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
PMMST [114]13.9 6.46 4 14.1 4 3.23 1 5.42 1 12.7 24 3.51 14 8.20 9 14.7 32 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 29 11.3 29 2.25 2
NNF-Local [87]14.4 6.84 16 15.1 25 4.48 12 6.28 5 15.5 28 3.00 4 7.42 3 13.5 27 2.39 3 7.71 7 22.7 31 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 24 10.7 24 2.48 26
NN-field [71]18.2 7.29 36 16.0 51 4.74 25 6.15 2 15.2 27 3.02 6 7.77 7 14.1 31 2.71 6 7.56 5 22.8 32 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 25 10.8 25 2.49 27
OFLAF [77]21.0 6.75 13 14.9 18 4.44 10 7.07 11 17.5 38 3.10 7 8.45 10 15.5 34 2.50 5 13.0 47 35.0 107 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 28 11.0 27 2.79 28
MDP-Flow2 [68]28.7 6.66 8 14.7 15 4.53 14 6.79 8 17.0 32 3.23 8 8.68 11 15.8 35 2.90 7 13.4 57 33.7 94 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 32 12.8 34 3.33 34
FC-2Layers-FF [74]31.5 7.07 25 15.5 36 4.91 31 8.30 34 19.7 59 4.30 23 7.61 5 13.6 28 4.29 25 11.8 21 30.2 52 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 38 14.3 40 4.12 41
nLayers [57]31.6 7.20 31 16.0 51 4.66 22 6.25 4 14.7 25 3.70 19 7.72 6 13.7 29 4.81 34 13.1 51 34.8 105 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 44 15.6 45 6.10 51
3DFlow [135]36.5 6.97 19 15.1 25 3.90 3 8.12 28 19.7 59 3.79 20 13.6 76 24.2 86 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 56 8.87 64 2.38 72 3.11 38 2.45 75 5.82 27 11.1 28 3.00 30
ComponentFusion [96]37.7 7.22 32 15.9 47 4.61 19 7.60 17 19.2 53 3.30 9 9.70 16 17.6 40 3.77 16 11.1 16 31.0 61 4.45 7 4.96 31 5.88 32 4.25 50 10.9 60 23.7 84 9.40 72 1.90 40 3.08 31 1.69 43 8.00 42 15.1 43 4.57 44
FESL [72]40.4 6.97 19 15.3 32 4.47 11 9.74 63 21.4 81 5.49 57 11.4 51 20.2 53 4.25 24 12.5 30 31.5 68 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 67 17.6 59 10.1 67
AGIF+OF [85]41.4 7.17 29 15.6 38 4.93 32 10.2 73 22.1 90 5.16 44 12.5 65 21.2 65 4.88 36 12.5 30 31.7 73 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 64 17.6 59 11.0 70
NNF-EAC [103]41.8 6.83 15 14.9 18 4.80 26 7.59 16 18.0 40 4.31 24 9.03 13 16.1 36 3.09 9 13.2 54 32.2 78 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 17.0 106 27.6 110 18.0 127
PWC-Net_ROB [147]41.8 8.30 81 16.2 59 6.58 91 8.56 39 20.6 68 4.38 26 12.3 62 21.4 67 6.00 55 10.8 12 27.0 40 6.88 46 4.94 28 5.79 22 3.98 29 8.37 17 19.3 58 5.42 11 1.65 16 3.29 58 1.02 4 7.86 41 14.2 39 3.37 35
Layers++ [37]42.5 7.19 30 15.7 40 5.08 38 6.15 2 14.8 26 3.42 12 7.83 8 14.0 30 4.84 35 10.9 14 26.9 39 6.19 17 4.83 18 5.84 27 4.36 55 12.4 82 25.2 97 10.5 87 2.43 73 3.56 84 1.92 53 8.66 47 16.1 47 7.77 58
Correlation Flow [75]43.4 6.66 8 14.5 10 3.81 2 7.78 22 17.5 38 2.85 2 18.0 111 29.0 121 4.31 27 9.28 9 22.1 30 5.57 12 5.12 53 6.13 73 3.98 29 11.0 63 23.3 79 10.5 87 2.07 54 3.08 31 2.32 70 6.79 33 12.5 32 4.83 45
Efficient-NL [60]43.6 7.43 50 16.2 59 4.85 27 7.73 20 18.1 41 4.58 29 14.0 82 23.6 82 4.47 29 13.1 51 32.9 87 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 34 12.1 30 5.78 49
PH-Flow [101]44.6 7.38 44 15.9 47 5.22 45 9.30 53 19.5 55 5.71 60 9.62 15 17.2 38 5.09 37 13.4 57 34.5 100 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 37 13.3 37 5.33 48
IROF++ [58]45.6 7.44 51 16.1 55 5.11 40 8.61 41 19.4 54 5.12 42 12.3 62 21.0 63 5.12 38 12.8 41 32.1 75 7.13 56 4.88 21 5.76 18 3.89 22 9.01 23 18.9 56 6.76 31 1.78 29 3.22 52 1.23 11 10.4 61 18.5 66 13.3 86
LME [70]46.5 7.04 23 15.6 38 4.53 14 6.68 6 16.9 31 2.85 2 13.6 76 22.6 74 12.0 132 11.5 19 27.8 41 6.39 21 5.03 42 5.93 38 4.52 64 12.4 82 27.0 111 10.9 94 1.76 27 3.38 66 1.43 24 6.62 31 12.5 32 2.86 29
Classic+CPF [83]47.2 7.31 38 15.8 43 5.09 39 9.93 68 22.1 90 5.05 40 13.3 73 22.4 73 4.64 32 12.5 30 32.0 74 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 57 16.5 49 13.8 89
CombBMOF [113]47.2 7.30 37 15.1 25 4.61 19 8.08 27 18.2 43 3.69 18 10.2 20 18.1 43 2.47 4 11.2 17 28.1 42 6.67 29 4.82 15 5.76 18 4.13 44 13.3 94 22.1 70 14.1 121 2.90 93 4.33 111 2.14 61 11.8 73 21.0 77 3.23 33
NL-TV-NCC [25]47.3 6.92 18 14.6 14 3.96 5 8.32 35 19.8 63 2.84 1 15.4 93 26.0 98 3.92 19 10.8 12 26.6 36 5.58 13 5.09 50 6.00 51 4.07 36 11.1 66 23.5 80 10.5 87 2.09 55 3.06 29 2.27 68 11.6 70 20.4 73 9.14 63
LSM [39]47.3 7.06 24 15.2 30 5.21 44 9.65 61 21.2 80 5.48 56 11.9 57 20.2 53 5.33 43 12.0 22 30.0 50 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 43 14.3 40 6.76 55
