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]12.9 6.84 16 15.1 25 4.48 12 6.28 5 15.5 22 3.00 4 7.42 3 13.5 21 2.39 3 7.71 7 22.7 25 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 18 10.7 18 2.48 20
PMMST [114]12.9 6.46 4 14.1 4 3.23 1 5.42 1 12.7 18 3.51 14 8.20 9 14.7 26 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 23 11.3 23 2.25 2
NN-field [71]16.7 7.29 36 16.0 51 4.74 25 6.15 2 15.2 21 3.02 6 7.77 7 14.1 25 2.71 6 7.56 5 22.8 26 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 19 10.8 19 2.49 21
OFLAF [77]19.5 6.75 13 14.9 18 4.44 10 7.07 11 17.5 32 3.10 7 8.45 10 15.5 28 2.50 5 13.0 47 35.0 101 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 22 11.0 21 2.79 22
MDP-Flow2 [68]27.2 6.66 8 14.7 15 4.53 14 6.79 8 17.0 26 3.23 8 8.68 11 15.8 29 2.90 7 13.4 57 33.7 88 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 26 12.8 28 3.33 28
FC-2Layers-FF [74]30.0 7.07 25 15.5 36 4.91 31 8.30 34 19.7 53 4.30 23 7.61 5 13.6 22 4.29 25 11.8 21 30.2 46 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 32 14.3 34 4.12 35
nLayers [57]30.1 7.20 31 16.0 51 4.66 22 6.25 4 14.7 19 3.70 19 7.72 6 13.7 23 4.81 34 13.1 51 34.8 99 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 38 15.6 39 6.10 45
3DFlow [135]34.8 6.97 19 15.1 25 3.90 3 8.12 28 19.7 53 3.79 20 13.6 70 24.2 80 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 50 8.87 64 2.38 72 3.11 38 2.45 75 5.82 21 11.1 22 3.00 24
ComponentFusion [96]36.0 7.22 32 15.9 47 4.61 19 7.60 17 19.2 47 3.30 9 9.70 16 17.6 34 3.77 16 11.1 16 31.0 55 4.45 7 4.96 31 5.88 32 4.25 50 10.9 60 23.7 78 9.40 72 1.90 40 3.08 31 1.69 43 8.00 36 15.1 37 4.57 38
FESL [72]38.7 6.97 19 15.3 32 4.47 11 9.74 63 21.4 75 5.49 57 11.4 45 20.2 47 4.25 24 12.5 30 31.5 62 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 61 17.6 53 10.1 61
AGIF+OF [85]39.6 7.17 29 15.6 38 4.93 32 10.2 73 22.1 84 5.16 44 12.5 59 21.2 59 4.88 36 12.5 30 31.7 67 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 58 17.6 53 11.0 64
PWC-Net_ROB [147]39.8 8.30 81 16.2 59 6.58 91 8.56 39 20.6 62 4.38 26 12.3 56 21.4 61 6.00 55 10.8 12 27.0 34 6.88 46 4.94 28 5.79 22 3.98 29 8.37 17 19.3 52 5.42 11 1.65 16 3.29 58 1.02 4 7.86 35 14.2 33 3.37 29
NNF-EAC [103]40.3 6.83 15 14.9 18 4.80 26 7.59 16 18.0 34 4.31 24 9.03 13 16.1 30 3.09 9 13.2 54 32.2 72 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 17.0 100 27.6 104 18.0 121
