Optical flow evaluation results Statistics:     Average   SD   R2.5   R5.0   R10.0   A50   A75   A95  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
R5.0
angle
error
avg. Army
(Hidden texture)
GT   im0   im1
Mequon
(Hidden texture)
GT   im0   im1
Schefflera
(Hidden texture)
GT   im0   im1
Wooden
(Hidden texture)
GT   im0   im1
Grove
(Synthetic)
GT   im0   im1
Urban
(Synthetic)
GT   im0   im1
Yosemite
(Synthetic)
GT   im0   im1
Teddy
(Stereo)
GT   im0   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
RAFT-it+_RVC [198]2.7 7.80 3 25.6 4 2.77 1 5.39 4 19.9 1 5.35 13 4.02 2 13.8 2 1.39 2 0.86 2 9.09 2 0.01 1 11.4 1 16.3 4 4.51 1 3.05 1 13.0 1 1.89 1 1.46 3 11.5 3 0.05 1 1.08 4 3.98 7 0.02 1
RAFT-it [194]9.2 9.16 12 28.0 12 3.69 5 6.15 9 22.7 3 5.47 15 4.36 3 14.6 3 2.64 7 0.76 1 8.31 1 0.15 3 13.4 9 18.7 11 6.14 6 5.09 3 13.6 2 5.33 4 4.89 25 23.7 74 0.67 6 0.87 2 3.19 2 0.05 2
MS_RAFT+_RVC [195]10.9 9.48 16 25.6 4 3.00 2 11.0 64 24.1 7 12.7 95 5.23 5 16.1 5 4.55 24 0.97 3 10.2 4 0.14 2 11.8 4 16.2 2 5.30 3 4.33 2 13.8 3 4.19 3 1.06 1 9.70 1 0.22 3 0.70 1 2.13 1 0.42 7
NNF-Local [75]16.3 7.69 2 26.2 7 3.54 4 7.19 19 30.7 33 6.11 27 5.88 8 19.3 12 4.53 22 4.01 15 23.9 25 2.00 18 11.7 2 16.4 5 5.52 5 10.4 22 29.7 14 9.30 15 5.25 32 20.0 30 2.61 22 1.88 13 6.47 35 0.19 5
MDP-Flow2 [68]18.0 10.3 24 30.4 22 6.57 28 5.28 2 23.9 5 4.13 3 5.46 6 17.6 6 3.58 12 4.49 24 25.3 31 2.11 21 15.8 28 21.4 28 10.2 36 10.6 24 29.9 15 9.87 25 4.44 16 19.3 22 2.81 23 1.39 8 4.82 12 1.11 11
OFLAF [78]19.2 8.96 10 27.9 11 4.57 12 7.36 23 26.4 13 6.68 30 4.80 4 14.9 4 3.37 11 4.43 23 21.2 15 2.81 37 13.4 9 19.0 13 7.08 11 11.4 34 28.0 8 9.28 13 5.35 34 19.1 20 3.15 26 2.47 25 5.73 26 5.50 49
NN-field [71]20.6 8.65 6 28.3 13 4.00 7 8.38 35 33.1 50 7.44 36 5.86 7 19.0 10 4.53 22 3.15 6 21.4 17 1.25 8 12.0 6 16.9 7 5.41 4 6.58 5 20.2 4 3.45 2 8.64 71 23.6 71 2.88 24 2.47 25 8.48 53 0.20 6
RAFT-TF_RVC [179]22.0 13.0 56 35.5 51 4.17 9 8.26 33 28.0 18 7.49 37 7.92 37 23.2 27 7.98 66 1.09 4 9.43 3 0.18 4 15.1 21 21.3 23 6.37 7 8.49 7 22.6 5 8.43 11 4.54 17 23.1 64 0.69 7 1.31 7 4.62 10 0.10 4
CoT-AMFlow [174]25.5 10.1 20 30.9 25 6.87 31 6.06 7 25.8 11 5.30 12 5.99 10 19.1 11 4.65 27 4.70 29 25.8 37 2.42 27 16.0 31 21.3 23 12.2 56 10.5 23 31.1 19 9.77 20 5.57 36 21.3 45 3.87 40 2.08 16 5.30 18 4.37 37
PMMST [112]27.1 12.9 54 32.6 35 8.45 54 10.2 50 30.5 30 10.7 67 7.39 24 22.2 19 6.31 42 3.87 14 13.5 5 2.73 33 14.0 13 18.7 11 7.52 12 10.9 30 28.9 11 9.95 26 4.99 28 20.8 37 3.18 28 1.52 9 3.87 6 1.12 12
HAST [107]30.3 7.13 1 21.8 1 3.37 3 7.28 21 26.1 12 6.10 26 3.86 1 12.2 1 0.97 1 3.85 13 21.3 16 1.50 9 11.7 2 16.5 6 4.64 2 15.1 79 35.5 41 14.0 82 19.4 117 36.3 123 39.0 148 1.24 6 3.55 4 1.32 13
ComponentFusion [94]31.0 8.86 9 28.7 15 5.91 21 6.30 10 24.2 8 5.98 22 6.79 17 21.6 16 4.99 30 4.11 16 24.4 26 2.04 20 16.2 37 22.0 35 11.3 48 13.4 54 40.4 70 12.4 67 7.66 63 21.3 45 5.22 55 2.05 15 5.21 16 3.61 28
ALD-Flow [66]31.3 8.44 5 27.6 10 4.09 8 6.49 12 27.2 16 5.04 11 7.66 29 24.1 32 3.72 14 4.58 27 27.1 45 2.01 19 16.0 31 22.7 43 8.55 17 9.39 14 33.3 28 8.46 12 7.21 58 18.5 14 17.3 115 4.06 65 11.1 68 5.94 59
nLayers [57]32.2 8.66 7 25.4 3 4.54 10 13.0 94 32.1 43 13.7 103 7.74 31 21.8 17 8.85 72 3.29 8 18.2 7 1.89 15 11.8 4 16.2 2 6.65 10 12.2 41 28.4 9 10.3 29 8.59 70 21.5 52 4.98 51 2.36 23 5.74 27 5.08 45
LME [70]32.8 9.71 17 29.0 17 6.46 27 5.49 6 22.8 4 4.79 9 8.62 46 22.4 21 11.2 85 4.73 30 28.3 62 2.35 26 16.5 41 21.9 33 12.6 64 10.7 25 34.0 34 9.81 23 5.57 36 21.3 45 3.87 40 2.40 24 6.32 32 4.52 39
NNF-EAC [101]33.3 10.9 34 31.8 30 6.97 32 6.64 14 26.4 13 5.65 16 6.61 13 20.7 13 4.44 21 5.48 51 27.1 45 2.97 42 16.5 41 22.3 39 11.1 45 12.1 40 30.7 17 9.97 27 6.42 48 21.4 48 3.94 42 2.95 41 7.51 45 4.63 42
TC/T-Flow [77]34.0 9.15 11 32.1 32 3.69 5 6.89 17 31.2 37 4.32 4 7.32 23 23.1 26 4.08 16 5.14 42 27.2 48 2.80 36 15.6 26 21.9 33 9.71 29 8.63 10 29.2 12 8.40 9 6.72 51 20.2 33 19.7 129 3.86 62 9.43 58 6.28 66
ProFlow_ROB [142]34.2 10.7 29 32.8 41 5.26 17 7.26 20 30.8 34 5.92 19 9.43 54 29.1 58 5.30 33 4.35 22 25.3 31 1.73 14 17.4 51 24.7 57 9.39 24 9.20 11 33.5 29 9.28 13 3.74 11 21.4 48 0.91 8 4.20 67 11.6 70 6.06 61
WLIF-Flow [91]35.3 9.40 15 27.1 8 6.06 23 10.0 47 33.0 48 9.71 52 7.26 22 22.4 21 5.90 41 4.53 25 23.7 23 2.56 32 16.1 33 22.3 39 11.3 48 12.8 43 33.2 27 10.4 32 6.85 53 18.8 17 7.36 72 2.80 37 6.48 36 5.62 53
FC-2Layers-FF [74]36.4 9.97 19 28.7 15 7.96 43 10.4 52 35.3 60 9.95 54 6.11 11 18.1 9 6.82 46 4.12 17 20.9 13 2.48 30 13.3 8 17.7 8 9.47 26 13.5 55 32.6 22 11.3 45 14.0 98 26.0 88 12.5 96 1.84 11 4.18 8 4.53 40
RNLOD-Flow [119]36.8 7.93 4 24.8 2 5.41 19 8.33 34 31.7 39 6.84 32 7.47 25 23.3 28 4.60 25 3.62 11 21.1 14 1.66 12 14.4 15 21.0 19 7.80 13 12.7 42 32.9 23 12.2 66 17.4 112 34.4 118 20.7 131 2.55 28 5.57 24 5.30 47
PRAFlow_RVC [177]36.9 18.4 91 41.9 72 7.63 36 13.9 105 36.5 64 13.3 100 11.1 68 30.2 63 10.6 80 2.23 5 15.0 6 0.54 5 15.3 23 21.3 23 8.44 16 9.59 17 24.7 6 9.82 24 2.25 5 20.1 31 0.44 4 1.96 14 4.67 11 1.90 16
Layers++ [37]37.2 10.2 22 29.1 18 8.58 57 10.8 58 30.6 31 11.0 73 5.90 9 17.7 7 6.34 43 3.40 9 18.2 7 1.66 12 12.2 7 16.0 1 9.69 28 13.9 62 33.6 30 11.9 59 13.9 97 27.9 94 8.74 78 2.33 22 4.94 13 5.70 56
UnDAF [187]37.2 10.6 28 32.9 42 6.71 29 6.11 8 28.4 23 4.73 7 6.87 18 22.3 20 4.21 18 4.82 32 28.2 60 2.25 23 16.2 37 21.8 32 11.5 50 11.7 35 38.7 61 9.79 21 5.77 40 21.1 41 3.69 36 5.19 80 16.5 111 4.58 41
FESL [72]38.8 8.67 8 25.6 4 4.73 13 13.6 100 39.4 101 12.9 97 8.22 40 24.3 36 7.10 50 3.76 12 20.3 12 2.12 22 14.1 14 20.1 15 9.08 20 11.2 33 31.0 18 9.80 22 11.3 81 30.4 104 7.66 74 2.10 17 5.40 20 2.40 18
SVFilterOh [109]38.9 12.7 52 28.4 14 8.58 57 9.41 42 29.1 25 8.31 43 6.39 12 17.7 7 5.05 32 3.23 7 18.8 10 0.95 6 14.9 18 20.9 18 6.51 9 13.2 49 32.1 21 11.6 51 22.0 123 46.5 150 30.5 142 1.61 10 4.97 15 2.45 20
TC-Flow [46]41.0 9.24 13 30.9 25 5.24 16 5.48 5 25.7 10 4.01 2 7.25 20 23.3 28 2.66 8 5.52 52 28.4 63 3.26 50 16.7 45 23.9 52 9.52 27 11.7 35 36.8 46 11.5 50 6.69 50 21.4 48 19.0 126 4.21 68 10.6 65 6.91 80
OAR-Flow [123]42.6 10.8 32 34.0 46 6.23 24 8.94 38 31.9 41 7.53 38 10.4 62 30.3 65 7.58 58 5.60 56 25.9 40 3.04 45 17.0 46 24.0 53 9.35 23 8.62 9 33.0 24 7.87 7 3.37 8 14.6 5 5.54 61 4.80 75 10.4 64 9.44 103
IROF++ [58]43.8 10.2 22 30.9 25 7.02 33 11.1 66 38.1 84 10.7 67 8.32 44 25.1 41 7.61 59 5.83 59 28.0 57 4.08 71 15.4 25 21.3 23 9.83 31 13.6 56 38.0 56 11.3 45 5.83 41 20.8 37 1.97 19 2.32 21 5.71 25 4.87 44