MLDP_OF [89]47.6 7.02 21 14.5 10 4.89 30 7.00 10 17.0 32 3.34 10 14.3 84 24.0 83 3.73 15 12.9 44 34.8 105 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 83 20.5 75 9.16 64
TC/T-Flow [76]47.8 6.31 2 13.3 2 4.85 27 11.5 113 23.6 105 6.67 78 13.4 75 23.2 80 3.00 8 14.2 74 36.9 128 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 66 18.2 64 3.59 37
Sparse-NonSparse [56]48.1 7.26 35 15.7 40 5.22 45 9.83 65 21.6 84 5.45 55 12.2 59 20.8 59 5.35 46 12.1 25 30.0 50 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 39 13.8 38 5.98 50
HAST [109]48.3 7.11 27 16.0 51 4.27 6 8.90 45 17.4 37 7.54 89 6.79 1 12.4 24 1.56 1 14.8 80 37.2 129 6.63 25 4.68 6 5.70 11 2.91 2 10.5 55 20.7 62 11.1 95 3.74 118 4.39 114 5.40 128 5.74 26 10.9 26 2.09 1
WLIF-Flow [93]48.4 6.80 14 14.9 18 4.60 18 6.93 9 16.7 30 4.11 22 10.3 21 18.2 44 4.11 23 12.7 39 30.9 59 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 89 23.2 90 15.3 98
HCFN [162]48.8 6.51 6 14.1 4 4.64 21 8.25 31 20.6 68 4.51 27 10.1 19 18.2 44 4.68 33 13.4 57 35.1 109 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 70 19.6 69 14.0 91
Ramp [62]49.6 7.32 40 15.8 43 5.20 43 8.74 42 19.8 63 5.27 50 11.4 51 19.7 52 5.40 49 12.5 30 31.6 71 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 46 15.3 44 11.7 75
PMF [73]50.7 7.59 56 16.5 91 4.94 33 7.64 18 18.3 46 3.66 16 7.48 4 13.2 26 2.31 2 14.7 79 36.3 124 6.84 41 4.66 5 5.64 7 3.18 6 9.85 39 21.3 65 9.22 68 3.62 113 5.25 136 3.70 113 7.12 36 13.2 36 6.82 56
Classic+NL [31]51.3 7.40 47 16.1 55 5.36 55 9.49 60 20.9 74 5.44 54 12.3 62 20.8 59 5.20 41 12.5 30 31.3 67 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 56 17.0 55 11.9 77
CostFilter [40]52.5 7.36 42 15.7 40 4.96 35 7.76 21 18.1 41 3.83 21 7.07 2 12.4 24 3.12 10 14.6 78 36.3 124 6.57 24 4.82 15 5.81 24 3.54 8 12.4 82 20.5 61 10.3 85 3.86 123 5.96 140 4.36 120 8.86 50 16.7 52 3.72 39
FlowFields+ [130]52.6 8.95 94 17.2 109 7.26 103 7.52 15 17.3 35 5.15 43 10.4 22 17.6 40 6.16 56 10.1 10 24.5 33 6.49 23 5.11 52 6.00 51 4.57 66 9.28 34 22.2 71 6.70 30 1.77 28 3.20 48 1.51 35 13.1 82 21.8 81 15.6 101
FMOF [94]54.6 7.14 28 15.5 36 5.28 49 10.4 99 22.7 96 5.42 51 10.8 46 19.0 50 3.90 18 12.2 27 31.0 61 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 91 23.2 90 10.1 67
TV-L1-MCT [64]55.8 7.42 49 16.1 55 5.22 45 9.84 66 21.6 84 5.20 46 14.3 84 24.7 89 5.27 42 12.5 30 31.2 66 7.21 59 5.01 38 5.90 34 4.41 58 9.10 27 18.8 55 7.14 40 2.17 63 2.78 6 4.69 122 9.81 55 16.8 54 11.5 72
RNLOD-Flow [121]56.1 6.72 11 14.9 18 4.39 8 9.09 48 21.0 76 5.06 41 15.2 91 25.8 94 5.42 50 12.6 37 32.2 78 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 51 16.1 47 9.83 65
WRT [150]56.1 7.40 47 15.9 47 3.93 4 9.33 54 21.1 78 3.42 12 21.1 135 31.0 141 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 67 10.8 92 1.71 22 2.85 14 1.65 40 16.7 103 20.4 73 20.8 144
SVFilterOh [111]56.2 7.94 63 17.5 115 4.94 33 8.27 33 19.8 63 3.66 16 9.83 18 17.7 42 4.59 30 13.4 57 34.5 100 6.82 38 4.89 23 5.93 38 3.15 5 10.4 53 22.7 73 9.35 71 3.51 110 4.72 124 4.17 118 7.68 40 14.3 40 4.90 46
ProbFlowFields [128]56.6 8.84 92 17.9 121 6.90 96 7.20 13 17.3 35 4.75 36 11.6 54 20.5 57 6.31 60 8.48 8 22.0 29 5.26 10 5.25 78 6.24 92 4.67 79 9.96 44 23.9 88 6.99 37 1.64 13 2.80 8 1.41 22 14.7 91 25.5 101 14.7 94
IIOF-NLDP [131]57.0 7.31 38 15.4 33 4.42 9 8.37 36 19.9 66 3.01 5 15.4 93 25.9 96 4.00 21 7.56 5 18.6 28 4.73 8 6.04 121 7.28 133 5.15 96 10.1 47 21.3 65 9.54 74 1.74 24 2.90 20 1.50 32 15.8 96 21.6 80 20.5 141
Complementary OF [21]57.7 7.37 43 15.1 25 5.30 52 9.46 56 22.5 94 4.63 30 13.0 68 22.8 76 4.04 22 14.8 80 37.9 138 6.87 45 4.97 32 5.86 29 4.39 57 11.0 63 24.4 92 8.06 52 1.79 30 2.79 7 2.22 65 12.2 74 22.0 84 11.2 71
EPPM w/o HM [88]58.5 7.33 41 14.5 10 5.00 37 7.20 13 17.2 34 3.41 11 11.8 55 20.8 59 3.20 11 12.6 37 31.1 65 7.00 51 5.14 58 6.08 65 4.67 79 12.0 76 22.7 73 9.97 81 4.48 134 3.69 91 6.02 131 10.4 61 17.6 59 11.5 72
ALD-Flow [66]59.3 6.69 10 14.4 9 4.54 16 12.5 124 25.7 119 6.93 82 14.3 84 24.9 90 4.29 25 14.8 80 35.3 114 7.04 52 4.98 35 5.92 36 3.66 13 10.1 47 23.6 82 6.92 34 2.02 48 3.23 53 2.86 88 10.2 60 18.9 68 6.45 54
FlowFields [110]59.7 9.03 97 17.5 115 7.31 104 8.02 26 18.6 49 5.24 49 11.1 50 18.9 48 6.32 61 11.6 20 28.7 44 7.40 66 5.14 58 6.03 59 4.64 74 10.1 47 23.8 87 7.62 44 1.69 19 2.86 17 1.51 35 12.9 78 22.8 88 14.9 97
