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        
SD
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
NNF-Local [87]12.1 6.84 16 15.1 25 4.48 12 6.28 5 15.5 19 3.00 4 7.42 3 13.5 18 2.39 3 7.71 7 22.7 22 2.48 4 4.26 1 5.09 1 2.83 1 6.52 2 14.9 2 4.55 4 1.74 24 3.32 60 1.23 11 5.63 15 10.7 15 2.48 17
PMMST [114]12.4 6.46 4 14.1 4 3.23 1 5.42 1 12.7 15 3.51 14 8.20 9 14.7 23 3.66 14 7.46 4 17.8 4 4.34 6 4.79 14 5.67 9 3.91 23 6.77 3 15.2 4 3.61 2 1.74 24 3.36 63 1.34 15 5.95 20 11.3 20 2.25 2
NN-field [71]15.9 7.29 36 16.0 51 4.74 25 6.15 2 15.2 18 3.02 6 7.77 7 14.1 22 2.71 6 7.56 5 22.8 23 1.96 3 4.49 2 5.36 2 3.09 3 5.72 1 14.1 1 1.96 1 1.96 43 3.34 61 1.32 14 5.70 16 10.8 16 2.49 18
OFLAF [77]18.8 6.75 13 14.9 18 4.44 10 7.07 11 17.5 29 3.10 7 8.45 10 15.5 25 2.50 5 13.0 47 35.0 98 6.38 20 4.57 3 5.57 6 3.12 4 7.63 7 15.9 7 5.90 16 1.68 18 2.86 17 1.43 24 5.83 19 11.0 18 2.79 19
MDP-Flow2 [68]26.5 6.66 8 14.7 15 4.53 14 6.79 8 17.0 23 3.23 8 8.68 11 15.8 26 2.90 7 13.4 57 33.7 85 6.89 47 4.95 30 5.84 27 4.15 46 8.49 18 18.7 30 7.72 45 1.64 13 3.08 31 1.27 13 6.77 23 12.8 25 3.33 25
FC-2Layers-FF [74]29.2 7.07 25 15.5 36 4.91 31 8.30 34 19.7 50 4.30 23 7.61 5 13.6 19 4.29 25 11.8 21 30.2 43 6.20 18 4.60 4 5.54 3 3.52 7 9.20 33 18.3 24 6.27 23 2.20 64 3.42 72 1.85 50 7.54 29 14.3 31 4.12 32
nLayers [57]29.4 7.20 31 16.0 51 4.66 22 6.25 4 14.7 16 3.70 19 7.72 6 13.7 20 4.81 34 13.1 51 34.8 96 6.69 32 4.76 11 5.75 16 4.12 43 7.19 5 14.9 2 4.40 3 1.99 45 3.10 36 1.80 49 8.22 35 15.6 36 6.10 42
3DFlow [135]33.9 6.97 19 15.1 25 3.90 3 8.12 28 19.7 50 3.79 20 13.6 67 24.2 77 3.63 12 4.18 1 12.4 1 1.73 2 4.97 32 5.98 48 3.83 20 10.5 55 18.9 47 8.87 64 2.38 72 3.11 38 2.45 75 5.82 18 11.1 19 3.00 21
ComponentFusion [96]35.1 7.22 32 15.9 47 4.61 19 7.60 17 19.2 44 3.30 9 9.70 16 17.6 31 3.77 16 11.1 16 31.0 52 4.45 7 4.96 31 5.88 32 4.25 50 10.9 60 23.7 75 9.40 72 1.90 40 3.08 31 1.69 43 8.00 33 15.1 34 4.57 35
FESL [72]37.8 6.97 19 15.3 32 4.47 11 9.74 63 21.4 72 5.49 57 11.4 42 20.2 44 4.25 24 12.5 30 31.5 59 6.81 37 4.72 7 5.71 12 3.72 16 7.03 4 16.0 8 4.81 5 2.21 66 3.49 79 1.94 54 11.1 58 17.6 50 10.1 58
AGIF+OF [85]38.8 7.17 29 15.6 38 4.93 32 10.2 73 22.1 81 5.16 44 12.5 56 21.2 56 4.88 36 12.5 30 31.7 64 6.76 34 4.78 13 5.73 14 3.91 23 7.85 10 16.3 10 5.20 7 1.83 34 3.10 36 1.71 44 10.8 55 17.6 50 11.0 61
PWC-Net_ROB [147]38.8 8.30 81 16.2 59 6.58 91 8.56 39 20.6 59 4.38 26 12.3 53 21.4 58 6.00 55 10.8 12 27.0 31 6.88 46 4.94 28 5.79 22 3.98 29 8.37 17 19.3 49 5.42 11 1.65 16 3.29 58 1.02 4 7.86 32 14.2 30 3.37 26
NNF-EAC [103]39.6 6.83 15 14.9 18 4.80 26 7.59 16 18.0 31 4.31 24 9.03 13 16.1 27 3.09 9 13.2 54 32.2 69 7.10 54 5.06 49 5.96 41 4.02 33 8.19 14 17.1 11 6.04 20 1.79 30 3.30 59 1.38 21 17.0 97 27.6 101 18.0 118
Layers++ [37]39.8 7.19 30 15.7 40 5.08 38 6.15 2 14.8 17 3.42 12 7.83 8 14.0 21 4.84 35 10.9 14 26.9 30 6.19 17 4.83 18 5.84 27 4.36 55 12.4 82 25.2 88 10.5 87 2.43 73 3.56 84 1.92 53 8.66 38 16.1 38 7.77 49
Correlation Flow [75]40.4 6.66 8 14.5 10 3.81 2 7.78 22 17.5 29 2.85 2 18.0 102 29.0 112 4.31 27 9.28 9 22.1 21 5.57 12 5.12 53 6.13 73 3.98 29 11.0 63 23.3 70 10.5 87 2.07 54 3.08 31 2.32 70 6.79 24 12.5 23 4.83 36
Efficient-NL [60]41.0 7.43 50 16.2 59 4.85 27 7.73 20 18.1 32 4.58 29 14.0 73 23.6 73 4.47 29 13.1 51 32.9 78 7.50 68 4.77 12 5.77 20 3.65 12 8.08 12 16.1 9 5.25 8 2.48 77 3.37 65 3.12 94 6.91 25 12.1 21 5.78 40
PH-Flow [101]42.4 7.38 44 15.9 47 5.22 45 9.30 53 19.5 46 5.71 60 9.62 15 17.2 29 5.09 37 13.4 57 34.5 91 7.10 54 4.82 15 5.73 14 3.82 19 8.36 16 17.1 11 5.35 10 2.66 82 3.43 74 3.42 103 7.13 28 13.3 28 5.33 39
IROF++ [58]42.6 7.44 51 16.1 55 5.11 40 8.61 41 19.4 45 5.12 42 12.3 53 21.0 54 5.12 38 12.8 41 32.1 66 7.13 56 4.88 21 5.76 18 3.89 22 9.01 23 18.9 47 6.76 31 1.78 29 3.22 52 1.23 11 10.4 52 18.5 57 13.3 77
LME [70]43.2 7.04 23 15.6 38 4.53 14 6.68 6 16.9 22 2.85 2 13.6 67 22.6 65 12.0 123 11.5 19 27.8 32 6.39 21 5.03 42 5.93 38 4.52 64 12.4 82 27.0 102 10.9 94 1.76 27 3.38 66 1.43 24 6.62 22 12.5 23 2.86 20
NL-TV-NCC [25]44.3 6.92 18 14.6 14 3.96 5 8.32 35 19.8 54 2.84 1 15.4 84 26.0 89 3.92 19 10.8 12 26.6 27 5.58 13 5.09 50 6.00 51 4.07 36 11.1 66 23.5 71 10.5 87 2.09 55 3.06 29 2.27 68 11.6 61 20.4 64 9.14 54
Classic+CPF [83]44.6 7.31 38 15.8 43 5.09 39 9.93 68 22.1 81 5.05 40 13.3 64 22.4 64 4.64 32 12.5 30 32.0 65 6.79 36 4.87 20 5.83 26 3.99 31 7.43 6 15.6 6 5.32 9 2.26 68 3.21 50 2.78 86 9.89 48 16.5 40 13.8 80
CombBMOF [113]44.6 7.30 37 15.1 25 4.61 19 8.08 27 18.2 34 3.69 18 10.2 20 18.1 34 2.47 4 11.2 17 28.1 33 6.67 29 4.82 15 5.76 18 4.13 44 13.3 94 22.1 61 14.1 121 2.90 93 4.33 111 2.14 61 11.8 64 21.0 68 3.23 24
