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
SoftSplat [169]3.1 8.60 1 23.7 1 1.22 8 18.0 1 27.0 1 1.73 1 3.66 1 10.3 1 0.59 1 53.3 1 59.3 1 33.7 1 73.6 3 83.2 5 31.5 2 29.5 2 56.5 4 18.4 2 30.8 8 60.0 12 3.83 3 35.2 6 71.9 6 2.07 2
EAFI [171]6.4 9.70 7 27.3 6 1.23 10 20.7 7 30.8 4 2.40 4 5.54 4 14.1 6 0.85 3 55.4 4 60.7 4 36.1 8 75.1 13 84.5 14 32.7 7 30.4 5 58.4 9 18.7 4 30.2 5 57.5 7 3.79 2 36.0 9 73.8 9 2.11 3
EDSC [174]9.7 10.1 10 28.2 12 1.11 4 20.5 5 31.0 7 2.77 41 7.15 11 16.0 9 1.44 14 57.3 12 63.0 11 37.3 12 73.8 6 83.1 3 34.3 13 30.2 4 56.9 6 19.2 9 30.1 4 56.4 4 4.16 11 35.2 6 71.8 5 2.55 13
FGME [158]12.2 8.82 3 23.7 1 0.69 1 21.6 10 30.8 4 3.50 120 8.22 15 16.0 9 1.51 24 57.2 11 61.4 6 40.0 19 72.2 1 81.7 1 32.2 5 30.6 7 53.5 1 21.1 18 30.7 7 54.6 1 4.26 14 33.3 2 68.0 2 2.54 12
AdaCoF [165]17.5 11.9 19 31.3 20 2.21 123 21.9 11 32.2 12 2.99 79 10.7 20 19.7 18 1.47 18 57.0 10 62.4 9 36.3 9 76.0 19 84.7 17 37.2 19 29.1 1 55.3 3 18.3 1 29.6 1 56.1 3 3.71 1 33.7 3 70.4 3 2.02 1
STSR [170]17.7 9.47 5 27.4 7 1.22 8 19.4 2 29.2 2 2.25 3 8.48 16 18.7 16 1.28 7 55.7 5 61.4 6 37.9 13 76.7 21 86.2 22 36.1 17 32.9 18 62.4 20 21.0 17 33.2 144 62.4 19 4.27 15 37.5 12 77.0 19 2.48 11
DSepConv [162]18.2 10.9 14 30.0 15 1.48 12 23.3 17 34.3 19 3.74 126 9.22 18 18.6 15 1.56 36 58.8 17 64.3 16 38.2 15 74.2 7 83.3 6 35.8 16 30.6 7 56.8 5 19.8 14 30.4 6 56.4 4 4.36 17 36.3 10 73.3 8 2.69 17
TC-GAN [166]21.2 10.8 13 30.3 16 1.87 75 22.7 15 34.3 19 3.38 111 6.03 7 15.8 8 1.16 5 56.2 9 62.8 10 35.5 5 74.3 8 83.9 10 33.5 9 31.5 11 60.4 13 19.5 12 32.1 79 62.6 21 3.97 8 38.6 19 77.2 20 2.31 5
DAIN [152]22.8 11.1 16 30.7 18 2.01 98 23.2 16 34.6 21 3.46 119 6.24 8 16.0 9 1.19 6 56.0 8 63.0 11 35.4 4 74.5 10 84.0 11 34.1 12 31.5 11 60.4 13 19.6 13 32.0 64 62.4 19 3.96 7 38.7 22 77.3 22 2.38 10
DCM [185]22.9 9.89 9 28.0 10 1.13 5 20.1 3 30.2 3 2.04 2 4.52 2 12.0 3 0.84 2 54.5 3 60.5 3 34.6 3 75.1 13 84.6 16 32.9 8 32.2 14 61.8 17 19.0 5 36.1 177 63.5 29 4.19 12 40.9 164 78.0 28 2.78 19
BMBC [172]23.9 11.6 17 28.6 13 1.73 45 22.5 13 31.6 11 3.44 117 17.4 28 27.0 25 2.50 153 55.7 5 61.0 5 35.8 6 73.6 3 83.1 3 31.5 2 30.4 5 57.8 8 19.0 5 32.1 79 59.4 10 3.90 5 34.7 4 71.0 4 2.34 8
GDCN [173]26.2 11.0 15 30.8 19 1.29 11 25.8 99 36.7 47 3.33 106 5.80 6 14.9 7 1.67 64 58.8 17 64.0 14 36.6 11 74.5 10 83.8 9 35.7 15 31.6 13 59.1 11 20.6 16 32.2 98 59.7 11 4.23 13 35.0 5 72.2 7 2.31 5
STAR-Net [164]26.2 10.2 12 27.0 5 1.62 20 22.4 12 31.0 7 3.18 98 6.65 9 11.8 2 1.35 8 55.9 7 61.8 8 34.3 2 72.8 2 82.8 2 30.8 1 31.2 10 59.3 12 18.6 3 38.9 182 61.0 13 4.00 9 42.1 177 75.9 14 2.61 15
MEMC-Net+ [160]28.6 12.4 22 32.3 25 2.16 112 24.1 20 34.1 17 3.39 112 7.37 12 16.6 14 1.59 43 57.6 14 63.0 11 35.8 6 75.4 15 84.9 18 33.9 11 32.2 14 62.7 23 19.2 9 32.6 124 62.2 17 3.92 6 38.3 16 77.2 20 2.31 5
DAI [168]29.8 10.1 10 25.7 4 2.27 128 21.1 9 30.8 4 3.41 115 4.76 3 12.0 3 1.10 4 54.4 2 59.8 2 36.4 10 75.8 18 85.4 20 32.6 6 32.3 16 61.8 17 19.3 11 34.3 170 61.5 14 4.00 9 39.7 111 76.4 15 2.55 13
ADC [161]30.3 13.4 29 34.4 26 2.33 132 24.4 27 34.6 21 4.50 142 12.7 22 22.5 21 1.73 75 59.8 93 65.4 22 38.1 14 75.6 16 84.5 14 36.4 18 30.1 3 57.2 7 19.1 7 29.7 2 56.6 6 3.84 4 35.9 8 74.0 10 2.36 9
MAF-net [163]30.7 8.73 2 25.0 3 0.81 2 20.9 8 31.1 9 2.87 62 6.82 10 16.4 13 1.74 81 59.1 35 64.6 17 42.5 121 76.9 22 85.6 21 38.9 21 33.7 20 60.6 15 22.8 20 31.5 10 58.6 8 4.90 129 36.7 11 74.0 10 3.19 86
NNF-Local [75]34.6 13.4 29 36.1 35 1.56 14 24.2 21 35.7 28 2.60 9 18.4 47 30.4 31 1.43 11 59.2 42 68.4 83 41.6 40 79.1 38 87.3 31 43.1 52 36.4 40 66.6 45 25.0 51 31.7 22 63.5 29 4.66 40 38.9 28 78.4 33 3.01 31
PH-Flow [99]37.2 13.7 49 37.1 63 1.77 51 24.3 24 35.5 27 2.58 7 18.5 51 30.6 34 1.54 31 58.8 17 66.8 27 41.6 40 79.0 31 87.2 29 42.9 37 36.3 32 67.1 91 24.6 32 31.6 11 63.7 39 4.64 31 39.0 35 78.6 43 3.10 62
NN-field [71]38.7 13.5 35 36.9 57 1.67 29 24.2 21 35.4 26 2.54 5 18.7 67 30.6 34 1.52 27 59.3 54 68.5 88 41.7 49 79.1 38 87.3 31 43.2 71 36.4 40 66.2 30 25.0 51 31.6 11 63.6 33 4.64 31 38.9 28 78.1 30 3.05 42
MDP-Flow2 [68]40.7 13.3 25 35.1 29 1.62 20 24.6 34 36.5 38 2.63 14 18.5 51 30.5 32 1.42 10 59.0 30 67.8 53 41.4 24 79.1 38 87.3 31 43.4 99 36.5 48 66.4 35 25.0 51 32.0 64 63.9 48 4.64 31 39.3 68 78.7 50 3.08 53
UnDAF [184]41.0 13.3 25 35.1 29 1.62 20 24.6 34 36.4 35 2.66 18 18.6 60 30.9 41 1.44 14 59.0 30 67.8 53 41.4 24 79.2 61 87.3 31 43.4 99 36.4 40 66.5 41 25.0 51 31.9 47 63.8 41 4.63 25 39.3 68 78.8 56 3.05 42
CoT-AMFlow [175]41.7 13.3 25 35.0 27 1.63 26 24.6 34 36.5 38 2.66 18 18.6 60 30.9 41 1.43 11 58.9 23 67.5 43 41.4 24 79.2 61 87.3 31 43.5 114 36.5 48 66.6 45 25.0 51 31.9 47 63.8 41 4.63 25 39.2 59 78.8 56 3.08 53
PMMST [112]42.0 13.4 29 35.0 27 1.70 37 25.1 59 37.1 53 2.73 27 18.5 51 30.5 32 1.39 9 58.9 23 67.4 39 41.5 34 79.2 61 87.4 41 43.4 99 36.3 32 66.2 30 24.9 41 31.8 32 63.8 41 4.67 44 39.2 59 78.7 50 3.09 58
COFM [59]42.5 13.6 44 36.0 33 1.89 78 24.6 34 36.4 35 2.71 25 18.5 51 30.3 29 1.59 43 58.8 17 66.8 27 41.1 22 79.0 31 87.4 41 42.6 31 35.8 25 67.2 101 24.1 22 31.2 9 61.6 15 4.89 127 38.5 17 78.1 30 3.34 132