MDP-Flow [26]60.0 6.73 12 14.1 4 5.59 64 6.70 7 16.0 29 4.65 32 9.78 17 17.2 38 6.61 65 13.0 47 34.7 104 6.48 22 5.54 101 6.17 82 5.84 113 10.5 55 23.6 82 7.81 48 1.89 38 3.42 72 1.37 18 20.0 125 32.5 131 19.1 133
JOF [140]60.2 7.77 59 16.9 101 5.33 53 10.6 101 20.8 73 7.75 92 10.9 48 18.9 48 5.34 44 12.7 39 32.6 81 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 85 21.4 79 12.2 81
TC-Flow [46]60.7 6.56 7 14.1 4 4.48 12 9.25 52 21.4 81 5.03 39 14.9 89 25.8 94 3.93 20 14.5 77 35.9 118 6.97 50 5.01 38 5.97 42 3.63 9 9.98 45 22.8 76 6.83 33 2.11 57 3.25 54 3.61 111 16.7 103 26.8 107 20.0 139
S2F-IF [123]60.9 8.86 93 17.2 109 7.05 100 7.84 25 18.3 46 5.20 46 10.8 46 18.5 47 6.21 57 13.0 47 30.7 57 8.15 78 5.09 50 5.98 48 4.58 67 9.62 37 22.7 73 7.20 41 1.92 41 3.77 96 1.73 45 10.7 63 18.4 65 12.8 84
ProFlow_ROB [146]61.5 7.98 68 17.0 102 5.55 63 9.17 50 21.5 83 5.69 59 13.9 80 24.5 88 5.39 48 13.9 68 32.3 80 7.54 69 5.19 71 6.19 85 4.26 51 9.15 30 21.8 69 5.47 12 1.57 6 2.92 21 1.15 8 13.9 88 23.8 94 12.3 82
SimpleFlow [49]62.1 7.56 55 16.2 59 5.59 64 9.48 57 21.0 76 5.68 58 17.1 106 27.0 109 6.29 59 13.0 47 32.8 85 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 54 17.4 57 7.10 57
IROF-TV [53]63.1 7.55 54 16.1 55 5.46 60 9.23 51 21.8 86 5.88 63 13.3 73 22.2 72 5.50 52 12.8 41 31.6 71 7.28 61 5.12 53 6.09 66 4.67 79 13.3 94 29.6 130 9.97 81 1.60 7 3.12 42 1.06 5 11.5 69 21.3 78 11.5 72
SRR-TVOF-NL [91]63.7 7.83 60 15.4 33 5.99 77 13.2 130 26.1 123 8.61 98 13.2 71 22.0 71 6.78 66 13.6 64 30.3 53 7.34 65 4.72 7 5.56 5 4.04 35 9.87 41 19.8 60 8.30 56 3.25 105 3.73 94 3.18 97 6.93 35 12.9 35 4.92 47
HBM-GC [105]64.8 8.35 85 18.4 126 4.98 36 7.66 19 18.2 43 5.20 46 13.8 79 24.2 86 5.34 44 12.0 22 30.5 55 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 98 26.0 103 17.9 125
ACK-Prior [27]65.0 6.39 3 13.4 3 4.38 7 8.58 40 19.7 59 3.63 15 11.4 51 20.3 55 3.82 17 12.5 30 33.7 94 5.09 9 5.53 99 6.42 104 4.76 84 15.0 112 28.4 118 11.4 97 3.54 111 4.36 113 4.84 124 13.2 83 20.2 72 8.94 61
LiteFlowNet [142]65.2 9.19 98 16.6 92 7.02 99 8.23 30 18.9 52 4.53 28 12.9 66 21.5 68 6.23 58 12.0 22 26.7 37 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 19.2 119 24.7 97 21.9 150
2DHMM-SAS [92]67.2 7.39 46 15.9 47 5.25 48 10.7 104 23.4 102 5.43 52 18.0 111 27.0 109 7.95 110 13.1 51 32.7 83 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 87 22.4 87 15.5 100
Sparse Occlusion [54]67.4 7.38 44 15.8 43 5.28 49 8.25 31 19.9 66 4.71 34 15.5 96 26.3 103 4.63 31 13.5 63 33.3 93 6.92 48 5.25 78 6.26 93 4.11 41 9.70 38 21.1 64 5.94 18 4.85 136 5.95 139 3.71 114 10.8 64 20.0 71 8.01 60
DPOF [18]68.9 8.43 87 16.8 96 6.36 86 10.7 104 20.7 71 9.52 106 8.72 12 15.4 33 3.63 12 11.3 18 29.1 46 6.09 15 5.34 86 6.18 83 5.38 103 12.2 78 22.4 72 8.06 52 5.27 137 3.55 81 6.79 136 8.85 49 16.5 49 4.24 42
ROF-ND [107]69.2 7.02 21 14.7 15 4.66 22 8.18 29 19.5 55 4.66 33 15.5 96 25.9 96 5.47 51 4.68 3 12.6 2 2.76 5 5.93 115 7.12 130 5.27 98 12.2 78 25.4 100 9.09 67 4.23 131 4.20 107 3.32 100 14.7 91 22.1 86 18.8 131
ResPWCR_ROB [144]69.7 8.30 81 14.5 10 7.12 101 8.82 43 19.6 58 5.91 64 11.8 55 19.3 51 7.90 109 12.4 29 28.5 43 7.89 75 5.18 68 5.97 42 5.36 101 10.9 60 23.9 88 8.84 63 2.85 90 3.65 87 2.34 71 14.7 91 21.8 81 16.2 112
OFH [38]69.9 7.25 34 15.0 24 5.29 51 11.1 108 25.0 115 7.19 86 18.6 116 29.1 123 5.56 53 16.0 96 40.8 155 7.44 67 5.05 46 5.92 36 4.28 52 11.4 68 26.0 104 8.73 60 1.64 13 3.04 27 1.36 17 12.5 76 23.3 92 7.79 59
COFM [59]69.9 8.49 89 18.5 129 5.95 73 8.44 37 18.7 50 4.71 34 13.0 68 22.9 77 5.84 54 13.8 66 35.2 112 6.78 35 5.63 107 6.58 111 5.94 114 11.7 72 23.5 80 9.80 77 2.29 70 3.20 48 2.72 83 6.42 30 12.1 30 3.07 32
PGM-C [120]70.7 9.43 102 18.5 129 7.51 109 9.84 66 23.4 102 6.05 66 12.0 58 20.6 58 7.17 73 15.8 92 35.3 114 9.67 96 5.20 74 6.11 69 4.66 76 9.86 40 23.7 84 7.06 39 1.63 10 2.84 13 1.49 31 11.1 67 20.8 76 6.23 53
TCOF [69]71.0 7.46 52 15.1 25 5.70 67 9.13 49 21.1 78 5.43 52 19.6 122 29.8 128 8.31 114 12.9 44 31.0 61 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 45 15.9 46 3.80 40
S2D-Matching [84]72.3 8.25 78 18.0 123 5.76 70 10.9 106 22.8 97 5.71 60 17.3 107 28.5 116 6.38 63 12.1 25 30.3 53 6.65 28 5.15 62 6.13 73 4.63 72 9.18 32 19.5 59 6.69 29 2.66 82 3.35 62 3.50 105 11.6 70 19.9 70 14.7 94
ComplOF-FED-GPU [35]72.9 7.49 53 15.4 33 5.37 57 12.1 120 26.5 130 7.51 88 13.1 70 22.7 75 4.33 28 15.6 89 37.7 136 7.55 71 4.94 28 5.82 25 4.13 44 12.3 80 27.7 115 8.48 58 2.49 79 3.04 27 3.56 108 12.9 78 23.9 95 9.01 62
