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        
R10.0
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
OFLAF [77]10.0 3.84 5 17.2 11 1.99 15 2.48 5 14.1 5 1.41 9 2.96 2 10.1 2 1.17 12 2.36 10 14.7 9 0.82 11 5.15 3 7.90 7 2.15 4 6.43 35 18.2 12 4.98 18 0.27 2 2.42 4 0.07 16 0.79 10 1.88 8 1.81 26
NNF-Local [87]10.2 3.83 4 16.9 9 1.87 9 2.64 7 16.1 12 1.33 8 3.02 3 10.7 3 1.33 17 2.79 19 18.9 25 1.11 20 4.82 1 6.85 1 1.73 2 4.13 4 14.6 3 2.27 2 0.52 27 5.08 60 0.00 1 0.28 3 1.04 3 0.04 2
MDP-Flow2 [68]12.0 3.86 7 17.2 11 1.90 11 2.06 1 12.6 1 1.04 2 3.22 5 11.0 4 1.16 10 3.27 31 21.7 37 1.19 25 6.35 17 8.86 14 3.12 11 5.40 14 15.7 4 5.11 20 0.38 13 3.75 28 0.02 3 0.49 6 1.80 7 0.13 7
NN-field [71]14.4 4.31 18 18.6 23 2.22 24 3.13 17 18.3 26 1.79 20 3.16 4 11.1 5 1.40 18 2.08 7 16.7 13 0.78 9 5.28 4 7.44 3 2.25 5 2.53 1 8.92 1 0.92 1 0.89 52 6.39 85 0.02 3 0.27 2 0.98 2 0.04 2
PMMST [114]15.3 4.02 10 16.5 7 1.46 1 3.86 34 16.9 18 3.33 50 3.91 10 12.6 9 2.82 42 2.18 9 9.47 3 1.30 31 5.68 9 7.88 6 2.78 8 5.25 12 13.7 2 4.29 10 0.53 29 5.11 61 0.02 3 0.26 1 0.94 1 0.04 2
nLayers [57]25.5 4.08 13 16.2 5 2.80 43 4.71 59 19.3 34 3.82 80 4.64 21 15.2 21 3.96 64 1.99 5 13.2 4 0.80 10 5.34 6 7.57 5 3.22 13 5.85 28 16.8 7 4.64 13 0.87 50 3.68 26 0.96 64 0.84 11 2.94 18 0.75 12
LME [70]26.8 3.70 3 16.1 4 1.69 2 2.13 2 13.0 2 1.19 4 5.91 48 15.4 22 7.43 94 3.23 27 22.4 42 1.19 25 6.60 24 9.12 17 4.39 47 6.11 30 20.8 21 6.60 56 0.52 27 4.96 58 0.07 16 1.09 16 3.28 26 1.86 29
ComponentFusion [96]27.1 4.03 11 17.7 15 2.19 23 2.17 4 13.1 3 1.26 5 3.86 9 13.2 11 1.58 20 2.85 23 18.0 18 1.03 18 6.68 25 9.59 24 4.14 38 8.35 78 27.3 77 8.34 93 0.60 33 4.03 36 0.52 51 0.76 9 2.22 12 1.09 14
SVFilterOh [111]28.0 4.36 20 15.9 3 2.01 18 3.04 15 16.3 14 1.78 19 3.31 6 11.3 6 1.20 13 2.02 6 13.6 6 0.57 3 5.94 13 8.69 13 2.12 3 6.61 38 19.3 14 6.32 52 5.10 116 12.9 130 10.0 128 0.75 8 2.20 11 1.32 16
FC-2Layers-FF [74]28.4 4.03 11 16.3 6 2.39 32 4.23 43 20.9 44 3.21 46 3.40 8 11.4 7 2.64 36 2.74 16 17.1 15 1.03 18 5.73 10 8.29 10 3.31 15 7.49 53 20.5 20 6.66 60 1.30 68 6.84 91 0.34 44 0.64 7 1.78 6 1.20 15
NNF-EAC [103]28.7 4.32 19 18.6 23 2.18 22 2.69 9 15.1 7 1.64 14 3.93 11 13.1 10 1.27 15 4.17 65 23.0 51 1.95 61 7.09 38 9.97 32 3.89 33 6.33 33 17.4 9 5.53 23 0.55 30 5.18 62 0.02 3 1.60 42 4.32 45 1.93 32
HAST [109]31.0 2.98 1 12.9 1 1.71 3 3.63 30 15.0 6 2.78 38 2.46 1 8.38 1 0.25 1 2.84 22 18.0 18 0.67 5 5.02 2 7.35 2 1.66 1 8.83 88 22.4 36 8.37 94 6.13 122 12.0 125 18.0 137 0.31 4 1.13 4 0.03 1
WLIF-Flow [93]31.3 3.97 9 17.0 10 2.12 20 3.53 24 18.5 28 2.37 31 4.60 20 15.1 19 2.34 32 3.40 34 20.3 32 1.50 36 7.69 62 11.4 73 4.79 62 6.67 39 17.8 11 5.53 23 0.40 16 3.68 26 0.07 16 1.59 41 3.82 36 2.63 51
RNLOD-Flow [121]33.4 3.58 2 15.7 2 1.83 7 3.60 28 19.9 37 2.06 24 5.53 42 18.1 44 2.42 34 2.75 17 17.7 16 1.01 17 6.01 14 9.09 16 3.98 35 7.21 45 20.0 16 6.87 69 2.59 91 9.67 107 1.95 83 1.06 15 2.66 15 1.79 25
FESL [72]33.5 3.91 8 16.6 8 2.13 21 5.68 86 23.5 63 4.23 87 5.17 32 16.8 28 2.99 45 2.41 12 15.8 11 0.89 15 5.76 11 8.62 12 4.05 36 5.81 24 17.6 10 5.32 22 1.09 60 5.68 76 1.21 71 1.35 25 2.89 17 1.72 23
Layers++ [37]33.7 4.39 22 17.8 16 3.14 51 3.70 31 18.0 23 2.84 39 3.37 7 11.5 8 2.65 37 2.38 11 14.1 8 0.82 11 5.33 5 7.52 4 3.78 31 7.58 56 22.0 32 6.13 45 1.81 85 7.08 95 0.54 52 1.45 32 2.46 14 4.56 94
3DFlow [135]33.9 4.65 28 19.4 27 1.86 8 3.01 14 18.5 28 1.32 7 4.17 12 14.5 14 0.62 2 1.38 2 7.93 2 0.72 7 6.90 29 10.3 46 3.76 29 11.3 110 30.0 92 10.5 113 1.63 80 4.03 36 5.22 113 0.35 5 1.27 5 0.06 5
ALD-Flow [66]35.3 4.22 14 18.2 19 1.93 13 3.20 20 16.8 17 1.59 13 5.21 33 17.4 35 1.13 9 3.70 44 22.9 49 1.26 27 6.54 23 9.31 20 3.14 12 5.25 12 21.5 27 4.98 18 0.88 51 4.67 48 4.48 109 2.69 70 6.66 68 4.79 96
TC/T-Flow [76]35.8 4.57 26 20.6 32 2.00 16 3.45 23 18.7 30 1.52 11 4.30 15 14.3 13 0.67 4 3.97 60 23.1 52 1.80 52 6.35 17 9.50 23 3.36 18 4.48 6 15.7 4 4.78 15 1.30 68 6.94 92 5.07 112 2.08 57 5.10 55 2.83 57
PMF [73]36.3 4.65 28 18.3 22 2.34 27 3.37 21 18.2 25 1.92 22 4.20 13 14.6 16 1.01 7 3.24 29 18.6 22 1.11 20 5.50 7 8.09 8 2.43 6 6.99 42 24.8 57 6.27 50 6.87 125 17.3 141 8.77 127 0.91 12 2.06 9 2.06 35
AGIF+OF [85]37.3 4.39 22 18.0 18 2.80 43 5.10 71 23.7 67 3.70 74 5.06 28 16.8 28 3.11 46 3.29 32 20.1 30 1.45 35 6.45 20 9.31 20 4.62 53 6.77 41 19.7 15 5.86 33 0.37 12 3.60 22 0.25 37 1.79 49 3.68 32 3.12 68
Correlation Flow [75]37.4 4.57 26 20.5 31 1.87 9 2.71 10 16.2 13 1.16 3 5.74 46 17.9 42 0.66 3 1.91 3 13.5 5 0.85 14 8.00 72 12.0 85 4.57 51 8.69 82 23.8 47 8.93 100 0.84 47 4.74 50 0.96 64 1.38 28 3.81 35 1.91 31
Efficient-NL [60]37.5 4.24 15 17.4 13 2.24 25 4.30 44 21.8 47 2.75 36 5.26 36 16.9 30 2.67 38 3.43 36 21.0 34 1.74 47 6.02 15 9.16 18 3.31 15 7.84 66 21.7 29 6.26 48 1.36 71 6.79 90 1.03 67 1.48 36 3.08 21 1.77 24
TC-Flow [46]39.6 4.27 16 19.0 26 1.91 12 2.85 11 16.6 16 1.45 10 5.05 27 16.9 30 0.80 6 4.05 61 23.9 61 1.74 47 6.73 26 9.68 26 2.93 10 5.83 25 22.9 41 5.68 30 1.39 73 4.87 55 7.32 123 2.46 65 6.13 63 4.49 90
ProFlow_ROB [146]39.8 5.24 46 22.0 47 2.36 30 3.71 33 20.5 41 2.17 28 6.59 55 21.5 59 2.88 44 3.48 37 22.0 39 1.14 24 6.88 28 9.84 29 3.61 22 5.84 26 23.0 42 6.06 40 0.50 26 4.91 56 0.15 27 2.29 60 6.62 67 2.50 49
OAR-Flow [125]40.1 5.41 49 21.6 44 2.61 37 4.96 67 22.3 50 2.88 40 7.90 66 23.8 64 4.19 68 4.45 72 22.7 48 1.90 56 7.03 35 10.1 36 3.39 19 5.10 10 22.3 34 4.56 12 0.29 4 2.64 8 0.17 29 1.58 40 4.89 53 1.68 21
Classic+CPF [83]41.5 4.77 33 19.7 29 2.99 46 4.59 50 23.3 61 3.08 44 5.24 34 17.2 33 2.81 41 3.32 33 21.3 35 1.57 41 6.51 22 9.49 22 4.24 43 7.39 50 21.5 27 6.27 50 1.02 55 5.33 66 1.40 74 1.47 35 3.19 24 2.47 47