Layers++ [37]43.3 14.0 85 37.5 75 1.91 82 24.3 24 35.3 25 2.75 32 18.3 45 31.0 46 1.56 36 59.2 42 67.5 43 41.7 49 79.2 61 87.4 41 43.1 52 36.4 40 66.5 41 25.0 51 31.6 11 63.2 23 4.60 20 38.7 22 77.7 26 3.12 68
FeFlow [167]44.0 9.85 8 27.9 9 1.17 7 22.5 13 33.7 15 3.61 122 7.73 13 16.2 12 1.94 111 58.5 15 64.7 18 38.2 15 73.6 3 83.6 7 32.1 4 33.0 19 62.0 19 19.9 15 37.0 178 62.1 16 4.86 123 41.1 167 76.7 17 3.33 131
AGIF+OF [84]44.8 13.9 76 37.5 75 1.67 29 24.6 34 36.5 38 2.68 20 18.1 40 31.0 46 1.61 51 58.9 23 66.9 29 41.4 24 79.2 61 87.5 74 43.1 52 36.6 61 67.2 101 25.0 51 31.8 32 63.6 33 4.60 20 39.0 35 78.6 43 2.98 26
HAST [107]45.4 13.7 49 36.2 40 1.93 89 24.7 44 37.0 51 2.77 41 18.8 70 32.2 74 1.66 63 59.1 35 67.9 62 41.4 24 79.0 31 87.4 41 42.6 31 36.3 32 66.9 68 24.6 32 31.6 11 63.3 25 4.71 62 39.0 35 78.4 33 3.06 46
Sparse-NonSparse [56]45.6 13.8 64 37.3 68 1.81 55 24.4 27 36.0 31 2.61 10 18.0 38 31.2 51 1.52 27 59.0 30 67.1 34 42.0 76 79.2 61 87.4 41 43.1 52 36.7 80 66.7 50 25.3 99 31.7 22 63.6 33 4.63 25 38.9 28 78.5 40 3.08 53
nLayers [57]46.0 13.9 76 36.7 53 1.85 66 24.5 30 36.1 32 2.76 35 17.7 31 30.0 28 1.44 14 59.2 42 67.6 46 41.6 40 79.3 91 87.5 74 43.3 81 36.4 40 66.8 61 25.1 69 31.7 22 63.2 23 4.72 69 38.7 22 77.6 24 3.03 34
ProbFlowFields [126]49.8 13.5 35 36.6 47 1.82 58 24.4 27 36.4 35 2.68 20 18.5 51 31.2 51 1.49 21 59.2 42 67.2 35 42.1 81 79.3 91 87.5 74 43.6 134 36.5 48 67.0 79 25.2 80 31.6 11 63.5 29 4.64 31 39.0 35 78.4 33 3.06 46
FRUCnet [153]50.4 14.5 129 31.5 23 5.94 178 24.5 30 34.1 17 5.10 157 10.4 19 20.2 19 2.68 158 61.6 163 66.9 29 39.4 18 74.3 8 83.7 8 33.5 9 30.8 9 58.8 10 19.1 7 33.3 148 58.8 9 4.44 18 37.7 14 74.6 12 2.74 18
CyclicGen [149]50.7 13.7 49 31.4 22 4.62 173 26.2 111 34.0 16 12.3 183 13.8 24 27.5 26 2.63 157 61.2 155 65.1 19 44.0 158 76.0 19 84.3 13 39.2 22 32.3 16 53.7 2 24.3 25 29.7 2 55.6 2 4.29 16 31.7 1 66.4 1 2.16 4
2DHMM-SAS [90]50.7 14.1 95 38.9 126 1.82 58 25.5 83 38.0 69 2.77 41 17.2 26 30.9 41 1.56 36 58.9 23 66.5 24 41.7 49 79.1 38 87.4 41 42.9 37 36.5 48 66.6 45 24.9 41 31.7 22 63.9 48 4.68 52 39.2 59 79.0 66 3.07 49
OFLAF [78]51.0 13.5 35 36.1 35 1.62 20 24.3 24 35.8 29 2.62 13 18.7 67 31.5 59 1.47 18 59.1 35 67.8 53 41.2 23 79.3 91 87.4 41 43.4 99 36.6 61 67.4 118 25.0 51 31.9 47 64.3 61 4.79 103 38.9 28 78.7 50 3.10 62
LSM [39]51.3 13.9 76 38.0 95 1.78 53 24.6 34 36.5 38 2.61 10 18.1 40 32.0 68 1.55 34 59.2 42 67.6 46 42.1 81 79.2 61 87.4 41 43.1 52 36.7 80 66.9 68 25.3 99 31.7 22 63.6 33 4.65 39 38.9 28 78.6 43 3.07 49
FMOF [92]53.0 14.2 105 38.6 112 1.91 82 24.5 30 36.2 33 2.70 24 18.4 47 31.2 51 1.77 88 59.5 67 68.0 66 41.5 34 79.2 61 87.4 41 43.1 52 36.6 61 66.8 61 25.0 51 31.6 11 63.3 25 4.61 23 39.1 47 78.4 33 3.11 67
SepConv-v1 [125]54.7 9.23 4 28.0 10 1.08 3 20.5 5 32.4 13 3.35 107 8.95 17 20.5 20 2.08 125 60.8 142 66.9 29 44.2 160 79.1 38 87.1 27 43.2 71 35.6 23 62.4 20 25.1 69 32.2 98 62.3 18 5.34 164 37.6 13 76.4 15 3.28 121
CombBMOF [111]55.2 13.6 44 36.4 44 1.71 40 24.5 30 36.9 49 2.58 7 18.1 40 31.5 59 1.81 97 59.5 67 68.2 73 41.6 40 79.1 38 87.3 31 43.0 44 36.8 93 66.5 41 25.0 51 33.9 164 65.2 119 4.68 52 39.1 47 78.4 33 2.92 22
ComponentFusion [94]55.4 13.4 29 36.1 35 1.72 43 24.6 34 36.8 48 2.57 6 18.9 78 32.9 88 1.69 67 59.1 35 67.8 53 41.4 24 79.2 61 87.4 41 43.6 134 36.5 48 66.3 32 25.1 69 32.0 64 64.8 87 4.76 95 39.1 47 78.7 50 3.10 62
MPRN [151]56.0 12.4 22 32.0 24 1.81 55 26.3 114 36.9 49 3.69 123 21.6 173 37.6 168 2.47 151 58.8 17 65.1 19 40.0 19 78.3 23 86.6 23 41.3 23 35.8 25 63.1 24 24.8 38 32.8 133 63.8 41 4.48 19 38.5 17 78.0 28 2.68 16
IROF++ [58]56.2 13.8 64 37.8 87 1.72 43 24.6 34 36.6 44 2.61 10 18.6 60 31.3 55 1.64 59 58.8 17 66.7 26 41.8 58 79.0 31 87.3 31 42.7 34 36.5 48 66.6 45 25.0 51 32.0 64 65.0 98 4.74 85 39.5 96 79.2 83 3.30 125
OFRI [154]58.1 11.9 19 29.6 14 2.70 147 24.0 19 33.6 14 4.57 147 5.54 4 12.5 5 1.52 27 57.5 13 64.0 14 38.7 17 74.6 12 84.2 12 35.1 14 34.0 21 62.6 22 21.3 19 43.5 184 65.4 125 5.73 177 43.3 182 76.7 17 3.87 170
Ramp [62]58.7 14.1 95 38.7 117 1.92 87 24.6 34 36.6 44 2.69 22 17.9 35 31.0 46 1.47 18 58.9 23 67.0 33 41.9 64 79.2 61 87.5 74 43.1 52 37.0 112 67.4 118 25.5 115 31.6 11 63.5 29 4.63 25 39.1 47 78.9 61 3.19 86
S2F-IF [121]60.2 13.5 35 36.6 47 1.70 37 24.9 52 37.9 65 2.77 41 18.8 70 32.7 84 1.54 31 59.1 35 67.7 50 41.6 40 79.3 91 87.5 74 43.3 81 36.5 48 67.1 91 25.0 51 31.9 47 64.7 83 4.74 85 39.3 68 79.1 76 3.10 62
PRAFlow_RVC [178]60.9 13.5 35 36.3 42 1.61 16 24.9 52 37.6 60 2.73 27 18.4 47 31.2 51 1.43 11 59.5 67 68.8 112 42.4 114 79.3 91 87.4 41 43.5 114 36.4 40 65.8 29 25.2 80 31.6 11 63.9 48 4.73 74 40.0 130 79.4 99 3.13 70
TV-L1-MCT [64]60.9 14.5 129 39.7 150 1.86 70 25.2 64 37.8 63 2.78 45 17.3 27 31.1 50 1.59 43 58.9 23 66.6 25 41.6 40 79.1 38 87.4 41 42.9 37 36.8 93 66.4 35 25.6 122 31.8 32 64.0 55 4.73 74 39.1 47 79.0 66 3.20 93
RAFT-TF_RVC [180]61.6 13.3 25 36.2 40 1.54 13 24.7 44 37.5 59 2.74 31 18.6 60 31.8 62 1.59 43 59.5 67 69.0 123 41.9 64 79.3 91 87.5 74 43.3 81 41.7 180 66.9 68 31.8 180 31.7 22 63.8 41 4.66 40 38.7 22 77.9 27 2.90 21