LSM [39]44.7 7.06 24 15.2 30 5.21 44 9.65 61 21.2 71 5.48 56 11.9 48 20.2 44 5.33 43 12.0 22 30.0 41 6.84 41 5.14 58 6.13 73 4.62 70 9.12 29 18.1 21 6.53 27 2.13 60 3.11 38 2.11 60 8.09 34 14.3 31 6.76 46
TC/T-Flow [76]44.8 6.31 2 13.3 2 4.85 27 11.5 104 23.6 96 6.67 78 13.4 66 23.2 71 3.00 8 14.2 74 36.9 119 6.33 19 4.72 7 5.64 7 3.64 10 7.70 8 17.1 11 5.61 15 2.00 46 3.45 77 2.86 88 10.9 57 18.2 55 3.59 28
MLDP_OF [89]45.0 7.02 21 14.5 10 4.89 30 7.00 10 17.0 23 3.34 10 14.3 75 24.0 74 3.73 15 12.9 44 34.8 96 5.88 14 4.89 23 5.69 10 3.92 26 8.18 13 17.4 15 7.22 43 3.64 114 3.68 89 5.99 130 13.2 74 20.5 66 9.16 55
Sparse-NonSparse [56]45.5 7.26 35 15.7 40 5.22 45 9.83 65 21.6 75 5.45 55 12.2 50 20.8 50 5.35 46 12.1 25 30.0 41 6.86 43 5.14 58 6.13 73 4.58 67 9.16 31 18.5 27 6.58 28 2.05 52 3.03 26 2.06 59 7.62 30 13.8 29 5.98 41
HAST [109]46.0 7.11 27 16.0 51 4.27 6 8.90 45 17.4 28 7.54 89 6.79 1 12.4 15 1.56 1 14.8 80 37.2 120 6.63 25 4.68 6 5.70 11 2.91 2 10.5 55 20.7 53 11.1 95 3.74 118 4.39 114 5.40 128 5.74 17 10.9 17 2.09 1
WLIF-Flow [93]46.2 6.80 14 14.9 18 4.60 18 6.93 9 16.7 21 4.11 22 10.3 21 18.2 35 4.11 23 12.7 39 30.9 50 6.67 29 6.60 135 7.87 139 5.60 109 8.54 19 17.4 15 6.03 19 1.85 35 3.18 47 1.67 41 14.4 80 23.2 81 15.3 89
HCFN [163]46.6 6.51 6 14.1 4 4.64 21 8.25 31 20.6 59 4.51 27 10.1 19 18.2 35 4.68 33 13.4 57 35.1 100 6.09 15 4.73 10 5.55 4 3.64 10 8.77 21 18.6 28 7.20 41 4.73 135 5.10 130 5.62 129 11.6 61 19.6 60 14.0 82
Ramp [62]47.0 7.32 40 15.8 43 5.20 43 8.74 42 19.8 54 5.27 50 11.4 42 19.7 43 5.40 49 12.5 30 31.6 62 6.86 43 4.97 32 5.88 32 4.08 38 9.04 24 18.3 24 7.00 38 2.65 81 3.36 63 4.00 117 8.65 37 15.3 35 11.7 66
PMF [73]47.7 7.59 56 16.5 82 4.94 33 7.64 18 18.3 37 3.66 16 7.48 4 13.2 17 2.31 2 14.7 79 36.3 115 6.84 41 4.66 5 5.64 7 3.18 6 9.85 39 21.3 56 9.22 68 3.62 113 5.25 136 3.70 113 7.12 27 13.2 27 6.82 47
Classic+NL [31]48.7 7.40 47 16.1 55 5.36 55 9.49 60 20.9 65 5.44 54 12.3 53 20.8 50 5.20 41 12.5 30 31.3 58 6.82 38 5.03 42 5.98 48 4.18 48 8.94 22 17.5 17 5.91 17 2.29 70 3.44 76 2.17 62 9.88 47 17.0 46 11.9 68
FlowFields+ [130]49.6 8.95 94 17.2 100 7.26 103 7.52 15 17.3 26 5.15 43 10.4 22 17.6 31 6.16 56 10.1 10 24.5 24 6.49 23 5.11 52 6.00 51 4.57 66 9.28 34 22.2 62 6.70 30 1.77 28 3.20 48 1.51 35 13.1 73 21.8 72 15.6 92
CostFilter [40]49.9 7.36 42 15.7 40 4.96 35 7.76 21 18.1 32 3.83 21 7.07 2 12.4 15 3.12 10 14.6 78 36.3 115 6.57 24 4.82 15 5.81 24 3.54 8 12.4 82 20.5 52 10.3 85 3.86 123 5.96 140 4.36 120 8.86 41 16.7 43 3.72 30
FMOF [94]51.6 7.14 28 15.5 36 5.28 49 10.4 90 22.7 87 5.42 51 10.8 37 19.0 41 3.90 18 12.2 27 31.0 52 6.63 25 4.98 35 5.97 42 4.10 39 10.0 46 17.2 14 6.98 36 2.46 75 3.40 69 4.60 121 14.7 82 23.2 81 10.1 58
TV-L1-MCT [64]52.8 7.42 49 16.1 55 5.22 45 9.84 66 21.6 75 5.20 46 14.3 75 24.7 80 5.27 42 12.5 30 31.2 57 7.21 59 5.01 38 5.90 34 4.41 58 9.10 27 18.8 46 7.14 40 2.17 63 2.78 6 4.69 122 9.81 46 16.8 45 11.5 63
SVFilterOh [111]53.2 7.94 63 17.5 106 4.94 33 8.27 33 19.8 54 3.66 16 9.83 18 17.7 33 4.59 30 13.4 57 34.5 91 6.82 38 4.89 23 5.93 38 3.15 5 10.4 53 22.7 64 9.35 71 3.51 110 4.72 124 4.17 118 7.68 31 14.3 31 4.90 37
ProbFlowFields [128]53.2 8.84 92 17.9 112 6.90 96 7.20 13 17.3 26 4.75 36 11.6 45 20.5 48 6.31 60 8.48 8 22.0 20 5.26 10 5.25 78 6.24 92 4.67 79 9.96 44 23.9 79 6.99 37 1.64 13 2.80 8 1.41 22 14.7 82 25.5 92 14.7 85
RNLOD-Flow [121]53.5 6.72 11 14.9 18 4.39 8 9.09 48 21.0 67 5.06 41 15.2 82 25.8 85 5.42 50 12.6 37 32.2 69 6.64 27 5.46 97 6.48 108 4.34 54 8.35 15 17.8 19 6.16 22 2.82 88 3.90 100 3.36 101 9.02 42 16.1 38 9.83 56
WRT [150]53.5 7.40 47 15.9 47 3.93 4 9.33 54 21.1 69 3.42 12 21.1 126 31.0 132 6.88 68 4.33 2 13.0 3 1.43 1 4.84 19 5.80 23 4.44 60 13.6 98 21.4 58 10.8 92 1.71 22 2.85 14 1.65 40 16.7 94 20.4 64 20.8 135
IIOF-NLDP [131]54.0 7.31 38 15.4 33 4.42 9 8.37 36 19.9 57 3.01 5 15.4 84 25.9 87 4.00 21 7.56 5 18.6 19 4.73 8 6.04 121 7.28 133 5.15 96 10.1 47 21.3 56 9.54 74 1.74 24 2.90 20 1.50 32 15.8 87 21.6 71 20.5 132
Complementary OF [21]54.7 7.37 43 15.1 25 5.30 52 9.46 56 22.5 85 4.63 30 13.0 59 22.8 67 4.04 22 14.8 80 37.9 129 6.87 45 4.97 32 5.86 29 4.39 57 11.0 63 24.4 83 8.06 52 1.79 30 2.79 7 2.22 65 12.2 65 22.0 75 11.2 62
EPPM w/o HM [88]55.5 7.33 41 14.5 10 5.00 37 7.20 13 17.2 25 3.41 11 11.8 46 20.8 50 3.20 11 12.6 37 31.1 56 7.00 51 5.14 58 6.08 65 4.67 79 12.0 76 22.7 64 9.97 81 4.48 134 3.69 91 6.02 131 10.4 52 17.6 50 11.5 63
ALD-Flow [66]55.9 6.69 10 14.4 9 4.54 16 12.5 115 25.7 110 6.93 82 14.3 75 24.9 81 4.29 25 14.8 80 35.3 105 7.04 52 4.98 35 5.92 36 3.66 13 10.1 47 23.6 73 6.92 34 2.02 48 3.23 53 2.86 88 10.2 51 18.9 59 6.45 45