IROF++ [58]44.0 4.68 30 19.4 27 2.70 40 4.66 54 23.1 56 3.42 60 5.25 35 17.2 33 3.79 60 3.95 58 23.2 54 2.05 66 6.97 32 9.84 29 4.64 54 7.99 70 24.6 53 7.05 73 0.44 19 4.30 43 0.00 1 1.37 27 3.26 25 2.83 57
ProbFlowFields [128]44.0 8.29 89 31.1 87 5.73 106 3.54 25 18.0 23 2.75 36 6.07 51 18.9 49 5.22 71 3.54 40 17.7 16 1.91 57 7.66 61 10.8 58 4.59 52 5.06 9 20.0 16 5.58 27 0.38 13 3.08 15 0.07 16 1.70 45 4.56 49 2.41 46
PH-Flow [101]44.5 5.11 40 21.0 35 3.62 65 4.59 50 22.4 51 3.37 54 4.37 16 14.5 14 3.45 52 3.93 57 22.5 44 2.07 69 6.34 16 9.00 15 3.74 27 7.28 48 21.7 29 6.39 54 1.61 79 5.58 74 1.58 77 1.15 18 2.12 10 3.39 74
COFM [59]44.6 4.75 32 20.2 30 2.63 39 3.40 22 18.3 26 2.14 26 6.19 52 19.3 50 4.00 65 3.04 25 18.8 23 1.11 20 7.45 51 10.1 36 7.01 99 8.80 86 20.9 22 6.68 61 1.41 74 3.66 25 2.76 95 1.22 19 2.28 13 3.72 79
HBM-GC [105]45.2 5.82 57 18.2 19 2.00 16 4.47 48 18.7 30 3.80 79 4.39 17 15.1 19 1.73 24 2.42 13 13.8 7 0.72 7 6.77 27 9.60 25 4.08 37 7.61 58 19.0 13 5.76 31 4.61 112 12.6 127 2.83 97 2.39 63 5.72 58 5.01 100
HCFN [162]45.4 4.29 17 20.6 32 1.71 3 2.64 7 15.1 7 1.69 15 4.21 14 14.8 17 1.26 14 2.81 21 19.5 27 0.84 13 5.93 12 8.53 11 2.64 7 7.75 62 26.3 70 7.82 86 12.7 145 17.7 142 17.4 136 2.56 67 6.04 62 5.29 102
PWC-Net_ROB [147]45.8 9.12 97 32.2 93 4.81 92 4.68 56 22.6 52 3.66 71 7.60 63 25.0 74 5.34 72 2.47 14 15.4 10 0.97 16 7.07 36 9.98 33 3.95 34 6.32 32 25.4 63 6.26 48 0.47 23 4.66 47 0.17 29 0.98 13 3.17 23 0.31 9
Sparse-NonSparse [56]46.4 4.98 36 20.8 34 4.09 74 4.63 53 22.9 53 3.41 59 5.02 26 16.7 27 3.47 55 3.89 53 22.6 47 1.91 57 7.17 41 10.2 40 4.30 45 7.66 60 22.3 34 6.80 65 0.69 39 3.53 21 0.89 61 1.52 38 3.56 31 2.97 64
WRT [150]46.6 5.66 56 21.6 44 1.98 14 5.17 76 23.5 63 3.40 57 7.54 62 21.3 58 1.16 10 1.32 1 7.54 1 0.47 1 6.97 32 10.2 40 4.90 68 11.5 112 27.6 78 8.28 92 0.45 22 3.92 32 0.22 34 2.30 61 4.18 42 2.94 63
CostFilter [40]46.8 5.29 47 22.0 47 2.85 45 3.54 25 17.7 21 2.16 27 4.64 21 16.0 23 1.75 25 3.68 43 22.5 44 1.27 29 5.67 8 8.14 9 2.85 9 7.76 63 25.9 65 6.80 65 6.98 128 24.2 147 12.9 131 1.43 29 4.11 39 2.02 34
MLDP_OF [89]47.8 6.35 65 26.0 66 3.41 56 2.97 13 16.4 15 1.76 18 5.47 40 17.8 40 1.30 16 2.79 19 19.7 28 1.12 23 7.13 40 10.0 34 3.75 28 7.49 53 21.4 26 9.75 107 5.04 114 6.22 82 17.0 135 1.79 49 4.28 43 2.14 37
LSM [39]48.1 5.00 38 21.2 41 3.93 71 4.62 52 22.9 53 3.37 54 5.13 30 17.1 32 3.26 49 3.80 48 22.9 49 1.87 54 6.92 30 9.78 27 4.41 49 7.71 61 22.4 36 6.74 63 1.00 54 4.76 52 1.16 69 1.68 44 3.94 37 2.90 61
Classic+NL [31]48.2 5.07 39 21.0 35 4.22 78 4.70 58 23.4 62 3.27 48 4.98 25 16.5 25 3.48 56 3.75 47 22.5 44 1.68 44 7.21 44 10.2 40 4.32 46 7.82 64 22.4 36 6.71 62 1.47 75 6.39 85 1.18 70 1.12 17 2.87 16 2.27 41
FMOF [94]48.6 4.42 24 17.8 16 3.06 49 5.03 68 23.1 56 3.63 68 4.45 19 14.8 17 2.80 40 2.94 24 18.8 23 1.26 27 7.00 34 10.2 40 4.71 57 8.92 89 20.9 22 7.13 75 1.06 58 6.34 84 1.85 82 2.58 69 5.80 60 3.06 66
JOF [140]48.7 4.36 20 18.2 19 2.55 35 5.21 78 23.2 58 4.14 84 4.40 18 14.2 12 3.37 51 3.66 42 21.4 36 1.95 61 6.49 21 9.25 19 3.76 29 7.05 44 21.0 24 5.58 27 4.19 109 8.20 100 6.97 121 1.84 53 4.37 46 2.92 62
Ramp [62]48.8 5.12 41 21.1 39 3.82 70 4.68 56 23.2 58 3.47 63 4.89 24 16.3 24 3.46 53 3.83 50 22.3 41 1.93 60 7.23 45 10.2 40 4.80 63 7.61 58 22.1 33 6.80 65 1.20 64 5.04 59 1.43 75 1.36 26 2.98 19 2.31 45
IIOF-NLDP [131]49.5 6.16 61 25.7 64 2.54 34 4.55 49 23.7 67 2.40 32 5.35 39 17.6 38 1.06 8 2.78 18 17.0 14 1.54 37 8.90 95 13.4 115 4.73 58 8.04 71 22.8 39 7.69 85 0.64 37 4.61 45 0.25 37 1.81 52 4.16 41 2.72 53
S2D-Matching [84]51.0 4.97 35 21.3 43 3.55 62 4.74 60 23.6 65 3.35 52 6.50 54 20.9 55 3.46 53 3.49 38 20.4 33 1.60 42 7.07 36 10.0 34 4.22 41 7.82 64 23.1 43 6.87 69 1.78 84 5.90 79 2.12 85 1.30 22 3.14 22 2.74 54
Aniso-Texture [82]51.1 3.84 5 17.5 14 1.76 5 2.88 12 15.9 10 2.11 25 7.10 61 20.9 55 2.30 28 1.97 4 16.5 12 0.57 3 8.24 80 11.9 81 5.22 78 8.82 87 26.6 74 6.77 64 8.34 134 16.2 140 1.43 75 2.42 64 5.55 56 2.84 59
NL-TV-NCC [25]51.8 5.44 50 21.7 46 2.24 25 4.00 38 21.9 48 1.69 15 5.27 37 17.8 40 0.67 4 2.52 15 19.1 26 0.67 5 8.37 84 12.5 95 5.12 77 11.5 112 32.0 104 9.19 103 0.86 48 4.93 57 1.35 73 2.16 58 6.46 64 1.63 18
TV-L1-MCT [64]52.7 4.69 31 18.9 25 3.60 64 5.64 85 25.6 81 4.21 85 5.53 42 18.1 44 3.23 47 3.04 25 19.9 29 1.35 32 7.49 52 10.6 51 4.91 70 8.34 76 22.8 39 7.50 84 0.79 46 2.61 6 3.57 103 1.73 47 3.45 29 3.26 72
MDP-Flow [26]52.8 5.65 54 24.7 61 4.93 94 3.70 31 17.6 20 3.40 57 5.47 40 18.7 48 4.66 69 3.87 51 24.3 64 1.88 55 7.12 39 9.89 31 5.00 74 6.17 31 25.9 65 4.66 14 0.61 34 5.65 75 0.05 13 3.28 85 8.39 85 3.45 77
IROF-TV [53]53.5 5.22 44 22.6 53 3.59 63 4.80 62 24.2 73 3.73 78 5.71 45 18.4 47 3.64 58 4.19 66 25.7 78 1.92 59 7.63 60 10.7 55 5.26 79 9.22 95 30.2 93 6.60 56 0.30 7 2.86 11 0.02 3 1.32 24 3.76 34 2.27 41
AggregFlow [97]53.5 6.17 62 23.3 55 2.58 36 7.01 96 28.0 101 5.29 97 8.46 71 24.2 66 7.66 97 3.73 45 20.2 31 1.73 46 7.25 46 10.6 51 3.52 20 4.43 5 16.4 6 4.80 17 0.75 43 5.43 70 0.25 37 1.92 54 4.46 48 4.12 84
CombBMOF [113]56.5 6.51 67 28.6 76 2.61 37 3.98 37 18.7 30 2.29 30 5.29 38 17.4 35 2.33 31 5.12 82 26.1 85 3.28 88 6.35 17 9.81 28 3.34 17 12.0 117 28.4 83 15.1 129 3.73 103 12.8 129 0.76 58 0.98 13 3.00 20 0.09 6
OFH [38]57.0 6.38 66 25.7 64 4.69 87 3.90 35 20.6 42 2.24 29 7.85 65 24.2 66 2.27 27 4.11 64 25.1 69 1.72 45 7.44 50 10.4 47 4.69 55 8.13 72 28.9 85 8.44 97 0.44 19 4.25 40 0.12 24 2.80 72 8.82 95 2.74 54
Adaptive [20]57.5 5.12 41 22.0 47 2.34 27 4.82 64 23.2 58 3.50 64 8.67 77 24.5 71 3.56 57 4.19 66 25.3 75 1.83 53 7.40 49 10.6 51 3.63 23 5.84 26 23.2 45 3.75 8 3.25 99 8.86 103 0.89 61 2.87 75 6.69 69 3.14 70