AGIF+OF [84]43.9 10.4 25 29.4 20 7.42 35 12.4 85 37.5 74 12.4 90 7.91 36 24.3 36 7.24 52 4.84 35 23.8 24 2.91 39 14.8 17 20.6 17 9.72 30 13.2 49 36.5 44 10.5 34 7.06 55 20.8 37 7.54 73 3.02 47 6.27 30 6.37 69
Efficient-NL [60]44.0 9.31 14 27.5 9 5.65 20 12.1 83 38.1 84 11.2 75 8.07 39 24.1 32 6.69 45 5.39 48 25.9 40 3.51 61 14.9 18 21.1 21 9.39 24 14.0 65 35.2 39 11.1 42 11.5 83 25.7 86 6.90 69 2.19 20 5.45 22 1.94 17
PMF [73]45.3 11.6 44 29.9 21 4.55 11 7.81 26 30.2 27 6.00 23 7.17 19 23.3 28 3.21 10 4.88 38 23.1 21 2.42 27 13.6 11 18.5 9 6.49 8 16.1 87 42.7 85 15.4 91 27.2 140 43.5 147 28.9 139 2.15 19 4.96 14 4.81 43
PH-Flow [99]45.4 10.9 34 32.6 35 7.94 42 10.9 60 37.4 72 10.5 61 7.56 28 22.8 25 7.74 63 5.75 58 27.2 48 4.04 69 14.4 15 19.8 14 8.81 18 13.0 45 33.6 30 11.1 42 12.7 91 23.1 64 17.6 118 1.84 11 4.19 9 4.50 38
Classic+CPF [82]46.8 10.9 34 31.7 29 7.88 41 11.5 72 37.9 80 10.9 71 8.27 42 25.1 41 7.51 57 5.05 40 25.8 37 3.16 47 15.1 21 21.0 19 10.6 37 13.1 46 34.6 37 10.3 29 9.87 75 22.0 58 13.1 102 2.68 31 5.85 28 5.53 50
3DFlow [133]47.8 12.6 51 34.9 47 5.05 15 8.12 30 31.5 38 5.95 20 6.67 15 21.9 18 2.51 5 4.59 28 18.4 9 3.30 53 16.6 43 23.0 45 10.9 40 19.7 108 46.8 108 19.8 118 18.3 115 24.2 79 33.3 144 1.20 5 3.86 5 0.68 8
COFM [59]47.9 10.1 20 32.0 31 7.63 36 8.06 29 30.4 29 7.17 33 8.93 51 25.9 47 8.04 68 4.17 18 24.9 29 1.63 11 18.8 63 24.0 53 18.6 112 14.4 69 33.0 24 11.7 53 8.15 66 20.4 34 14.7 109 3.16 49 5.36 19 8.09 96
Ramp [62]48.6 10.9 34 32.7 39 7.96 43 10.9 60 37.1 69 10.6 63 7.85 32 24.2 34 7.41 55 5.29 45 27.0 44 3.44 56 16.1 33 22.3 39 10.8 38 13.8 60 35.4 40 11.0 41 11.6 84 21.1 41 18.2 122 2.52 27 5.44 21 5.23 46
Sparse-NonSparse [56]49.2 10.7 29 32.5 34 8.38 52 10.9 60 36.8 67 10.7 67 7.95 38 24.5 40 7.30 53 5.42 50 27.6 51 3.49 60 16.1 33 22.1 36 11.0 43 13.3 51 36.0 43 10.6 36 10.6 79 21.1 41 10.9 87 2.91 38 5.93 29 6.18 64
Correlation Flow [76]49.5 11.9 48 35.3 48 6.03 22 6.85 16 28.0 18 4.77 8 8.29 43 25.8 45 2.17 4 4.84 35 27.2 48 2.77 35 18.5 59 25.9 70 11.7 52 16.9 95 39.5 64 16.7 99 12.1 87 24.6 81 17.8 119 2.59 29 7.33 43 3.08 21
JOF [136]49.9 9.77 18 29.1 18 7.11 34 12.1 83 37.9 80 12.0 86 7.25 20 21.2 15 7.73 61 4.82 32 25.8 37 3.02 44 14.9 18 20.2 16 10.0 35 13.1 46 33.7 32 10.6 36 17.8 113 29.5 99 28.8 138 2.94 40 6.80 39 5.71 57
LSM [39]50.2 10.4 25 32.6 35 8.24 47 10.8 58 37.4 72 10.4 60 7.85 32 24.3 36 7.05 48 5.32 46 27.6 51 3.41 55 15.8 28 21.5 29 11.1 45 13.7 58 35.6 42 10.9 40 13.0 92 23.2 66 12.5 96 2.99 46 6.43 34 6.14 63
ProbFlowFields [126]50.3 16.2 73 47.8 88 11.7 87 8.96 39 31.0 35 8.86 46 9.73 58 28.4 56 10.1 77 6.09 68 25.5 34 4.53 81 18.2 57 25.5 63 10.9 40 9.76 19 34.2 35 11.7 53 4.63 19 18.8 17 3.79 39 2.95 41 8.94 57 3.52 26
PBOFVI [189]50.5 19.4 100 38.3 59 13.1 94 7.96 28 31.8 40 6.15 28 6.77 16 21.0 14 2.12 3 3.57 10 19.8 11 1.24 7 18.5 59 25.4 60 11.5 50 14.7 73 38.6 60 16.2 97 7.61 61 21.6 53 17.3 115 3.38 54 8.26 52 6.29 68
Classic+NL [31]52.8 10.5 27 31.4 28 8.38 52 11.1 66 37.9 80 10.6 63 7.87 34 24.0 31 7.48 56 5.57 54 27.6 51 3.62 63 15.8 28 21.5 29 10.8 38 14.1 66 37.4 51 11.4 47 14.8 101 25.9 87 13.4 105 2.61 30 5.29 17 6.10 62
S2D-Matching [83]54.6 10.7 29 32.2 33 8.71 59 10.7 56 36.6 66 10.2 57 8.94 52 27.2 52 6.96 47 5.17 43 26.0 42 3.36 54 16.3 39 22.1 36 10.9 40 14.4 69 37.0 47 11.7 53 16.4 106 26.0 88 16.5 113 2.79 36 5.49 23 6.49 71
FMOF [92]54.6 11.0 42 30.4 22 8.33 51 13.0 94 38.5 91 12.6 92 7.51 26 22.6 23 7.34 54 5.06 41 25.2 30 3.44 56 15.3 23 21.3 23 9.87 33 14.9 77 33.1 26 11.4 47 11.7 86 24.3 80 15.0 111 3.92 63 8.59 54 6.28 66
HCFN [157]55.9 10.9 34 36.7 56 6.43 26 5.32 3 24.0 6 4.44 5 6.63 14 22.6 23 2.60 6 4.85 37 27.9 56 2.54 31 15.6 26 21.5 29 9.30 22 15.0 78 40.7 74 13.9 81 35.1 154 46.6 151 40.3 152 5.63 90 12.3 75 11.0 112
IROF-TV [53]56.2 11.6 44 35.3 48 9.03 62 11.2 69 38.2 87 10.9 71 8.85 50 26.5 48 7.73 61 6.04 66 33.0 86 3.62 63 17.1 49 23.1 47 13.5 80 16.3 88 44.8 93 13.5 79 3.41 9 16.9 7 1.13 14 2.71 33 6.80 39 5.67 55
IIOF-NLDP [129]56.6 14.6 60 41.6 71 6.71 29 11.0 64 37.5 74 8.25 42 8.77 49 26.9 50 4.19 17 6.07 67 28.0 57 3.76 65 19.7 78 27.1 85 12.6 64 16.7 92 40.7 74 15.4 91 4.68 23 23.0 62 4.41 46 2.78 35 7.26 42 3.16 22
TV-L1-MCT [64]58.0 10.9 34 30.5 24 8.56 56 13.8 103 40.9 112 13.2 99 8.68 47 25.8 45 7.98 66 4.83 34 25.7 35 3.26 50 17.4 51 23.5 50 13.7 84 14.8 76 36.7 45 12.7 69 5.84 42 19.4 23 10.1 84 3.53 57 6.42 33 6.63 73
SimpleFlow [49]59.2 11.6 44 33.7 43 8.98 61 12.5 90 38.9 94 12.6 92 10.4 62 29.3 60 9.20 73 5.99 63 27.6 51 4.08 71 16.3 39 22.2 38 11.1 45 16.7 92 37.4 51 12.7 69 8.29 67 19.9 28 6.11 65 2.74 34 6.28 31 5.86 58
2DHMM-SAS [90]59.2 10.9 34 32.6 35 8.06 45 11.5 72 39.5 102 10.6 63 10.0 61 28.3 55 7.91 65 5.93 62 28.2 60 4.07 70 16.1 33 22.3 39 11.0 43 13.7 58 38.3 58 11.1 42 12.3 89 23.2 66 18.0 121 3.08 48 6.48 36 6.24 65
CostFilter [40]59.8 14.1 59 36.2 55 8.48 55 8.61 37 30.6 31 7.43 35 8.26 41 26.9 50 4.40 20 5.72 57 28.1 59 3.24 49 13.7 12 18.5 9 7.81 14 16.6 91 45.0 98 16.0 95 26.8 138 48.6 154 32.7 143 2.93 39 7.59 46 5.38 48
AggregFlow [95]60.0 13.9 58 33.8 44 11.2 80 13.7 101 39.6 104 12.6 92 12.0 76 31.3 66 13.7 98 5.40 49 23.5 22 3.44 56 17.5 53 25.4 60 7.98 15 8.57 8 25.9 7 8.42 10 7.00 54 24.1 78 4.53 47 5.53 87 9.80 60 11.7 115
Adaptive [20]60.9 10.9 34 33.8 44 4.92 14 10.5 53 35.0 59 9.53 51 12.2 77 33.7 71 7.68 60 5.57 54 30.3 72 2.95 41 21.7 105 26.7 79 20.6 119 10.8 27 34.9 38 7.26 6 14.0 98 28.8 98 4.88 48 4.50 72 10.2 63 6.84 78
MDP-Flow [26]61.5 12.2 50 40.6 65 8.88 60 9.32 41 28.3 21 10.5 61 9.09 53 28.1 54 9.37 75 6.03 65 30.6 74 3.99 67 17.2 50 23.1 47 12.4 59 13.9 62 42.7 85 12.5 68 7.10 57 23.6 71 4.09 44 5.35 83 13.2 82 7.09 83
RFlow [88]62.8 14.8 61 43.9 76 11.2 80 6.64 14 26.6 15 5.76 17 11.7 72 35.9 81 5.04 31 4.31 20 27.1 45 1.94 16 19.4 69 26.8 82 13.0 75 14.7 73 42.2 82 11.8 58 13.1 93 22.2 59 13.1 102 5.87 95 14.1 91 8.71 100
Occlusion-TV-L1 [63]63.1 12.9 54 36.1 54 8.26 50 9.51 45 32.7 45 8.99 47 12.3 78 34.4 76 8.27 69 5.53 53 29.8 70 3.04 45 20.5 94 28.5 105 13.8 86 9.95 20 37.9 53 11.6 51 7.64 62 21.8 57 3.47 31 5.69 91 13.9 89 7.59 90
WRT [146]63.3 15.4 68 39.7 61 5.30 18 15.2 109 40.5 109 13.7 103 12.4 79 33.7 71 4.05 15 4.55 26 22.8 20 2.34 25 17.0 46 22.7 43 13.0 75 24.7 136 45.1 99 18.9 113 6.51 49 23.5 69 6.55 67 3.24 51 7.37 44 3.24 23
OFH [38]64.6 15.0 63 40.9 67 14.4 100 7.06 18 29.9 26 5.37 14 10.8 65 33.1 70 4.86 29 5.84 60 30.6 74 3.46 59 19.5 73 26.1 72 15.3 94 15.6 83 46.5 106 16.6 98 4.19 14 21.7 55 3.74 38 5.39 85 15.4 102 7.23 85