FlowFields [110]56.3 9.03 97 17.5 106 7.31 104 8.02 26 18.6 40 5.24 49 11.1 41 18.9 39 6.32 61 11.6 20 28.7 35 7.40 66 5.14 58 6.03 59 4.64 74 10.1 47 23.8 78 7.62 44 1.69 19 2.86 17 1.51 35 12.9 69 22.8 79 14.9 88
JOF [140]56.8 7.77 59 16.9 92 5.33 53 10.6 92 20.8 64 7.75 92 10.9 39 18.9 39 5.34 44 12.7 39 32.6 72 6.67 29 4.91 26 5.86 29 3.97 28 9.05 25 17.9 20 5.47 12 3.04 100 3.66 88 3.43 104 13.3 76 21.4 70 12.2 72
MDP-Flow [26]57.3 6.73 12 14.1 4 5.59 64 6.70 7 16.0 20 4.65 32 9.78 17 17.2 29 6.61 65 13.0 47 34.7 95 6.48 22 5.54 101 6.17 82 5.84 113 10.5 55 23.6 73 7.81 48 1.89 38 3.42 72 1.37 18 20.0 116 32.5 122 19.1 124
S2F-IF [123]57.5 8.86 93 17.2 100 7.05 100 7.84 25 18.3 37 5.20 46 10.8 37 18.5 38 6.21 57 13.0 47 30.7 48 8.15 78 5.09 50 5.98 48 4.58 67 9.62 37 22.7 64 7.20 41 1.92 41 3.77 96 1.73 45 10.7 54 18.4 56 12.8 75
TC-Flow [46]57.7 6.56 7 14.1 4 4.48 12 9.25 52 21.4 72 5.03 39 14.9 80 25.8 85 3.93 20 14.5 77 35.9 109 6.97 50 5.01 38 5.97 42 3.63 9 9.98 45 22.8 67 6.83 33 2.11 57 3.25 54 3.61 111 16.7 94 26.8 98 20.0 130
ProFlow_ROB [146]58.1 7.98 68 17.0 93 5.55 63 9.17 50 21.5 74 5.69 59 13.9 71 24.5 79 5.39 48 13.9 68 32.3 71 7.54 69 5.19 71 6.19 85 4.26 51 9.15 30 21.8 60 5.47 12 1.57 6 2.92 21 1.15 8 13.9 79 23.8 85 12.3 73
SimpleFlow [49]59.5 7.56 55 16.2 59 5.59 64 9.48 57 21.0 67 5.68 58 17.1 97 27.0 100 6.29 59 13.0 47 32.8 76 7.09 53 5.18 68 6.16 78 4.62 70 8.75 20 17.6 18 6.81 32 2.13 60 3.50 80 2.30 69 9.78 45 17.4 48 7.10 48
IROF-TV [53]60.1 7.55 54 16.1 55 5.46 60 9.23 51 21.8 77 5.88 63 13.3 64 22.2 63 5.50 52 12.8 41 31.6 62 7.28 61 5.12 53 6.09 66 4.67 79 13.3 94 29.6 121 9.97 81 1.60 7 3.12 42 1.06 5 11.5 60 21.3 69 11.5 63
SRR-TVOF-NL [91]60.3 7.83 60 15.4 33 5.99 77 13.2 121 26.1 114 8.61 98 13.2 62 22.0 62 6.78 66 13.6 64 30.3 44 7.34 65 4.72 7 5.56 5 4.04 35 9.87 41 19.8 51 8.30 56 3.25 105 3.73 94 3.18 97 6.93 26 12.9 26 4.92 38
HBM-GC [105]61.8 8.35 85 18.4 117 4.98 36 7.66 19 18.2 34 5.20 46 13.8 70 24.2 77 5.34 44 12.0 22 30.5 46 6.83 40 5.04 45 6.02 57 4.43 59 9.34 35 15.5 5 7.92 49 3.03 99 4.57 119 2.51 80 16.1 89 26.0 94 17.9 116
ACK-Prior [27]62.0 6.39 3 13.4 3 4.38 7 8.58 40 19.7 50 3.63 15 11.4 42 20.3 46 3.82 17 12.5 30 33.7 85 5.09 9 5.53 99 6.42 104 4.76 84 15.0 112 28.4 109 11.4 97 3.54 111 4.36 113 4.84 124 13.2 74 20.2 63 8.94 52
LiteFlowNet [142]62.2 9.19 98 16.6 83 7.02 99 8.23 30 18.9 43 4.53 28 12.9 57 21.5 59 6.23 58 12.0 22 26.7 28 7.32 64 5.39 93 6.23 89 5.47 106 9.09 26 18.7 30 6.31 24 2.02 48 3.14 44 1.47 26 19.2 110 24.7 88 21.9 141
2DHMM-SAS [92]63.8 7.39 46 15.9 47 5.25 48 10.7 95 23.4 93 5.43 52 18.0 102 27.0 100 7.95 101 13.1 51 32.7 74 7.28 61 4.89 23 5.78 21 4.01 32 9.88 42 18.2 22 6.37 25 2.50 80 3.39 67 3.37 102 13.8 78 22.4 78 15.5 91
Sparse Occlusion [54]64.4 7.38 44 15.8 43 5.28 49 8.25 31 19.9 57 4.71 34 15.5 87 26.3 94 4.63 31 13.5 63 33.3 84 6.92 48 5.25 78 6.26 93 4.11 41 9.70 38 21.1 55 5.94 18 4.85 136 5.95 139 3.71 114 10.8 55 20.0 62 8.01 51
DPOF [18]65.5 8.43 87 16.8 87 6.36 86 10.7 95 20.7 62 9.52 106 8.72 12 15.4 24 3.63 12 11.3 18 29.1 37 6.09 15 5.34 86 6.18 83 5.38 103 12.2 78 22.4 63 8.06 52 5.27 137 3.55 81 6.79 136 8.85 40 16.5 40 4.24 33
ResPWCR_ROB [144]66.3 8.30 81 14.5 10 7.12 101 8.82 43 19.6 49 5.91 64 11.8 46 19.3 42 7.90 100 12.4 29 28.5 34 7.89 75 5.18 68 5.97 42 5.36 101 10.9 60 23.9 79 8.84 63 2.85 90 3.65 87 2.34 71 14.7 82 21.8 72 16.2 103
OFH [38]66.5 7.25 34 15.0 24 5.29 51 11.1 99 25.0 106 7.19 86 18.6 107 29.1 114 5.56 53 16.0 96 40.8 146 7.44 67 5.05 46 5.92 36 4.28 52 11.4 68 26.0 95 8.73 60 1.64 13 3.04 27 1.36 17 12.5 67 23.3 83 7.79 50
COFM [59]66.5 8.49 89 18.5 120 5.95 73 8.44 37 18.7 41 4.71 34 13.0 59 22.9 68 5.84 54 13.8 66 35.2 103 6.78 35 5.63 107 6.58 111 5.94 114 11.7 72 23.5 71 9.80 77 2.29 70 3.20 48 2.72 83 6.42 21 12.1 21 3.07 23
ROF-ND [107]66.6 7.02 21 14.7 15 4.66 22 8.18 29 19.5 46 4.66 33 15.5 87 25.9 87 5.47 51 4.68 3 12.6 2 2.76 5 5.93 115 7.12 130 5.27 98 12.2 78 25.4 91 9.09 67 4.23 131 4.20 107 3.32 100 14.7 82 22.1 77 18.8 122
PGM-C [120]67.3 9.43 102 18.5 120 7.51 109 9.84 66 23.4 93 6.05 66 12.0 49 20.6 49 7.17 73 15.8 92 35.3 105 9.67 96 5.20 74 6.11 69 4.66 76 9.86 40 23.7 75 7.06 39 1.63 10 2.84 13 1.49 31 11.1 58 20.8 67 6.23 44
TCOF [69]68.0 7.46 52 15.1 25 5.70 67 9.13 49 21.1 69 5.43 52 19.6 113 29.8 119 8.31 105 12.9 44 31.0 52 7.17 58 6.02 120 7.00 125 4.59 69 7.92 11 18.4 26 6.11 21 3.78 120 4.09 104 5.18 126 8.51 36 15.9 37 3.80 31
S2D-Matching [84]68.6 8.25 78 18.0 114 5.76 70 10.9 97 22.8 88 5.71 60 17.3 98 28.5 107 6.38 63 12.1 25 30.3 44 6.65 28 5.15 62 6.13 73 4.63 72 9.18 32 19.5 50 6.69 29 2.66 82 3.35 62 3.50 105 11.6 61 19.9 61 14.7 85
