.4 122 43.3 137 0.51 118 22.1 137 52.9 133 0.53 137
IAOF2 [51]132.5 6.17 161 18.3 154 0.30 154 12.0 155 23.3 166 0.93 124 5.90 30 16.1 99 0.42 81 20.4 158 31.2 163 5.75 141 43.7 161 58.9 163 5.39 122 11.2 129 42.0 140 1.08 104 10.3 113 42.7 117 0.48 89 22.7 162 54.2 166 0.52 127
Correlation Flow [76]132.7 5.61 129 17.8 143 0.15 48 10.8 126 21.7 139 0.82 101 6.40 79 14.8 60 0.42 81 19.1 122 29.0 117 6.04 155 43.9 164 58.6 153 6.05 180 12.0 164 43.9 174 1.29 148 11.0 151 45.3 160 0.70 160 22.5 155 54.1 164 0.51 112
Filter Flow [19]134.6 5.64 135 16.4 92 0.32 159 12.2 158 22.2 150 1.08 146 6.61 104 16.2 101 0.57 129 20.3 153 29.0 117 6.32 160 44.1 168 59.1 166 5.74 174 10.9 88 40.7 88 1.04 91 10.2 105 43.2 134 0.54 131 22.7 162 54.3 169 0.54 150
Bartels [41]136.0 5.52 114 17.2 122 0.40 173 10.0 100 20.7 111 0.94 126 6.50 88 15.8 90 0.54 120 19.9 142 30.0 142 7.79 177 44.8 178 59.2 167 6.72 183 12.8 181 42.4 146 3.06 182 10.0 79 42.0 82 0.54 131 22.1 137 53.2 143 0.54 150
Dynamic MRF [7]137.6 5.39 92 17.4 132 0.20 103 10.5 119 21.8 141 0.74 89 7.60 161 20.3 173 0.99 160 21.3 166 31.1 161 7.06 170 43.0 41 58.1 86 5.34 103 11.6 150 43.0 161 1.49 165 10.7 140 45.8 163 0.85 169 22.5 155 53.2 143 0.55 160
LocallyOriented [52]138.1 5.79 148 17.9 146 0.26 143 12.1 157 23.2 163 1.01 135 7.05 134 17.6 144 0.51 113 19.9 142 30.9 157 5.72 136 43.3 90 58.2 99 5.23 69 11.9 160 42.6 149 1.52 167 10.8 144 44.0 146 0.53 128 22.5 155 54.0 162 0.52 127
ACK-Prior [27]140.7 5.46 104 17.7 141 0.15 48 9.70 87 20.3 105 0.67 76 7.76 163 16.4 111 1.08 166 19.9 142 31.0 159 6.01 154 44.7 177 59.6 174 5.78 175 12.1 167 44.2 178 1.33 151 10.6 137 44.2 150 0.53 128 23.4 176 56.1 181 0.52 127
StereoOF-V1MT [117]141.9 5.94 155 18.8 159 0.20 103 11.3 139 22.6 157 0.94 126 7.95 166 19.6 167 1.00 161 21.6 167 30.7 150 6.76 166 43.3 90 58.3 123 5.37 114 12.1 167 42.6 149 1.82 176 11.6 165 46.7 170 0.90 172 21.8 104 51.8 62 0.50 98
StereoFlow [44]144.2 10.4 184 27.1 184 0.35 165 16.3 183 28.4 184 1.03 141 6.55 95 16.8 123 0.50 110 18.8 100 28.2 79 5.38 85 45.7 183 62.1 183 5.58 167 13.6 183 50.3 184 1.28 146 10.0 79 42.4 97 0.49 95 23.0 167 55.5 178 0.56 165
TI-DOFE [24]144.5 6.39 166 18.7 157 0.36 169 14.8 179 25.5 181 1.66 176 7.45 156 20.2 171 0.78 151 22.8 174 32.5 169 6.04 155 43.2 78 58.4 138 5.17 48 10.9 88 40.4 73 0.92 52 11.2 156 45.6 162 0.65 153 23.2 173 54.2 166 0.65 178