PWC-Net_RVC [143]66.5 23.5 113 52.0 110 13.4 96 13.0 94 37.8 78 12.4 90 14.0 90 39.3 90 14.4 101 7.08 79 24.7 27 2.76 34 19.9 82 25.7 69 12.7 68 13.8 60 43.4 88 13.4 78 3.79 13 22.4 60 1.03 11 2.14 18 6.78 38 1.08 10
MLDP_OF [87]67.5 18.8 97 51.3 105 16.0 103 8.16 31 32.0 42 6.76 31 10.7 64 31.9 68 5.45 36 4.81 31 26.1 43 2.44 29 18.7 61 24.3 55 13.7 84 15.6 83 37.9 53 18.6 111 19.2 116 28.5 96 38.7 147 3.53 57 7.25 41 4.27 35
DeepFlow2 [106]69.8 15.0 63 43.6 75 11.0 76 10.1 48 34.2 56 9.29 49 12.9 81 36.8 82 11.1 84 7.47 86 32.1 81 4.75 87 17.8 54 25.4 60 9.97 34 10.7 25 40.2 69 10.3 29 6.78 52 18.7 16 13.3 104 9.05 122 17.3 116 15.3 126
SegFlow [156]70.2 17.6 83 50.4 98 10.9 72 11.9 76 39.1 96 11.7 82 13.7 86 39.9 98 13.3 95 7.50 89 35.7 104 4.56 83 19.7 78 27.4 89 13.0 75 9.37 13 37.2 49 9.48 18 5.08 31 19.8 26 5.25 56 4.01 64 11.9 72 5.55 51
DMF_ROB [135]70.7 16.8 79 47.5 87 11.2 80 10.6 55 34.1 55 9.86 53 14.7 93 41.2 102 11.9 88 7.41 85 33.9 92 4.25 74 18.8 63 25.9 70 12.7 68 11.9 38 41.3 80 11.7 53 4.39 15 18.8 17 5.30 58 6.00 97 14.9 98 8.11 97
S2F-IF [121]71.0 18.0 89 51.9 108 10.9 72 11.1 66 38.6 92 10.6 63 13.9 88 40.6 100 13.4 97 7.68 95 32.6 83 5.18 94 19.7 78 27.2 86 13.3 79 10.8 27 39.5 64 11.9 59 4.99 28 19.9 28 6.26 66 3.26 52 10.1 62 3.57 27
PGM-C [118]71.1 17.7 84 50.5 99 11.0 76 11.9 76 39.1 96 11.6 80 13.9 88 40.4 99 13.3 95 7.52 90 35.8 106 4.62 86 19.6 76 27.5 90 12.4 59 9.48 16 37.9 53 9.36 16 4.63 19 16.9 7 5.02 52 4.83 76 14.2 94 6.69 74
Steered-L1 [116]71.4 11.4 43 37.9 58 7.71 40 4.42 1 21.7 2 3.76 1 7.71 30 25.7 43 4.29 19 4.91 39 29.8 70 2.26 24 20.2 88 26.7 79 16.6 102 18.1 101 46.1 105 14.6 84 32.4 147 37.9 131 51.5 158 8.58 119 15.5 104 15.2 125
Sparse Occlusion [54]72.0 12.7 52 35.8 53 8.24 47 12.4 85 33.4 51 13.4 101 9.67 56 29.1 58 6.55 44 5.99 63 28.5 64 3.56 62 19.4 69 26.4 77 12.4 59 14.7 73 39.4 63 11.7 53 37.7 155 48.6 154 17.8 119 3.66 59 9.43 58 5.64 54
CPM-Flow [114]72.2 17.7 84 50.5 99 11.0 76 11.9 76 39.0 95 11.7 82 13.7 86 39.8 96 13.2 93 7.49 88 35.5 101 4.58 85 19.5 73 27.2 86 12.3 58 9.44 15 37.3 50 9.46 17 5.05 30 19.5 24 5.17 54 5.21 81 14.8 96 7.36 88
Classic++ [32]72.4 10.8 32 32.7 39 8.25 49 10.5 53 32.9 46 10.7 67 10.8 65 31.6 67 8.46 70 5.25 44 29.7 69 2.99 43 20.0 84 28.0 98 13.9 88 15.2 81 44.1 91 11.9 59 17.3 111 26.2 90 18.3 123 5.82 93 12.7 78 8.14 98
FlowFields+ [128]72.5 18.4 91 52.2 112 11.4 84 11.9 76 39.9 105 11.5 77 14.9 97 43.4 109 14.4 101 7.97 98 33.1 87 5.58 99 19.4 69 26.9 84 12.7 68 10.2 21 39.9 67 10.5 34 4.74 24 20.1 31 4.29 45 3.80 60 12.4 77 3.48 25
MCPFlow_RVC [197]73.1 36.5 128 52.9 115 17.9 105 27.7 129 50.9 133 28.4 125 31.7 132 57.9 128 38.4 132 5.84 60 21.5 18 3.17 48 19.3 68 26.7 79 9.11 21 13.1 46 30.1 16 12.9 72 3.64 10 21.2 44 1.06 13 3.29 53 7.79 50 3.64 29
EpicFlow [100]73.8 17.7 84 50.6 101 10.9 72 12.0 81 39.3 100 11.7 82 14.5 92 42.2 104 13.2 93 7.47 86 35.5 101 4.57 84 19.8 81 27.6 91 12.8 73 9.73 18 38.1 57 10.1 28 4.63 19 17.2 9 4.88 48 5.31 82 14.3 95 7.47 89
VCN_RVC [178]74.1 24.5 114 58.3 120 19.8 110 13.8 103 38.2 87 14.0 106 13.4 84 39.2 89 10.1 77 7.66 94 35.8 106 4.85 90 18.7 61 24.6 56 12.6 64 13.6 56 41.1 79 13.2 77 3.76 12 21.4 48 1.03 11 2.97 44 8.89 56 4.24 34
NL-TV-NCC [25]74.5 16.5 75 40.4 63 9.10 63 10.7 56 37.0 68 8.07 40 8.59 45 26.8 49 3.17 9 6.24 70 33.4 88 3.26 50 21.4 102 29.7 119 12.7 68 21.2 116 48.2 110 17.3 104 13.4 96 35.6 121 13.0 101 4.73 74 12.8 79 3.24 23
ACK-Prior [27]75.0 19.5 103 41.5 69 14.3 99 6.57 13 27.6 17 4.53 6 7.87 34 25.7 43 3.70 13 4.33 21 25.7 35 1.53 10 20.5 94 25.6 66 18.3 109 23.1 131 44.0 90 18.5 110 29.9 143 33.1 112 45.6 156 7.91 115 14.8 96 11.7 115
BriefMatch [122]75.1 11.8 47 35.7 52 6.41 25 7.52 24 30.3 28 5.97 21 7.54 27 24.2 34 4.62 26 4.28 19 25.4 33 1.98 17 20.6 96 26.2 75 20.9 121 26.8 142 49.2 112 28.2 144 22.8 128 35.9 122 39.6 151 9.81 125 15.1 100 18.3 133
CombBMOF [111]75.5 15.2 65 48.2 90 7.67 38 11.3 70 34.5 57 9.95 54 8.75 48 27.2 52 5.37 35 7.60 93 32.1 81 5.65 102 18.0 56 23.0 45 13.9 88 21.7 121 44.9 95 24.3 135 22.6 125 37.2 126 14.5 108 2.97 44 7.73 49 4.35 36
FlowFields [108]75.7 18.3 90 51.9 108 11.1 79 11.9 76 39.5 102 11.5 77 14.8 94 43.3 108 14.2 99 7.96 97 33.5 91 5.52 98 19.9 82 27.6 91 13.6 82 11.0 31 40.5 71 12.1 63 4.93 27 19.7 25 5.34 59 3.85 61 12.3 75 3.89 31
Complementary OF [21]77.2 20.9 106 51.7 106 21.5 116 6.41 11 28.3 21 4.86 10 9.56 55 30.2 63 5.62 37 8.21 100 31.4 77 6.20 105 19.2 66 25.6 66 15.5 95 21.5 119 49.3 113 17.4 105 6.34 46 19.8 26 11.5 90 6.44 105 16.1 109 10.2 107
ROF-ND [105]78.2 18.4 91 45.8 83 11.5 85 7.31 22 25.4 9 6.02 24 9.70 57 29.4 61 4.66 28 9.09 107 28.7 65 5.98 104 21.6 104 29.5 116 14.5 91 19.9 109 44.8 93 15.3 90 33.3 151 41.0 137 30.1 141 2.95 41 7.63 48 2.41 19
TF+OM [98]78.3 14.8 61 35.4 50 7.68 39 9.06 40 28.4 23 9.32 50 11.6 71 28.4 56 16.0 107 6.43 71 29.0 67 4.29 75 20.2 88 25.6 66 18.4 110 17.9 99 38.5 59 16.9 102 16.6 107 33.8 114 14.7 109 6.87 108 15.5 104 9.68 104
DeepFlow [85]80.2 17.5 82 46.9 85 16.5 104 11.8 74 35.8 61 11.2 75 15.1 98 39.6 94 15.2 105 7.81 96 32.6 83 5.12 93 17.8 54 25.5 63 9.86 32 12.0 39 44.9 95 11.4 47 6.11 45 18.0 12 12.8 99 10.8 130 18.7 125 18.8 135
GMFlow_RVC [196]80.2 46.3 141 57.0 118 42.4 139 15.4 110 33.8 52 17.3 110 16.6 108 32.3 69 12.8 92 8.66 104 22.6 19 5.32 95 19.4 69 24.7 57 13.1 78 21.1 115 38.7 61 19.0 114 17.1 109 41.9 140 1.75 18 0.93 3 3.40 3 0.05 2
ComplOF-FED-GPU [35]80.4 17.9 87 52.0 110 15.4 102 7.90 27 33.9 54 5.82 18 10.8 65 34.2 74 5.67 38 6.99 78 31.5 78 4.51 80 19.2 66 26.3 76 12.9 74 18.2 102 50.5 121 18.6 111 15.1 103 23.6 71 22.3 133 5.37 84 15.4 102 6.76 75
TCOF [69]80.4 17.2 81 45.4 82 15.3 101 12.6 91 37.6 76 12.3 88 15.7 100 39.5 92 16.6 109 6.72 74 27.7 55 4.48 79 22.5 114 30.9 132 11.9 53 9.21 12 28.4 9 10.8 39 22.9 129 35.0 120 9.29 80 4.22 69 11.3 69 6.79 76
CVENG22+RIC [199]81.1 16.7 78 49.7 94 10.8 70 12.4 85 41.2 113 11.6 80 14.8 94 43.2 107 12.2 89 7.23 82 35.7 104 4.53 81 22.0 110 29.9 121 16.1 100 11.0 31 40.5 71 12.1 63 4.63 19 17.2 9 4.90 50 5.84 94 16.8 114 7.32 87
TV-L1-improved [17]81.2 11.9 48 36.8 57 8.23 46 8.49 36 31.0 35 7.83 39 11.9 74 33.7 71 7.19 51 5.35 47 28.9 66 2.91 39 20.3 92 28.0 98 12.0 55 27.2 144 55.4 135 30.4 146 23.1 131 38.0 132 22.9 134 5.61 89 14.0 90 7.74 93
EPPM w/o HM [86]81.8 19.4 100 53.2 116 11.2 80 8.23 32 34.8 58 6.07 25 11.1 68 35.1 79 5.89 40 7.31 83 33.4 88 4.76 88 18.9 65 23.2 49 17.1 104 21.3 117 50.3 120 20.1 119 20.7 121 30.3 103 40.9 154 3.20 50 8.13 51 5.59 52