OAR-Flow [125]68.8 8.08 72 16.8 87 6.19 82 17.4 135 28.9 133 12.3 132 16.3 93 26.7 99 7.01 70 15.1 85 35.2 103 7.31 63 5.17 65 6.16 78 4.24 49 9.51 36 22.9 69 5.52 14 1.54 5 2.98 24 1.59 39 9.10 43 17.1 47 3.69 29
ComplOF-FED-GPU [35]69.5 7.49 53 15.4 33 5.37 57 12.1 111 26.5 121 7.51 88 13.1 61 22.7 66 4.33 28 15.6 89 37.7 127 7.55 71 4.94 28 5.82 25 4.13 44 12.3 80 27.7 106 8.48 58 2.49 79 3.04 27 3.56 108 12.9 69 23.9 86 9.01 53
SegFlow [161]69.6 9.47 105 18.6 123 7.51 109 10.2 73 24.1 102 6.22 69 12.2 50 21.0 54 7.22 74 16.1 97 36.3 115 9.76 99 5.21 77 6.12 71 4.69 82 10.1 47 24.2 82 7.76 47 1.66 17 2.89 19 1.50 32 9.31 44 17.5 49 4.27 34
AggregFlow [97]72.9 10.3 116 21.3 151 6.91 97 15.1 128 27.6 128 10.7 111 14.0 73 24.0 74 8.70 108 14.1 71 35.0 98 7.15 57 5.05 46 6.03 59 4.02 33 7.73 9 18.2 22 5.09 6 2.13 60 4.40 115 1.67 41 9.91 49 18.1 54 6.13 43
CompactFlow_ROB [160]75.0 11.5 126 20.6 145 8.79 144 8.99 47 18.8 42 6.75 79 14.8 78 21.3 57 14.7 130 14.0 69 32.1 66 9.13 86 5.17 65 6.02 57 4.82 87 10.4 53 22.8 67 7.73 46 1.63 10 2.68 4 0.88 3 19.0 107 24.6 87 24.3 146
CPM-Flow [116]75.8 9.46 104 18.6 123 7.51 109 10.0 70 23.7 97 6.20 68 12.2 50 20.9 53 7.13 71 15.8 92 35.6 108 9.71 98 5.20 74 6.12 71 4.65 75 10.9 60 23.7 75 8.90 65 1.73 23 3.15 45 1.51 35 14.5 81 26.0 94 13.6 79
EpicFlow [102]77.0 9.39 101 18.4 117 7.50 108 10.0 70 23.8 99 6.29 71 15.8 90 26.6 97 7.35 81 15.5 87 34.4 90 9.65 94 5.20 74 6.11 69 4.66 76 10.2 51 24.5 84 8.18 55 1.63 10 2.81 10 1.48 27 15.8 87 24.8 89 17.1 112
Aniso-Texture [82]78.5 6.49 5 14.2 8 4.54 16 7.83 24 19.5 46 4.37 25 22.0 140 33.6 153 8.47 106 10.3 11 25.4 25 5.55 11 5.19 71 6.10 67 4.45 61 18.7 134 33.0 146 20.1 155 4.07 129 4.62 121 2.47 78 20.1 117 28.5 103 20.7 133
Occlusion-TV-L1 [63]79.2 7.73 58 16.4 67 5.36 55 9.48 57 22.4 84 6.18 67 19.2 109 30.0 122 7.14 72 14.4 76 33.8 87 7.91 76 5.31 85 6.27 95 4.47 62 11.9 74 27.9 107 8.04 50 2.09 55 3.08 31 1.50 32 21.9 128 35.3 138 17.5 113
ContinualFlow_ROB [152]79.6 11.4 124 20.8 146 8.47 127 9.76 64 18.5 39 7.94 95 16.5 94 26.6 97 11.7 121 15.7 90 37.2 120 8.85 85 5.25 78 5.97 42 5.27 98 11.8 73 24.9 86 11.4 97 1.53 4 3.06 29 1.10 6 12.4 66 17.7 53 13.1 76
RFlow [90]80.2 7.10 26 14.9 18 5.40 58 8.98 46 21.9 79 5.19 45 18.5 106 29.3 116 5.35 46 18.1 129 44.9 164 9.86 102 5.12 53 6.01 54 4.38 56 13.0 91 29.3 118 9.93 80 2.28 69 2.85 14 3.52 106 20.3 119 33.3 128 16.1 101
FF++_ROB [145]80.6 9.92 111 19.4 131 7.55 113 8.87 44 20.9 65 5.83 62 15.3 83 25.3 83 7.95 101 11.0 15 25.4 25 7.23 60 5.19 71 6.10 67 4.80 85 17.1 121 25.3 90 13.2 113 1.88 36 2.96 23 2.77 84 18.7 104 27.2 99 25.3 148
DeepFlow2 [108]81.5 8.14 74 16.6 83 5.96 75 14.1 123 26.5 121 10.2 107 15.8 90 26.2 93 6.46 64 16.5 117 37.4 124 9.54 92 5.01 38 5.94 40 3.72 16 10.7 58 25.1 87 8.08 54 1.92 41 3.12 42 2.45 75 20.3 119 32.1 119 16.3 104
Adaptive [20]81.7 7.94 63 17.0 93 5.33 53 10.2 73 23.9 100 6.28 70 21.2 127 31.7 141 7.69 97 13.6 64 29.8 39 7.87 74 4.88 21 5.75 16 3.71 15 13.2 92 28.9 115 9.72 76 3.21 104 4.71 123 2.91 90 19.3 112 30.5 110 15.6 92
DMF_ROB [139]81.9 8.27 79 16.7 85 6.36 86 11.7 107 26.4 119 7.10 85 17.8 101 28.6 109 7.33 80 15.9 95 35.9 109 9.46 90 5.05 46 5.97 42 4.51 63 12.8 89 27.4 103 9.90 79 1.60 7 2.99 25 1.48 27 19.8 115 32.0 117 16.8 108
TF+OM [100]83.5 7.97 67 16.8 87 5.98 76 9.40 55 20.7 62 6.33 72 15.4 84 22.9 68 17.5 135 13.4 57 31.5 59 8.10 77 5.13 57 6.06 64 4.66 76 13.9 101 29.3 118 14.0 119 2.47 76 4.09 104 2.00 55 18.3 102 29.4 107 19.3 126
Steered-L1 [118]84.0 5.97 1 12.7 1 4.67 24 7.14 12 18.2 34 4.63 30 13.2 62 23.3 72 5.12 38 15.2 86 38.1 130 7.54 69 5.85 114 6.73 115 6.98 133 13.7 100 26.5 97 11.7 103 6.39 142 4.25 109 13.3 158 22.3 131 32.7 124 20.3 131
Aniso. Huber-L1 [22]84.7 7.96 66 16.3 65 6.10 80 11.4 101 24.7 104 6.77 80 20.6 120 29.6 118 7.26 76 13.2 54 29.2 38 7.77 73 5.52 98 6.58 111 4.29 53 12.4 82 26.7 100 8.83 62 2.93 96 3.68 89 3.10 93 16.5 93 27.4 100 13.9 81
AdaConv-v1 [126]85.8 13.0 137 16.4 67 8.62 129 10.2 73 9.17 1 11.5 116 10.7 23 11.1 1 7.66 83 16.3 102 17.8 4 14.4 127 10.8 147 8.97 144 16.5 148 19.7 138 18.7 30 19.4 139 19.7 152 17.1 152 8.18 141 3.51 1 4.92 1 2.42 3
SepConv-v1 [127]85.8 13.0 137 16.4 67 8.62 129 10.2 73 9.17 1 11.5 116 10.7 23 11.1 1 7.66 83 16.3 102 17.8 4 14.4 127 10.8 147 8.97 144 16.5 148 19.7 138 18.7 30 19.4 139 19.7 152 17.1 152 8.18 141 3.51 1 4.92 1 2.42 3
SuperSlomo [132]85.8 13.0 137 16.4 67 8.62 129 10.2 73 9.17 1 11.5 116 10.7 23 11.1 1 7.66 83 16.3 102 17.8 4 14.4 127 10.8 147 8.97 144 16.5 148 19.7 138 18.7 30 19.4 139 19.7 152 17.1 152 8.18 141 3.51 1 4.92 1 2.42 3
CtxSyn [136]85.8 13.0 137 16.4 67 8.62 129 10.2 73 9.17 1 11.5 116 10.7 23 11.1 1 7.66 83 16.3 102 17.8 4 14.4 127 10.8 147 8.97 144 16.5 148 19.7 138 18.7 30 19.4 139 19.7 152 17.1 152 8.18 141 3.51 1 4.92 1 2.42 3