VCN_RVC [179]61.8 13.7 49 37.7 85 1.68 32 25.1 59 38.2 76 2.69 22 19.1 99 35.1 142 1.64 59 59.3 54 68.5 88 42.2 94 79.1 38 87.4 41 43.0 44 36.3 32 66.7 50 24.5 29 32.3 107 64.8 87 4.77 98 39.0 35 78.5 40 2.95 24
FlowFields+ [128]62.2 13.5 35 37.0 60 1.69 36 25.0 56 38.2 76 2.78 45 18.9 78 33.3 100 1.55 34 59.1 35 67.6 46 41.9 64 79.3 91 87.5 74 43.3 81 36.6 61 67.2 101 25.1 69 31.8 32 64.5 75 4.67 44 39.3 68 79.2 83 3.07 49
RNLOD-Flow [119]62.8 13.9 76 37.9 92 1.86 70 25.2 64 37.9 65 2.78 45 19.0 86 32.1 70 1.78 90 59.2 42 67.8 53 41.5 34 79.1 38 87.4 41 43.1 52 36.7 80 66.8 61 25.2 80 31.9 47 64.2 58 4.75 91 39.2 59 79.0 66 3.06 46
FC-2Layers-FF [74]63.0 14.0 85 38.6 112 1.84 62 24.2 21 35.1 23 2.82 55 17.9 35 31.3 55 1.51 24 59.3 54 67.7 50 42.1 81 79.3 91 87.6 115 43.3 81 36.7 80 67.4 118 25.3 99 31.6 11 63.6 33 4.67 44 39.1 47 78.7 50 3.19 86
Classic+NL [31]63.4 14.2 105 38.8 120 1.98 93 24.6 34 36.5 38 2.65 16 17.7 31 30.9 41 1.51 24 59.2 42 67.5 43 42.2 94 79.2 61 87.5 74 43.3 81 37.0 112 67.1 91 25.5 115 31.7 22 63.6 33 4.67 44 39.2 59 79.0 66 3.18 83
Classic+CPF [82]64.5 14.1 95 38.3 106 1.74 47 24.9 52 37.1 53 2.73 27 17.6 30 31.4 57 1.60 49 59.0 30 67.3 37 41.4 24 79.3 91 87.6 115 43.3 81 36.9 101 67.9 147 25.2 80 31.9 47 64.3 61 4.64 31 39.3 68 79.2 83 3.04 37
CtxSyn [134]64.5 9.68 6 27.4 7 1.15 6 20.4 4 31.4 10 2.64 15 8.05 14 19.1 17 1.57 40 58.6 16 65.2 21 42.5 121 79.0 31 87.1 27 43.0 44 37.9 151 65.3 27 25.7 133 38.4 181 67.7 161 5.17 153 42.3 178 78.4 33 3.48 153
FlowFields [108]65.3 13.6 44 37.1 63 1.74 47 25.0 56 38.1 70 2.75 32 18.8 70 33.2 97 1.53 30 59.4 61 68.0 66 42.3 102 79.3 91 87.5 74 43.2 71 36.5 48 67.0 79 25.0 51 31.8 32 64.7 83 4.69 55 39.4 84 79.3 91 3.13 70
EAI-Flow [147]66.3 13.7 49 36.3 42 1.91 82 25.7 96 39.1 101 3.01 80 19.0 86 33.4 102 1.67 64 58.9 23 67.2 35 41.4 24 79.2 61 87.3 31 43.0 44 36.9 101 66.7 50 25.2 80 32.0 64 65.0 98 4.78 100 39.3 68 79.1 76 3.03 34
HCFN [157]67.7 13.2 24 35.8 32 1.61 16 25.2 64 38.7 92 2.73 27 18.8 70 33.0 92 1.59 43 59.3 54 68.1 72 42.3 102 79.1 38 87.4 41 42.9 37 40.0 177 66.8 61 29.9 178 32.2 98 64.9 94 4.74 85 39.1 47 78.6 43 3.04 37
NNF-EAC [101]68.2 14.2 105 37.3 68 2.09 107 25.3 71 37.6 60 2.76 35 18.9 78 30.6 34 1.61 51 59.8 93 68.5 88 43.3 149 79.1 38 87.3 31 43.1 52 36.5 48 66.5 41 25.0 51 32.1 79 64.3 61 4.73 74 39.4 84 79.0 66 3.14 74
LME [70]68.8 13.5 35 36.1 35 1.62 20 25.3 71 37.8 63 3.44 117 19.0 86 32.8 86 1.63 57 59.0 30 67.8 53 41.5 34 79.7 168 87.9 162 44.4 167 36.5 48 67.0 79 24.9 41 32.0 64 64.2 58 4.66 40 39.0 35 78.6 43 3.09 58
S2D-Matching [83]69.2 14.2 105 38.9 126 1.96 90 25.3 71 37.9 65 2.76 35 17.5 29 31.0 46 1.60 49 59.3 54 67.4 39 42.8 131 79.2 61 87.5 74 43.2 71 36.9 101 67.3 111 25.4 109 31.8 32 63.8 41 4.64 31 39.1 47 78.6 43 3.21 100
WLIF-Flow [91]69.6 13.8 64 37.4 72 1.73 45 24.9 52 37.1 53 2.81 52 18.5 51 30.9 41 1.49 21 59.4 61 67.8 53 42.5 121 79.2 61 87.4 41 43.8 158 37.2 127 67.5 127 25.9 140 31.8 32 63.9 48 4.64 31 39.4 84 78.9 61 3.14 74
FESL [72]72.0 14.4 124 39.1 133 1.83 60 25.0 56 37.4 57 2.76 35 18.2 44 31.6 61 1.70 69 59.7 81 68.5 88 41.7 49 79.3 91 87.6 115 43.3 81 36.9 101 67.9 147 25.2 80 31.8 32 63.8 41 4.61 23 39.3 68 78.8 56 3.04 37
JOF [136]74.6 14.4 124 39.1 133 2.17 113 24.7 44 36.3 34 2.87 62 18.1 40 30.6 34 1.54 31 59.7 81 67.9 62 43.2 147 79.3 91 87.5 74 43.6 134 36.9 101 67.0 79 25.4 109 31.6 11 63.4 28 4.66 40 39.1 47 78.7 50 3.29 122
FF++_ROB [141]74.8 13.5 35 36.6 47 1.68 32 25.4 80 38.6 89 2.89 66 19.1 99 33.5 104 1.74 81 59.3 54 68.0 66 41.8 58 79.3 91 87.5 74 43.4 99 37.1 119 66.9 68 25.9 140 31.7 22 64.3 61 4.73 74 39.3 68 79.1 76 3.20 93
PGM-C [118]76.9 13.8 64 37.7 85 1.85 66 25.1 59 38.1 70 2.90 67 19.1 99 33.6 105 1.59 43 59.3 54 68.2 73 41.9 64 79.3 91 87.5 74 43.5 114 36.6 61 67.2 101 25.2 80 31.9 47 64.8 87 4.67 44 39.5 96 79.4 99 3.22 102
PMF [73]77.5 13.7 49 37.1 63 1.66 28 25.5 83 39.3 104 2.71 25 19.0 86 34.9 136 1.74 81 59.4 61 68.4 83 41.8 58 79.4 130 87.6 115 43.3 81 37.3 131 66.9 68 26.2 150 31.9 47 64.3 61 4.73 74 39.3 68 78.8 56 2.93 23
MDP-Flow [26]78.5 13.4 29 36.1 35 1.67 29 24.8 49 37.2 56 2.79 49 18.8 70 32.0 68 1.70 69 59.8 93 68.9 118 42.1 81 79.3 91 87.6 115 43.5 114 36.7 80 67.7 138 25.2 80 32.5 120 65.5 131 4.77 98 39.1 47 79.0 66 3.09 58
SegFlow [156]79.6 13.7 49 37.6 79 1.86 70 25.1 59 38.2 76 2.90 67 19.0 86 33.2 97 1.62 55 59.2 42 67.9 62 41.9 64 79.3 91 87.5 74 43.5 114 36.7 80 67.4 118 25.4 109 31.9 47 65.0 98 4.70 60 39.5 96 79.5 110 3.23 108
Efficient-NL [60]80.0 14.3 118 38.7 117 1.77 51 25.2 64 37.6 60 2.76 35 19.0 86 31.8 62 2.08 125 59.8 93 68.7 106 41.4 24 79.1 38 87.4 41 43.0 44 36.9 101 68.4 162 24.6 32 32.1 79 64.7 83 4.69 55 40.1 138 79.8 132 3.14 74
SVFilterOh [109]80.5 14.1 95 37.3 68 1.96 90 24.7 44 36.6 44 2.87 62 18.3 45 30.8 39 1.63 57 59.9 105 68.5 88 43.1 146 79.5 160 87.7 143 44.5 169 36.6 61 66.7 50 25.3 99 31.6 11 62.8 22 5.05 144 38.6 19 78.2 32 3.37 139
TC-Flow [46]81.1 13.7 49 36.9 57 1.91 82 25.3 71 38.5 86 3.05 85 19.3 118 34.1 122 1.73 75 59.2 42 67.8 53 42.2 94 79.3 91 87.5 74 43.5 114 37.1 119 68.0 151 25.6 122 31.9 47 64.3 61 4.71 62 39.0 35 79.0 66 3.13 70