OAR-Flow [125]73.0 8.08 72 16.8 96 6.19 82 17.4 144 28.9 142 12.3 141 16.3 102 26.7 108 7.01 70 15.1 85 35.2 112 7.31 63 5.17 65 6.16 78 4.24 49 9.51 36 22.9 78 5.52 14 1.54 5 2.98 24 1.59 39 9.10 52 17.1 56 3.69 38
SegFlow [160]73.0 9.47 105 18.6 132 7.51 109 10.2 73 24.1 111 6.22 69 12.2 59 21.0 63 7.22 74 16.1 97 36.3 124 9.76 99 5.21 77 6.12 71 4.69 82 10.1 47 24.2 91 7.76 47 1.66 17 2.89 19 1.50 32 9.31 53 17.5 58 4.27 43
AggregFlow [97]76.6 10.3 116 21.3 160 6.91 97 15.1 137 27.6 137 10.7 111 14.0 82 24.0 83 8.70 117 14.1 71 35.0 107 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 58 18.1 63 6.13 52
CompactFlow_ROB [159]79.2 11.5 126 20.6 154 8.79 153 8.99 47 18.8 51 6.75 79 14.8 87 21.3 66 14.7 139 14.0 69 32.1 75 9.13 86 5.17 65 6.02 57 4.82 87 10.4 53 22.8 76 7.73 46 1.63 10 2.68 4 0.88 3 19.0 116 24.6 96 24.3 155
CPM-Flow [116]79.2 9.46 104 18.6 132 7.51 109 10.0 70 23.7 106 6.20 68 12.2 59 20.9 62 7.13 71 15.8 92 35.6 117 9.71 98 5.20 74 6.12 71 4.65 75 10.9 60 23.7 84 8.90 65 1.73 23 3.15 45 1.51 35 14.5 90 26.0 103 13.6 88
EpicFlow [102]80.4 9.39 101 18.4 126 7.50 108 10.0 70 23.8 108 6.29 71 15.8 99 26.6 106 7.35 81 15.5 87 34.4 99 9.65 94 5.20 74 6.11 69 4.66 76 10.2 51 24.5 93 8.18 55 1.63 10 2.81 10 1.48 27 15.8 96 24.8 98 17.1 121
Occlusion-TV-L1 [63]82.2 7.73 58 16.4 67 5.36 55 9.48 57 22.4 93 6.18 67 19.2 118 30.0 131 7.14 72 14.4 76 33.8 96 7.91 76 5.31 85 6.27 95 4.47 62 11.9 74 27.9 116 8.04 50 2.09 55 3.08 31 1.50 32 21.9 137 35.3 147 17.5 122
Aniso-Texture [82]82.3 6.49 5 14.2 8 4.54 16 7.83 24 19.5 55 4.37 25 22.0 149 33.6 162 8.47 115 10.3 11 25.4 34 5.55 11 5.19 71 6.10 67 4.45 61 18.7 134 33.0 155 20.1 164 4.07 129 4.62 121 2.47 78 20.1 126 28.5 112 20.7 142
ContinualFlow_ROB [152]83.3 11.4 124 20.8 155 8.47 127 9.76 64 18.5 48 7.94 95 16.5 103 26.6 106 11.7 130 15.7 90 37.2 129 8.85 85 5.25 78 5.97 42 5.27 98 11.8 73 24.9 95 11.4 97 1.53 4 3.06 29 1.10 6 12.4 75 17.7 62 13.1 85
RFlow [90]83.5 7.10 26 14.9 18 5.40 58 8.98 46 21.9 88 5.19 45 18.5 115 29.3 125 5.35 46 18.1 138 44.9 173 9.86 102 5.12 53 6.01 54 4.38 56 13.0 91 29.3 127 9.93 80 2.28 69 2.85 14 3.52 106 20.3 128 33.3 137 16.1 110
FF++_ROB [145]84.3 9.92 111 19.4 140 7.55 113 8.87 44 20.9 74 5.83 62 15.3 92 25.3 92 7.95 110 11.0 15 25.4 34 7.23 60 5.19 71 6.10 67 4.80 85 17.1 121 25.3 99 13.2 113 1.88 36 2.96 23 2.77 84 18.7 113 27.2 108 25.3 157
Adaptive [20]85.4 7.94 63 17.0 102 5.33 53 10.2 73 23.9 109 6.28 70 21.2 136 31.7 150 7.69 106 13.6 64 29.8 48 7.87 74 4.88 21 5.75 16 3.71 15 13.2 92 28.9 124 9.72 76 3.21 104 4.71 123 2.91 90 19.3 121 30.5 119 15.6 101
DeepFlow2 [108]85.6 8.14 74 16.6 92 5.96 75 14.1 132 26.5 130 10.2 107 15.8 99 26.2 102 6.46 64 16.5 126 37.4 133 9.54 92 5.01 38 5.94 40 3.72 16 10.7 58 25.1 96 8.08 54 1.92 41 3.12 42 2.45 75 20.3 128 32.1 128 16.3 113
DMF_ROB [139]85.7 8.27 79 16.7 94 6.36 86 11.7 116 26.4 128 7.10 85 17.8 110 28.6 118 7.33 80 15.9 95 35.9 118 9.46 90 5.05 46 5.97 42 4.51 63 12.8 89 27.4 112 9.90 79 1.60 7 2.99 25 1.48 27 19.8 124 32.0 126 16.8 117
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
MPRN [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
DAIN [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
FRUCnet [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
OFRI [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
PyrWarp [161]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 [163]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 [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
MEMC-Net+ [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
ADC [166]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
DSepConv [167]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
MAF-net [168]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
STAR-Net [169]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
Lite-VFI [170]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
AdaMoF [171]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
TC-GAN [172]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
SeFlow [173]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
DAI [174]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
TF+OM [100]87.2 7.97 67 16.8 96 5.98 76 9.40 55 20.7 71 6.33 72 15.4 93 22.9 77 17.5 144 13.4 57 31.5 68 8.10 77 5.13 57 6.06 64 4.66 76 13.9 101 29.3 127 14.0 119 2.47 76 4.09 104 2.00 55 18.3 111 29.4 116 19.3 135