Layers++ [37]40.7 7.19 30 15.7 40 5.08 38 6.15 2 14.8 20 3.42 12 7.83 8 14.0 24 4.84 35 10.9 14 26.9 33 6.19 17 4.83 18 5.84 27 4.36 55 12.4 82 25.2 91 10.5 87 2.43 73 3.56 84 1.92 53 8.66 41 16.1 41 7.77 52
Correlation Flow [75]41.4 6.66 8 14.5 10 3.81 2 7.78 22 17.5 32 2.85 2 18.0 105 29.0 115 4.31 27 9.28 9 22.1 24 5.57 12 5.12 53 6.13 73 3.98 29 11.0 63 23.3 73 10.5 87 2.07 54 3.08 31 2.32 70 6.79 27 12.5 26 4.83 39
Efficient-NL [60]41.9 7.43 50 16.2 59 4.85 27 7.73 20 18.1 35 4.58 29 14.0 76 23.6 76 4.47 29 13.1 51 32.9 81 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 28 12.1 24 5.78 43
PH-Flow [101]43.1 7.38 44 15.9 47 5.22 45 9.30 53 19.5 49 5.71 60 9.62 15 17.2 32 5.09 37 13.4 57 34.5 94 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 31 13.3 31 5.33 42
IROF++ [58]43.6 7.44 51 16.1 55 5.11 40 8.61 41 19.4 48 5.12 42 12.3 56 21.0 57 5.12 38 12.8 41 32.1 69 7.13 56 4.88 21 5.76 18 3.89 22 9.01 23 18.9 50 6.76 31 1.78 29 3.22 52 1.23 11 10.4 55 18.5 60 13.3 80
LME [70]44.3 7.04 23 15.6 38 4.53 14 6.68 6 16.9 25 2.85 2 13.6 70 22.6 68 12.0 126 11.5 19 27.8 35 6.39 21 5.03 42 5.93 38 4.52 64 12.4 82 27.0 105 10.9 94 1.76 27 3.38 66 1.43 24 6.62 25 12.5 26 2.86 23
NL-TV-NCC [25]45.3 6.92 18 14.6 14 3.96 5 8.32 35 19.8 57 2.84 1 15.4 87 26.0 92 3.92 19 10.8 12 26.6 30 5.58 13 5.09 50 6.00 51 4.07 36 11.1 66 23.5 74 10.5 87 2.09 55 3.06 29 2.27 68 11.6 64 20.4 67 9.14 57
Classic+CPF [83]45.5 7.31 38 15.8 43 5.09 39 9.93 68 22.1 84 5.05 40 13.3 67 22.4 67 4.64 32 12.5 30 32.0 68 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 51 16.5 43 13.8 83
CombBMOF [113]45.5 7.30 37 15.1 25 4.61 19 8.08 27 18.2 37 3.69 18 10.2 20 18.1 37 2.47 4 11.2 17 28.1 36 6.67 29 4.82 15 5.76 18 4.13 44 13.3 94 22.1 64 14.1 121 2.90 93 4.33 111 2.14 61 11.8 67 21.0 71 3.23 27
LSM [39]45.5 7.06 24 15.2 30 5.21 44 9.65 61 21.2 74 5.48 56 11.9 51 20.2 47 5.33 43 12.0 22 30.0 44 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 37 14.3 34 6.76 49
TC/T-Flow [76]45.8 6.31 2 13.3 2 4.85 27 11.5 107 23.6 99 6.67 78 13.4 69 23.2 74 3.00 8 14.2 74 36.9 122 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 60 18.2 58 3.59 31
MLDP_OF [89]45.9 7.02 21 14.5 10 4.89 30 7.00 10 17.0 26 3.34 10 14.3 78 24.0 77 3.73 15 12.9 44 34.8 99 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 77 20.5 69 9.16 58