CyclicGen [153]85.8 13.0 137 16.4 67 8.62 129 10.2 73 9.17 1 11.5 116 10.7 23 11.1 1 7.66 83 16.3 102 17.8 4 14.4 127 10.8 147 8.97 144 16.5 148 19.7 138 18.7 30 19.4 139 19.7 152 17.1 152 8.18 141 3.51 1 4.92 1 2.42 3
TOF-M [154]85.8 13.0 137 16.4 67 8.62 129 10.2 73 9.17 1 11.5 116 10.7 23 11.1 1 7.66 83 16.3 102 17.8 4 14.4 127 10.8 147 8.97 144 16.5 148 19.7 138 18.7 30 19.4 139 19.7 152 17.1 152 8.18 141 3.51 1 4.92 1 2.42 3
MEMC-Net+ [155]85.8 13.0 137 16.4 67 8.62 129 10.2 73 9.17 1 11.5 116 10.7 23 11.1 1 7.66 83 16.3 102 17.8 4 14.4 127 10.8 147 8.97 144 16.5 148 19.7 138 18.7 30 19.4 139 19.7 152 17.1 152 8.18 141 3.51 1 4.92 1 2.42 3
MPRN [156]85.8 13.0 137 16.4 67 8.62 129 10.2 73 9.17 1 11.5 116 10.7 23 11.1 1 7.66 83 16.3 102 17.8 4 14.4 127 10.8 147 8.97 144 16.5 148 19.7 138 18.7 30 19.4 139 19.7 152 17.1 152 8.18 141 3.51 1 4.92 1 2.42 3
DAIN [157]85.8 13.0 137 16.4 67 8.62 129 10.2 73 9.17 1 11.5 116 10.7 23 11.1 1 7.66 83 16.3 102 17.8 4 14.4 127 10.8 147 8.97 144 16.5 148 19.7 138 18.7 30 19.4 139 19.7 152 17.1 152 8.18 141 3.51 1 4.92 1 2.42 3
InterpCNN [158]85.8 13.0 137 16.4 67 8.62 129 10.2 73 9.17 1 11.5 116 10.7 23 11.1 1 7.66 83 16.3 102 17.8 4 14.4 127 10.8 147 8.97 144 16.5 148 19.7 138 18.7 30 19.4 139 19.7 152 17.1 152 8.18 141 3.51 1 4.92 1 2.42 3
OFRI [159]85.8 13.0 137 16.4 67 8.62 129 10.2 73 9.17 1 11.5 116 10.7 23 11.1 1 7.66 83 16.3 102 17.8 4 14.4 127 10.8 147 8.97 144 16.5 148 19.7 138 18.7 30 19.4 139 19.7 152 17.1 152 8.18 141 3.51 1 4.92 1 2.42 3
PyrWarp [162]85.8 13.0 137 16.4 67 8.62 129 10.2 73 9.17 1 11.5 116 10.7 23 11.1 1 7.66 83 16.3 102 17.8 4 14.4 127 10.8 147 8.97 144 16.5 148 19.7 138 18.7 30 19.4 139 19.7 152 17.1 152 8.18 141 3.51 1 4.92 1 2.42 3
FGME [164]85.8 13.0 137 16.4 67 8.62 129 10.2 73 9.17 1 11.5 116 10.7 23 11.1 1 7.66 83 16.3 102 17.8 4 14.4 127 10.8 147 8.97 144 16.5 148 19.7 138 18.7 30 19.4 139 19.7 152 17.1 152 8.18 141 3.51 1 4.92 1 2.42 3
MS-PFT [165]85.8 13.0 137 16.4 67 8.62 129 10.2 73 9.17 1 11.5 116 10.7 23 11.1 1 7.66 83 16.3 102 17.8 4 14.4 127 10.8 147 8.97 144 16.5 148 19.7 138 18.7 30 19.4 139 19.7 152 17.1 152 8.18 141 3.51 1 4.92 1 2.42 3
OFRF [134]85.9 9.69 107 19.6 134 6.25 83 22.2 154 29.4 136 20.7 157 21.6 131 30.1 123 17.0 134 14.1 71 31.0 52 8.47 81 4.93 27 5.87 31 3.94 27 9.10 27 18.6 28 6.40 26 2.84 89 4.62 121 3.66 112 12.6 68 16.7 43 15.9 100
AugFNG_ROB [143]86.9 12.7 134 22.1 152 9.46 148 12.1 111 24.6 103 9.39 104 18.8 108 27.1 104 14.7 130 14.0 69 30.9 50 9.24 88 5.03 42 5.72 13 5.09 93 11.0 63 24.0 81 9.53 73 1.82 33 3.25 54 1.22 9 18.2 101 23.7 84 21.6 138
LocallyOriented [52]87.2 9.89 109 19.9 138 6.55 89 14.7 127 27.7 129 11.0 113 21.7 134 31.9 143 7.32 79 13.3 56 30.5 46 8.32 79 5.16 63 6.04 61 4.11 41 9.90 43 21.6 59 8.75 61 2.20 64 3.43 74 2.17 62 18.3 102 26.0 94 19.6 127
EAI-Flow [151]87.2 10.4 119 19.0 128 7.83 115 13.2 121 25.8 111 9.43 105 13.7 69 21.6 60 8.47 106 14.8 80 33.0 79 9.68 97 5.12 53 6.01 54 4.74 83 11.6 69 25.7 93 9.23 69 3.66 115 3.57 85 2.04 57 13.4 77 24.8 89 10.5 60
SIOF [67]90.1 8.21 77 17.0 93 5.49 61 13.0 120 27.4 127 8.63 99 20.1 118 29.0 112 16.3 133 16.8 119 37.3 123 10.0 106 5.40 94 6.34 100 4.88 88 11.6 69 25.4 91 10.1 84 1.81 32 3.27 56 1.34 15 15.1 86 25.1 91 11.9 68
LFNet_ROB [149]90.2 10.1 114 17.0 93 8.16 123 9.48 57 21.8 77 6.00 65 16.8 95 26.1 91 11.1 118 13.4 57 29.9 40 8.73 84 5.40 94 6.20 86 5.58 108 13.3 94 29.4 120 10.0 83 2.04 51 3.21 50 1.85 50 22.7 135 35.6 139 21.8 140
SegOF [10]91.2 9.43 102 17.7 108 8.06 120 12.0 110 22.9 91 10.4 110 17.0 96 26.1 91 12.6 125 13.8 66 26.8 29 11.2 114 5.53 99 6.26 93 6.06 117 19.0 135 35.6 158 18.8 137 1.37 2 2.60 2 0.83 2 16.4 91 30.0 108 14.0 82
TriangleFlow [30]91.4 8.08 72 17.0 93 5.12 41 11.7 107 26.1 114 6.98 84 19.5 111 30.3 126 6.34 62 12.9 44 33.0 79 6.71 33 7.00 138 8.16 142 6.63 130 12.8 89 24.5 84 10.5 87 3.59 112 5.17 134 3.27 99 12.9 69 21.9 74 12.1 70
DeepFlow [86]91.5 8.73 90 17.1 99 6.26 84 15.3 131 26.7 124 11.9 131 17.3 98 26.5 96 14.1 129 18.6 135 42.8 158 11.0 112 5.00 37 5.91 35 3.75 18 11.2 67 26.2 96 8.35 57 1.88 36 2.80 8 2.60 81 22.5 133 33.6 129 17.5 113
CRTflow [80]92.2 7.92 61 16.0 51 5.91 72 11.4 101 23.7 97 6.55 76 19.8 115 30.1 123 7.77 98 17.2 125 41.3 149 9.76 99 5.34 86 6.30 96 3.69 14 15.8 117 31.0 133 14.3 122 2.12 59 2.92 21 2.35 72 19.2 110 32.9 126 15.3 89
TriFlow [95]93.8 9.01 96 18.5 120 6.60 92 11.4 101 26.4 119 7.40 87 20.9 123 29.9 121 20.9 144 12.2 27 30.8 49 6.95 49 5.26 83 6.16 78 4.88 88 12.0 76 26.5 97 11.6 101 6.97 143 4.54 117 6.57 135 13.0 72 22.0 75 9.86 57