MS-PFT [159]82.8 13.7 49 36.6 47 1.56 14 28.1 158 38.1 70 4.52 145 11.2 21 23.0 22 3.22 172 64.4 175 73.4 179 41.6 40 75.7 17 85.3 19 38.3 20 35.3 22 61.3 16 25.2 80 40.9 183 67.8 163 6.03 180 39.0 35 74.8 13 3.45 148
AggregFlow [95]83.0 14.5 129 38.3 106 2.20 121 25.7 96 38.5 86 3.23 100 18.6 60 30.8 39 1.44 14 59.7 81 68.4 83 41.7 49 79.4 130 87.6 115 43.8 158 37.5 137 66.9 68 26.4 155 31.8 32 64.2 58 4.70 60 38.9 28 78.4 33 3.08 53
DMF_ROB [135]83.5 13.9 76 37.0 60 1.98 93 25.8 99 39.0 98 2.96 72 19.8 151 35.0 139 2.12 131 59.7 81 68.2 73 41.9 64 79.3 91 87.4 41 43.7 150 36.3 32 66.4 35 25.0 51 32.1 79 64.4 72 4.93 132 39.2 59 79.1 76 3.07 49
Second-order prior [8]83.6 14.0 85 37.1 63 2.11 108 26.2 111 39.3 104 2.93 70 19.4 126 35.1 142 2.16 137 59.4 61 67.8 53 41.8 58 79.1 38 87.3 31 43.1 52 36.5 48 66.7 50 25.0 51 32.3 107 65.4 125 4.74 85 39.5 96 79.6 120 3.19 86
EPPM w/o HM [86]83.9 13.4 29 36.6 47 1.61 16 25.5 83 39.3 104 2.76 35 19.4 126 35.7 153 1.99 119 59.6 74 69.3 133 41.9 64 79.2 61 87.4 41 43.1 52 37.0 112 67.5 127 25.3 99 32.8 133 65.0 98 4.85 120 39.4 84 79.0 66 3.04 37
IROF-TV [53]83.9 14.0 85 38.1 97 1.99 95 24.7 44 36.5 38 2.65 16 19.1 99 34.2 124 1.78 90 59.1 35 67.4 39 42.4 114 79.4 130 87.7 143 43.6 134 36.0 27 66.4 35 24.4 26 32.1 79 64.6 79 4.75 91 39.8 121 79.9 138 3.35 135
SuperSlomo [130]84.2 12.3 21 30.3 16 2.92 158 24.8 49 35.2 24 6.60 172 13.6 23 25.5 24 2.01 120 60.5 134 65.5 23 43.9 156 78.3 23 86.6 23 41.9 25 37.4 135 64.3 25 26.4 155 35.3 176 63.9 48 5.33 163 40.3 147 77.6 24 3.51 156
PWC-Net_RVC [143]84.4 13.7 49 38.1 97 1.70 37 25.8 99 39.7 115 2.83 57 19.3 118 35.0 139 1.75 85 59.4 61 69.1 130 42.1 81 79.3 91 87.6 115 43.4 99 37.0 112 66.7 50 25.5 115 32.0 64 64.4 72 4.74 85 39.3 68 78.9 61 2.98 26
DeepFlow2 [106]84.8 13.9 76 36.6 47 2.07 105 25.6 91 38.4 82 3.08 87 19.1 99 33.6 105 1.70 69 59.6 74 68.5 88 41.9 64 79.4 130 87.5 74 43.7 150 36.7 80 66.3 32 25.4 109 31.9 47 64.7 83 4.67 44 39.4 84 79.4 99 3.26 117
CPM-Flow [114]85.0 13.8 64 37.8 87 1.87 75 25.1 59 38.2 76 2.93 70 19.0 86 33.4 102 1.61 51 59.6 74 68.7 106 42.1 81 79.3 91 87.5 74 43.5 114 36.8 93 66.9 68 25.5 115 32.0 64 65.2 119 4.68 52 39.5 96 79.5 110 3.25 113
TF+OM [98]85.4 13.7 49 36.5 45 2.17 113 25.2 64 37.4 57 3.76 127 17.9 35 32.7 84 1.76 87 59.8 93 68.5 88 42.3 102 79.3 91 87.5 74 43.7 150 36.9 101 66.7 50 25.7 133 31.8 32 64.3 61 4.79 103 39.3 68 79.3 91 3.47 152
ProFlow_ROB [142]85.8 13.6 44 36.5 45 1.85 66 25.3 71 38.4 82 2.96 72 18.9 78 32.9 88 1.62 55 59.7 81 69.6 151 42.5 121 79.4 130 87.6 115 43.4 99 36.6 61 66.7 50 25.1 69 32.1 79 65.1 109 4.71 62 39.7 111 79.7 128 3.20 93
LiteFlowNet [138]86.2 13.8 64 38.6 112 1.68 32 26.0 103 40.1 127 2.84 58 19.2 110 35.3 149 1.64 59 59.8 93 69.4 139 42.3 102 79.1 38 87.4 41 42.9 37 36.6 61 67.6 133 24.4 26 32.9 137 65.8 138 4.81 112 39.6 104 78.9 61 3.03 34
SRR-TVOF-NL [89]86.6 14.2 105 37.6 79 2.07 105 26.1 107 39.8 119 3.30 104 19.4 126 33.9 115 1.82 98 59.8 93 68.6 100 41.0 21 79.1 38 87.5 74 42.9 37 36.0 27 66.9 68 24.1 22 32.9 137 64.8 87 4.81 112 39.6 104 79.4 99 3.22 102
TriFlow [93]87.0 14.2 105 39.0 130 2.20 121 26.6 121 39.3 104 4.59 148 19.0 86 33.7 108 1.71 74 59.9 105 68.7 106 41.4 24 79.2 61 87.5 74 43.5 114 36.7 80 67.1 91 25.2 80 31.8 32 63.9 48 4.69 55 39.1 47 79.0 66 3.23 108
EpicFlow [100]87.0 13.8 64 37.6 79 1.87 75 25.5 83 38.9 95 2.96 72 18.9 78 33.7 108 1.64 59 59.5 67 68.5 88 42.3 102 79.4 130 87.6 115 43.5 114 36.5 48 67.5 127 24.9 41 32.0 64 65.1 109 4.74 85 39.4 84 79.4 99 3.22 102
DeepFlow [85]87.0 13.7 49 35.7 31 2.03 101 25.6 91 38.2 76 3.30 104 19.2 110 33.9 115 1.74 81 59.7 81 68.0 66 42.2 94 79.4 130 87.5 74 43.7 150 37.3 131 66.4 35 26.2 150 31.8 32 64.8 87 4.63 25 39.3 68 79.3 91 3.26 117
SimpleFlow [49]87.5 14.1 95 38.9 126 1.92 87 25.5 83 37.9 65 2.85 60 19.0 86 32.3 76 2.26 142 59.2 42 67.3 37 42.4 114 79.2 61 87.5 74 43.2 71 36.7 80 67.6 133 25.1 69 32.0 64 66.1 147 5.29 159 39.3 68 79.2 83 3.15 77
CostFilter [40]88.2 13.6 44 37.4 72 1.63 26 25.5 83 39.7 115 2.75 32 19.0 86 36.0 156 1.79 92 59.4 61 68.8 112 42.0 76 79.4 130 87.6 115 43.7 150 38.6 162 67.1 91 28.1 172 31.9 47 64.6 79 4.81 112 39.0 35 78.5 40 3.00 29
OFH [38]88.6 14.1 95 38.2 103 2.03 101 25.6 91 38.4 82 3.01 80 19.4 126 35.1 142 1.79 92 59.5 67 68.8 112 42.3 102 79.1 38 87.4 41 43.1 52 36.7 80 67.6 133 25.2 80 32.1 79 65.1 109 4.79 103 39.2 59 79.2 83 3.15 77
Aniso. Huber-L1 [22]89.2 14.3 118 38.5 110 2.17 113 26.6 121 39.5 112 3.21 99 19.2 110 32.5 82 1.83 100 59.7 81 68.7 106 41.9 64 79.2 61 87.4 41 43.2 71 36.3 32 67.1 91 24.6 32 32.2 98 64.9 94 4.71 62 39.7 111 79.6 120 3.24 112
Complementary OF [21]89.4 13.7 49 37.8 87 1.71 40 25.2 64 38.6 89 2.81 52 19.8 151 33.7 108 2.38 147 59.9 105 69.2 132 42.8 131 79.2 61 87.5 74 43.1 52 36.6 61 67.4 118 25.2 80 32.3 107 65.4 125 4.79 103 38.8 26 78.9 61 3.29 122
RFlow [88]89.7 13.8 64 37.8 87 2.02 99 26.0 103 39.1 101 2.85 60 19.0 86 33.1 95 1.86 102 59.7 81 68.4 83 42.2 94 79.2 61 87.6 115 43.4 99 36.1 31 66.8 61 24.5 29 32.2 98 65.1 109 4.82 119 39.7 111 79.8 132 3.34 132