Sparse-NonSparse [56]46.3 7.26 35 15.7 40 5.22 45 9.83 65 21.6 78 5.45 55 12.2 53 20.8 53 5.35 46 12.1 25 30.0 44 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 33 13.8 32 5.98 44
HAST [109]46.8 7.11 27 16.0 51 4.27 6 8.90 45 17.4 31 7.54 89 6.79 1 12.4 18 1.56 1 14.8 80 37.2 123 6.63 25 4.68 6 5.70 11 2.91 2 10.5 55 20.7 56 11.1 95 3.74 118 4.39 114 5.40 128 5.74 20 10.9 20 2.09 1
WLIF-Flow [93]46.9 6.80 14 14.9 18 4.60 18 6.93 9 16.7 24 4.11 22 10.3 21 18.2 38 4.11 23 12.7 39 30.9 53 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 83 23.2 84 15.3 92
HCFN [162]47.3 6.51 6 14.1 4 4.64 21 8.25 31 20.6 62 4.51 27 10.1 19 18.2 38 4.68 33 13.4 57 35.1 103 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 64 19.6 63 14.0 85
Ramp [62]47.9 7.32 40 15.8 43 5.20 43 8.74 42 19.8 57 5.27 50 11.4 45 19.7 46 5.40 49 12.5 30 31.6 65 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 40 15.3 38 11.7 69
PMF [73]48.7 7.59 56 16.5 85 4.94 33 7.64 18 18.3 40 3.66 16 7.48 4 13.2 20 2.31 2 14.7 79 36.3 118 6.84 41 4.66 5 5.64 7 3.18 6 9.85 39 21.3 59 9.22 68 3.62 113 5.25 136 3.70 113 7.12 30 13.2 30 6.82 50
Classic+NL [31]49.6 7.40 47 16.1 55 5.36 55 9.49 60 20.9 68 5.44 54 12.3 56 20.8 53 5.20 41 12.5 30 31.3 61 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 50 17.0 49 11.9 71
FlowFields+ [130]50.6 8.95 94 17.2 103 7.26 103 7.52 15 17.3 29 5.15 43 10.4 22 17.6 34 6.16 56 10.1 10 24.5 27 6.49 23 5.11 52 6.00 51 4.57 66 9.28 34 22.2 65 6.70 30 1.77 28 3.20 48 1.51 35 13.1 76 21.8 75 15.6 95
CostFilter [40]50.8 7.36 42 15.7 40 4.96 35 7.76 21 18.1 35 3.83 21 7.07 2 12.4 18 3.12 10 14.6 78 36.3 118 6.57 24 4.82 15 5.81 24 3.54 8 12.4 82 20.5 55 10.3 85 3.86 123 5.96 140 4.36 120 8.86 44 16.7 46 3.72 33
FMOF [94]52.6 7.14 28 15.5 36 5.28 49 10.4 93 22.7 90 5.42 51 10.8 40 19.0 44 3.90 18 12.2 27 31.0 55 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 85 23.2 84 10.1 61
TV-L1-MCT [64]53.8 7.42 49 16.1 55 5.22 45 9.84 66 21.6 78 5.20 46 14.3 78 24.7 83 5.27 42 12.5 30 31.2 60 7.21 59 5.01 38 5.90 34 4.41 58 9.10 27 18.8 49 7.14 40 2.17 63 2.78 6 4.69 122 9.81 49 16.8 48 11.5 66
SVFilterOh [111]54.2 7.94 63 17.5 109 4.94 33 8.27 33 19.8 57 3.66 16 9.83 18 17.7 36 4.59 30 13.4 57 34.5 94 6.82 38 4.89 23 5.93 38 3.15 5 10.4 53 22.7 67 9.35 71 3.51 110 4.72 124 4.17 118 7.68 34 14.3 34 4.90 40
RNLOD-Flow [121]54.3 6.72 11 14.9 18 4.39 8 9.09 48 21.0 70 5.06 41 15.2 85 25.8 88 5.42 50 12.6 37 32.2 72 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 45 16.1 41 9.83 59