HBM-GC [103]81.9 31.9 120 41.2 68 25.6 123 13.2 97 32.9 46 14.2 107 9.93 60 24.4 39 8.75 71 10.1 115 24.7 27 6.95 113 16.6 43 21.1 21 13.6 82 18.5 103 33.7 32 15.5 93 33.9 153 47.5 153 20.1 130 3.38 54 8.62 55 5.97 60
Rannacher [23]85.1 15.5 69 43.5 74 10.7 68 11.4 71 35.8 61 11.5 77 14.2 91 39.0 88 10.8 81 6.59 73 30.8 76 4.20 73 21.0 98 29.6 118 12.6 64 19.1 106 50.8 122 15.2 88 14.7 100 26.8 91 16.7 114 4.86 77 12.9 80 7.03 82
Aniso. Huber-L1 [22]85.2 13.6 57 40.4 63 9.77 64 19.4 114 40.1 107 22.0 116 16.4 104 38.4 84 18.3 112 7.56 91 33.4 88 5.00 92 20.1 87 27.7 96 12.5 62 14.5 71 39.7 66 10.4 32 20.8 122 32.0 108 12.9 100 4.35 70 10.8 66 6.56 72
SIOF [67]85.8 16.5 75 40.1 62 10.8 70 10.3 51 37.1 69 9.10 48 16.4 104 38.3 83 18.4 113 8.56 101 35.1 99 5.87 103 21.3 101 28.5 105 16.5 101 17.6 97 43.6 89 19.7 117 7.08 56 21.6 53 3.65 35 6.65 106 16.1 109 10.9 111
FF++_ROB [141]85.9 19.0 98 52.4 114 12.2 91 12.4 85 40.0 106 11.9 85 16.2 102 45.2 112 16.3 108 9.16 109 35.6 103 7.36 115 20.2 88 28.0 98 13.8 86 13.3 51 40.5 71 12.8 71 5.68 38 19.2 21 8.50 76 4.50 72 11.8 71 7.66 91
F-TV-L1 [15]86.1 31.8 119 60.6 123 43.6 143 13.7 101 38.4 90 13.1 98 15.6 99 39.4 91 10.1 77 10.9 118 37.3 113 8.78 119 20.0 84 26.5 78 16.0 99 12.9 44 40.7 74 10.7 38 9.68 74 23.7 74 3.52 33 4.49 71 12.0 73 4.19 33
Brox et al. [5]89.2 18.5 94 51.2 103 20.8 115 14.0 106 37.8 78 15.1 109 13.6 85 38.8 86 11.7 86 7.20 81 36.8 110 4.02 68 23.0 118 28.5 105 24.3 134 10.8 27 45.3 101 9.57 19 7.81 64 22.7 61 1.58 16 9.61 124 19.2 128 15.0 124
SRR-TVOF-NL [89]89.3 22.3 112 44.7 78 12.5 92 12.0 81 38.1 84 10.2 57 14.8 94 40.6 100 10.9 83 6.13 69 34.1 94 2.81 37 19.6 76 25.5 63 13.5 80 16.4 89 42.4 83 13.0 74 30.5 144 42.5 143 18.3 123 6.41 104 11.0 67 12.0 117
LocallyOriented [52]89.6 15.8 72 41.5 69 10.9 72 15.0 108 44.5 120 13.7 103 17.6 109 43.4 109 14.2 99 7.16 80 31.5 78 4.82 89 21.0 98 29.0 111 12.5 62 11.7 35 34.5 36 12.9 72 11.6 84 29.6 100 12.0 93 7.94 116 18.4 122 11.1 113
DPOF [18]90.1 20.5 105 50.2 97 10.5 65 12.6 91 41.8 115 11.0 73 11.8 73 34.3 75 10.8 81 8.61 103 38.9 121 5.43 96 19.5 73 26.1 72 15.1 92 16.8 94 41.5 81 15.2 88 23.3 132 23.9 77 50.1 157 5.05 78 14.1 91 4.13 32
CRTflow [81]91.2 16.5 75 49.5 93 10.6 67 9.63 46 33.8 52 8.65 45 13.1 82 38.8 86 7.80 64 6.86 76 34.3 96 4.44 78 20.0 84 27.8 97 12.2 56 31.4 150 59.0 146 36.7 150 10.3 76 30.4 104 12.0 93 8.56 118 20.4 134 12.9 122
Bartels [41]93.2 19.3 99 39.6 60 22.4 119 9.47 44 28.2 20 10.0 56 9.91 59 29.7 62 7.09 49 9.18 110 29.3 68 7.40 116 21.7 105 27.6 91 21.1 123 19.1 106 44.4 92 24.2 134 23.0 130 36.3 123 36.2 145 7.46 114 14.9 98 11.5 114
Dynamic MRF [7]94.2 22.0 110 52.3 113 25.2 121 7.67 25 33.0 48 6.18 29 12.4 79 39.8 96 5.34 34 6.49 72 35.4 100 3.86 66 22.9 116 29.2 114 20.7 120 22.2 125 57.8 143 22.9 129 7.42 59 18.1 13 25.1 135 13.2 137 21.3 139 20.5 139
CBF [12]96.3 15.2 65 44.8 79 12.1 89 23.7 121 37.7 77 30.9 128 13.2 83 34.6 77 14.5 103 6.86 76 32.8 85 4.32 76 22.6 115 28.4 104 20.2 118 15.6 83 41.0 78 12.1 63 32.9 149 39.7 135 29.8 140 5.49 86 13.2 82 8.30 99
Local-TV-L1 [65]97.1 24.6 115 51.2 103 30.0 125 22.5 120 40.6 110 25.2 119 23.5 120 46.1 114 28.3 123 9.73 113 37.4 114 6.92 112 18.3 58 25.2 59 12.7 68 13.9 62 43.2 87 12.0 62 5.25 32 20.6 35 5.15 53 15.8 142 21.0 137 32.1 147
DF-Auto [113]97.1 19.4 100 46.0 84 10.5 65 26.6 127 46.1 124 31.1 129 23.7 121 46.1 114 37.0 128 9.05 106 36.8 110 5.59 100 21.7 105 29.1 113 17.4 106 7.80 6 31.8 20 7.93 8 19.5 118 37.4 128 3.25 29 10.9 131 19.6 130 16.4 128
TriangleFlow [30]97.9 18.7 96 43.9 76 18.0 106 10.1 48 37.2 71 8.18 41 11.9 74 35.5 80 5.81 39 6.72 74 34.6 98 4.37 77 26.7 143 34.7 146 23.4 129 23.1 131 49.6 114 23.5 130 16.7 108 37.2 126 16.3 112 6.85 107 17.3 116 10.3 108
LDOF [28]98.7 17.1 80 48.0 89 12.9 93 13.3 98 40.6 110 12.2 87 15.8 101 42.4 105 12.7 91 9.70 112 44.0 130 6.27 107 20.7 97 28.0 98 16.8 103 14.3 68 45.9 104 13.8 80 8.36 68 23.3 68 7.98 75 11.2 134 21.2 138 18.3 133
CNN-flow-warp+ref [115]100.0 18.5 94 50.0 95 13.9 98 17.8 112 37.9 80 21.1 114 21.3 117 47.3 118 29.7 124 9.13 108 38.8 118 6.72 110 21.8 108 28.2 102 19.6 114 14.2 67 45.7 103 13.1 75 5.94 43 18.5 14 10.9 87 12.4 136 20.6 136 16.4 128
CLG-TV [48]100.5 15.7 71 42.2 73 11.7 87 20.9 115 39.2 99 24.8 118 16.4 104 39.5 92 18.0 111 9.23 111 37.9 115 6.54 108 22.9 116 30.0 124 17.9 108 16.5 90 47.2 109 14.2 83 19.9 119 30.4 104 11.5 90 5.79 92 14.1 91 6.98 81
TriFlow [93]100.5 21.3 108 44.9 80 13.5 97 16.0 111 36.5 64 18.7 112 18.2 111 38.6 85 27.8 120 7.35 84 30.3 72 5.59 100 21.2 100 27.3 88 18.5 111 15.1 79 37.1 48 15.0 87 49.5 160 41.7 139 95.6 163 6.38 103 13.3 84 9.77 105
p-harmonic [29]101.4 21.2 107 63.8 131 20.6 114 12.4 85 35.9 63 12.7 95 17.7 110 47.5 119 14.9 104 10.9 118 42.1 126 8.85 120 20.4 93 26.1 72 17.1 104 17.9 99 52.5 126 18.4 108 15.6 105 28.6 97 5.86 63 5.89 96 13.5 86 7.67 92
OFRF [132]102.0 20.1 104 40.7 66 18.8 108 25.4 125 43.7 117 27.8 124 20.4 115 39.7 95 25.4 116 12.5 121 34.3 96 11.1 126 17.0 46 23.7 51 8.99 19 17.6 97 40.0 68 16.7 99 15.0 102 28.4 95 28.3 137 16.1 143 19.4 129 34.6 148
FlowNetS+ft+v [110]102.2 15.2 65 44.9 80 10.7 68 13.4 99 38.2 87 13.4 101 18.8 113 42.8 106 24.4 115 9.01 105 38.8 118 6.24 106 23.2 121 31.5 137 15.9 97 13.3 51 42.6 84 13.1 75 18.2 114 32.6 111 21.9 132 8.73 120 19.1 127 12.8 121
Second-order prior [8]104.8 15.6 70 48.2 90 12.1 89 12.6 91 39.1 96 12.3 88 16.2 102 44.6 111 12.2 89 7.57 92 31.6 80 5.45 97 22.2 111 30.6 126 14.3 90 20.8 114 56.8 139 17.7 107 28.0 141 33.8 114 27.1 136 7.43 113 17.4 118 10.4 110
ContinualFlow_ROB [148]107.8 38.4 129 64.1 133 31.4 127 31.9 134 52.5 138 35.2 135 32.8 133 61.5 135 38.0 131 15.4 126 42.4 127 9.42 123 27.2 147 32.9 145 23.6 131 30.9 147 52.8 129 37.9 151 3.27 7 17.7 11 1.31 15 3.48 56 10.0 61 1.76 15
Fusion [6]109.2 17.9 87 57.7 119 18.6 107 9.42 43 32.3 44 10.2 57 11.4 70 34.8 78 11.7 86 8.57 102 40.2 122 6.89 111 25.0 133 30.8 131 24.9 140 23.9 134 52.3 125 25.0 138 33.3 151 43.4 145 19.3 128 9.01 121 18.8 126 13.4 123
C-RAFT_RVC [181]109.4 46.7 142 69.9 142 38.2 133 33.2 137 55.6 143 34.0 133 33.8 136 63.4 138 37.9 129 14.2 125 34.0 93 9.21 121 26.2 139 32.8 144 21.9 126 20.0 110 46.5 106 21.2 125 10.3 76 31.1 107 3.57 34 2.70 32 7.59 46 1.02 9
Learning Flow [11]109.7 16.4 74 47.3 86 11.5 85 14.0 106 40.3 108 14.4 108 16.4 104 41.7 103 15.6 106 8.05 99 40.7 124 4.87 91 27.1 145 35.0 148 22.5 127 17.2 96 50.0 119 16.0 95 15.5 104 34.1 117 13.9 107 10.1 127 20.2 133 12.5 120