DPOF [18]89.8 14.2 105 39.1 133 2.19 120 24.8 49 37.0 51 2.80 50 19.3 118 31.9 64 2.01 120 60.2 124 69.5 146 42.3 102 79.1 38 87.4 41 43.1 52 36.7 80 67.1 91 24.6 32 32.4 115 65.3 123 4.81 112 39.5 96 79.5 110 3.18 83
TC/T-Flow [77]90.4 14.3 118 38.8 120 1.84 62 25.3 71 38.6 89 2.81 52 18.9 78 32.4 81 1.58 41 59.9 105 69.5 146 42.1 81 79.3 91 87.5 74 43.5 114 37.1 119 68.0 151 25.2 80 32.1 79 65.2 119 4.81 112 39.2 59 79.4 99 3.00 29
OAR-Flow [123]90.8 14.0 85 36.9 57 2.05 104 25.3 71 38.1 70 3.11 91 19.1 99 34.0 121 1.70 69 59.2 42 68.6 100 41.9 64 79.4 130 87.6 115 43.5 114 36.9 101 67.8 142 25.3 99 32.0 64 65.1 109 4.75 91 39.3 68 79.3 91 3.18 83
Sparse Occlusion [54]91.5 14.2 105 38.6 112 1.99 95 25.8 99 39.2 103 2.78 45 19.3 118 32.3 76 1.80 95 59.8 93 68.8 112 41.7 49 79.3 91 87.5 74 43.2 71 37.1 119 68.4 162 25.3 99 32.1 79 64.4 72 4.60 20 39.7 111 79.6 120 3.15 77
Brox et al. [5]91.6 14.0 85 37.4 72 1.90 80 26.4 116 40.1 127 3.08 87 19.3 118 35.0 139 1.97 115 59.7 81 68.2 73 41.7 49 79.4 130 87.6 115 43.6 134 36.6 61 66.9 68 25.1 69 31.9 47 64.8 87 4.73 74 39.4 84 79.5 110 3.15 77
ContinualFlow_ROB [148]92.0 14.6 135 40.3 157 2.11 108 26.6 121 40.8 143 3.96 131 19.8 151 36.5 164 1.98 116 59.6 74 69.0 123 42.3 102 79.2 61 87.5 74 43.4 99 36.0 27 66.8 61 24.4 26 31.9 47 64.3 61 4.64 31 39.2 59 79.4 99 3.04 37
TOF-M [150]92.2 11.7 18 31.3 20 1.68 32 23.9 18 35.8 29 5.13 160 14.0 25 25.4 23 2.53 154 60.9 144 66.9 29 43.8 153 78.9 27 87.0 26 43.4 99 38.3 157 65.3 27 26.7 160 37.9 180 65.0 98 5.51 170 43.2 180 79.5 110 3.94 173
ComplOF-FED-GPU [35]93.2 14.0 85 38.0 95 1.91 82 25.3 71 38.5 86 2.90 67 20.2 159 34.6 132 2.16 137 59.5 67 68.5 88 42.5 121 79.2 61 87.4 41 43.2 71 36.6 61 67.4 118 25.0 51 32.2 98 65.4 125 4.75 91 39.7 111 79.8 132 3.19 86
LFNet_ROB [145]93.7 13.8 64 37.5 75 1.80 54 27.0 135 41.7 157 3.08 87 19.6 138 35.5 150 1.87 104 59.2 42 67.4 39 41.7 49 79.1 38 87.4 41 42.8 36 36.8 93 67.3 111 24.8 38 33.2 144 65.7 137 4.79 103 40.4 153 80.0 143 3.26 117
GraphCuts [14]93.8 15.1 150 39.3 139 2.68 145 26.4 116 39.4 110 4.50 142 19.2 110 30.7 38 2.69 159 60.7 140 68.6 100 42.8 131 79.0 31 87.4 41 42.5 29 35.6 23 66.7 50 23.7 21 32.0 64 65.0 98 5.04 143 39.0 35 79.2 83 3.48 153
Fusion [6]94.8 13.8 64 38.4 109 1.84 62 25.3 71 38.1 70 2.88 65 19.1 99 32.2 74 1.90 108 60.9 144 69.8 152 41.8 58 79.1 38 87.9 162 42.1 26 36.0 27 67.8 142 24.1 22 32.7 130 66.3 152 4.88 126 39.5 96 80.4 161 3.26 117
Classic++ [32]95.2 14.0 85 38.1 97 2.17 113 25.7 96 38.8 93 2.96 72 19.3 118 33.9 115 1.93 110 59.7 81 67.9 62 42.8 131 79.2 61 87.5 74 43.3 81 37.4 135 67.0 79 26.6 159 31.8 32 64.3 61 4.78 100 39.4 84 79.5 110 3.36 136
DF-Auto [113]96.1 14.2 105 36.7 53 2.25 126 26.5 119 39.0 98 4.23 136 18.8 70 31.4 57 1.58 41 60.1 119 69.3 133 41.6 40 79.3 91 87.5 74 43.6 134 36.6 61 67.0 79 25.1 69 32.3 107 65.1 109 4.81 112 39.9 122 80.1 149 3.22 102
Steered-L1 [116]96.3 13.7 49 37.5 75 1.84 62 25.5 83 38.9 95 3.17 97 19.7 146 33.1 95 2.40 148 60.2 124 68.5 88 42.8 131 79.4 130 87.7 143 43.5 114 36.6 61 67.0 79 25.6 122 31.8 32 64.6 79 4.96 137 38.6 19 79.0 66 3.36 136
ALD-Flow [66]97.0 14.1 95 37.9 92 2.17 113 25.4 80 38.4 82 3.14 93 19.1 99 33.9 115 1.73 75 59.6 74 69.0 123 42.6 128 79.4 130 87.6 115 43.6 134 37.0 112 67.5 127 25.6 122 31.7 22 64.0 55 4.69 55 39.4 84 79.5 110 3.20 93
p-harmonic [29]97.2 13.5 35 36.7 53 1.85 66 26.7 130 39.9 123 3.25 102 19.4 126 35.2 145 2.10 128 60.1 119 68.7 106 42.2 94 79.3 91 87.5 74 43.3 81 36.7 80 66.7 50 25.3 99 32.6 124 65.8 138 4.76 95 39.4 84 79.5 110 3.17 81
Shiralkar [42]101.1 14.2 105 39.0 130 2.02 99 26.8 131 40.3 133 2.98 76 18.5 51 38.0 173 2.48 152 60.1 119 67.7 50 41.8 58 78.8 26 87.2 29 42.3 28 37.7 144 67.2 101 26.2 150 33.2 144 67.1 157 4.94 134 39.4 84 79.3 91 3.10 62
AugFNG_ROB [139]101.6 14.6 135 39.7 150 2.31 130 27.3 145 41.3 150 4.30 140 19.5 133 37.8 170 1.92 109 59.8 93 68.8 112 42.1 81 79.4 130 87.7 143 43.3 81 36.3 32 66.4 35 24.9 41 32.7 130 65.6 135 4.73 74 38.8 26 78.6 43 2.84 20
HBM-GC [103]104.1 14.7 139 39.4 144 2.41 138 25.4 80 38.1 70 3.07 86 18.0 38 29.8 27 1.56 36 59.8 93 68.2 73 42.8 131 80.1 174 88.0 168 45.9 178 37.5 137 68.2 158 26.1 148 31.9 47 63.3 25 4.99 139 39.3 68 79.1 76 3.30 125
C-RAFT_RVC [182]104.1 15.1 150 41.1 162 2.13 110 26.4 116 40.6 141 3.40 113 19.3 118 34.1 122 1.85 101 60.0 111 69.9 154 42.3 102 79.3 91 87.5 74 43.4 99 36.6 61 67.1 91 24.9 41 32.1 79 64.9 94 4.69 55 39.9 122 79.4 99 3.20 93
FlowNet2 [120]105.0 15.9 165 41.4 164 2.76 149 27.1 137 40.2 130 4.29 138 19.6 138 34.3 126 1.88 105 60.0 111 70.2 158 42.0 76 79.4 130 87.7 143 43.3 81 36.4 40 66.3 32 24.9 41 32.1 79 64.5 75 4.71 62 39.6 104 79.2 83 3.08 53
CLG-TV [48]106.0 14.3 118 38.8 120 2.17 113 26.6 121 39.8 119 3.24 101 19.5 133 33.9 115 2.11 130 60.0 111 69.0 123 42.4 114 79.3 91 87.6 115 43.5 114 36.6 61 66.9 68 25.1 69 32.1 79 65.1 109 4.71 62 39.9 122 80.0 143 3.20 93
SIOF [67]106.5 14.7 139 39.5 147 2.23 125 27.1 137 40.3 133 4.25 137 19.1 99 32.9 88 1.82 98 59.8 93 68.6 100 42.1 81 79.1 38 87.4 41 43.0 44 37.1 119 67.1 91 25.5 115 32.4 115 64.9 94 4.79 103 40.1 138 79.9 138 3.40 143