Steered-L1 [118]87.4 5.97 1 12.7 1 4.67 24 7.14 12 18.2 43 4.63 30 13.2 71 23.3 81 5.12 38 15.2 86 38.1 139 7.54 69 5.85 114 6.73 115 6.98 133 13.7 100 26.5 106 11.7 103 6.39 142 4.25 109 13.3 167 22.3 140 32.7 133 20.3 140
Aniso. Huber-L1 [22]88.1 7.96 66 16.3 65 6.10 80 11.4 110 24.7 113 6.77 80 20.6 129 29.6 127 7.26 76 13.2 54 29.2 47 7.77 73 5.52 98 6.58 111 4.29 53 12.4 82 26.7 109 8.83 62 2.93 96 3.68 89 3.10 93 16.5 102 27.4 109 13.9 90
OFRF [134]90.0 9.69 107 19.6 143 6.25 83 22.2 163 29.4 145 20.7 166 21.6 140 30.1 132 17.0 143 14.1 71 31.0 61 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 77 16.7 52 15.9 109
LocallyOriented [52]91.0 9.89 109 19.9 147 6.55 89 14.7 136 27.7 138 11.0 113 21.7 143 31.9 152 7.32 79 13.3 56 30.5 55 8.32 79 5.16 63 6.04 61 4.11 41 9.90 43 21.6 68 8.75 61 2.20 64 3.43 74 2.17 62 18.3 111 26.0 103 19.6 136
AugFNG_ROB [143]91.4 12.7 134 22.1 161 9.46 157 12.1 120 24.6 112 9.39 104 18.8 117 27.1 113 14.7 139 14.0 69 30.9 59 9.24 88 5.03 42 5.72 13 5.09 93 11.0 63 24.0 90 9.53 73 1.82 33 3.25 54 1.22 9 18.2 110 23.7 93 21.6 147
EAI-Flow [151]91.4 10.4 119 19.0 137 7.83 115 13.2 130 25.8 120 9.43 105 13.7 78 21.6 69 8.47 115 14.8 80 33.0 88 9.68 97 5.12 53 6.01 54 4.74 83 11.6 69 25.7 102 9.23 69 3.66 115 3.57 85 2.04 57 13.4 86 24.8 98 10.5 69
LFNet_ROB [149]93.9 10.1 114 17.0 102 8.16 123 9.48 57 21.8 86 6.00 65 16.8 104 26.1 100 11.1 127 13.4 57 29.9 49 8.73 84 5.40 94 6.20 86 5.58 108 13.3 94 29.4 129 10.0 83 2.04 51 3.21 50 1.85 50 22.7 144 35.6 148 21.8 149
SIOF [67]94.6 8.21 77 17.0 102 5.49 61 13.0 129 27.4 136 8.63 99 20.1 127 29.0 121 16.3 142 16.8 128 37.3 132 10.0 106 5.40 94 6.34 100 4.88 88 11.6 69 25.4 100 10.1 84 1.81 32 3.27 56 1.34 15 15.1 95 25.1 100 11.9 77
TriangleFlow [30]95.2 8.08 72 17.0 102 5.12 41 11.7 116 26.1 123 6.98 84 19.5 120 30.3 135 6.34 62 12.9 44 33.0 88 6.71 33 7.00 138 8.16 142 6.63 130 12.8 89 24.5 93 10.5 87 3.59 112 5.17 134 3.27 99 12.9 78 21.9 83 12.1 79
SegOF [10]95.3 9.43 102 17.7 117 8.06 120 12.0 119 22.9 100 10.4 110 17.0 105 26.1 100 12.6 134 13.8 66 26.8 38 11.2 114 5.53 99 6.26 93 6.06 117 19.0 135 35.6 167 18.8 137 1.37 2 2.60 2 0.83 2 16.4 100 30.0 117 14.0 91
CRTflow [80]96.3 7.92 61 16.0 51 5.91 72 11.4 110 23.7 106 6.55 76 19.8 124 30.1 132 7.77 107 17.2 134 41.3 158 9.76 99 5.34 86 6.30 96 3.69 14 15.8 117 31.0 142 14.3 122 2.12 59 2.92 21 2.35 72 19.2 119 32.9 135 15.3 98
DeepFlow [86]96.4 8.73 90 17.1 108 6.26 84 15.3 140 26.7 133 11.9 140 17.3 107 26.5 105 14.1 138 18.6 144 42.8 167 11.0 112 5.00 37 5.91 35 3.75 18 11.2 67 26.2 105 8.35 57 1.88 36 2.80 8 2.60 81 22.5 142 33.6 138 17.5 122
TriFlow [95]97.9 9.01 96 18.5 129 6.60 92 11.4 110 26.4 128 7.40 87 20.9 132 29.9 130 20.9 153 12.2 27 30.8 58 6.95 49 5.26 83 6.16 78 4.88 88 12.0 76 26.5 106 11.6 101 6.97 143 4.54 117 6.57 135 13.0 81 22.0 84 9.86 66
Fusion [6]98.7 8.76 91 17.7 117 7.01 98 7.82 23 19.7 59 4.78 37 10.9 48 18.4 46 7.23 75 12.8 41 32.6 81 8.32 79 7.04 139 8.11 140 6.57 128 14.9 110 28.3 117 13.2 113 4.37 133 5.18 135 2.77 84 26.2 157 38.6 159 26.4 159
Brox et al. [5]99.1 8.46 88 16.7 94 6.56 90 11.3 109 26.2 125 6.94 83 15.0 90 25.4 93 6.89 69 17.4 135 38.8 143 9.80 101 5.99 118 6.88 122 6.26 122 14.1 104 31.1 145 12.0 105 2.03 50 3.41 71 1.14 7 19.1 118 30.3 118 12.1 79
p-harmonic [29]99.2 8.15 76 16.2 59 6.50 88 9.66 62 22.6 95 6.57 77 21.2 136 31.2 143 9.65 120 15.7 90 33.9 97 10.0 106 5.18 68 6.04 61 5.31 100 14.3 106 30.3 137 12.2 109 3.10 101 3.55 81 1.91 52 23.1 147 34.8 145 17.8 124
CBF [12]100.3 7.23 33 14.9 18 5.16 42 9.95 69 21.9 88 7.69 91 17.6 109 27.0 109 7.28 78 16.4 125 39.3 147 9.18 87 6.34 131 7.35 136 6.11 120 13.4 97 28.4 118 8.52 59 5.54 139 5.11 131 6.41 133 18.7 113 30.8 120 16.4 114
CLG-TV [48]101.9 7.94 63 16.2 59 5.80 71 10.5 100 24.0 110 6.44 74 19.9 125 29.8 128 6.83 67 14.1 71 31.5 68 7.73 72 5.98 116 7.01 126 5.15 96 14.8 109 31.0 142 12.2 109 4.20 130 4.80 125 5.22 127 19.3 121 32.6 132 15.7 105
EPMNet [133]102.2 11.6 128 20.5 152 8.03 119 17.7 146 28.9 142 13.2 146 12.9 66 20.3 55 10.7 123 15.5 87 37.4 133 9.48 91 5.36 90 6.23 89 4.94 90 14.0 102 29.9 133 12.2 109 2.97 97 5.82 138 2.01 56 10.1 59 18.8 67 3.51 36
TV-L1-improved [17]102.3 7.64 57 16.2 59 5.67 66 10.1 72 23.4 102 6.38 73 21.3 138 32.0 155 9.27 119 17.5 136 42.1 162 9.54 92 5.25 78 6.13 73 4.07 36 14.5 107 30.4 139 11.4 97 3.38 107 5.02 128 2.99 92 19.6 123 32.1 128 16.6 116