Sparse Occlusion [54]57.5 4.99 37 21.1 39 2.79 42 4.13 41 20.1 40 3.00 43 5.94 50 19.4 51 2.15 26 3.41 35 21.8 38 1.35 32 8.17 78 12.1 88 4.74 59 7.87 68 25.6 64 6.34 53 11.4 140 17.7 142 2.71 94 1.64 43 4.70 52 1.81 26
Occlusion-TV-L1 [63]58.0 5.23 45 22.2 50 2.36 30 4.40 46 21.2 45 3.39 56 8.46 71 24.8 72 3.83 62 3.92 55 24.8 66 1.74 47 9.11 98 13.1 110 5.75 86 4.65 7 23.9 48 3.52 6 1.27 67 3.13 16 0.44 47 3.56 93 8.92 96 3.28 73
2DHMM-SAS [92]59.4 5.14 43 21.0 35 3.79 69 5.26 79 25.2 78 3.45 61 6.97 60 20.2 52 4.18 67 4.06 62 23.3 56 2.10 70 7.18 42 10.2 40 4.92 71 8.29 74 23.7 46 7.16 76 1.26 65 5.41 69 1.63 78 1.71 46 3.75 33 2.74 54
RFlow [90]59.5 5.85 58 24.8 63 4.44 84 3.18 18 17.9 22 1.88 21 7.81 64 24.4 70 2.32 30 3.25 30 23.4 57 1.55 38 7.94 66 11.6 77 4.86 65 8.23 73 28.0 82 6.64 59 1.16 63 2.13 2 1.13 68 4.10 104 9.22 103 6.81 110
SimpleFlow [49]60.0 5.65 54 22.4 52 4.93 94 5.47 84 24.5 76 4.28 88 6.88 59 21.0 57 3.95 63 4.74 75 25.2 71 3.02 81 7.19 43 10.1 36 4.70 56 8.34 76 23.1 43 7.16 76 1.02 55 4.61 45 0.89 61 1.29 21 3.44 27 2.47 47
ACK-Prior [27]61.4 5.49 52 24.0 58 1.81 6 2.55 6 15.7 9 0.83 1 5.07 29 17.7 39 1.52 19 2.14 8 18.1 20 0.50 2 8.64 87 11.6 77 7.10 102 14.6 129 30.7 95 11.7 118 8.46 135 11.5 121 19.5 139 3.68 97 7.25 73 2.64 52
S2F-IF [123]62.1 9.49 103 37.6 109 4.93 94 4.81 63 25.6 81 3.34 51 8.25 69 26.1 76 6.40 81 4.99 79 25.6 77 2.93 79 7.80 63 11.0 63 4.90 68 5.61 17 24.9 60 5.83 32 0.62 36 5.35 68 0.22 34 1.43 29 4.11 39 1.67 20
Complementary OF [21]64.0 7.27 76 30.0 81 4.31 79 3.18 18 18.9 33 1.52 11 5.91 48 20.2 52 2.31 29 4.22 69 24.8 66 2.05 66 7.50 55 10.4 47 4.99 73 12.3 120 31.7 103 8.87 99 0.61 34 2.69 9 1.72 80 3.33 86 9.22 103 4.88 99
ROF-ND [107]64.9 6.70 68 27.6 72 3.53 60 3.08 16 16.0 11 1.73 17 5.81 47 18.3 46 1.58 20 3.81 49 18.4 21 2.20 71 9.45 103 14.0 126 6.31 93 11.3 110 29.6 90 7.27 80 9.92 138 10.8 112 7.29 122 1.53 39 3.44 27 1.64 19
PGM-C [120]65.3 9.47 101 37.1 105 4.81 92 5.08 69 26.1 88 3.63 68 8.75 79 27.6 83 7.02 87 5.65 94 28.1 104 3.63 99 7.99 69 11.3 70 4.88 66 5.71 21 24.5 52 5.97 36 0.31 8 3.01 14 0.02 3 2.07 56 6.50 66 2.14 37
TCOF [69]65.5 7.04 74 26.9 69 3.54 61 4.93 65 23.7 67 3.45 61 9.94 92 27.8 85 7.40 93 3.74 46 23.7 60 1.55 38 10.0 118 14.3 127 4.40 48 4.91 8 17.0 8 5.53 23 5.08 115 9.68 108 4.19 107 1.43 29 4.44 47 1.69 22
SegFlow [160]66.0 9.46 100 37.1 105 4.79 89 5.13 72 26.3 91 3.65 70 8.62 76 27.1 80 7.00 85 5.59 90 28.1 104 3.52 95 8.07 75 11.4 73 5.09 76 5.72 22 24.6 53 6.10 43 0.35 11 3.43 19 0.02 3 1.76 48 5.06 54 2.50 49
FlowFields [110]67.3 9.65 105 37.6 109 5.13 99 5.09 70 25.9 85 3.72 76 8.92 81 28.3 89 7.07 89 5.45 86 26.0 83 3.82 100 7.95 67 11.2 69 5.01 75 5.75 23 26.1 69 6.01 37 0.40 16 3.29 18 0.12 24 1.92 54 5.99 61 1.89 30
TF+OM [100]67.5 6.03 60 23.7 57 2.78 41 4.39 45 19.9 37 3.57 65 8.73 78 23.0 63 11.2 103 3.57 41 23.2 54 1.36 34 7.98 68 11.1 67 5.89 88 8.95 90 25.3 62 7.06 74 1.68 82 11.2 117 0.20 31 3.56 93 8.35 84 4.18 85
DMF_ROB [139]68.3 8.16 87 33.3 96 4.93 94 4.95 66 23.7 67 3.23 47 9.38 85 28.5 91 5.85 80 5.64 93 27.3 94 3.41 93 7.49 52 10.6 51 4.44 50 6.49 36 25.9 65 6.07 41 0.40 16 3.65 23 0.07 16 3.81 100 9.06 101 4.63 95
Steered-L1 [118]68.8 4.54 25 21.2 41 2.09 19 2.13 2 13.9 4 1.31 6 4.80 23 16.5 25 1.64 22 3.87 51 25.1 69 1.60 42 8.62 86 11.5 76 7.01 99 11.1 107 28.7 84 10.4 112 12.0 144 12.3 126 34.9 147 5.90 116 9.03 100 11.6 124
FlowFields+ [130]68.8 9.76 107 38.1 113 5.31 102 5.14 73 26.2 90 3.72 76 8.99 82 28.6 92 7.15 92 5.09 81 25.9 82 3.29 89 7.82 64 11.0 63 4.94 72 5.22 11 24.7 56 5.18 21 0.70 41 5.85 78 0.30 42 1.79 49 5.77 59 1.45 17
DeepFlow2 [108]69.4 6.80 70 28.5 75 2.99 46 5.20 77 22.9 53 3.60 67 8.88 80 26.2 77 5.75 77 5.76 96 26.8 92 3.41 93 7.34 48 10.7 55 3.58 21 5.86 29 24.8 57 6.22 47 1.02 55 3.78 30 3.08 101 4.35 107 9.84 108 5.80 105
CPM-Flow [116]69.5 9.47 101 37.1 105 4.79 89 5.15 74 26.3 91 3.67 72 8.59 75 27.1 80 7.00 85 5.59 90 27.8 101 3.57 97 7.99 69 11.3 70 4.74 59 5.70 20 24.1 50 6.05 39 0.48 24 4.29 42 0.02 3 2.76 71 7.63 78 4.11 83
EPPM w/o HM [88]69.5 8.62 93 33.5 97 3.62 65 3.58 27 19.7 35 1.93 23 6.19 52 20.5 54 1.64 22 4.64 74 25.2 71 2.54 74 7.60 59 10.4 47 5.81 87 11.2 108 31.6 101 9.82 108 6.91 127 8.93 104 15.9 134 1.48 36 4.06 38 2.01 33
EpicFlow [102]70.4 9.44 99 37.1 105 4.80 91 5.15 74 26.4 93 3.70 74 9.58 87 30.0 95 7.07 89 5.38 85 27.8 101 3.29 89 8.01 73 11.3 70 4.88 66 5.67 19 24.6 53 6.12 44 0.32 10 3.13 16 0.02 3 3.10 82 7.52 76 4.79 96
ComplOF-FED-GPU [35]72.7 6.96 72 30.7 84 3.33 54 4.74 60 24.9 77 2.66 34 6.71 57 22.4 60 2.45 35 4.44 71 26.2 86 2.05 66 7.50 55 10.7 55 4.20 40 9.78 97 34.0 113 9.47 105 2.42 90 4.74 50 6.63 119 3.09 80 9.17 102 3.91 82
SRR-TVOF-NL [91]73.2 7.45 80 28.6 76 3.09 50 6.20 89 26.1 88 3.90 81 9.82 90 28.4 90 5.78 78 3.96 59 23.5 58 1.55 38 7.55 57 10.8 58 5.27 80 9.21 93 26.7 75 7.25 79 5.74 119 11.5 121 4.01 105 1.30 22 3.49 30 2.19 40
F-TV-L1 [15]73.9 8.70 94 31.4 89 8.47 115 7.61 100 27.3 98 5.86 98 11.0 95 28.0 86 5.73 76 5.75 95 28.7 109 3.32 92 7.28 47 10.8 58 3.72 24 6.59 37 26.4 71 4.38 11 1.26 65 5.30 65 0.44 47 3.04 78 7.76 79 2.29 44
SIOF [67]75.0 5.37 48 22.6 53 2.34 27 6.11 87 28.4 102 4.30 89 12.6 102 29.2 94 14.4 108 5.52 89 27.4 97 3.00 80 8.96 96 12.6 97 6.02 89 8.72 83 27.9 80 7.93 88 0.38 13 3.48 20 0.02 3 3.09 80 7.58 77 4.85 98
TV-L1-improved [17]75.1 5.52 53 23.4 56 3.42 57 4.13 41 20.8 43 2.96 41 8.29 70 24.2 66 3.64 58 4.06 62 24.4 65 1.77 50 8.34 83 12.1 88 4.15 39 13.7 124 38.4 126 14.9 126 4.40 111 10.1 110 2.14 86 3.33 86 8.42 86 3.40 75
DPOF [18]75.3 9.01 96 34.7 99 3.68 68 6.16 88 25.4 80 4.32 90 5.55 44 17.9 42 3.36 50 3.92 55 25.3 75 2.00 64 8.14 77 11.0 63 6.05 90 10.5 102 27.9 80 8.16 90 9.33 136 6.19 81 21.0 141 1.46 33 4.57 50 0.80 13