Brox et al. [5]95.0 8.46 88 16.7 85 6.56 90 11.3 100 26.2 116 6.94 83 15.0 81 25.4 84 6.89 69 17.4 126 38.8 134 9.80 101 5.99 118 6.88 122 6.26 122 14.1 104 31.1 136 12.0 105 2.03 50 3.41 71 1.14 7 19.1 109 30.3 109 12.1 70
Fusion [6]95.3 8.76 91 17.7 108 7.01 98 7.82 23 19.7 50 4.78 37 10.9 39 18.4 37 7.23 75 12.8 41 32.6 72 8.32 79 7.04 139 8.11 140 6.57 128 14.9 110 28.3 108 13.2 113 4.37 133 5.18 135 2.77 84 26.2 148 38.6 150 26.4 150
p-harmonic [29]95.8 8.15 76 16.2 59 6.50 88 9.66 62 22.6 86 6.57 77 21.2 127 31.2 134 9.65 111 15.7 90 33.9 88 10.0 106 5.18 68 6.04 61 5.31 100 14.3 106 30.3 128 12.2 109 3.10 101 3.55 81 1.91 52 23.1 138 34.8 136 17.8 115
CBF [12]96.9 7.23 33 14.9 18 5.16 42 9.95 69 21.9 79 7.69 91 17.6 100 27.0 100 7.28 78 16.4 116 39.3 138 9.18 87 6.34 131 7.35 136 6.11 120 13.4 97 28.4 109 8.52 59 5.54 139 5.11 131 6.41 133 18.7 104 30.8 111 16.4 105
EPMNet [133]97.8 11.6 128 20.5 143 8.03 119 17.7 137 28.9 133 13.2 137 12.9 57 20.3 46 10.7 114 15.5 87 37.4 124 9.48 91 5.36 90 6.23 89 4.94 90 14.0 102 29.9 124 12.2 109 2.97 97 5.82 138 2.01 56 10.1 50 18.8 58 3.51 27
TV-L1-improved [17]98.5 7.64 57 16.2 59 5.67 66 10.1 72 23.4 93 6.38 73 21.3 129 32.0 146 9.27 110 17.5 127 42.1 153 9.54 92 5.25 78 6.13 73 4.07 36 14.5 107 30.4 130 11.4 97 3.38 107 5.02 128 2.99 92 19.6 114 32.1 119 16.6 107
CLG-TV [48]98.5 7.94 63 16.2 59 5.80 71 10.5 91 24.0 101 6.44 74 19.9 116 29.8 119 6.83 67 14.1 71 31.5 59 7.73 72 5.98 116 7.01 126 5.15 96 14.8 109 31.0 133 12.2 109 4.20 130 4.80 125 5.22 127 19.3 112 32.6 123 15.7 96
FlowNet2 [122]98.5 12.8 135 23.3 157 8.09 121 16.8 134 28.5 130 12.5 133 13.9 71 21.6 60 12.0 123 15.0 84 34.0 89 9.98 105 5.36 90 6.23 89 4.94 90 14.0 102 29.9 124 12.2 109 3.36 106 6.60 144 2.24 66 8.83 39 16.6 42 3.02 22
WOLF_ROB [148]98.9 9.97 112 18.4 117 7.33 105 20.8 145 34.8 161 13.9 139 22.2 142 30.7 130 10.9 115 17.0 124 33.2 83 12.3 121 5.16 63 6.01 54 5.11 95 10.2 51 20.7 53 9.05 66 1.97 44 3.28 57 2.48 79 17.9 100 23.1 80 21.3 137
Local-TV-L1 [65]100.4 9.74 108 17.9 112 6.89 95 18.4 140 29.4 136 14.9 141 24.4 146 30.8 131 20.2 142 19.4 140 42.4 156 12.7 123 5.35 89 6.00 51 4.10 39 13.6 98 28.9 115 9.26 70 1.62 9 2.58 1 1.48 27 20.3 119 32.0 117 16.4 105
Classic++ [32]100.8 8.05 70 17.4 105 6.09 79 11.5 104 26.3 118 6.91 81 18.1 104 28.7 110 8.18 103 16.2 98 39.0 136 8.57 82 5.36 90 6.33 98 4.54 65 15.0 112 30.4 130 11.6 101 2.70 85 3.55 81 2.94 91 21.9 128 34.0 132 17.9 116
SuperFlow [81]101.4 9.27 100 17.3 103 6.63 93 11.7 107 22.8 88 8.84 101 19.3 110 28.0 106 18.4 139 16.9 121 38.2 131 9.89 103 5.44 96 6.32 97 5.61 110 11.9 74 26.6 99 9.56 75 2.92 94 4.08 103 1.79 47 20.1 117 32.4 121 15.8 98
Rannacher [23]102.3 8.07 71 16.8 87 6.15 81 10.6 92 24.8 105 6.51 75 21.9 138 32.6 152 10.9 115 18.4 132 43.3 160 10.5 108 5.27 84 6.18 83 4.17 47 15.5 115 32.3 143 12.0 105 2.69 84 3.57 85 2.68 82 17.8 99 31.0 112 16.1 101
F-TV-L1 [15]103.1 8.41 86 16.8 87 6.31 85 18.0 139 29.7 138 12.8 134 21.6 131 30.5 127 10.1 113 18.2 130 42.3 155 9.65 94 5.02 41 5.97 42 3.91 23 14.1 104 30.8 132 10.6 91 2.79 86 4.90 126 2.35 72 20.5 122 32.7 124 15.6 92
BriefMatch [124]105.2 6.91 17 14.8 17 4.85 27 11.0 98 22.8 88 8.24 96 9.42 14 16.6 28 5.13 40 16.7 118 40.7 145 8.61 83 9.76 145 10.6 160 14.1 146 18.2 131 31.0 133 17.4 133 9.26 147 6.60 144 20.9 164 28.0 152 36.5 142 34.9 157
StereoOF-V1MT [119]105.8 8.14 74 15.8 43 5.42 59 17.6 136 34.3 159 10.3 108 21.6 131 31.5 138 7.27 77 15.8 92 32.7 74 10.7 109 5.62 106 6.40 102 6.00 116 16.6 120 30.0 126 15.5 124 2.01 47 3.08 31 3.15 95 33.6 158 44.0 159 32.8 155
DF-Auto [115]107.1 10.7 122 19.8 137 7.42 107 16.3 133 25.3 107 13.1 136 19.5 111 28.5 107 17.8 137 16.9 121 37.2 120 10.8 110 6.76 137 8.12 141 5.56 107 10.8 59 25.2 88 6.95 35 3.69 117 4.92 127 1.48 27 17.7 98 27.9 102 14.6 84
Dynamic MRF [7]107.8 8.32 84 17.3 103 5.95 73 12.3 113 28.5 130 7.75 92 19.6 113 31.8 142 7.56 82 18.4 132 42.2 154 11.6 118 5.25 78 6.16 78 4.80 85 17.7 125 34.4 154 16.6 129 1.89 38 2.63 3 3.21 98 30.3 154 43.6 158 29.0 152
Bartels [41]107.9 8.31 83 17.7 108 5.51 62 8.46 38 20.6 59 4.89 38 14.8 78 26.0 89 7.89 99 18.5 134 43.6 161 11.1 113 6.18 124 6.51 110 8.63 141 15.6 116 32.6 145 13.9 118 3.86 123 4.56 118 7.09 137 22.5 133 36.5 142 18.4 120
Shiralkar [42]109.5 7.92 61 15.2 30 5.73 68 14.6 126 30.3 139 9.04 102 21.7 134 31.2 134 9.77 112 19.6 142 41.5 150 13.2 125 5.17 65 6.04 61 4.63 72 18.0 130 31.1 136 14.7 123 3.67 116 3.40 69 4.74 123 23.9 143 36.6 144 18.9 123
GraphCuts [14]110.0 9.24 99 17.2 100 7.53 112 22.1 152 33.0 153 16.8 149 15.9 92 23.1 70 15.6 132 14.2 74 28.9 36 9.34 89 5.83 113 6.82 118 6.25 121 18.5 133 29.7 122 12.0 105 2.85 90 3.39 67 3.52 106 23.8 142 36.1 140 19.1 124