2bit-BM-tele [96]145.2 5.61 129 15.9 63 0.50 176 11.5 145 21.9 144 1.04 143 6.57 98 15.1 72 0.79 152 20.1 149 29.8 139 7.50 174 44.8 178 59.6 174 6.26 181 12.2 171 42.8 153 2.11 178 11.2 156 49.2 181 1.26 180 21.8 104 52.1 84 0.55 160
UnFlow [127]145.2 6.39 166 20.9 169 0.21 110 13.0 164 24.4 177 1.15 151 8.06 168 21.1 176 0.82 155 19.2 126 29.6 134 5.64 127 43.1 54 58.0 66 5.40 130 11.8 158 42.8 153 1.36 156 11.0 151 42.4 97 0.70 160 24.3 183 54.8 174 0.70 180
Horn & Schunck [3]146.0 5.81 150 17.3 126 0.21 110 13.1 166 23.5 167 1.26 158 8.03 167 19.7 168 1.08 166 22.6 172 32.7 171 5.59 122 43.6 152 58.7 158 5.39 122 10.9 88 40.6 85 1.02 85 11.7 169 46.5 168 0.60 148 22.8 165 53.9 160 0.55 160
WRT [146]148.8 5.83 151 18.2 150 0.17 74 11.3 139 21.5 132 0.92 123 8.29 172 15.2 76 1.12 170 19.5 138 29.6 134 5.93 149 43.6 152 58.7 158 5.31 93 12.4 176 45.8 183 1.43 162 12.1 174 51.8 184 1.66 183 22.6 159 54.6 172 0.58 168
WOLF_ROB [144]157.7 6.71 171 21.0 170 0.32 159 12.5 160 23.2 163 1.12 147 7.54 159 17.6 144 0.65 141 20.3 153 33.1 174 6.43 163 43.6 152 58.8 160 5.47 152 11.9 160 42.8 153 1.56 169 12.1 174 46.5 168 0.71 162 22.1 137 52.8 126 0.58 168
NL-TV-NCC [25]159.4 6.44 168 20.3 168 0.24 135 10.7 124 22.1 148 0.68 79 7.38 154 17.2 133 0.59 132 22.2 170 34.7 179 6.82 167 45.5 182 60.2 181 6.68 182 12.3 175 44.6 180 1.19 130 14.4 182 48.1 178 0.67 155 24.0 182 56.4 182 0.55 160
Adaptive flow [45]160.5 7.18 178 19.2 162 0.69 179 15.0 180 25.0 179 2.11 181 7.29 148 16.7 121 0.87 156 22.6 172 31.3 164 7.85 179 44.8 178 60.2 181 5.63 169 11.7 156 43.4 170 1.36 156 10.4 122 43.7 144 0.57 140 23.0 167 54.7 173 0.50 98
HCIC-L [97]160.7 8.84 183 25.2 182 1.06 183 14.0 176 24.1 174 1.43 169 9.42 178 19.3 166 0.69 146 24.3 177 34.1 177 6.48 164 45.1 181 60.1 179 5.86 177 12.1 167 44.1 176 1.06 99 10.2 105 42.6 109 0.51 118 23.6 178 56.0 180 0.51 112
SILK [80]160.9 6.21 162 19.3 164 0.39 172 13.8 172 24.0 172 1.73 178 8.85 175 20.2 171 1.41 175 21.8 168 31.1 161 7.10 171 43.5 136 58.5 146 5.45 147 11.9 160 41.4 114 2.03 177 10.8 144 45.5 161 0.77 167 22.4 153 53.2 143 0.60 172
H+S_RVC [177]162.5 6.49 169 21.0 170 0.14 38 13.5 169 23.2 163 1.23 155 9.69 180 25.4 181 1.25 172 26.6 183 32.3 167 6.22 158 43.9 164 59.3 171 5.49 157 11.8 158 43.0 161 1.23 143 12.3 178 47.9 177 0.92 174 23.8 181 53.9 160 0.59 170