Aniso. Huber-L1 [22]75.5 5.98 59 24.2 59 3.23 53 8.53 104 27.3 98 7.91 103 9.64 88 25.6 75 5.52 74 5.00 80 25.7 78 2.75 77 8.66 88 12.8 103 4.74 59 7.60 57 24.8 57 3.51 5 3.65 102 7.24 96 3.00 100 2.57 68 6.69 69 2.86 60
Classic++ [32]77.7 5.46 51 22.2 50 4.35 81 4.66 54 22.1 49 3.57 65 8.00 67 24.3 69 5.06 70 4.21 68 25.2 71 2.01 65 8.77 91 12.7 101 5.47 81 9.03 92 30.2 93 7.29 81 2.92 97 7.73 98 3.10 102 3.83 101 8.53 87 3.87 81
LocallyOriented [52]77.8 8.05 86 30.6 83 3.63 67 8.09 102 30.8 110 6.17 100 12.3 101 32.3 102 7.04 88 4.88 78 25.2 71 2.88 78 8.80 93 12.7 101 4.27 44 5.41 15 20.4 18 6.07 41 1.35 70 6.03 80 0.99 66 3.73 99 8.62 90 4.18 85
BriefMatch [124]78.8 4.78 34 21.0 35 2.40 33 4.00 38 19.8 36 2.68 35 5.13 30 17.5 37 2.41 33 3.23 27 22.1 40 1.28 30 9.81 112 12.0 85 13.1 136 17.2 131 33.8 109 17.8 133 7.84 130 12.7 128 22.3 142 8.01 128 10.5 114 16.1 135
DeepFlow [86]80.5 7.55 81 29.3 79 4.67 86 6.29 91 23.7 67 4.86 92 10.0 93 28.0 86 8.76 102 6.15 103 27.3 94 3.83 101 7.49 52 10.8 58 3.72 24 6.40 34 26.8 76 6.85 68 1.12 61 2.92 13 3.94 104 7.07 121 11.2 119 12.7 126
FF++_ROB [145]80.5 9.90 110 38.2 114 5.12 98 5.32 82 26.0 86 4.01 82 9.76 89 30.0 95 7.58 95 5.48 87 26.2 86 3.88 103 7.83 65 11.0 63 5.63 84 7.26 46 24.3 51 7.33 82 0.78 45 3.65 23 2.88 98 2.92 77 6.46 64 6.17 108
TriFlow [95]81.0 7.87 85 30.1 82 3.19 52 7.12 97 24.4 75 7.15 102 13.9 106 31.4 99 20.0 114 3.50 39 22.4 42 1.77 50 8.70 89 11.7 79 7.03 101 7.51 55 21.9 31 6.63 58 28.6 148 14.7 137 78.3 150 2.16 58 5.57 57 2.14 37
CRTflow [80]81.1 7.63 83 31.8 92 3.42 57 4.40 46 21.2 45 2.97 42 8.99 82 26.6 78 4.11 66 4.86 77 26.5 89 2.57 75 7.99 69 11.7 79 3.26 14 18.0 135 40.2 129 22.2 138 1.47 75 4.45 44 2.51 92 4.73 109 11.4 120 7.30 111
Rannacher [23]83.5 6.99 73 27.1 70 5.36 104 5.27 80 24.3 74 4.22 86 9.51 86 27.1 80 5.54 75 4.76 76 25.7 78 2.58 76 8.80 93 12.9 106 4.82 64 11.0 105 35.7 118 9.36 104 2.33 89 4.76 52 2.39 91 2.82 74 8.01 81 3.13 69
Brox et al. [5]83.7 8.32 90 32.6 94 6.95 109 6.23 90 26.9 97 5.23 95 9.13 84 27.6 83 6.55 83 5.85 98 28.2 106 3.26 86 10.2 120 12.9 106 11.0 131 5.43 16 29.3 89 4.79 16 0.86 48 4.00 34 0.12 24 4.32 105 10.2 111 4.54 93
Local-TV-L1 [65]83.8 9.60 104 30.8 85 7.89 114 12.7 114 30.2 109 13.3 114 15.9 114 32.3 102 17.3 111 6.19 104 28.0 103 3.84 102 7.55 57 10.9 62 4.22 41 7.48 52 26.4 71 6.02 38 0.28 3 1.87 1 0.15 27 9.10 130 10.8 116 20.5 136
Bartels [41]84.9 6.83 71 26.2 67 5.19 101 3.93 36 17.4 19 3.30 49 6.63 56 22.6 61 3.25 48 4.45 72 23.9 61 2.48 73 9.12 99 12.1 88 8.25 114 10.6 103 31.1 97 12.3 121 5.74 119 10.4 111 18.9 138 5.34 111 9.52 105 8.47 117
Dynamic MRF [7]84.9 7.74 84 31.6 91 4.44 84 4.12 40 23.6 65 2.47 33 8.49 73 28.0 86 2.83 43 4.25 70 27.4 97 2.41 72 8.61 85 12.0 85 6.08 91 14.5 128 43.2 133 14.9 126 0.64 37 2.35 3 4.51 110 9.85 133 15.6 136 15.3 133
SuperFlow [81]85.8 7.15 75 27.4 71 3.52 59 10.4 109 27.8 100 11.2 111 14.5 112 31.5 101 22.4 116 5.93 99 31.6 116 3.23 85 8.77 91 11.9 81 8.59 119 5.61 17 25.9 65 3.72 7 3.76 106 11.1 116 0.37 46 3.59 95 8.96 98 3.01 65
LiteFlowNet [142]87.4 15.0 118 50.3 132 7.15 110 6.37 92 25.8 84 4.98 93 11.5 98 36.2 113 6.96 84 5.48 87 23.1 52 3.06 84 9.02 97 12.3 93 7.10 102 11.7 116 33.8 109 9.65 106 0.44 19 4.00 34 0.20 31 3.07 79 6.97 72 4.52 92
CBF [12]90.3 6.32 63 26.2 67 3.35 55 11.1 111 25.6 81 13.7 115 8.51 74 24.1 65 7.12 91 5.12 82 26.0 83 3.04 83 10.3 121 13.6 120 9.59 127 7.85 67 26.4 71 4.25 9 11.8 141 13.8 132 14.2 133 3.54 92 8.06 82 5.32 103
OFRF [134]90.3 7.28 77 24.5 60 4.75 88 14.7 119 29.6 107 15.2 117 14.3 108 29.0 93 15.9 110 6.64 107 25.7 78 5.02 112 6.95 31 10.1 36 3.72 24 8.44 79 23.9 48 7.17 78 3.30 100 6.51 87 10.8 129 9.99 134 9.82 107 24.2 139
CLG-TV [48]91.3 6.33 64 24.7 61 4.13 75 9.08 107 26.6 94 9.31 109 9.85 91 26.8 79 5.82 79 5.30 84 26.5 89 3.03 82 10.4 123 14.6 131 7.57 107 7.95 69 31.1 97 6.51 55 5.92 121 11.4 118 4.36 108 3.41 89 8.81 94 3.06 66
TriangleFlow [30]92.2 7.35 78 28.2 74 4.31 79 5.35 83 25.2 78 3.36 53 8.00 67 24.8 72 2.70 39 3.90 54 24.1 63 1.97 63 12.9 137 17.8 143 10.7 129 13.1 122 32.3 106 13.9 124 4.71 113 16.1 139 4.04 106 3.65 96 8.73 92 5.69 104
DF-Auto [115]93.5 9.74 106 34.1 98 4.36 82 14.1 118 31.9 115 15.4 119 15.6 113 33.1 108 23.6 118 5.94 100 27.3 94 3.59 98 10.4 123 14.8 134 6.97 98 3.80 3 21.1 25 2.46 3 5.25 118 11.4 118 0.49 49 4.33 106 10.4 112 4.33 87
CNN-flow-warp+ref [117]94.2 9.81 109 35.7 101 7.67 113 8.14 103 26.0 86 8.55 105 14.3 108 35.8 111 15.7 109 6.69 108 30.3 112 4.31 107 9.17 101 12.2 91 8.71 121 7.03 43 29.6 90 5.55 26 0.69 39 3.77 29 2.00 84 7.79 126 12.1 124 8.13 116
p-harmonic [29]94.4 8.47 91 36.3 103 7.17 111 5.27 80 24.1 72 4.39 91 11.2 97 31.4 99 8.13 101 7.18 112 32.4 118 5.24 114 8.04 74 11.1 67 6.89 96 9.82 98 36.4 121 10.6 114 2.61 92 5.51 72 0.54 52 4.07 103 9.01 99 4.34 88
ContinualFlow_ROB [152]95.1 15.9 122 42.0 117 9.15 118 15.5 121 32.1 116 16.9 121 19.1 119 43.0 124 24.3 119 6.50 106 26.2 86 3.53 96 9.84 114 13.0 108 6.92 97 13.8 125 33.9 112 17.4 132 0.57 32 5.33 66 0.32 43 1.46 33 4.29 44 0.68 11
FlowNet2 [122]97.4 21.7 132 43.8 120 13.5 124 24.6 134 42.3 133 27.3 134 19.8 120 40.5 118 29.9 127 8.21 119 23.6 59 5.39 116 9.85 115 12.6 97 8.54 116 8.76 84 28.9 85 5.89 34 2.77 94 15.5 138 0.81 60 1.28 20 4.68 51 0.26 8
FlowNetS+ft+v [112]98.1 7.57 82 29.4 80 3.96 72 7.50 99 26.6 94 6.48 101 14.3 108 32.7 106 17.5 112 7.55 113 31.3 114 5.28 115 10.5 125 14.7 132 7.49 106 6.75 40 27.8 79 6.97 72 4.01 108 8.84 102 6.77 120 3.52 91 9.71 106 3.61 78