LiteFlowNet [138]109.8 32.9 122 71.7 147 19.9 111 18.2 113 45.2 122 17.8 111 21.8 118 55.4 125 17.5 110 10.7 117 34.2 95 7.20 114 24.3 129 30.7 129 20.9 121 21.5 119 52.5 126 18.4 108 11.3 81 33.3 113 3.15 26 6.04 98 13.5 86 7.98 95
StereoFlow [44]109.9 85.4 163 89.0 163 87.9 162 73.1 163 88.5 163 68.8 158 66.8 162 87.5 161 52.4 154 81.5 162 91.1 162 78.5 161 25.9 138 27.6 91 29.7 149 6.38 4 29.4 13 6.60 5 1.39 2 10.9 2 0.20 2 6.34 102 13.8 88 10.3 108
SegOF [10]113.1 28.8 118 51.1 102 13.2 95 37.3 141 51.8 136 44.6 144 30.0 129 53.0 123 43.3 141 27.0 143 49.6 137 22.4 139 24.0 128 27.6 91 28.4 147 24.9 138 58.5 144 24.4 136 2.04 4 16.2 6 0.47 5 10.0 126 16.5 111 16.7 130
EAI-Flow [147]114.2 40.7 131 62.9 128 39.5 134 21.2 117 43.8 118 21.4 115 25.8 122 57.4 126 28.2 121 11.7 120 38.0 116 9.37 122 21.9 109 29.0 111 15.1 92 22.2 125 50.8 122 20.5 120 29.0 142 36.6 125 10.6 86 5.07 79 13.3 84 6.83 77
Shiralkar [42]115.6 22.0 110 69.5 140 19.6 109 10.9 60 42.6 116 8.48 44 18.4 112 54.0 124 9.43 76 10.1 115 45.4 131 7.72 117 21.5 103 28.9 110 15.9 97 26.8 142 60.7 147 25.4 140 24.3 136 29.9 102 39.4 149 11.0 132 23.8 144 12.2 118
Ad-TV-NDC [36]116.2 44.8 140 63.0 129 69.1 154 40.3 145 48.4 129 48.3 147 34.8 138 58.5 129 39.9 134 26.5 142 47.8 135 27.7 143 20.2 88 28.5 105 11.9 53 15.2 81 40.9 77 14.7 85 8.46 69 21.0 40 5.69 62 23.9 153 28.3 153 41.9 159
AugFNG_ROB [139]116.6 44.1 138 62.1 126 25.2 121 42.2 147 56.7 144 50.8 149 37.7 142 66.7 141 42.9 139 19.0 132 41.2 125 13.4 128 26.5 141 32.3 141 23.4 129 22.6 128 57.7 142 21.1 123 6.07 44 27.3 92 0.91 8 5.54 88 15.1 100 3.80 30
StereoOF-V1MT [117]116.7 21.7 109 68.0 138 20.3 113 11.8 74 50.4 132 7.18 34 20.7 116 62.8 136 9.21 74 9.80 114 50.8 138 6.56 109 27.9 149 35.8 150 23.9 132 25.0 139 67.3 151 24.0 132 8.00 65 27.7 93 12.2 95 13.4 138 23.5 143 15.8 127
CompactFlow_ROB [155]117.0 53.0 151 62.6 127 27.7 124 31.6 133 53.2 140 35.5 136 39.0 144 69.8 146 49.1 149 16.7 127 40.3 123 12.3 127 26.3 140 32.1 139 23.1 128 22.1 124 53.3 131 24.0 132 4.89 25 23.7 74 0.94 10 6.25 101 15.9 107 6.48 70
WOLF_ROB [144]117.2 26.7 117 70.6 143 21.9 117 21.8 119 51.3 135 19.4 113 28.0 126 61.1 134 26.7 119 12.6 122 42.5 128 10.5 125 22.2 111 28.7 109 19.4 113 21.3 117 55.6 136 19.6 116 7.42 59 23.5 69 8.87 79 11.1 133 20.5 135 20.0 138
FlowNet2 [120]121.0 47.2 144 61.0 124 42.4 139 44.5 149 57.5 145 51.3 150 37.6 141 64.7 139 43.1 140 21.0 135 35.8 106 17.9 135 25.8 134 30.6 126 24.6 136 20.4 111 49.7 117 21.0 121 32.5 148 53.3 159 4.06 43 4.13 66 13.0 81 1.49 14
LSM_FLOW_RVC [182]121.5 52.5 150 83.5 158 49.8 145 28.0 130 54.9 142 28.5 126 38.4 143 77.4 155 34.8 127 16.8 129 53.2 141 13.4 128 25.8 134 32.7 143 19.9 117 21.7 121 57.2 140 23.7 131 5.76 39 24.9 83 2.24 21 7.05 109 18.1 120 7.10 84
HBpMotionGpu [43]122.3 32.0 121 50.0 95 22.9 120 36.1 140 47.0 126 43.9 142 29.2 128 51.9 122 38.6 133 13.0 123 37.1 112 10.2 124 23.5 123 29.5 116 24.2 133 18.9 105 44.9 95 15.9 94 33.2 150 41.2 138 12.6 98 11.8 135 18.5 123 22.7 140
IAOF2 [51]123.4 25.3 116 49.2 92 22.2 118 24.6 122 44.3 119 28.6 127 20.0 114 45.4 113 25.5 117 49.8 152 57.5 147 60.5 155 23.2 121 31.0 133 15.7 96 23.2 133 49.6 114 19.3 115 30.5 144 39.0 134 19.0 126 9.25 123 18.6 124 9.82 106
Modified CLG [34]124.5 34.8 126 61.1 125 35.3 130 33.3 138 46.5 125 41.7 141 36.8 140 63.0 137 45.1 145 22.1 137 55.4 143 18.7 137 23.9 126 31.2 134 21.7 125 15.8 86 51.5 124 14.8 86 9.01 72 24.6 81 11.1 89 17.6 147 25.7 149 29.6 145
LFNet_ROB [145]125.5 42.0 133 80.9 156 30.7 126 25.2 124 54.8 141 25.3 120 33.7 135 74.4 149 26.0 118 17.2 130 48.0 136 14.4 131 26.5 141 32.5 142 24.8 139 23.0 130 56.4 137 22.7 127 12.5 90 38.3 133 6.87 68 6.05 99 15.7 106 9.05 102
Filter Flow [19]125.8 33.3 123 51.7 106 20.1 112 25.0 123 47.2 128 27.7 123 27.7 125 50.0 120 37.9 129 31.7 145 54.1 142 29.9 144 25.8 134 31.2 134 28.3 146 26.4 141 52.9 130 24.7 137 42.3 157 61.5 161 13.6 106 6.09 100 12.1 74 6.88 79
2D-CLG [1]126.0 44.0 137 63.3 130 36.1 131 44.3 148 52.3 137 55.1 152 49.1 153 75.4 150 50.5 151 64.3 158 76.4 157 67.8 158 24.8 131 29.7 119 27.4 144 20.5 113 53.6 132 22.4 126 2.52 6 13.0 4 3.50 32 22.8 152 27.9 152 36.9 151
EPMNet [131]126.8 47.1 143 71.6 146 41.3 137 41.8 146 61.0 150 47.5 146 34.2 137 60.0 132 40.1 135 22.9 140 38.8 118 20.2 138 25.8 134 30.6 126 24.6 136 20.4 111 49.7 117 21.0 121 23.9 135 44.7 148 3.33 30 7.39 112 18.0 119 7.28 86
ResPWCR_ROB [140]126.8 47.7 145 78.6 150 41.4 138 20.9 115 45.6 123 22.0 116 26.3 124 59.1 131 28.2 121 16.7 127 47.4 133 13.7 130 23.7 124 28.3 103 27.2 143 25.0 139 57.6 141 25.4 140 22.7 127 42.0 141 10.0 82 8.31 117 16.9 115 12.2 118
TVL1_RVC [175]126.8 66.5 157 79.2 153 85.9 159 52.8 155 52.7 139 65.9 156 51.6 154 78.1 156 53.5 157 55.5 156 75.9 156 58.3 154 23.0 118 31.4 136 17.6 107 14.5 71 49.6 114 17.1 103 4.61 18 20.7 36 2.07 20 26.8 157 31.4 154 40.9 158
BlockOverlap [61]126.9 41.4 132 54.1 117 36.2 132 27.3 128 41.4 114 32.6 131 26.2 123 46.5 116 31.8 125 20.0 133 36.6 109 18.1 136 22.4 113 26.8 82 25.7 141 24.5 135 45.6 102 21.1 123 39.3 156 47.0 152 43.5 155 13.8 139 16.0 108 28.7 144
SPSA-learn [13]127.3 35.8 127 71.2 144 43.1 142 28.4 131 47.0 126 32.8 132 31.4 131 57.7 127 42.2 138 22.2 138 51.0 139 22.9 141 23.9 126 29.4 115 24.6 136 24.8 137 56.5 138 25.1 139 10.7 80 25.1 84 3.72 37 21.7 150 24.9 148 35.5 150
IRR-PWC_RVC [180]127.4 50.0 149 66.8 136 32.5 129 39.5 143 57.5 145 44.5 143 42.2 147 69.5 145 50.4 150 21.9 136 43.8 129 17.4 133 27.1 145 30.7 129 29.0 148 18.7 104 49.0 111 17.4 105 23.6 133 53.1 158 2.93 25 7.06 110 16.5 111 7.87 94
IAOF [50]128.4 33.8 124 58.3 120 40.6 135 33.0 136 44.5 120 39.5 139 30.6 130 58.7 130 33.8 126 34.1 148 52.4 140 40.8 148 23.1 120 29.9 121 19.7 116 22.5 127 53.7 133 16.8 101 22.3 124 34.0 116 10.0 82 19.5 148 23.9 145 37.1 153
GraphCuts [14]129.4 34.5 125 59.0 122 32.1 128 26.2 126 51.1 134 26.4 122 28.1 127 51.7 121 40.4 137 13.0 123 47.5 134 7.98 118 23.7 124 30.0 124 24.3 134 33.4 151 45.2 100 25.7 142 31.2 146 37.7 130 36.8 146 10.7 129 19.7 131 17.7 132
Black & Anandan [4]131.3 38.5 130 69.5 140 53.4 146 28.5 132 49.6 131 32.0 130 33.4 134 60.5 133 40.2 136 22.6 139 55.9 144 22.8 140 24.5 130 32.2 140 19.6 114 21.7 121 58.9 145 22.7 127 22.6 125 37.6 129 5.27 57 16.7 145 22.6 142 25.4 142
GroupFlow [9]132.2 42.7 134 67.1 137 53.4 146 44.8 150 63.8 155 50.2 148 36.7 139 69.4 144 43.9 142 17.2 130 46.0 132 16.7 132 27.8 148 34.9 147 21.2 124 36.7 154 67.0 150 43.6 155 6.40 47 21.7 55 7.17 70 16.6 144 25.9 150 25.0 141