Learning Flow [11]164.3 5.91 154 18.6 156 0.30 154 12.0 155 22.9 161 1.00 133 8.30 173 20.0 170 1.33 174 21.9 169 32.9 172 6.94 169 44.5 176 59.7 177 5.97 179 11.5 147 42.6 149 1.35 153 11.3 158 46.8 171 0.69 159 23.7 179 55.9 179 0.62 176
GroupFlow [9]165.3 7.04 176 22.5 177 0.28 147 12.5 160 24.0 172 1.13 149 9.10 176 22.0 178 1.45 176 21.0 165 33.6 176 5.93 149 44.1 168 59.3 171 5.50 160 12.2 171 44.4 179 1.42 161 11.1 155 45.2 159 0.61 151 22.7 162 54.1 164 0.56 165
SLK [47]166.8 6.55 170 21.1 173 0.32 159 13.5 169 23.1 162 1.44 171 9.16 177 21.2 177 1.49 180 24.9 179 34.2 178 7.81 178 43.5 136 58.8 160 5.34 103 12.2 171 43.1 164 1.45 163 11.9 171 48.9 180 0.96 176 23.0 167 54.0 162 0.64 177
Heeger++ [102]169.0 7.79 181 25.2 182 0.17 74 13.9 175 24.2 175 1.33 161 11.8 182 28.7 183 1.49 180 23.4 175 30.8 154 7.63 175 44.4 175 59.9 178 5.62 168 12.6 180 43.1 164 1.77 175 12.6 179 46.9 172 0.87 171 23.2 173 53.5 153 0.60 172
FFV1MT [104]169.4 6.93 175 22.8 179 0.24 135 14.0 176 23.5 167 1.48 173 11.2 181 27.7 182 1.52 182 23.4 175 30.8 154 7.63 175 44.0 166 59.2 167 5.69 171 12.0 164 41.6 127 1.56 169 12.1 174 47.3 175 0.95 175 23.4 176 54.2 166 0.79 182
FOLKI [16]172.8 7.10 177 21.1 173 0.94 182 15.3 181 25.5 181 2.28 182 8.49 174 22.2 179 1.47 179 26.3 181 35.2 181 10.6 183 44.0 166 59.6 174 5.54 164 11.6 150 41.8 136 1.49 165 11.4 161 47.7 176 0.90 172 23.3 175 54.9 175 0.67 179
Pyramid LK [2]174.0 7.19 179 21.0 170 0.93 181 16.2 182 25.1 180 2.91 183 14.0 183 18.5 157 2.57 183 32.5 184 46.2 184 13.7 184 44.2 172 60.1 179 5.48 155 11.6 150 42.5 148 1.40 160 11.4 161 47.2 174 1.28 181 23.7 179 56.7 183 1.08 183
PGAM+LK [55]174.8 7.51 180 23.5 181 0.73 180 13.8 172 24.2 175 1.92 180 9.44 179 22.7 180 1.45 176 26.4 182 36.9 182 10.5 182 44.1 168 59.5 173 5.72 173 12.4 176 44.0 175 1.75 174 11.3 158 47.0 173 0.68 158 23.0 167 54.5 171 0.76 181
Periodicity [79]181.7 8.05 182 23.2 180 1.34 184 20.5 184 27.4 183 3.39 184 15.2 184 30.5 184 4.22 184 26.2 180 43.5 183 9.47 181 46.4 184 62.7 184 6.92 184 13.7 184 44.6 180 2.88 181 11.4 161 48.3 179 1.18 179 25.7 184 59.2 184 1.29 184
AVG_FLOW_ROB [137]185.0 30.2 185 60.4 185 6.56 185 42.6 185 49.8 185 9.03 185 34.7 185 42.2 185 9.09 185 57.3 185 72.3 185 20.9 185 51.6 185 69.0 185 7.96 185 25.2 185 71.8 185 4.67 185 39.2 185 64.3 185 3.36 185 43.7 185 66.4 185 8.60 185
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

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