CompactFlow_ROB [159]98.2 23.6 134 47.8 127 9.55 119 13.6 115 31.6 113 14.9 116 22.7 126 48.3 129 36.1 137 8.92 121 28.6 107 5.54 117 9.61 106 13.2 111 6.45 94 8.97 91 34.7 115 8.76 98 0.29 4 2.81 10 0.10 22 3.17 84 7.86 80 3.76 80
EAI-Flow [151]99.2 18.4 124 42.5 118 11.6 121 10.8 110 32.2 117 9.62 110 14.3 108 38.9 117 14.0 106 7.07 111 28.6 107 5.13 113 8.20 79 11.9 81 5.47 81 9.21 93 30.7 95 9.05 101 9.33 136 6.96 93 0.49 49 2.48 66 7.31 74 3.20 71
LDOF [28]99.5 8.22 88 31.4 89 4.08 73 7.64 101 29.4 104 5.87 99 10.7 94 30.3 97 7.99 100 7.80 116 36.8 125 4.86 111 9.14 100 12.4 94 8.24 113 8.58 80 32.0 104 8.38 95 1.75 83 5.26 64 5.02 111 5.52 113 12.9 128 6.04 107
SegOF [10]99.9 12.6 114 34.9 100 7.20 112 21.3 128 36.9 125 25.3 132 21.6 124 40.5 118 31.8 131 14.1 130 37.7 127 10.8 125 10.3 121 12.5 95 12.6 135 10.2 100 40.2 129 11.2 116 0.29 4 2.91 12 0.07 16 2.90 76 8.68 91 2.07 36
Fusion [6]100.1 8.51 92 37.6 109 6.69 108 3.62 29 20.0 39 3.08 44 6.82 58 22.6 61 6.47 82 5.78 97 31.3 114 4.29 106 11.2 133 14.7 132 10.6 128 14.0 126 35.2 116 15.0 128 7.88 131 14.3 135 2.22 87 5.35 112 11.0 117 8.56 118
AugFNG_ROB [143]100.4 18.1 123 47.6 126 10.8 120 23.9 132 39.8 131 28.6 135 22.8 128 49.1 130 29.3 125 7.57 114 25.0 68 4.54 110 9.90 117 12.8 103 8.92 122 8.31 75 33.8 109 8.19 91 0.76 44 7.01 94 0.25 37 2.80 72 7.45 75 1.85 28
EPMNet [133]101.3 21.3 131 48.9 131 14.5 126 23.2 131 44.2 135 25.1 131 18.8 118 37.9 115 28.4 123 8.92 121 27.5 100 5.90 119 9.85 115 12.6 97 8.54 116 8.76 84 28.9 85 5.89 34 1.98 86 11.4 118 0.59 54 2.36 62 8.59 89 0.63 10
ResPWCR_ROB [144]102.8 18.8 125 53.9 135 13.5 124 8.80 105 29.4 104 8.15 104 12.6 102 36.0 112 12.1 104 7.61 115 32.2 117 5.71 118 8.07 75 10.4 47 8.08 110 9.68 96 34.5 114 10.3 110 3.74 105 9.01 105 1.82 81 3.35 88 8.20 83 4.45 89
WOLF_ROB [148]103.0 11.7 111 48.4 128 5.18 100 12.5 113 38.6 128 8.94 106 18.0 117 43.3 125 13.5 105 7.96 117 30.5 113 5.97 121 8.25 81 11.4 73 6.75 95 10.9 104 36.1 120 10.2 109 0.72 42 4.15 38 1.28 72 5.67 114 11.0 117 10.2 122
Learning Flow [11]103.0 6.74 69 28.1 73 3.03 48 6.37 92 28.7 103 5.02 94 11.8 99 32.6 105 7.93 99 6.87 110 33.2 122 4.32 108 12.5 136 17.4 141 7.78 108 9.98 99 35.2 116 8.41 96 2.66 93 10.9 114 2.24 88 6.76 120 13.7 130 6.41 109
StereoFlow [44]105.0 58.0 150 76.4 150 63.7 147 51.8 149 66.9 150 48.3 145 51.0 150 73.0 149 41.6 142 63.5 149 83.4 150 56.7 147 13.3 139 13.7 121 19.1 142 3.63 2 20.4 18 2.73 4 0.26 1 2.49 5 0.05 13 4.06 102 8.57 88 5.81 106
Second-order prior [8]105.3 7.35 78 31.2 88 4.16 76 6.80 95 29.5 106 5.27 96 11.8 99 33.3 109 7.78 98 6.05 101 27.2 93 3.90 104 9.67 109 13.8 124 5.74 85 14.0 126 41.8 132 11.7 118 6.86 124 9.72 109 7.61 125 4.72 108 10.1 110 7.78 114
Ad-TV-NDC [36]105.9 21.2 130 36.8 104 34.1 141 25.9 136 38.5 127 29.9 136 23.5 130 41.0 120 27.1 120 13.3 127 32.4 118 13.3 130 8.75 90 13.2 111 3.82 32 7.43 51 25.1 61 6.92 71 1.50 77 4.84 54 0.34 44 17.1 144 15.9 140 37.2 148
HBpMotionGpu [43]106.6 11.7 111 32.8 95 6.34 107 18.9 125 35.4 123 22.0 128 22.3 125 42.7 123 31.1 130 5.62 92 26.7 91 3.31 91 9.47 104 13.0 108 8.55 118 8.68 81 31.2 99 5.58 27 6.88 126 11.9 123 0.64 55 7.67 125 11.4 120 15.2 131
Shiralkar [42]108.6 9.76 107 46.6 124 4.40 83 6.53 94 31.3 112 4.04 83 12.7 104 37.5 114 5.34 72 6.47 105 32.9 121 4.34 109 8.33 82 11.9 81 5.58 83 17.4 134 43.3 135 15.5 130 6.82 123 8.77 101 14.0 132 7.36 123 15.7 139 7.83 115
StereoOF-V1MT [119]108.9 9.29 98 44.8 122 4.17 77 7.22 98 34.5 120 3.68 73 13.7 105 42.6 122 3.80 61 6.06 102 38.5 129 3.27 87 11.0 130 15.1 136 9.55 126 15.1 130 49.9 139 14.0 125 1.08 59 5.51 72 5.44 114 9.33 132 15.5 135 9.73 121
LFNet_ROB [149]109.4 20.5 129 60.8 140 12.8 123 10.1 108 31.7 114 9.00 107 20.6 122 53.4 133 14.0 106 9.26 123 32.6 120 7.53 122 9.83 113 13.2 111 8.22 112 11.5 112 37.7 123 11.3 117 1.13 62 6.72 88 0.74 57 3.50 90 8.77 93 5.19 101
SPSA-learn [13]110.6 15.7 120 48.8 129 16.5 128 16.6 122 35.0 122 17.5 123 21.4 123 42.3 121 29.7 126 12.6 125 37.4 126 12.3 128 9.64 107 12.8 103 9.16 123 11.0 105 37.9 125 12.2 120 0.98 53 3.88 31 0.05 13 8.38 129 11.6 122 15.2 131
Filter Flow [19]112.4 14.6 116 38.2 114 8.96 117 12.4 112 34.6 121 11.3 112 20.2 121 38.3 116 30.1 128 19.2 132 43.4 133 18.6 133 10.0 118 13.4 115 9.43 125 10.3 101 31.4 100 9.08 102 8.21 133 19.6 144 0.79 59 3.72 98 6.85 71 3.41 76
Modified CLG [34]113.3 15.7 120 43.7 119 12.2 122 19.1 126 33.3 119 23.7 129 25.1 131 47.4 128 35.6 136 13.2 126 35.5 124 11.1 126 10.7 127 14.4 129 9.36 124 7.26 46 35.8 119 6.19 46 1.66 81 5.21 63 6.43 117 5.94 117 13.8 132 7.73 113
IAOF2 [51]113.5 8.72 95 30.9 86 5.32 103 13.9 117 31.1 111 15.4 119 14.1 107 33.0 107 18.2 113 30.8 141 42.2 132 36.4 143 9.74 111 13.8 124 6.09 92 12.0 117 33.4 107 7.96 89 7.92 132 13.9 133 7.49 124 5.69 115 10.6 115 4.51 91
GraphCuts [14]113.6 12.6 114 36.1 102 5.46 105 14.7 119 39.4 130 12.5 113 17.8 116 35.6 110 29.1 124 6.86 109 33.7 123 4.15 105 9.33 102 12.6 97 8.69 120 23.0 140 31.6 101 15.5 130 3.52 101 7.38 97 11.7 130 5.33 110 9.87 109 8.75 119
2D-CLG [1]114.8 24.4 135 51.8 134 19.4 132 27.4 137 38.7 129 33.8 139 34.6 138 57.7 137 42.2 144 33.4 143 57.1 144 32.9 142 9.64 107 12.2 91 11.0 131 11.2 108 40.2 129 12.8 122 0.31 8 2.62 7 0.25 37 6.33 118 13.7 130 7.33 112
TVL1_ROB [138]115.7 36.9 142 55.3 136 54.3 146 36.5 141 40.3 132 46.0 143 36.6 140 59.4 140 43.5 147 30.0 140 49.3 137 31.8 140 9.70 110 13.7 121 7.19 105 7.34 49 33.4 107 7.88 87 0.56 31 3.98 33 0.10 22 15.1 141 15.9 140 33.3 146
BlockOverlap [61]117.1 12.3 113 29.2 78 8.49 116 13.7 116 29.6 107 15.3 118 16.2 115 32.5 104 20.0 114 8.87 120 27.4 97 7.62 123 10.9 129 13.4 115 12.5 134 13.3 123 29.1 88 10.3 110 11.8 141 14.4 136 23.8 143 10.6 135 8.92 96 24.8 140