FlowNet2 [122]103.0 12.8 135 23.3 166 8.09 121 16.8 143 28.5 139 12.5 142 13.9 80 21.6 69 12.0 132 15.0 84 34.0 98 9.98 105 5.36 90 6.23 89 4.94 90 14.0 102 29.9 133 12.2 109 3.36 106 6.60 144 2.24 66 8.83 48 16.6 51 3.02 31
WOLF_ROB [148]103.8 9.97 112 18.4 126 7.33 105 20.8 154 34.8 170 13.9 148 22.2 151 30.7 139 10.9 124 17.0 133 33.2 92 12.3 121 5.16 63 6.01 54 5.11 95 10.2 51 20.7 62 9.05 66 1.97 44 3.28 57 2.48 79 17.9 109 23.1 89 21.3 146
Classic++ [32]104.9 8.05 70 17.4 114 6.09 79 11.5 113 26.3 127 6.91 81 18.1 113 28.7 119 8.18 112 16.2 98 39.0 145 8.57 82 5.36 90 6.33 98 4.54 65 15.0 112 30.4 139 11.6 101 2.70 85 3.55 81 2.94 91 21.9 137 34.0 141 17.9 125
Local-TV-L1 [65]105.3 9.74 108 17.9 121 6.89 95 18.4 149 29.4 145 14.9 150 24.4 155 30.8 140 20.2 151 19.4 149 42.4 165 12.7 123 5.35 89 6.00 51 4.10 39 13.6 98 28.9 124 9.26 70 1.62 9 2.58 1 1.48 27 20.3 128 32.0 126 16.4 114
SuperFlow [81]105.9 9.27 100 17.3 112 6.63 93 11.7 116 22.8 97 8.84 101 19.3 119 28.0 115 18.4 148 16.9 130 38.2 140 9.89 103 5.44 96 6.32 97 5.61 110 11.9 74 26.6 108 9.56 75 2.92 94 4.08 103 1.79 47 20.1 126 32.4 130 15.8 107
Rannacher [23]106.8 8.07 71 16.8 96 6.15 81 10.6 101 24.8 114 6.51 75 21.9 147 32.6 161 10.9 124 18.4 141 43.3 169 10.5 108 5.27 84 6.18 83 4.17 47 15.5 115 32.3 152 12.0 105 2.69 84 3.57 85 2.68 82 17.8 108 31.0 121 16.1 110
F-TV-L1 [15]108.0 8.41 86 16.8 96 6.31 85 18.0 148 29.7 147 12.8 143 21.6 140 30.5 136 10.1 122 18.2 139 42.3 164 9.65 94 5.02 41 5.97 42 3.91 23 14.1 104 30.8 141 10.6 91 2.79 86 4.90 126 2.35 72 20.5 131 32.7 133 15.6 101
StereoOF-V1MT [119]109.2 8.14 74 15.8 43 5.42 59 17.6 145 34.3 168 10.3 108 21.6 140 31.5 147 7.27 77 15.8 92 32.7 83 10.7 109 5.62 106 6.40 102 6.00 116 16.6 120 30.0 135 15.5 124 2.01 47 3.08 31 3.15 95 33.6 167 44.0 168 32.8 164
BriefMatch [124]109.3 6.91 17 14.8 17 4.85 27 11.0 107 22.8 97 8.24 96 9.42 14 16.6 37 5.13 40 16.7 127 40.7 154 8.61 83 9.76 145 10.6 169 14.1 146 18.2 131 31.0 142 17.4 133 9.26 147 6.60 144 20.9 173 28.0 161 36.5 151 34.9 166
Dynamic MRF [7]112.0 8.32 84 17.3 112 5.95 73 12.3 122 28.5 139 7.75 92 19.6 122 31.8 151 7.56 82 18.4 141 42.2 163 11.6 118 5.25 78 6.16 78 4.80 85 17.7 125 34.4 163 16.6 129 1.89 38 2.63 3 3.21 98 30.3 163 43.6 167 29.0 161
DF-Auto [115]112.0 10.7 122 19.8 146 7.42 107 16.3 142 25.3 116 13.1 145 19.5 120 28.5 116 17.8 146 16.9 130 37.2 129 10.8 110 6.76 137 8.12 141 5.56 107 10.8 59 25.2 97 6.95 35 3.69 117 4.92 127 1.48 27 17.7 107 27.9 111 14.6 93
Bartels [41]112.0 8.31 83 17.7 117 5.51 62 8.46 38 20.6 68 4.89 38 14.8 87 26.0 98 7.89 108 18.5 143 43.6 170 11.1 113 6.18 124 6.51 110 8.63 141 15.6 116 32.6 154 13.9 118 3.86 123 4.56 118 7.09 137 22.5 142 36.5 151 18.4 129
Shiralkar [42]113.6 7.92 61 15.2 30 5.73 68 14.6 135 30.3 148 9.04 102 21.7 143 31.2 143 9.77 121 19.6 151 41.5 159 13.2 125 5.17 65 6.04 61 4.63 72 18.0 130 31.1 145 14.7 123 3.67 116 3.40 69 4.74 123 23.9 152 36.6 153 18.9 132
GraphCuts [14]114.5 9.24 99 17.2 109 7.53 112 22.1 161 33.0 162 16.8 158 15.9 101 23.1 79 15.6 141 14.2 74 28.9 45 9.34 89 5.83 113 6.82 118 6.25 121 18.5 133 29.7 131 12.0 105 2.85 90 3.39 67 3.52 106 23.8 151 36.1 149 19.1 133
Second-order prior [8]117.0 8.04 69 16.3 65 6.01 78 12.5 124 26.5 130 9.10 103 21.0 133 31.1 142 9.23 118 16.2 98 36.2 123 9.93 104 5.70 110 6.67 114 5.09 93 20.7 163 34.1 161 21.0 165 3.76 119 3.89 99 4.25 119 18.9 115 31.8 125 19.9 138
Filter Flow [19]117.9 10.5 120 19.4 140 8.33 124 12.5 124 25.8 120 8.69 100 19.9 125 27.0 109 21.7 156 19.0 146 33.1 91 15.9 152 5.34 86 6.21 87 5.37 102 16.2 119 26.7 109 15.5 124 3.46 109 4.48 116 2.26 67 23.3 150 31.5 124 18.5 130
CNN-flow-warp+ref [117]118.8 9.91 110 19.6 143 7.85 116 10.6 101 22.9 100 8.55 97 21.3 138 32.1 157 11.9 131 18.7 145 42.0 161 11.3 115 5.56 102 6.34 100 6.08 119 12.3 80 27.6 113 10.8 92 2.06 53 3.69 91 3.16 96 33.3 165 40.4 162 34.7 165
FlowNetS+ft+v [112]119.5 8.96 95 17.8 120 6.83 94 14.2 133 26.2 125 11.1 114 22.3 152 32.2 158 12.7 135 16.8 128 36.1 122 10.9 111 6.31 130 7.29 134 6.26 122 12.5 86 28.8 122 9.88 78 3.84 122 6.75 146 6.30 132 16.4 100 29.0 114 14.7 94
StereoFlow [44]120.1 16.2 168 22.6 164 13.9 170 22.1 161 31.6 154 18.8 163 24.7 156 30.6 138 21.2 155 23.3 163 39.9 148 19.6 163 5.98 116 6.22 88 7.11 135 11.6 69 27.6 113 8.05 51 1.36 1 2.85 14 0.65 1 20.7 132 33.7 139 17.0 120
IAOF2 [51]120.2 10.0 113 19.9 147 7.91 118 14.4 134 26.7 133 10.9 112 22.0 149 32.2 158 17.6 145 19.1 147 33.0 88 17.1 156 5.81 112 6.86 120 4.94 90 12.6 87 25.9 103 11.9 104 4.26 132 4.11 106 7.75 140 16.2 99 26.5 106 13.5 87