MLDP_OF [87]106.5 13.9 76 38.1 97 1.81 55 25.6 91 38.9 95 2.80 50 18.8 70 32.3 76 1.61 51 59.6 74 68.3 80 42.3 102 79.3 91 87.6 115 43.9 161 39.6 175 68.7 168 28.5 174 33.0 142 65.3 123 5.09 147 39.6 104 79.2 83 3.51 156
EPMNet [131]107.0 15.7 163 42.3 168 2.55 141 26.9 132 39.5 112 4.05 133 19.6 138 34.3 126 1.88 105 60.1 119 70.4 164 42.0 76 79.4 130 87.7 143 43.3 81 36.5 48 66.9 68 24.9 41 32.1 79 64.5 75 4.71 62 40.0 130 79.3 91 3.05 42
Local-TV-L1 [65]110.2 14.9 144 37.3 68 3.21 163 27.3 145 39.5 112 4.67 149 18.9 78 32.3 76 1.70 69 61.3 157 68.6 100 47.1 176 79.3 91 87.6 115 43.6 134 39.0 167 66.7 50 28.9 176 31.7 22 64.3 61 4.79 103 39.3 68 79.1 76 3.41 146
F-TV-L1 [15]110.5 15.0 145 39.3 139 2.88 156 27.2 141 40.2 130 3.69 123 19.2 110 34.5 131 2.19 139 59.7 81 68.4 83 42.8 131 78.9 27 87.4 41 42.7 34 37.3 131 67.0 79 25.6 122 32.1 79 64.5 75 4.89 127 40.1 138 80.0 143 3.42 147
3DFlow [133]110.8 14.1 95 38.7 117 1.71 40 25.2 64 38.2 76 2.84 58 19.0 86 32.3 76 1.69 67 59.9 105 69.0 123 42.4 114 79.6 163 87.6 115 45.1 174 37.7 144 69.2 175 25.4 109 33.7 159 66.7 154 4.86 123 39.9 122 79.8 132 3.12 68
OFRF [132]111.1 16.1 167 39.8 152 3.51 167 27.6 149 40.2 130 4.76 151 18.4 47 34.3 126 1.75 85 60.4 129 68.9 118 43.0 143 79.2 61 87.5 74 43.1 52 38.1 153 68.1 155 26.4 155 32.2 98 65.0 98 4.79 103 39.0 35 79.1 76 3.05 42
IAOF [50]111.2 15.5 159 39.2 137 2.93 160 29.4 164 43.0 166 5.18 161 17.8 33 33.0 92 2.04 123 60.8 142 68.9 118 42.2 94 79.2 61 87.4 41 43.3 81 36.8 93 67.2 101 25.1 69 32.7 130 65.6 135 4.67 44 40.0 130 80.0 143 3.20 93
TCOF [69]111.3 14.4 124 39.3 139 1.83 60 27.3 145 40.9 146 3.35 107 18.7 67 32.1 70 1.50 23 60.2 124 70.2 158 42.1 81 79.3 91 87.6 115 43.2 71 36.9 101 68.5 164 24.8 38 33.3 148 65.8 138 4.72 69 41.2 168 81.4 174 3.46 150
LSM_FLOW_RVC [183]112.3 14.5 129 40.7 160 2.04 103 27.2 141 42.6 162 3.51 121 19.5 133 36.2 159 1.73 75 59.7 81 69.3 133 41.7 49 79.2 61 87.4 41 43.1 52 37.0 112 67.3 111 24.9 41 33.4 151 66.0 144 4.81 112 40.5 158 79.9 138 3.32 129
BriefMatch [122]113.8 14.0 85 37.0 60 2.17 113 25.6 91 38.8 93 3.98 132 19.7 146 33.0 92 2.69 159 61.1 152 69.0 123 46.4 173 79.3 91 87.6 115 43.8 158 40.5 179 67.9 147 30.6 179 31.8 32 64.0 55 4.94 134 39.0 35 78.8 56 3.34 132
CompactFlow_ROB [155]114.6 14.2 105 39.2 137 1.96 90 27.1 137 41.9 158 4.22 135 20.0 156 37.0 165 1.80 95 60.0 111 69.4 139 42.5 121 79.3 91 87.5 74 43.2 71 36.6 61 67.4 118 24.5 29 33.2 144 65.9 142 4.78 100 40.5 158 80.0 143 3.13 70
Adaptive [20]114.7 14.5 129 39.6 149 2.31 130 27.1 137 40.4 136 3.35 107 18.6 60 33.7 108 1.98 116 59.6 74 68.2 73 42.4 114 79.4 130 87.6 115 43.4 99 37.1 119 67.5 127 25.7 133 32.4 115 64.8 87 4.73 74 40.0 130 80.1 149 3.38 141
IIOF-NLDP [129]114.8 14.1 95 38.2 103 1.62 20 26.1 107 39.9 123 2.98 76 19.3 118 32.1 70 1.77 88 60.6 139 69.4 139 43.2 147 79.3 91 87.5 74 43.6 134 37.8 149 68.6 165 25.6 122 34.1 168 69.5 177 5.66 176 39.9 122 79.6 120 3.01 31
IRR-PWC_RVC [181]115.2 15.0 145 40.8 161 2.39 137 27.2 141 41.3 150 4.51 144 20.2 159 38.0 173 1.86 102 60.4 129 69.8 152 41.9 64 79.4 130 87.6 115 43.4 99 36.6 61 67.0 79 25.0 51 32.6 124 65.5 131 4.72 69 39.7 111 79.5 110 2.99 28
CNN-flow-warp+ref [115]116.0 13.8 64 36.0 33 2.35 134 26.6 121 39.8 119 3.83 128 20.0 156 35.5 150 2.34 144 60.9 144 68.9 118 43.0 143 79.4 130 87.6 115 43.7 150 36.8 93 67.0 79 25.6 122 32.1 79 66.2 149 4.94 134 39.4 84 79.5 110 3.19 86
FlowNetS+ft+v [110]116.1 14.7 139 38.1 97 2.80 152 27.5 148 40.6 141 4.81 153 19.6 138 34.9 136 2.07 124 60.1 119 69.5 146 42.2 94 79.4 130 87.7 143 43.4 99 36.6 61 67.1 91 25.2 80 32.0 64 65.4 125 4.73 74 39.6 104 79.7 128 3.21 100
AdaConv-v1 [124]117.7 16.5 171 42.3 168 4.36 172 30.4 170 43.8 170 9.06 179 20.6 165 36.3 161 4.45 179 64.5 177 71.3 174 45.3 168 78.4 25 86.7 25 42.2 27 36.3 32 64.9 26 25.4 109 32.5 120 63.7 39 5.53 171 38.0 15 77.4 23 3.53 159
SPSA-learn [13]118.2 14.8 143 37.8 87 2.72 148 27.6 149 40.1 127 4.71 150 20.5 162 33.7 108 2.97 166 60.4 129 67.6 46 41.5 34 79.3 91 87.5 74 43.5 114 36.8 93 67.2 101 25.2 80 33.4 151 70.8 183 6.21 183 39.7 111 79.6 120 3.19 86
ResPWCR_ROB [140]118.4 13.9 76 38.2 103 1.89 78 26.5 119 40.4 136 3.42 116 19.9 155 35.6 152 1.95 113 60.5 134 70.2 158 43.3 149 78.9 27 87.4 41 42.5 29 42.1 181 67.7 138 32.5 181 33.9 164 65.4 125 4.85 120 40.1 138 79.7 128 3.17 81
CRTflow [81]118.5 14.4 124 38.9 126 2.38 135 26.0 103 39.0 98 3.14 93 20.2 159 36.2 159 2.37 146 60.5 134 69.5 146 44.1 159 79.3 91 87.5 74 43.4 99 37.1 119 67.3 111 25.7 133 32.0 64 64.6 79 4.85 120 39.6 104 79.6 120 3.45 148
LDOF [28]118.6 15.0 145 38.8 120 2.92 158 28.0 156 41.1 148 5.03 156 19.7 146 34.8 135 2.15 135 60.0 111 68.9 118 42.6 128 79.4 130 87.6 115 43.5 114 36.9 101 66.8 61 25.5 115 31.9 47 65.1 109 4.73 74 39.5 96 79.6 120 3.23 108
ROF-ND [105]118.8 15.1 150 37.9 92 1.86 70 26.3 114 40.5 140 3.12 92 19.6 138 32.8 86 1.68 66 60.9 144 71.1 173 41.9 64 79.3 91 87.5 74 43.5 114 37.0 112 68.2 158 24.9 41 34.3 170 68.3 169 5.28 158 40.5 158 80.5 164 3.25 113