IAOF [50]119.7 14.7 117 37.8 112 14.8 127 17.3 124 33.2 118 18.7 124 22.7 126 44.3 126 23.3 117 20.9 134 38.7 130 24.5 137 9.60 105 13.3 114 8.28 115 13.0 121 38.8 127 7.37 83 4.20 110 7.90 99 2.59 93 14.5 140 13.4 129 32.0 145
2bit-BM-tele [98]121.3 20.3 128 39.1 116 26.1 136 8.84 106 26.8 96 9.29 108 11.1 96 30.7 98 7.60 96 8.06 118 29.9 111 5.91 120 11.0 130 13.7 121 11.8 133 18.0 135 37.1 122 19.8 137 17.1 146 20.4 146 30.8 146 6.54 119 11.7 123 11.8 125
Black & Anandan [4]121.6 15.1 119 45.4 123 18.1 131 16.6 122 36.3 124 16.9 121 23.3 129 44.9 127 27.8 121 13.5 128 38.1 128 13.1 129 11.1 132 15.7 137 7.97 109 11.6 115 39.6 128 11.0 115 5.17 117 9.06 106 2.27 89 7.28 122 12.3 125 10.2 122
UnFlow [129]122.7 45.7 147 58.8 137 25.7 135 28.2 138 44.0 134 31.2 138 38.6 145 68.3 147 37.0 139 19.4 133 46.0 134 16.6 132 13.8 141 14.9 135 18.2 141 20.9 138 49.2 138 23.5 139 2.86 95 6.76 89 0.22 34 3.12 83 10.4 112 2.27 41
GroupFlow [9]123.6 22.9 133 47.1 125 26.7 139 28.4 139 50.0 141 30.8 137 25.4 132 52.4 132 30.6 129 9.32 124 29.6 110 8.14 124 10.7 127 13.4 115 7.16 104 23.0 140 46.3 136 27.8 143 1.56 78 5.72 77 2.76 95 8.00 127 12.5 126 15.3 133
Nguyen [33]123.9 20.0 127 44.7 121 17.4 130 39.5 145 37.5 126 52.5 146 34.0 137 56.0 136 38.8 140 35.6 144 47.9 136 41.1 144 12.1 134 14.3 127 16.5 139 12.0 117 37.8 124 13.8 123 1.37 72 4.27 41 0.71 56 11.6 138 14.5 134 20.8 137
SILK [79]129.3 26.9 136 51.7 133 36.6 143 22.3 130 45.5 137 24.5 130 28.8 133 54.7 135 34.2 132 18.4 131 41.6 131 15.8 131 13.1 138 16.5 138 16.1 138 19.1 137 47.8 137 19.3 136 2.87 96 4.22 39 6.53 118 15.9 142 19.1 142 25.8 141
Heeger++ [104]130.7 42.8 145 66.4 149 26.2 137 25.0 135 60.7 149 19.8 127 38.4 144 66.9 144 28.0 122 23.5 136 49.3 137 19.7 134 10.6 126 13.4 115 8.12 111 40.8 148 67.2 150 45.1 148 2.04 88 10.9 114 1.70 79 11.2 136 15.6 136 12.8 127
H+S_ROB [137]131.8 35.2 140 65.0 146 26.4 138 38.8 144 57.8 148 44.7 142 46.2 149 74.1 150 43.1 146 64.3 150 66.9 147 69.3 149 17.9 146 19.2 146 29.2 148 30.3 146 59.6 147 34.1 145 0.49 25 4.67 48 0.20 31 22.3 148 23.4 145 21.4 138
Horn & Schunck [3]132.1 19.9 126 61.0 142 23.3 133 19.4 127 44.3 136 19.1 125 29.5 134 58.8 139 34.9 134 21.0 135 49.9 139 21.2 135 12.3 135 16.5 138 10.8 130 17.3 133 50.6 141 18.0 134 7.23 129 11.9 123 2.34 90 13.4 139 22.2 144 14.9 130
Periodicity [78]136.2 30.6 139 48.8 129 16.7 129 24.1 133 49.8 139 26.2 133 39.1 146 54.5 134 39.5 141 13.6 129 47.1 135 12.0 127 37.5 150 48.2 150 33.6 149 38.5 147 66.9 149 36.0 147 2.02 87 10.8 112 8.18 126 20.8 145 35.9 149 30.1 143
FFV1MT [106]136.8 39.5 143 59.3 138 25.4 134 21.8 129 56.3 147 19.1 125 38.0 143 67.0 145 34.9 134 24.3 137 55.7 143 22.2 136 17.7 145 18.9 145 25.5 146 41.8 149 66.3 148 45.5 149 3.73 103 12.9 130 6.35 116 11.2 136 15.6 136 12.8 127
TI-DOFE [24]137.2 44.7 146 66.3 148 66.5 149 44.2 147 50.5 142 54.8 148 43.5 148 72.0 148 44.7 148 48.6 146 63.3 145 54.0 146 13.6 140 17.7 142 15.1 137 17.2 131 50.3 140 19.0 135 3.07 98 5.50 71 2.93 99 21.5 146 24.7 147 33.9 147
SLK [47]138.5 28.9 138 63.3 145 36.4 142 42.3 146 54.0 146 52.8 147 36.6 140 67.7 146 42.5 145 51.4 147 54.3 142 60.0 148 14.5 143 16.7 140 20.8 144 21.5 139 53.4 145 24.1 140 3.92 107 6.27 83 5.91 115 21.7 147 23.7 146 31.5 144
Adaptive flow [45]141.5 49.6 148 62.1 143 66.8 150 37.4 142 46.5 138 43.1 141 34.9 139 58.6 138 41.7 143 27.3 139 53.5 141 28.7 138 16.1 144 18.2 144 17.6 140 25.3 144 52.9 143 25.1 142 45.4 149 38.1 149 74.4 148 9.25 131 14.4 133 13.9 129
PGAM+LK [55]142.1 35.2 140 65.7 147 44.1 145 31.5 140 51.1 143 36.1 140 30.9 135 60.0 142 36.8 138 33.0 142 72.3 149 32.7 141 13.8 141 14.4 129 22.6 145 24.6 142 53.2 144 24.6 141 27.1 147 32.6 148 26.2 144 17.0 143 20.4 143 28.4 142
FOLKI [16]142.3 27.4 137 59.9 139 40.6 144 37.4 142 51.5 144 46.6 144 32.4 136 61.6 143 34.2 132 26.3 138 50.6 140 30.2 139 18.2 148 19.7 147 26.3 147 24.6 142 56.6 146 28.8 144 10.3 139 13.9 133 26.7 145 27.1 149 26.9 148 45.3 149
HCIC-L [99]142.9 51.6 149 60.9 141 30.9 140 58.4 150 53.4 145 73.0 150 39.8 147 50.8 131 52.8 150 63.4 148 71.0 148 69.9 150 18.1 147 20.6 148 20.5 143 29.9 145 43.2 133 34.1 145 73.0 150 62.0 150 76.4 149 7.45 124 12.5 126 8.87 120
Pyramid LK [2]146.1 41.0 144 62.5 144 66.4 148 47.2 148 49.9 140 59.7 149 37.5 142 59.5 141 45.5 149 43.8 145 65.1 146 49.5 145 36.5 149 43.8 149 42.6 150 43.3 150 52.8 142 45.9 150 11.8 141 20.2 145 20.7 140 40.0 150 46.5 150 59.5 150
AVG_FLOW_ROB [141]151.7 99.3 151 98.3 168 99.2 151 99.8 151 100.0 151 99.7 151 99.9 151 99.9 151 99.9 151 98.3 151 96.8 151 98.0 151 96.2 151 96.6 151 93.9 151 87.7 151 86.6 151 88.2 151 96.9 151 84.2 151 98.7 151 93.0 151 98.4 151 95.3 151
AdaConv-v1 [126]151.8 99.3 151 97.8 151 99.8 152 99.9 152 100.0 151 99.8 152 99.9 151 99.9 151 99.9 151 99.5 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.1 152 98.9 152 99.7 152 98.5 152 93.0 152 100.0 152 99.9 152 99.9 152 99.9 152
SepConv-v1 [127]151.8 99.3 151 97.8 151 99.8 152 99.9 152 100.0 151 99.8 152 99.9 151 99.9 151 99.9 151 99.5 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.1 152 98.9 152 99.7 152 98.5 152 93.0 152 100.0 152 99.9 152 99.9 152 99.9 152
SuperSlomo [132]151.8 99.3 151 97.8 151 99.8 152 99.9 152 100.0 151 99.8 152 99.9 151 99.9 151 99.9 151 99.5 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.1 152 98.9 152 99.7 152 98.5 152 93.0 152 100.0 152 99.9 152 99.9 152 99.9 152
CtxSyn [136]151.8 99.3 151 97.8 151 99.8 152 99.9 152 100.0 151 99.8 152 99.9 151 99.9 151 99.9 151 99.5 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.1 152 98.9 152 99.7 152 98.5 152 93.0 152 100.0 152 99.9 152 99.9 152 99.9 152