Second-order prior [8]112.5 8.04 69 16.3 65 6.01 78 12.5 115 26.5 121 9.10 103 21.0 124 31.1 133 9.23 109 16.2 98 36.2 114 9.93 104 5.70 110 6.67 114 5.09 93 20.7 154 34.1 152 21.0 156 3.76 119 3.89 99 4.25 119 18.9 106 31.8 116 19.9 129
Filter Flow [19]113.0 10.5 120 19.4 131 8.33 124 12.5 115 25.8 111 8.69 100 19.9 116 27.0 100 21.7 147 19.0 137 33.1 82 15.9 143 5.34 86 6.21 87 5.37 102 16.2 119 26.7 100 15.5 124 3.46 109 4.48 116 2.26 67 23.3 141 31.5 115 18.5 121
StereoFlow [44]114.1 16.2 159 22.6 155 13.9 161 22.1 152 31.6 145 18.8 154 24.7 147 30.6 129 21.2 146 23.3 154 39.9 139 19.6 154 5.98 116 6.22 88 7.11 135 11.6 69 27.6 104 8.05 51 1.36 1 2.85 14 0.65 1 20.7 123 33.7 130 17.0 111
CNN-flow-warp+ref [117]114.3 9.91 110 19.6 134 7.85 116 10.6 92 22.9 91 8.55 97 21.3 129 32.1 148 11.9 122 18.7 136 42.0 152 11.3 115 5.56 102 6.34 100 6.08 119 12.3 80 27.6 104 10.8 92 2.06 53 3.69 91 3.16 96 33.3 156 40.4 153 34.7 156
FlowNetS+ft+v [112]115.0 8.96 95 17.8 111 6.83 94 14.2 124 26.2 116 11.1 114 22.3 143 32.2 149 12.7 126 16.8 119 36.1 113 10.9 111 6.31 130 7.29 134 6.26 122 12.5 86 28.8 113 9.88 78 3.84 122 6.75 146 6.30 132 16.4 91 29.0 105 14.7 85
IAOF2 [51]115.4 10.0 113 19.9 138 7.91 118 14.4 125 26.7 124 10.9 112 22.0 140 32.2 149 17.6 136 19.1 138 33.0 79 17.1 147 5.81 112 6.86 120 4.94 90 12.6 87 25.9 94 11.9 104 4.26 132 4.11 106 7.75 140 16.2 90 26.5 97 13.5 78
Ad-TV-NDC [36]118.8 12.1 132 18.6 123 10.7 153 25.5 158 32.0 149 22.2 158 29.3 160 34.3 158 22.8 151 16.9 121 32.8 76 12.2 120 5.99 118 7.20 132 3.83 20 12.6 87 28.5 111 10.3 85 2.79 86 4.07 102 1.78 46 24.1 144 31.4 114 25.1 147
TVL1_ROB [138]119.2 12.9 136 20.8 146 9.80 151 21.3 149 30.9 142 17.9 153 27.9 154 33.6 153 23.5 155 20.5 144 37.8 128 16.7 145 5.57 103 6.47 107 5.46 105 14.5 107 32.1 142 12.1 108 1.69 19 2.81 10 1.22 9 22.9 136 36.3 141 18.3 119
LDOF [28]120.9 9.66 106 18.9 127 7.13 102 15.1 128 29.1 135 11.3 115 15.6 89 25.1 82 10.9 115 20.9 147 43.1 159 14.9 141 6.12 122 7.01 126 6.26 122 16.0 118 31.2 138 13.2 113 3.89 125 5.61 137 8.96 155 19.0 107 33.0 127 11.7 66
2D-CLG [1]121.5 15.2 157 24.5 161 11.2 155 15.1 128 25.9 113 13.5 138 27.5 153 33.9 155 24.7 160 22.2 151 38.3 132 19.0 153 5.67 108 6.44 105 6.29 125 17.5 123 34.3 153 16.4 128 1.47 3 2.68 4 1.54 38 21.7 127 34.6 135 16.9 110
Nguyen [33]122.2 11.4 124 19.6 134 8.44 126 21.0 148 31.7 147 17.7 151 29.8 162 36.3 162 24.1 159 18.2 130 34.6 94 13.9 126 6.28 126 6.85 119 7.51 138 15.4 114 33.0 146 14.0 119 2.24 67 3.11 38 1.79 47 21.6 126 33.9 131 15.8 98
IAOF [50]122.9 10.1 114 18.6 123 7.89 117 22.2 154 33.7 156 15.9 145 33.0 164 39.2 165 23.7 156 16.2 98 32.1 66 11.6 118 5.80 111 6.87 121 5.39 104 17.8 127 30.1 127 11.4 97 3.13 103 3.69 91 3.88 116 22.4 132 29.3 106 21.6 138
UnFlow [129]122.9 16.0 158 25.1 162 11.3 156 12.7 119 22.2 83 11.7 130 20.4 119 27.6 105 13.6 127 20.8 145 36.0 111 17.9 150 6.34 131 6.89 123 7.74 139 17.7 125 33.5 149 17.1 132 2.92 94 4.33 111 1.37 18 20.7 123 37.3 148 15.6 92
SPSA-learn [13]124.2 11.3 123 19.4 131 8.52 128 20.9 146 34.2 158 16.2 148 26.5 151 33.9 155 22.4 150 22.5 153 39.9 139 18.9 152 5.59 104 6.41 103 5.94 114 17.8 127 31.4 140 18.3 136 2.11 57 3.11 38 1.37 18 24.3 145 35.1 137 19.7 128
Learning Flow [11]124.3 8.28 80 17.0 93 5.75 69 12.3 113 28.5 130 7.79 94 18.4 105 28.7 110 8.29 104 22.2 151 40.6 144 17.3 148 8.52 140 10.3 159 7.04 134 19.9 152 35.1 156 16.8 131 3.11 102 4.59 120 3.59 110 26.9 150 40.0 152 20.9 136
HBpMotionGpu [43]125.6 12.2 133 22.1 152 8.34 125 17.9 138 31.4 144 14.7 140 29.2 159 37.8 164 20.6 143 19.1 138 44.6 163 11.5 117 5.60 105 6.45 106 6.06 117 13.2 92 28.8 113 11.1 95 3.45 108 3.97 101 2.04 57 23.1 138 34.1 133 20.7 133
Modified CLG [34]128.9 11.6 128 20.5 143 9.14 147 12.6 118 25.4 109 10.3 108 27.4 152 34.4 159 23.8 157 21.8 149 42.7 157 16.7 145 6.18 124 7.06 129 6.57 128 14.9 110 33.0 146 13.4 116 2.45 74 3.80 97 3.81 115 22.0 130 36.6 144 16.8 108
Black & Anandan [4]130.5 10.5 120 18.0 114 8.14 122 21.4 151 32.8 152 16.1 147 26.1 150 32.3 151 21.8 148 20.8 145 38.9 135 16.1 144 6.29 128 7.41 137 5.62 111 17.1 121 31.2 138 13.7 117 4.06 128 5.11 131 2.37 74 23.1 138 34.1 133 15.7 96
GroupFlow [9]131.8 11.5 126 21.2 150 8.71 143 20.5 143 33.0 153 15.7 144 23.6 144 31.6 139 20.1 141 16.2 98 34.5 91 11.3 115 8.86 141 9.84 158 6.50 127 18.2 131 30.3 128 17.4 133 3.82 121 5.05 129 6.55 134 21.1 125 28.8 104 22.4 144
2bit-BM-tele [98]131.8 10.3 116 20.1 140 7.40 106 11.5 104 26.7 124 7.57 90 20.6 120 32.0 146 11.4 120 17.9 128 40.3 142 12.3 121 6.29 128 6.80 117 6.93 132 21.0 155 32.0 141 18.0 135 7.61 144 6.57 143 11.1 157 27.5 151 39.4 151 29.2 153