2bit-BM-tele [96]133.7 55.1 152 64.1 133 69.1 154 21.4 118 38.7 93 25.3 120 23.3 119 46.7 117 21.2 114 26.2 141 38.7 117 25.2 142 24.9 132 29.9 121 27.7 145 31.3 149 52.6 128 34.6 148 43.3 158 51.7 157 54.5 159 10.3 128 20.1 132 16.8 131
Nguyen [33]137.2 43.9 136 66.0 135 42.8 141 54.0 156 49.4 130 70.1 159 42.9 148 67.4 142 47.3 147 55.4 155 65.7 151 64.4 156 27.0 144 31.8 138 31.0 150 22.8 129 54.8 134 27.3 143 13.1 93 25.2 85 6.08 64 22.2 151 26.9 151 38.9 155
SILK [80]140.4 49.5 148 69.2 139 69.3 156 39.9 144 60.6 149 47.0 145 40.4 146 70.7 147 45.6 146 32.0 146 56.5 145 31.2 146 31.4 151 36.9 153 33.3 152 31.1 148 63.2 148 32.3 147 10.3 76 23.0 62 17.3 115 25.0 154 31.9 155 36.9 151
UnFlow [127]141.5 70.9 159 78.9 151 58.5 150 51.3 154 67.4 158 56.9 153 54.4 156 83.6 159 52.8 155 33.4 147 60.2 148 30.1 145 36.7 159 38.4 156 46.2 160 38.2 155 69.6 154 42.8 154 26.2 137 40.3 136 1.60 17 7.20 111 18.3 121 8.75 101
Periodicity [79]142.7 48.9 147 63.9 132 41.0 136 34.5 139 60.0 148 37.5 138 55.4 157 67.4 142 56.6 158 20.4 134 56.9 146 17.5 134 53.2 162 66.7 163 46.5 161 48.3 160 76.0 161 46.4 157 9.14 73 34.4 118 9.98 81 28.3 158 48.2 162 40.6 157
Horn & Schunck [3]143.3 43.3 135 80.7 155 58.6 151 32.5 135 59.7 147 35.1 134 40.2 145 76.3 153 44.7 144 31.5 144 64.8 149 32.6 147 29.3 150 36.4 152 27.0 142 27.5 145 68.7 152 29.7 145 27.0 139 43.3 144 7.32 71 25.9 155 36.5 158 34.6 148
H+S_RVC [176]145.7 57.6 153 76.9 148 55.7 149 56.7 157 76.2 161 62.8 155 60.6 159 89.2 163 51.5 153 78.6 161 78.7 158 82.0 162 34.1 155 35.7 149 43.6 159 46.6 159 75.5 160 53.1 160 5.52 35 32.5 110 5.42 60 34.3 159 35.1 157 37.9 154
Heeger++ [102]146.9 61.9 156 80.2 154 47.4 144 44.8 150 77.8 162 40.9 140 68.0 163 84.7 160 62.1 161 43.6 151 69.1 152 41.9 149 32.6 153 37.9 154 32.0 151 51.1 161 78.4 162 54.2 161 13.3 95 43.4 145 10.4 85 15.0 140 21.4 140 19.6 136
SLK [47]147.6 44.7 139 78.9 151 59.1 152 58.2 159 71.2 159 70.9 160 47.5 151 83.5 158 50.6 152 65.0 159 69.5 153 73.4 159 34.7 156 38.9 158 42.9 158 34.8 152 70.9 157 39.4 152 12.1 87 29.8 101 11.5 90 34.4 160 40.1 159 48.8 160
FFV1MT [104]149.9 59.9 155 77.8 149 53.6 148 37.7 142 72.5 160 37.0 137 63.6 161 82.1 157 62.4 162 42.8 150 73.9 155 42.6 150 41.9 161 45.8 161 52.3 162 52.5 162 81.8 163 56.1 162 20.2 120 42.4 142 18.3 123 15.0 140 21.4 140 19.6 136
TI-DOFE [24]150.2 73.1 160 84.6 161 89.6 163 61.2 161 64.7 157 74.8 162 58.6 158 88.7 162 58.0 159 70.9 160 81.6 160 76.1 160 31.7 152 38.0 155 35.4 153 29.7 146 68.7 152 36.3 149 17.1 109 32.0 108 8.67 77 35.5 161 42.8 160 49.8 161
FOLKI [16]152.3 48.0 146 71.5 145 68.8 153 48.6 153 63.2 152 59.5 154 43.0 149 75.6 151 44.0 143 40.4 149 65.6 150 45.8 151 35.3 157 40.6 159 41.6 156 36.3 153 71.6 159 44.4 156 23.6 133 44.7 148 40.4 153 36.9 162 43.4 161 54.5 162
PGAM+LK [55]154.8 58.6 154 80.9 156 69.8 157 45.1 152 63.7 154 51.9 151 43.2 150 76.2 152 47.5 148 50.3 153 82.2 161 51.4 152 32.7 154 36.0 151 42.3 157 41.4 156 70.1 155 41.2 153 56.3 161 58.0 160 55.0 160 25.9 155 32.4 156 40.3 156
Adaptive flow [45]155.3 76.7 162 83.7 160 86.4 160 57.9 158 63.6 153 67.3 157 48.7 152 73.2 148 52.9 156 52.7 154 69.9 154 56.0 153 35.4 158 38.4 156 39.4 155 46.1 157 70.6 156 47.6 158 73.1 162 75.2 162 88.1 161 17.2 146 24.6 147 25.6 143
HCIC-L [97]157.4 76.5 161 86.4 162 73.3 158 70.1 162 62.5 151 85.3 163 63.5 160 66.1 140 79.5 163 83.3 163 91.8 163 86.5 163 39.0 160 42.8 160 38.7 154 46.4 158 66.6 149 52.3 159 89.6 163 85.9 163 94.0 162 19.8 149 24.2 146 29.6 145
Pyramid LK [2]159.2 68.1 158 83.5 158 86.8 161 59.4 160 64.5 156 73.1 161 52.8 155 76.3 153 61.4 160 60.2 157 79.0 159 65.9 157 53.8 163 61.8 162 64.5 163 59.4 163 71.1 158 63.0 163 43.9 159 49.4 156 39.5 150 50.2 163 60.2 163 70.8 163
AdaConv-v1 [124]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
SepConv-v1 [125]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
SuperSlomo [130]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
CtxSyn [134]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
CyclicGen [149]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
TOF-M [150]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
MPRN [151]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
DAIN [152]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
FRUCnet [153]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
OFRI [154]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
FGME [158]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
MS-PFT [159]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
MEMC-Net+ [160]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
ADC [161]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
DSepConv [162]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
MAF-net [163]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
STAR-Net [164]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
AdaCoF [165]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
TC-GAN [166]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
FeFlow [167]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
DAI [168]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
SoftSplat [169]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
STSR [170]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
BMBC [171]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
GDCN [172]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
EDSC [173]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
MV_VFI [183]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
DistillNet [184]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
SepConv++ [185]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
EAFI [186]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
FLAVR [188]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
SoftsplatAug [190]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
ProBoost-Net [191]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
IDIAL [192]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
IFRNet [193]164.6 100.0 165 99.9 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 165 100.0 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.8 165 100.0 165 99.7 165 97.0 165 99.9 165 99.9 164 99.9 164 99.9 164
AVG_FLOW_ROB [137]165.5 99.9 164 99.7 164 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.6 164 98.8 164 99.5 164 99.6 164 99.7 164 99.0 164 97.0 164 96.3 164 95.6 164 99.1 164 92.9 164 99.6 164 100.0 199 99.9 164 99.9 164
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

Methodtime*framescolor Reference and notes
[1] 2D-CLG 844 2 gray The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences.