CyclicGen [153]151.8 99.3 151 97.8 151 99.8 152 99.9 152 100.0 151 99.8 152 99.9 151 99.9 151 99.9 151 99.5 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.1 152 98.9 152 99.7 152 98.5 152 93.0 152 100.0 152 99.9 152 99.9 152 99.9 152
TOF-M [154]151.8 99.3 151 97.8 151 99.8 152 99.9 152 100.0 151 99.8 152 99.9 151 99.9 151 99.9 151 99.5 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.1 152 98.9 152 99.7 152 98.5 152 93.0 152 100.0 152 99.9 152 99.9 152 99.9 152
MPRN [155]151.8 99.3 151 97.8 151 99.8 152 99.9 152 100.0 151 99.8 152 99.9 151 99.9 151 99.9 151 99.5 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.1 152 98.9 152 99.7 152 98.5 152 93.0 152 100.0 152 99.9 152 99.9 152 99.9 152
DAIN [156]151.8 99.3 151 97.8 151 99.8 152 99.9 152 100.0 151 99.8 152 99.9 151 99.9 151 99.9 151 99.5 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.1 152 98.9 152 99.7 152 98.5 152 93.0 152 100.0 152 99.9 152 99.9 152 99.9 152
FRUCnet [157]151.8 99.3 151 97.8 151 99.8 152 99.9 152 100.0 151 99.8 152 99.9 151 99.9 151 99.9 151 99.5 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.1 152 98.9 152 99.7 152 98.5 152 93.0 152 100.0 152 99.9 152 99.9 152 99.9 152
OFRI [158]151.8 99.3 151 97.8 151 99.8 152 99.9 152 100.0 151 99.8 152 99.9 151 99.9 151 99.9 151 99.5 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.1 152 98.9 152 99.7 152 98.5 152 93.0 152 100.0 152 99.9 152 99.9 152 99.9 152
PyrWarp [161]151.8 99.3 151 97.8 151 99.8 152 99.9 152 100.0 151 99.8 152 99.9 151 99.9 151 99.9 151 99.5 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.1 152 98.9 152 99.7 152 98.5 152 93.0 152 100.0 152 99.9 152 99.9 152 99.9 152
FGME [163]151.8 99.3 151 97.8 151 99.8 152 99.9 152 100.0 151 99.8 152 99.9 151 99.9 151 99.9 151 99.5 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.1 152 98.9 152 99.7 152 98.5 152 93.0 152 100.0 152 99.9 152 99.9 152 99.9 152
MS-PFT [164]151.8 99.3 151 97.8 151 99.8 152 99.9 152 100.0 151 99.8 152 99.9 151 99.9 151 99.9 151 99.5 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.1 152 98.9 152 99.7 152 98.5 152 93.0 152 100.0 152 99.9 152 99.9 152 99.9 152
MEMC-Net+ [165]151.8 99.3 151 97.8 151 99.8 152 99.9 152 100.0 151 99.8 152 99.9 151 99.9 151 99.9 151 99.5 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.1 152 98.9 152 99.7 152 98.5 152 93.0 152 100.0 152 99.9 152 99.9 152 99.9 152
ADC [166]151.8 99.3 151 97.8 151 99.8 152 99.9 152 100.0 151 99.8 152 99.9 151 99.9 151 99.9 151 99.5 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.1 152 98.9 152 99.7 152 98.5 152 93.0 152 100.0 152 99.9 152 99.9 152 99.9 152
DSepConv [167]151.8 99.3 151 97.8 151 99.8 152 99.9 152 100.0 151 99.8 152 99.9 151 99.9 151 99.9 151 99.5 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.1 152 98.9 152 99.7 152 98.5 152 93.0 152 100.0 152 99.9 152 99.9 152 99.9 152
MAF-net [168]151.8 99.3 151 97.8 151 99.8 152 99.9 152 100.0 151 99.8 152 99.9 151 99.9 151 99.9 151 99.5 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.1 152 98.9 152 99.7 152 98.5 152 93.0 152 100.0 152 99.9 152 99.9 152 99.9 152
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 T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011.
[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 D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011.
[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 A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011.
[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 L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013.
[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 M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to 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 W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013.
[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] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[76] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[77] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[78] Periodicity 8000 4 color G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013.
[79] SILK 572 2 gray P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP.
[80] 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.
[81] SuperFlow 178 2 color Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507.
[82] Aniso-Texture 300 2 color Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267.
[83] Classic+CPF 640 2 gray Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013.
[84] S2D-Matching 1200 2 color Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479.
[85] AGIF+OF 438 2 gray Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015.
[86] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[87] NNF-Local 673 2 color Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014.
[88] 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.
[89] 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.
[90] 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.
[91] 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.
[92] 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.
[93] 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.
[94] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[95] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[96] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[97] 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.
[98] 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.
[99] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[100] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[101] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[102] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[103] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[104] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[105] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[106] 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.