HBpMotionGpu [43]119.2 15.8 164 40.2 156 3.66 169 29.5 165 42.8 165 6.27 166 18.5 51 31.9 64 1.73 75 61.3 157 69.9 154 43.9 156 79.1 38 87.6 115 43.0 44 37.6 143 67.6 133 25.9 140 32.0 64 64.3 61 4.67 44 40.0 130 79.9 138 3.75 168
Occlusion-TV-L1 [63]119.2 14.3 118 39.1 133 2.21 123 26.6 121 40.0 125 3.14 93 19.2 110 34.2 124 2.15 135 60.0 111 68.5 88 42.8 131 79.3 91 87.5 74 43.6 134 37.5 137 67.0 79 26.2 150 32.9 137 65.1 109 5.16 152 40.0 130 79.8 132 3.30 125
Modified CLG [34]120.8 14.1 95 37.6 79 2.33 132 28.5 161 41.4 155 5.68 162 19.6 138 35.8 155 2.31 143 60.2 124 68.6 100 42.1 81 79.4 130 87.5 74 43.5 114 36.7 80 67.2 101 25.2 80 32.3 107 66.0 144 4.76 95 40.2 144 80.4 161 3.40 143
CBF [12]121.4 13.7 49 37.2 67 2.15 111 26.0 103 39.4 110 3.28 103 19.1 99 32.1 70 1.79 92 61.0 150 70.0 157 45.8 170 79.6 163 87.8 160 44.9 173 36.8 93 67.4 118 25.2 80 32.2 98 65.5 131 5.22 155 40.0 130 80.2 156 3.99 176
TriangleFlow [30]123.2 14.7 139 40.0 155 2.29 129 26.6 121 40.8 143 3.03 83 19.4 126 33.3 100 2.10 128 60.4 129 69.9 154 42.8 131 79.0 31 87.4 41 42.6 31 37.7 144 68.3 161 25.3 99 33.1 143 67.8 163 5.24 157 40.4 153 80.6 166 3.32 129
ACK-Prior [27]124.5 13.8 64 38.1 97 1.74 47 25.5 83 39.3 104 2.82 55 19.6 138 33.8 114 2.45 150 60.5 134 70.3 161 42.3 102 80.2 175 88.0 168 45.8 177 38.2 154 67.8 142 26.9 164 32.6 124 66.2 149 5.35 165 38.9 28 79.7 128 3.60 164
BlockOverlap [61]124.7 15.1 150 37.6 79 3.31 165 27.7 152 39.3 104 5.73 163 18.6 60 30.3 29 2.09 127 60.9 144 68.2 73 47.1 176 80.2 175 87.9 162 46.5 179 39.0 167 67.3 111 28.4 173 31.9 47 63.9 48 5.09 147 39.7 111 79.3 91 3.55 160
2D-CLG [1]124.8 14.5 129 37.6 79 2.76 149 29.8 167 42.4 161 6.69 173 19.7 146 35.2 145 2.74 162 60.7 140 68.7 106 41.5 34 79.4 130 87.7 143 43.5 114 36.6 61 67.0 79 25.1 69 32.5 120 66.7 154 4.90 129 40.2 144 80.1 149 3.25 113
Nguyen [33]125.1 15.6 160 38.5 110 3.62 168 30.1 169 43.2 167 6.04 164 19.6 138 36.3 161 2.25 141 61.1 152 69.4 139 42.0 76 79.2 61 87.5 74 43.1 52 36.4 40 67.2 101 24.7 37 34.3 170 67.4 160 5.00 140 40.2 144 80.3 157 3.29 122
SegOF [10]125.4 14.2 105 36.8 56 2.54 140 27.0 135 40.0 125 4.18 134 21.1 169 36.1 158 3.15 171 60.5 134 70.7 169 41.6 40 79.4 130 87.6 115 43.6 134 36.9 101 68.2 158 25.2 80 32.5 120 68.0 168 5.31 162 39.6 104 79.4 99 3.22 102
IAOF2 [51]126.6 15.6 160 41.3 163 2.58 143 27.6 149 41.4 155 4.29 138 17.8 33 33.6 105 1.94 111 61.2 155 70.8 170 42.8 131 79.4 130 87.7 143 43.3 81 37.2 127 67.5 127 25.6 122 32.3 107 65.0 98 4.63 25 40.6 161 80.4 161 3.40 143
TV-L1-improved [17]127.2 14.2 105 38.8 120 2.25 126 26.9 132 40.3 133 3.40 113 19.5 133 33.9 115 2.44 149 59.9 105 69.0 123 42.7 130 79.4 130 87.7 143 43.5 114 37.2 127 67.6 133 25.8 137 32.1 79 66.1 147 5.05 144 39.9 122 80.0 143 3.46 150
Correlation Flow [76]127.5 14.0 85 38.3 106 1.61 16 26.2 111 39.8 119 2.98 76 19.1 99 31.9 64 1.73 75 60.4 129 69.4 139 43.6 152 80.2 175 87.9 162 47.8 182 38.0 152 68.7 168 26.0 145 33.4 151 67.2 158 5.29 159 40.1 138 80.3 157 3.39 142
StereoOF-V1MT [117]127.8 14.6 135 39.9 153 2.00 97 27.2 141 41.9 158 3.04 84 20.9 168 37.8 170 2.85 165 61.3 157 68.3 80 43.8 153 79.2 61 87.5 74 42.9 37 38.2 154 67.8 142 26.3 154 33.8 160 68.5 170 5.36 166 40.0 130 79.4 99 3.09 58
Dynamic MRF [7]127.9 13.9 76 38.6 112 1.90 80 26.1 107 40.4 136 3.08 87 20.0 156 37.7 169 2.73 161 61.3 157 69.3 133 44.6 163 79.1 38 87.6 115 43.0 44 37.7 144 68.0 151 25.9 140 32.6 124 67.2 158 5.08 146 40.4 153 80.5 164 3.49 155
WRT [146]129.2 14.3 118 39.0 130 1.76 50 26.6 121 39.7 115 3.14 93 20.8 166 31.9 64 2.57 155 60.2 124 69.5 146 42.3 102 79.6 163 87.7 143 44.4 167 37.8 149 69.5 180 25.5 115 34.2 169 71.4 184 6.06 181 39.7 111 79.8 132 2.95 24
Rannacher [23]131.2 14.4 124 39.3 139 2.38 135 26.9 132 40.4 136 3.36 110 19.5 133 34.6 132 2.58 156 59.8 93 68.8 112 42.8 131 79.4 130 87.7 143 43.6 134 37.2 127 67.8 142 25.8 137 32.2 98 66.0 144 5.02 141 39.9 122 79.9 138 3.56 161
Black & Anandan [4]132.4 15.3 155 38.8 120 2.96 161 28.4 159 40.9 146 4.78 152 20.5 162 35.2 145 2.74 162 60.9 144 69.3 133 42.1 81 79.4 130 87.7 143 43.6 134 37.1 119 66.6 45 25.6 122 32.9 137 65.9 142 4.72 69 40.3 147 80.3 157 3.25 113
LocallyOriented [52]134.5 15.0 145 40.3 157 2.53 139 27.7 152 41.3 150 3.86 129 19.4 126 34.4 129 1.95 113 61.1 152 70.6 166 43.3 149 79.2 61 87.5 74 43.3 81 39.1 171 68.1 155 27.6 170 32.9 137 65.8 138 4.72 69 40.6 161 80.6 166 3.37 139
UnFlow [127]137.0 16.0 166 42.8 171 2.87 155 30.6 173 45.2 179 4.52 145 21.3 172 39.4 177 2.81 164 60.0 111 68.3 80 42.1 81 79.2 61 87.4 41 43.5 114 37.5 137 68.0 151 25.2 80 33.8 160 65.1 109 4.98 138 43.2 180 81.8 178 3.67 166
TVL1_RVC [176]140.1 16.2 168 39.4 144 4.14 171 30.4 170 43.4 168 6.38 168 18.9 78 34.9 136 2.12 131 61.3 157 69.1 130 42.9 142 79.4 130 87.7 143 43.6 134 37.5 137 67.2 101 26.0 145 32.3 107 66.2 149 4.91 131 40.1 138 80.3 157 3.31 128
Filter Flow [19]141.2 15.0 145 39.4 144 2.78 151 28.4 159 40.8 143 6.31 167 18.5 51 32.9 88 2.14 133 61.7 164 69.3 133 45.3 168 79.7 168 88.0 168 44.5 169 37.3 131 67.7 138 26.1 148 32.1 79 65.2 119 4.93 132 40.3 147 80.7 169 3.97 175