Heeger++ [104]133.5 11.7 130 18.3 116 9.04 146 23.3 157 37.0 164 17.4 150 21.0 124 29.1 114 11.1 118 27.0 158 40.5 143 24.4 157 5.69 109 6.33 98 5.80 112 25.9 161 37.5 161 26.3 161 2.48 77 3.88 98 2.20 64 37.6 161 46.0 162 41.6 164
HCIC-L [99]134.0 14.6 154 21.1 148 9.67 149 42.7 165 36.7 163 46.6 165 21.8 136 30.5 127 17.9 138 21.1 148 35.1 100 18.6 151 6.42 133 6.58 111 7.35 137 17.8 127 28.6 112 16.6 129 12.8 150 14.3 150 15.3 160 16.8 96 25.7 93 12.7 74
H+S_ROB [137]134.8 16.6 161 23.6 159 11.9 158 19.1 141 30.6 141 15.6 143 25.1 148 30.2 125 23.4 153 29.1 159 36.3 115 27.9 160 13.4 162 15.7 162 12.2 143 27.2 162 38.8 163 27.8 162 1.70 21 2.81 10 1.42 23 32.2 155 41.3 156 30.2 154
BlockOverlap [61]135.7 10.3 116 19.1 129 7.74 114 15.4 132 25.3 107 13.0 135 24.3 145 31.9 143 21.0 145 19.5 141 43.8 162 13.1 124 9.14 142 7.60 138 13.9 145 19.0 135 29.0 117 15.7 126 11.0 148 8.77 148 24.8 165 23.0 137 31.3 113 25.9 149
TI-DOFE [24]136.5 14.6 154 21.1 148 11.7 157 22.4 156 31.6 145 19.6 155 28.6 157 31.2 134 26.3 161 26.3 157 36.0 111 25.1 158 6.43 134 7.34 135 6.67 131 19.1 137 33.8 150 18.9 138 2.88 92 3.15 45 2.82 87 25.7 147 36.6 144 22.3 143
Horn & Schunck [3]137.9 11.8 131 19.3 130 8.85 145 20.1 142 33.5 155 15.3 142 25.5 149 31.2 134 24.0 158 26.1 156 38.6 133 23.5 155 6.12 122 6.99 124 6.34 126 19.9 152 33.9 151 19.6 153 3.95 127 4.28 110 2.46 77 25.3 146 37.5 149 22.0 142
FFV1MT [106]144.8 13.9 153 23.4 158 10.8 154 20.9 146 34.5 160 16.0 146 21.8 136 29.5 117 13.8 128 31.0 163 41.7 151 29.4 162 9.97 146 6.78 116 17.9 162 23.8 158 35.3 157 25.0 160 2.99 98 4.24 108 3.57 109 37.6 161 46.0 162 41.6 164
SILK [79]146.0 13.2 151 22.4 154 10.2 152 20.5 143 32.2 151 17.7 151 29.0 158 34.1 157 23.4 153 22.0 150 40.8 146 17.3 148 6.28 126 7.17 131 7.12 136 21.7 156 35.8 159 19.6 153 5.44 138 3.45 77 10.8 156 29.3 153 40.6 155 26.7 151
Adaptive flow [45]146.6 13.2 151 20.2 141 9.78 150 27.3 160 31.9 148 25.4 159 28.3 156 31.6 139 30.5 164 19.7 143 37.6 126 15.3 142 11.2 161 12.6 161 8.93 142 17.6 124 29.8 123 15.8 127 13.1 151 11.0 149 18.3 161 26.4 149 36.8 147 22.7 145
PGAM+LK [55]147.2 14.9 156 22.8 156 14.1 162 25.5 158 31.3 143 26.6 160 21.9 138 26.4 95 22.2 149 26.0 155 39.1 137 24.0 156 9.61 144 6.49 109 14.1 146 24.3 159 35.0 155 23.0 158 6.19 141 6.24 142 7.26 138 34.3 159 40.4 153 40.8 163
SLK [47]147.5 17.2 163 24.0 160 18.2 163 21.3 149 30.4 140 20.1 156 27.9 154 31.9 143 23.3 152 31.4 164 39.9 139 30.0 164 6.60 135 7.04 128 8.37 140 22.8 157 36.4 160 21.6 157 3.90 126 3.75 95 5.02 125 33.3 156 41.7 157 35.2 158
AVG_FLOW_ROB [141]152.6 32.4 165 34.1 165 37.7 165 35.1 164 33.7 156 37.0 164 20.7 122 24.1 76 19.4 140 34.1 165 35.1 100 34.8 165 39.6 164 37.0 164 44.9 164 40.6 165 42.2 164 38.5 165 11.3 149 15.3 151 7.36 139 46.5 165 52.3 165 38.9 160
FOLKI [16]156.1 16.2 159 25.9 163 12.7 160 32.5 162 35.6 162 34.7 162 29.4 161 35.1 161 26.9 162 29.1 159 41.0 148 27.9 160 9.58 143 8.90 143 13.5 144 25.7 160 38.3 162 24.5 159 7.71 145 5.13 133 14.5 159 36.5 160 44.4 160 36.1 159
Pyramid LK [2]156.4 17.0 162 20.4 142 19.4 164 31.7 161 32.1 150 32.5 161 32.9 163 34.8 160 29.9 163 29.4 161 35.3 105 29.9 163 31.7 163 35.5 163 29.8 163 29.9 163 32.3 143 28.0 163 9.01 146 7.93 147 18.9 162 39.9 163 45.4 161 39.0 161
Periodicity [78]161.6 18.0 164 30.5 164 12.3 159 34.0 163 41.4 165 35.6 163 36.5 165 36.5 163 35.2 165 29.7 162 46.6 165 26.8 159 51.8 165 56.5 165 45.5 165 36.7 164 42.4 165 37.1 164 5.99 140 6.16 141 19.3 163 40.1 164 51.1 164 40.4 162
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] MEMC-Net+ 0.16 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.
[156] MPRN 0.32 4 color Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[157] DAIN 0.13 2 color Anonymous. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019 submission 1769.
[158] InterpCNN 0.65 2 color Anonymous. (Interpolation results only.) Video frame interpolation with a stack of synthesis networks and intermediate optical flows. CVPR 2019 submission 6533.
[159] OFRI 0.31 2 color Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
[160] CompactFlow_ROB 0.05 2 color Anonymous. CompactFlow: spatially shiftable window revisited. CVPR 2019 submission 1387.
[161] 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.
[162] PyrWarp 0.14 2 color Anonymous. (Interpolation results only.) Video frame interpolation using differentiable forward-warping of feature pyramids. ICCV 2019 submission 741.
[163] HCFN 0.18 2 color Anonymous. Practical coarse-to-fine optical flow with deep networks. ICCV 2019 submission 116.
[164] FGME 0.23 2 color Anonymous. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. ICCV 2019 submission 4327.
[165] 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.
* 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.