[107] 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.
[108] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[109] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[110] 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.
[111] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[112] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[113] 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.)
[114] 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.
[115] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[116] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[117] 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.
[118] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[119] 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.
[120] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[121] 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.
[122] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[123] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[124] 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.
[125] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[126] AdaConv-v1 2.8 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[127] SepConv-v1 0.2 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[128] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[129] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[130] 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.
[131] 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.
[132] 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.
[133] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[134] 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.
[135] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
[136] CtxSyn 0.07 2 color S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[137] H+S_ROB 5 2 color ROB 2018 baseline submission, based on: E. Meinhardt-Llopis, J. Sanchez, and D. Kondermann. Horn-Schunck optical flow with a multi-scale strategy. Image Processing On Line 3:151–172, 2013.
[138] TVL1_ROB 1 2 color ROB 2018 baseline submission, based on: J. Sanchez, E. Meinhardt-Llopis, and G. Facciolo. TV-L1 optical flow estimation. Image Processing On Line 3:137-150, 2013.
[139] 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.
[140] 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.
[141] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[142] 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.
[143] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[144] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[145] 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.
[146] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[147] PWC-Net_ROB 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.
[148] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[149] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
[150] 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.
[151] 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.
[152] ContinualFlow_ROB 0.5 all color M Neoral, J. Sochman, and J. Matas. Continual occlusions and optical flow estimation. ACCV 2018.
[153] CyclicGen 0.088 2 color Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
[154] TOF-M 0.393 2 color T. Xue, B. Chen, J. Wu, D. Wei, and W. Freeman. Video enhancement with task-oriented flow. arXiv 1711.09078, 2017.
[155] MPRN 0.32 4 color Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[156] DAIN 0.13 2 color Anonymous. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019 submission 1769.
[157] FRUCnet 0.65 2 color V. T. Nguyen, K. Lee, and H.-J. Lee. (Interpolation results only.) A stacked deep MEMC network for frame rate up conversion and its application to HEVC. Submitted to IEEE TCSVT 2019.
[158] OFRI 0.31 2 color Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
[159] CompactFlow_ROB 0.05 2 color Anonymous. CompactFlow: spatially shiftable window revisited. CVPR 2019 submission 1387.
[160] SegFlow 3.2 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. Efficient segmentation-based PatchMatch for large displacement optical flow estimation. IEEE TCSVT 2018.
[161] PyrWarp 0.14 2 color Anonymous. (Interpolation results only.) Video frame interpolation using differentiable forward-warping of feature pyramids. ICCV 2019 submission 741.
[162] HCFN 0.18 2 color Anonymous. Practical coarse-to-fine optical flow with deep networks. ICCV 2019 submission 116.
[163] FGME 0.23 2 color Anonymous. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. ICCV 2019 submission 4327.
[164] MS-PFT 0.44 2 color X. Cheng and Z. Chen. (Interpolation results only.) A multi-scale position feature transform network for video frame interpolation. Submitted to TCSVT 2019.
[165] MEMC-Net+ 0.12 2 color W. Bao, W.-S. Lai, X. Zhang, Z. Gao, and M.-H. Yang. (Interpolation results only.) MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement. Submitted to TPAMI 2018.
[166] ADC 0.01 2 color Anonymous. (Interpolation results only.) Learning spatial transform for video frame interpolation. ICCV 2019 submission 5424.
[167] DSepConv 0.3 2 color Anonymous. (Interpolation results only.) Video frame interpolation via deformable separable convolution. AAAI 2020 submission 2271.
[168] MAF-net 0.3 2 color Anonymous. (Interpolation results only.) MAF-net: Motion attention feedback network for video frame interpolation. AAAI 2020 submission 9862.
* 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.