StereoFlow [44]142.4 22.8 183 51.1 184 4.80 174 36.2 183 51.1 184 6.57 171 19.2 110 34.6 132 1.89 107 60.0 111 68.5 88 42.4 114 80.3 178 89.1 183 43.9 161 39.0 167 74.1 184 25.3 99 32.1 79 65.0 98 4.73 74 40.3 147 80.9 170 3.36 136
WOLF_ROB [144]148.0 15.6 160 41.7 166 2.64 144 27.8 154 41.3 150 3.72 125 19.7 146 35.2 145 2.02 122 61.3 157 71.8 175 44.5 161 79.4 130 87.8 160 43.7 150 38.8 165 67.9 147 27.5 169 34.4 173 67.7 161 5.09 147 39.9 122 79.6 120 3.22 102
Ad-TV-NDC [36]148.0 17.2 174 39.9 153 5.26 176 29.6 166 42.1 160 6.18 165 19.2 110 33.7 108 1.98 116 62.4 166 70.3 161 45.2 167 79.6 163 87.9 162 43.9 161 38.3 157 67.3 111 27.2 168 32.3 107 65.5 131 4.80 111 40.3 147 80.1 149 3.58 163
Bartels [41]148.7 14.6 135 39.3 139 2.80 152 26.1 107 39.7 115 4.45 141 19.0 86 33.2 97 2.14 133 62.1 165 70.9 171 48.9 178 80.7 182 88.1 171 49.2 184 43.7 183 69.0 174 34.8 184 32.4 115 65.0 98 5.76 178 40.4 153 80.1 149 4.26 178
TI-DOFE [24]151.6 17.9 177 43.0 172 5.41 177 32.3 179 46.2 181 7.98 177 20.5 162 38.1 175 2.97 166 63.1 173 70.6 166 43.8 153 79.1 38 87.6 115 43.1 52 37.7 144 67.4 118 25.8 137 33.4 151 67.8 163 5.09 147 41.6 172 81.5 176 3.68 167
Horn & Schunck [3]152.6 15.3 155 40.4 159 2.69 146 29.0 162 42.7 163 5.10 157 21.1 169 37.9 172 3.33 173 62.5 168 70.3 161 43.0 143 79.3 91 87.7 143 43.6 134 37.5 137 67.3 111 25.9 140 33.9 164 68.5 170 5.03 142 41.2 168 81.2 173 3.57 162
GroupFlow [9]155.3 16.8 173 43.4 173 3.43 166 29.1 163 43.9 171 5.11 159 22.2 176 39.3 176 3.53 174 61.0 150 70.6 166 42.5 121 79.7 168 88.1 171 44.0 164 39.0 167 69.4 179 26.8 163 32.8 133 66.8 156 4.87 125 40.4 153 80.1 149 3.01 31
2bit-BM-tele [96]156.7 15.3 155 39.5 147 3.22 164 27.8 154 41.2 149 4.90 154 18.8 70 32.5 82 2.34 144 62.4 166 71.0 172 49.0 179 80.6 180 88.2 176 47.9 183 42.8 182 69.3 178 32.9 182 33.4 151 70.0 181 6.77 184 40.3 147 79.4 99 4.33 181
SLK [47]158.0 17.4 175 43.9 176 4.90 175 30.5 172 44.0 172 7.18 175 22.5 177 39.8 178 4.15 178 64.5 177 70.5 165 46.7 174 78.9 27 87.7 143 41.6 24 38.5 160 68.8 170 26.0 145 33.8 160 70.1 182 5.50 169 41.6 172 81.4 174 3.91 172
NL-TV-NCC [25]158.6 15.1 150 41.6 165 1.86 70 26.6 121 41.3 150 3.02 82 20.8 166 35.7 153 2.24 140 63.2 174 73.9 180 45.9 171 81.3 184 88.7 182 49.9 185 38.6 162 69.8 182 25.6 122 37.6 179 69.5 177 5.62 174 42.4 179 82.1 181 4.00 177
SILK [80]159.1 16.3 169 42.0 167 4.01 170 29.9 168 43.5 169 6.44 169 21.6 173 37.4 167 3.55 175 62.6 169 69.4 139 47.0 175 79.3 91 87.7 143 43.6 134 39.9 176 68.1 155 29.2 177 32.8 133 67.8 163 5.14 151 40.6 161 80.6 166 3.52 158
HCIC-L [97]160.1 23.2 184 49.0 183 11.0 184 32.1 178 44.4 173 9.93 180 23.2 179 36.4 163 3.02 168 64.4 175 72.1 176 44.9 164 80.6 180 88.5 180 46.6 180 39.1 171 68.9 172 27.1 166 32.4 115 65.0 98 5.53 171 39.1 47 79.3 91 3.65 165
Heeger++ [102]162.7 17.5 176 47.2 182 2.80 152 31.1 175 44.9 177 4.93 155 26.6 182 47.7 183 4.79 180 62.6 169 68.0 66 45.1 165 79.8 172 88.4 179 44.1 165 39.1 171 68.9 172 26.5 158 34.8 174 67.9 167 5.23 156 41.5 171 80.1 149 3.23 108
H+S_RVC [177]162.7 16.5 171 43.8 175 2.91 157 31.7 176 44.6 174 6.50 170 24.3 180 44.2 181 4.80 181 65.7 180 69.4 139 44.5 161 79.4 130 88.2 176 43.1 52 38.5 160 68.6 165 25.6 122 34.8 174 69.4 176 5.55 173 43.5 183 81.6 177 3.89 171
Learning Flow [11]165.0 15.3 155 42.7 170 2.55 141 28.0 156 42.7 163 3.95 130 21.1 169 37.0 165 3.03 170 63.0 172 73.3 178 46.2 172 80.0 173 88.2 176 45.1 174 38.2 154 68.6 165 26.7 160 33.8 160 68.5 170 5.21 154 41.9 176 82.3 182 3.95 174
FFV1MT [104]165.2 16.4 170 44.7 178 3.13 162 31.9 177 44.7 175 7.15 174 25.4 181 45.6 182 5.04 182 62.6 169 68.0 66 45.1 165 79.6 163 87.9 162 44.1 165 38.9 166 67.7 138 27.1 166 34.0 167 68.5 170 5.29 159 41.8 175 81.0 171 4.48 183
Adaptive flow [45]168.2 19.6 179 44.1 177 6.76 179 32.8 180 45.7 180 10.2 181 19.8 151 34.4 129 3.02 168 64.7 179 72.1 176 49.4 180 80.3 178 88.6 181 45.6 176 38.3 157 69.2 175 26.7 160 32.6 124 66.5 153 5.45 168 41.0 165 81.1 172 3.75 168
Pyramid LK [2]170.7 21.2 182 43.7 174 10.7 183 33.1 182 45.1 178 11.9 182 27.3 183 36.0 156 6.46 183 70.7 184 78.5 184 57.7 184 79.5 160 88.1 171 43.3 81 38.6 162 68.8 170 27.0 165 33.5 157 68.8 174 6.00 179 41.0 165 81.8 178 4.31 180
FOLKI [16]174.9 20.9 180 46.0 179 9.48 182 32.8 180 47.4 182 8.75 178 21.6 173 40.7 179 4.10 177 67.2 183 74.2 182 53.7 183 79.5 160 88.1 171 43.7 150 39.2 174 69.2 175 27.9 171 33.4 151 69.5 177 5.65 175 41.7 174 82.3 182 4.28 179
PGAM+LK [55]175.2 19.4 178 46.4 180 6.81 180 30.9 174 44.8 176 7.52 176 22.7 178 40.9 180 3.99 176 66.6 182 73.9 180 52.4 182 79.7 168 88.1 171 44.5 169 40.2 178 69.7 181 28.8 175 33.3 148 69.3 175 5.42 167 41.4 170 81.8 178 4.36 182
Periodicity [79]181.7 21.0 181 47.0 181 9.32 181 38.1 184 48.1 183 14.7 184 29.8 184 47.9 184 9.27 184 66.0 181 77.1 183 50.7 181 80.8 183 89.3 184 46.8 181 45.1 184 70.6 183 35.5 185 33.5 157 69.6 180 6.07 182 43.5 183 84.0 184 6.51 184
AVG_FLOW_ROB [137]184.2 51.4 185 76.8 185 29.6 185 67.5 185 74.0 185 36.6 185 51.8 185 59.9 185 20.1 185 84.7 185 90.1 185 64.7 185 81.8 185 91.0 185 44.5 169 51.7 185 87.4 185 33.4 183 57.5 185 81.8 185 10.1 185 63.2 185 86.1 185 26.5 185
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.