Ad-TV-NDC [36]124.0 12.1 132 18.6 132 10.7 162 25.5 167 32.0 158 22.2 167 29.3 169 34.3 167 22.8 160 16.9 130 32.8 85 12.2 120 5.99 118 7.20 132 3.83 20 12.6 87 28.5 120 10.3 85 2.79 86 4.07 102 1.78 46 24.1 153 31.4 123 25.1 156
TVL1_ROB [138]124.9 12.9 136 20.8 155 9.80 160 21.3 158 30.9 151 17.9 162 27.9 163 33.6 162 23.5 164 20.5 153 37.8 137 16.7 154 5.57 103 6.47 107 5.46 105 14.5 107 32.1 151 12.1 108 1.69 19 2.81 10 1.22 9 22.9 145 36.3 150 18.3 128
LDOF [28]126.2 9.66 106 18.9 136 7.13 102 15.1 137 29.1 144 11.3 115 15.6 98 25.1 91 10.9 124 20.9 156 43.1 168 14.9 150 6.12 122 7.01 126 6.26 122 16.0 118 31.2 147 13.2 113 3.89 125 5.61 137 8.96 164 19.0 116 33.0 136 11.7 75
Nguyen [33]127.0 11.4 124 19.6 143 8.44 126 21.0 157 31.7 156 17.7 160 29.8 171 36.3 171 24.1 168 18.2 139 34.6 103 13.9 126 6.28 126 6.85 119 7.51 138 15.4 114 33.0 155 14.0 119 2.24 67 3.11 38 1.79 47 21.6 135 33.9 140 15.8 107
IAOF [50]127.4 10.1 114 18.6 132 7.89 117 22.2 163 33.7 165 15.9 154 33.0 173 39.2 174 23.7 165 16.2 98 32.1 75 11.6 118 5.80 111 6.87 121 5.39 104 17.8 127 30.1 136 11.4 97 3.13 103 3.69 91 3.88 116 22.4 141 29.3 115 21.6 147
2D-CLG [1]127.5 15.2 166 24.5 170 11.2 164 15.1 137 25.9 122 13.5 147 27.5 162 33.9 164 24.7 169 22.2 160 38.3 141 19.0 162 5.67 108 6.44 105 6.29 125 17.5 123 34.3 162 16.4 128 1.47 3 2.68 4 1.54 38 21.7 136 34.6 144 16.9 119
UnFlow [129]128.9 16.0 167 25.1 171 11.3 165 12.7 128 22.2 92 11.7 139 20.4 128 27.6 114 13.6 136 20.8 154 36.0 120 17.9 159 6.34 131 6.89 123 7.74 139 17.7 125 33.5 158 17.1 132 2.92 94 4.33 111 1.37 18 20.7 132 37.3 157 15.6 101
SPSA-learn [13]129.5 11.3 123 19.4 140 8.52 128 20.9 155 34.2 167 16.2 157 26.5 160 33.9 164 22.4 159 22.5 162 39.9 148 18.9 161 5.59 104 6.41 103 5.94 114 17.8 127 31.4 149 18.3 136 2.11 57 3.11 38 1.37 18 24.3 154 35.1 146 19.7 137
Learning Flow [11]129.9 8.28 80 17.0 102 5.75 69 12.3 122 28.5 139 7.79 94 18.4 114 28.7 119 8.29 113 22.2 160 40.6 153 17.3 157 8.52 140 10.3 168 7.04 134 19.9 161 35.1 165 16.8 131 3.11 102 4.59 120 3.59 110 26.9 159 40.0 161 20.9 145
HBpMotionGpu [43]130.5 12.2 133 22.1 161 8.34 125 17.9 147 31.4 153 14.7 149 29.2 168 37.8 173 20.6 152 19.1 147 44.6 172 11.5 117 5.60 105 6.45 106 6.06 117 13.2 92 28.8 122 11.1 95 3.45 108 3.97 101 2.04 57 23.1 147 34.1 142 20.7 142
Modified CLG [34]134.1 11.6 128 20.5 152 9.14 156 12.6 127 25.4 118 10.3 108 27.4 161 34.4 168 23.8 166 21.8 158 42.7 166 16.7 154 6.18 124 7.06 129 6.57 128 14.9 110 33.0 155 13.4 116 2.45 74 3.80 97 3.81 115 22.0 139 36.6 153 16.8 117
Black & Anandan [4]135.7 10.5 120 18.0 123 8.14 122 21.4 160 32.8 161 16.1 156 26.1 159 32.3 160 21.8 157 20.8 154 38.9 144 16.1 153 6.29 128 7.41 137 5.62 111 17.1 121 31.2 147 13.7 117 4.06 128 5.11 131 2.37 74 23.1 147 34.1 142 15.7 105
GroupFlow [9]137.0 11.5 126 21.2 159 8.71 152 20.5 152 33.0 162 15.7 153 23.6 153 31.6 148 20.1 150 16.2 98 34.5 100 11.3 115 8.86 141 9.84 167 6.50 127 18.2 131 30.3 137 17.4 133 3.82 121 5.05 129 6.55 134 21.1 134 28.8 113 22.4 153
2bit-BM-tele [98]137.1 10.3 116 20.1 149 7.40 106 11.5 113 26.7 133 7.57 90 20.6 129 32.0 155 11.4 129 17.9 137 40.3 151 12.3 121 6.29 128 6.80 117 6.93 132 21.0 164 32.0 150 18.0 135 7.61 144 6.57 143 11.1 166 27.5 160 39.4 160 29.2 162
Heeger++ [104]139.9 11.7 130 18.3 125 9.04 155 23.3 166 37.0 173 17.4 159 21.0 133 29.1 123 11.1 127 27.0 167 40.5 152 24.4 166 5.69 109 6.33 98 5.80 112 25.9 170 37.5 170 26.3 170 2.48 77 3.88 98 2.20 64 37.6 170 46.0 171 41.6 173
HCIC-L [99]140.4 14.6 163 21.1 157 9.67 158 42.7 174 36.7 172 46.6 174 21.8 145 30.5 136 17.9 147 21.1 157 35.1 109 18.6 160 6.42 133 6.58 111 7.35 137 17.8 127 28.6 121 16.6 129 12.8 150 14.3 150 15.3 169 16.8 105 25.7 102 12.7 83
BlockOverlap [61]140.9 10.3 116 19.1 138 7.74 114 15.4 141 25.3 116 13.0 144 24.3 154 31.9 152 21.0 154 19.5 150 43.8 171 13.1 124 9.14 142 7.60 138 13.9 145 19.0 135 29.0 126 15.7 126 11.0 148 8.77 148 24.8 174 23.0 146 31.3 122 25.9 158
H+S_ROB [137]142.3 16.6 170 23.6 168 11.9 167 19.1 150 30.6 150 15.6 152 25.1 157 30.2 134 23.4 162 29.1 168 36.3 124 27.9 169 13.4 171 15.7 171 12.2 143 27.2 171 38.8 172 27.8 171 1.70 21 2.81 10 1.42 23 32.2 164 41.3 165 30.2 163
TI-DOFE [24]142.5 14.6 163 21.1 157 11.7 166 22.4 165 31.6 154 19.6 164 28.6 166 31.2 143 26.3 170 26.3 166 36.0 120 25.1 167 6.43 134 7.34 135 6.67 131 19.1 137 33.8 159 18.9 138 2.88 92 3.15 45 2.82 87 25.7 156 36.6 153 22.3 152