[2] Pyramid LK 12 2 color A modification of Bouguet's pyramidal implementation of Lucas-Kanade.
[3] Horn & Schunck 49 2 gray A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data.
[4] Black & Anandan 328 2 gray A modern Matlab implementation of the Black & Anandan method by Deqing Sun.
[5] Brox et al. 18 2 color T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.)
[6] Fusion 2,666 2 color V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008.
[7] Dynamic MRF 366 2 gray B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.)
[8] Second-order prior 14 2 gray W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[9] GroupFlow 600 2 gray X. Ren. Local Grouping for Optical Flow. CVPR 2008.
[10] SegOF 60 2 color L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available.
[11] Learning Flow 825 2 gray D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008.
[12] CBF 69 2 color W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[13] SPSA-learn 200 2 color Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008.
[14] GraphCuts 1,200 2 color T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008.
[15] F-TV-L1 8 2 gray A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008.
[16] FOLKI 1.4 2 gray G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005.
[17] TV-L1-improved 2.9 2 gray A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision.
[18] DPOF 287 2 color C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.)
[19] Filter Flow 34,000 2 color S. Seitz and S. Baker. Filter flow. ICCV 2009.
[20] Adaptive 9.2 2 gray A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009.
[21] Complementary OF 44 2 color H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[22] Aniso. Huber-L1 2 2 gray M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision.
[23] Rannacher 0.12 2 gray J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009.
[24] TI-DOFE 260 2 gray C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009.
[25] NL-TV-NCC 20 2 color M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010.
[26] MDP-Flow 188 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010.
[27] ACK-Prior 5872 2 color K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010.
[28] LDOF 122 2 color T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011.
[29] p-harmonic 565 2 gray J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010.
[30] TriangleFlow 4200 2 gray B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010.
[31] Classic+NL 972 2 color D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code.
[32] Classic++ 486 2 gray A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010.
[33] Nguyen 33 2 gray D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011.
[34] Modified CLG 133 2 gray R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010.
[35] ComplOF-FED-GPU 0.97 2 color P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010.
[36] Ad-TV-NDC 35 2 gray M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010.
[37] Layers++ 18206 2 color D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010.
[38] OFH 620 3 color H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011.
[39] LSM 1615 2 color K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011.
[40] CostFilter 55 2 color C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011.
[41] Bartels 0.15 2 gray C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU.
[42] Shiralkar 600 2 gray M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242.
[43] HBpMotionGpu 1000 5 gray S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.)
[44] StereoFlow 7200 2 color G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772.
[45] Adaptive flow 121 2 gray Tarik Arici and Vural Aksakalli. Energy minimization based motion estimation using adaptive smoothness priors. VISAPP 2012.
[46] TC-Flow 2500 5 color S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011.
[47] SLK 300 2 gray T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011.
[48] CLG-TV 29 2 gray M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code.
[49] SimpleFlow 1.7 2 color M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012.
[50] IAOF 57 2 gray D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011.
[51] IAOF2 56 2 gray Duc Dung Nguyen and Jae Wook Jeon. Enhancing accuracy and sharpness of motion field with adaptive scheme and occlusion-aware filter. IET Image Processing 7.2 (2013): 144-153.
[52] LocallyOriented 9541 2 gray Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012.
[53] IROF-TV 261 2 color H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop.
[54] Sparse Occlusion 2312 2 color Alper Ayvaci, Michalis Raptis, and Stefano Soatto. Sparse occlusion detection with optical flow. IJCV 97(3):322-338, 2012.
[55] PGAM+LK 0.37 2 gray A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010.
[56] Sparse-NonSparse 713 2 color Zhuoyuan Chen, Jiang Wang, and Ying Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. CVPR 2012.
[57] nLayers 36150 4 color D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012.
[58] IROF++ 187 2 color H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013.
[59] COFM 600 3 color M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013.
[60] Efficient-NL 400 2 color P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012.
[61] BlockOverlap 2 2 gray Michael Santoro, Ghassan AlRegib, and Yucel Altunbasak. Motion estimation using block overlap minimization. MMSP 2012.
[62] Ramp 1200 2 color A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012.
[63] Occlusion-TV-L1 538 3 gray C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012.
[64] TV-L1-MCT 90 2 color M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012.
[65] Local-TV-L1 500 2 gray L. Raket. Local smoothness for global optical flow. ICIP 2012.
[66] ALD-Flow 61 2 color M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012.
[67] SIOF 234 2 color L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012.
[68] MDP-Flow2 342 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available.
[69] TCOF 1421 all gray J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013.
[70] LME 476 2 color W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013.
[71] NN-field 362 2 color L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[72] FESL 3310 2 color Weisheng Dong, Guangming Shi, Xiaocheng Hu, and Yi Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. IEEE TIP 23(10):4527-4538, 2014.
[73] PMF 35 2 color J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013.
[74] FC-2Layers-FF 2662 4 color D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013.
[75] NNF-Local 673 2 color Zhuoyuan Chen, Hailin Jin, Zhe Lin, Scott Cohen, and Ying Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[76] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[77] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[78] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[79] Periodicity 8000 4 color Georgii Khachaturov, Silvia Gonzalez-Brambila, and Jesus Gonzalez-Trejo. Periodicity-based computation of optical flow. Computacion y Sistemas (CyS) 2014.
[80] SILK 572 2 gray Pascal Zille, Thomas Corpetti, Liang Shao, and Xu Chen. Observation model based on scale interactions for optical flow estimation. IEEE TIP 23(8):3281-3293, 2014.
[81] CRTflow 13 3 color O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013.
[82] Classic+CPF 640 2 gray Zhigang Tu, Nico van der Aa, Coert Van Gemeren, and Remco Veltkamp. A combined post-filtering method to improve accuracy of variational optical flow estimation. Pattern Recognition 47(5):1926-1940, 2014.
[83] S2D-Matching 1200 2 color Marius Leordeanu, Andrei Zanfir, and Cristian Sminchisescu. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013.
[84] AGIF+OF 438 2 gray Zhigang Tu, Ronald Poppe, and Remco Veltkamp. Adaptive guided image filter for warping in variational optical flow computation. Signal Processing 127:253-265, 2016.
[85] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[86] EPPM w/o HM 2.5 2 color L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014.
[87] MLDP_OF 165 2 gray M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014.
[88] RFlow 20 2 gray S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014.
[89] SRR-TVOF-NL 32 all color P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014.
[90] 2DHMM-SAS 157 2 color M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission.
[91] WLIF-Flow 700 2 color Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014.
[92] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[93] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[94] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[95] AggregFlow 1642 2 color D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759.
[96] 2bit-BM-tele 124 2 gray R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013.
[97] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[98] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[99] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[100] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[101] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[102] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[103] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[104] FFV1MT 358 5 gray F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015.
[105] ROF-ND 4 2 color S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015.
[106] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[107] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[108] FlowFields 15 2 color C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015.
[109] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[110] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[111] CombBMOF 51 2 color M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.)
[112] PMMST 182 2 color F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015.
[113] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[114] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[115] CNN-flow-warp+ref 1.4 3 color D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016.
[116] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[117] StereoOF-V1MT 343 2 gray Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132.
[118] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[119] RNLOD-Flow 1040 2 gray C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. IEEE TIP 26(8):4055-4067, 2017.
[120] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[121] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[122] BriefMatch 0.068 2 gray G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62.