Horn & Schunck [3]144.2 11.8 131 19.3 139 8.85 154 20.1 151 33.5 164 15.3 151 25.5 158 31.2 143 24.0 167 26.1 165 38.6 142 23.5 164 6.12 122 6.99 124 6.34 126 19.9 161 33.9 160 19.6 162 3.95 127 4.28 110 2.46 77 25.3 155 37.5 158 22.0 151
FFV1MT [106]151.9 13.9 162 23.4 167 10.8 163 20.9 155 34.5 169 16.0 155 21.8 145 29.5 126 13.8 137 31.0 172 41.7 160 29.4 171 9.97 146 6.78 116 17.9 171 23.8 167 35.3 166 25.0 169 2.99 98 4.24 108 3.57 109 37.6 170 46.0 171 41.6 173
SILK [79]153.2 13.2 160 22.4 163 10.2 161 20.5 152 32.2 160 17.7 160 29.0 167 34.1 166 23.4 162 22.0 159 40.8 155 17.3 157 6.28 126 7.17 131 7.12 136 21.7 165 35.8 168 19.6 162 5.44 138 3.45 77 10.8 165 29.3 162 40.6 164 26.7 160
Adaptive flow [45]153.8 13.2 160 20.2 150 9.78 159 27.3 169 31.9 157 25.4 168 28.3 165 31.6 148 30.5 173 19.7 152 37.6 135 15.3 151 11.2 170 12.6 170 8.93 142 17.6 124 29.8 132 15.8 127 13.1 151 11.0 149 18.3 170 26.4 158 36.8 156 22.7 154
PGAM+LK [55]153.9 14.9 165 22.8 165 14.1 171 25.5 167 31.3 152 26.6 169 21.9 147 26.4 104 22.2 158 26.0 164 39.1 146 24.0 165 9.61 144 6.49 109 14.1 146 24.3 168 35.0 164 23.0 167 6.19 141 6.24 142 7.26 138 34.3 168 40.4 162 40.8 172
SLK [47]154.3 17.2 172 24.0 169 18.2 172 21.3 158 30.4 149 20.1 165 27.9 163 31.9 152 23.3 161 31.4 173 39.9 148 30.0 173 6.60 135 7.04 128 8.37 140 22.8 166 36.4 169 21.6 166 3.90 126 3.75 95 5.02 125 33.3 165 41.7 166 35.2 167
AVG_FLOW_ROB [141]160.5 32.4 174 34.1 174 37.7 174 35.1 173 33.7 165 37.0 173 20.7 131 24.1 85 19.4 149 34.1 174 35.1 109 34.8 174 39.6 173 37.0 173 44.9 173 40.6 174 42.2 173 38.5 174 11.3 149 15.3 151 7.36 139 46.5 174 52.3 174 38.9 169
FOLKI [16]163.2 16.2 168 25.9 172 12.7 169 32.5 171 35.6 171 34.7 171 29.4 170 35.1 170 26.9 171 29.1 168 41.0 157 27.9 169 9.58 143 8.90 143 13.5 144 25.7 169 38.3 171 24.5 168 7.71 145 5.13 133 14.5 168 36.5 169 44.4 169 36.1 168
Pyramid LK [2]164.6 17.0 171 20.4 151 19.4 173 31.7 170 32.1 159 32.5 170 32.9 172 34.8 169 29.9 172 29.4 170 35.3 114 29.9 172 31.7 172 35.5 172 29.8 172 29.9 172 32.3 152 28.0 172 9.01 146 7.93 147 18.9 171 39.9 172 45.4 170 39.0 170
Periodicity [78]169.9 18.0 173 30.5 173 12.3 168 34.0 172 41.4 174 35.6 172 36.5 174 36.5 172 35.2 174 29.7 171 46.6 174 26.8 168 51.8 174 56.5 174 45.5 174 36.7 173 42.4 174 37.1 173 5.99 140 6.16 141 19.3 172 40.1 173 51.1 173 40.4 171
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 Michal Neoral, Jan Sochman, and Jiri 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 Tianfan Xue, Baian Chen, Jiajun Wu, Donglai Wei, and William 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 Van Thang Nguyen, Kyujoong Lee, and Hyuk-Jae Lee. (Interpolation results only.) A stacked deep MEMC network for frame rate up conversion and its application to HEVC. Submitted to IEEE TCSVT 2019.
[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 Jun Chen, Zemin Cai, Jianhuang Lai, and Xiaohua 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 Xianhang Cheng and Zhenzhong 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 Wenbo Bao, Wei-Sheng Lai, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang. (Interpolation results only.) MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement. Submitted to 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.
[169] STAR-Net 0.049 2 color Anonymous. (Interpolation results only.) Space-time-aware multiple resolution for video enhancement. CPVR 2020 submission 430.
[170] Lite-VFI 0.13 2 color Anonymous. (Interpolation results only.) Lite-VFI: Lightweight video frame interpolation via multi-stage error-adaptive refinement. CVPR 2020 submission 7434.
[171] AdaMoF 0.03 2 color Anonymous. (Interpolation results only.) AdaMoF: Adaptive mixture of flows for video frame interpolation. CVPR 2020 submission 710.
[172] TC-GAN 0.13 2 color Anonymous. (Interpolation results only.) A temporal and contextual generative adversarial network for video frame interpolation. CVPR 2020 submission 111.
[173] SeFlow 0.52 2 color Anonymous. (Interpolation results only.) SemanticFlow: Robust video interpolation via structure-to-texture generation. CVPR 2020 submission 8559.
[174] DAI 0.23 2 color Anonymous. (Interpolation results only.) Deep animation inbetweening. CVPR 2020 submission 6404.
* 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.