[123] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[124] AdaConv-v1 2.8 2 color Simon Niklaus, Long Mai, and Feng Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[125] SepConv-v1 0.2 2 color Simon Niklaus, Long Mai, and Feng Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[126] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[127] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[128] FlowFields+ 10.5 2 color C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017.
[129] IIOF-NLDP 150 2 color D.-H. Trinh, W. Blondel, and C. Daul. A general form of illumination-invariant descriptors in variational optical flow estimation. ICIP 2017.
[130] SuperSlomo 0.5 2 color Anonymous. (Interpolation results only.) Super SloMo: High quality estimation of multiple intermediate frames for video interpolation. CVPR 2018 submission 325.
[131] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[132] OFRF 90 2 color Tan Khoa Mai, Michele Gouiffes, and Samia Bouchafa. Optical flow refinement using iterative propagation under colour, proximity and flow reliability constraints. IET Image Processing 2020.
[133] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
[134] CtxSyn 0.07 2 color Simon Niklaus and Feng Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[135] DMF_ROB 10 2 color ROB 2018 baseline submission, based on: P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[136] JOF 657 2 gray C. Zhang, L. Ge, Z. Chen, M. Li, W. Liu, and H. Chen. Refined TV-L1 optical flow estimation using joint filtering. Submitted to IEEE TMM, 2018.
[137] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[138] LiteFlowNet 0.06 2 color T.-W. Hui, X. Tang, and C. C. Loy. LiteFlowNet: A lightweight convolutional neural network for optical flow estimation. CVPR 2018.
[139] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[140] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[141] FF++_ROB 17.43 2 color R. Schuster, C. Bailer, O. Wasenmueller, D. Stricker. FlowFields++: Accurate optical flow correspondences meet robust interpolation. ICIP 2018. Submitted to ROB 2018.
[142] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[143] PWC-Net_RVC 0.069 2 color D. Sun, X. Yang, M.-Y. Liu, and J. Kautz. PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. CVPR 2018. Also RVC 2020 baseline submission.
[144] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[145] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
[146] WRT 9 2 color L. Mei, J. Lai, X. Xie, J. Zhu, and J. Chen. Illumination-invariance optical flow estimation using weighted regularization transform. Submitted to IEEE TCSVT 2018.
[147] EAI-Flow 2.1 2 color Anonymous. Hierarchical coherency sensitive hashing and interpolation with RANSAC for large displacement optical flow. CVIU 2018 submission 17-678.
[148] ContinualFlow_ROB 0.5 all color Michal Neoral, Jan Sochman, and Jiri Matas. Continual occlusions and optical flow estimation. ACCV 2018.
[149] CyclicGen 0.088 2 color Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
[150] TOF-M 0.393 2 color Tianfan Xue, Baian Chen, Jiajun Wu, Donglai Wei, and William Freeman. Video enhancement with task-oriented flow. arXiv 1711.09078, 2017.
[151] MPRN 0.32 4 color Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[152] DAIN 0.13 2 color Wenbo Bao, Wei-Sheng Lai, Chao Ma, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019.
[153] FRUCnet 0.65 2 color Van Thang Nguyen, Kyujoong Lee, and Hyuk-Jae Lee. (Interpolation results only.) A stacked deep MEMC network for frame rate up conversion and its application to HEVC. Submitted to IEEE TCSVT 2019.
[154] OFRI 0.31 2 color Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
[155] CompactFlow_ROB 0.05 2 color Anonymous. CompactFlow: spatially shiftable window revisited. CVPR 2019 submission 1387.
[156] SegFlow 3.2 2 color Jun Chen, Zemin Cai, Jianhuang Lai, and Xiaohua Xie. Efficient segmentation-based PatchMatch for large displacement optical flow estimation. IEEE TCSVT 2018.
[157] HCFN 0.18 2 color Anonymous. Practical coarse-to-fine optical flow with deep networks. ICCV 2019 submission 116.
[158] FGME 0.23 2 color Bo Yan, Weimin Tan, Chuming Lin, and Liquan Shen. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. IEEE Transactions on Broadcasting, 2020.
[159] MS-PFT 0.44 2 color Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) A multi-scale position feature transform network for video frame interpolation. IEEE TCSVT 2020.
[160] MEMC-Net+ 0.12 2 color Wenbo Bao, Wei-Sheng Lai, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang. (Interpolation results only.) MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement. Submitted to PAMI 2018.
[161] ADC 0.01 2 color Anonymous. (Interpolation results only.) Learning spatial transform for video frame interpolation. ICCV 2019 submission 5424.
[162] DSepConv 0.3 2 color Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) Video frame interpolation via deformable separable convolution. AAAI 2020.
[163] MAF-net 0.3 2 color Mengshun Hu, Jing Xiao, Liang Liao, Zheng Wang, Chia-Wen Lin, Mi Wang, and Shinichi Satoh. Capturing small, fast-moving objects: Frame interpolation via recurrent motion enhancement. IEEE TCSVT 2021.
[164] STAR-Net 0.049 2 color Anonymous. (Interpolation results only.) Space-time-aware multiple resolution for video enhancement. CPVR 2020 submission 430.
[165] AdaCoF 0.03 2 color Hyeongmin Lee, Taeoh Kim, Tae-young Chung, Daehyun Pak, Yuseok Ban, and Sangyoun Lee. (Interpolation results only.) AdaCoF: Adaptive collaboration of flows for video frame interpolation. CVPR 2020. Code available.
[166] TC-GAN 0.13 2 color Anonymous. (Interpolation results only.) A temporal and contextual generative adversarial network for video frame interpolation. CVPR 2020 submission 111.
[167] FeFlow 0.52 2 color Shurui Gui, Chaoyue Wang, Qihua Chen, and Dacheng Tao. (Interpolation results only.) FeatureFlow: Robust video interpolation via structure-to-texture generation. CVPR 2020. Code available.
[168] DAI 0.23 2 color Anonymous. (Interpolation results only.) Deep animation inbetweening. CVPR 2020 submission 6404.
[169] SoftSplat 0.1 2 color Simon Niklaus and Feng Liu. (Interpolation results only.) Softmax splatting for video frame interpolation. CVPR 2020.
[170] STSR 5.35 2 color Anonymous. (Interpolation results only.) Spatial and temporal video super-resolution with a frequency domain loss. ECCV 2020 submission 2340.
[171] BMBC 0.77 2 color Anonymous. (Interpolation results only.) BMBC: Bilateral motion estimation with bilateral cost volume for video interpolation. ECCV 2020 submission 2095.
[172] GDCN 1.0 2 color Anonymous. (Interpolation results only.) Video interpolation via generalized deformable convolution. ECCV 2020 submission 4347.
[173] EDSC 0.56 2 color Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) Multiple video frame interpolation via enhanced deformable separable convolution. Submitted to PAMI 2020.
[174] CoT-AMFlow 0.04 2 color Anonymous. CoT-AMFlow: Adaptive modulation network with co-teaching strategy for unsupervised optical flow estimation. CoRL 2020 submission 36.
[175] TVL1_RVC 11.6 2 color RVC 2020 baseline submission by Toby Weed, based on: Javier Sanchez, Enric Meinhardt-Llopis, and Gabriele Facciolo. TV-L1 optical flow estimation. IPOL 3:137-150, 2013.
[176] H+S_RVC 44.7 2 color RVC 2020 baseline submission by Toby Weed, based on: Enric Meinhardt-Llopis, Javier Sanchez, and Daniel Kondermann. Horn-Schunck optical flow with a multi-scale strategy. IPOL 3:151–172, 2013.
[177] PRAFlow_RVC 0.34 2 color Zhexiong Wan, Yuxin Mao, and Yuchao Dai. Pyramid recurrent all-pairs flow. RVC 2020 submission.
[178] VCN_RVC 0.84 2 color Gengshan Yang and Deva Ramanan. Volumetric correspondence networks for optical flow. NeurIPS 2019. RVC 2020 submission.
[179] RAFT-TF_RVC 1.51 2 color Deqing Sun, Charles Herrmann, Varun Jampani, Mike Krainin, Forrester Cole, Austin Stone, Rico Jonschkowski, Ramin Zabih, William Freeman, and Ce Liu. A TensorFlow implementation of RAFT (Zachary Teed and Jia Deng. RAFT: Recurrent all-pairs field transforms for optical flow. ECCV 2020.) RVC 2020 submission.
[180] IRR-PWC_RVC 0.18 2 color Junhwa Hur and Stefan Roth. Iterative residual refinement for joint optical flow and occlusion estimation. CVPR 2019. RVC 2020 submission.
[181] C-RAFT_RVC 0.60 2 color Henrique Morimitsu and Xiangyang Ji. Classification RAFT. RVC 2020 submission.
[182] LSM_FLOW_RVC 0.2 2 color Chengzhou Tang, Lu Yuan, and Ping Tan. LSM: Learning subspace minimization for low-level vision. CVPR 2020. RVC 2020 submission.
[183] MV_VFI 0.23 2 color Zhenfang Wang, Yanjiang Wang, and Baodi Liu. (Interpolation results only.) Multi-view based video interpolation algorithm. ICASSP 2021 submission.
[184] DistillNet 0.12 2 color Anonymous. (Interpolation results only.) A teacher-student optical-flow distillation framework for video frame interpolation. CVPR 2021 submission 7534.
[185] SepConv++ 0.1 2 color Simon Niklaus, Long Mai, and Oliver Wang. (Interpolation results only.) Revisiting adaptive convolutions for video frame interpolation. WACV 2021.
[186] EAFI 0.18 2 color Anonymous. (Interpolation results only.) Error-aware spatial ensembles for video frame interpolation. ICCV 2021 submission 8020.
[187] UnDAF 0.04 2 color Anonymous. UnDAF: A general unsupervised domain adaptation framework for disparity, optical flow or scene flow estimation. CVPR 2021 submission 236.
[188] FLAVR 0.029 all color Anonymous. (Interpolation results only.) FLAVR frame interpolation. NeurIPS 2021 submission 1300.
[189] PBOFVI 150 2 color Zemin Cai, Jianhuang Lai, Xiaoxin Liao, and Xucong Chen. Physics-based optical flow under varying illumination. Submitted to IEEE TCSVT 2021.
[190] SoftsplatAug 0.17 2 color Anonymous. (Interpolation results only.) Transformation data augmentation for sports video frame interpolation. ICCV 2021 submission 3245.
* The "time" column lists the reported runtime in seconds on the "Urban" sequence. Note that these runtimes are not normalized by processor speed or type.