ProbFlowFields [128]54.3 8.84 92 17.9 115 6.90 96 7.20 13 17.3 29 4.75 36 11.6 48 20.5 51 6.31 60 8.48 8 22.0 23 5.26 10 5.25 78 6.24 92 4.67 79 9.96 44 23.9 82 6.99 37 1.64 13 2.80 8 1.41 22 14.7 85 25.5 95 14.7 88
WRT [150]54.4 7.40 47 15.9 47 3.93 4 9.33 54 21.1 72 3.42 12 21.1 129 31.0 135 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 61 10.8 92 1.71 22 2.85 14 1.65 40 16.7 97 20.4 67 20.8 138
IIOF-NLDP [131]55.0 7.31 38 15.4 33 4.42 9 8.37 36 19.9 60 3.01 5 15.4 87 25.9 90 4.00 21 7.56 5 18.6 22 4.73 8 6.04 121 7.28 133 5.15 96 10.1 47 21.3 59 9.54 74 1.74 24 2.90 20 1.50 32 15.8 90 21.6 74 20.5 135
Complementary OF [21]55.7 7.37 43 15.1 25 5.30 52 9.46 56 22.5 88 4.63 30 13.0 62 22.8 70 4.04 22 14.8 80 37.9 132 6.87 45 4.97 32 5.86 29 4.39 57 11.0 63 24.4 86 8.06 52 1.79 30 2.79 7 2.22 65 12.2 68 22.0 78 11.2 65
EPPM w/o HM [88]56.5 7.33 41 14.5 10 5.00 37 7.20 13 17.2 28 3.41 11 11.8 49 20.8 53 3.20 11 12.6 37 31.1 59 7.00 51 5.14 58 6.08 65 4.67 79 12.0 76 22.7 67 9.97 81 4.48 134 3.69 91 6.02 131 10.4 55 17.6 53 11.5 66
ALD-Flow [66]57.0 6.69 10 14.4 9 4.54 16 12.5 118 25.7 113 6.93 82 14.3 78 24.9 84 4.29 25 14.8 80 35.3 108 7.04 52 4.98 35 5.92 36 3.66 13 10.1 47 23.6 76 6.92 34 2.02 48 3.23 53 2.86 88 10.2 54 18.9 62 6.45 48
FlowFields [110]57.4 9.03 97 17.5 109 7.31 104 8.02 26 18.6 43 5.24 49 11.1 44 18.9 42 6.32 61 11.6 20 28.7 38 7.40 66 5.14 58 6.03 59 4.64 74 10.1 47 23.8 81 7.62 44 1.69 19 2.86 17 1.51 35 12.9 72 22.8 82 14.9 91
JOF [140]58.0 7.77 59 16.9 95 5.33 53 10.6 95 20.8 67 7.75 92 10.9 42 18.9 42 5.34 44 12.7 39 32.6 75 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 79 21.4 73 12.2 75
MDP-Flow [26]58.2 6.73 12 14.1 4 5.59 64 6.70 7 16.0 23 4.65 32 9.78 17 17.2 32 6.61 65 13.0 47 34.7 98 6.48 22 5.54 101 6.17 82 5.84 113 10.5 55 23.6 76 7.81 48 1.89 38 3.42 72 1.37 18 20.0 119 32.5 125 19.1 127
S2F-IF [123]58.6 8.86 93 17.2 103 7.05 100 7.84 25 18.3 40 5.20 46 10.8 40 18.5 41 6.21 57 13.0 47 30.7 51 8.15 78 5.09 50 5.98 48 4.58 67 9.62 37 22.7 67 7.20 41 1.92 41 3.77 96 1.73 45 10.7 57 18.4 59 12.8 78
TC-Flow [46]58.7 6.56 7 14.1 4 4.48 12 9.25 52 21.4 75 5.03 39 14.9 83 25.8 88 3.93 20 14.5 77 35.9 112 6.97 50 5.01 38 5.97 42 3.63 9 9.98 45 22.8 70 6.83 33 2.11 57 3.25 54 3.61 111 16.7 97 26.8 101 20.0 133
ProFlow_ROB [146]59.2 7.98 68 17.0 96 5.55 63 9.17 50 21.5 77 5.69 59 13.9 74 24.5 82 5.39 48 13.9 68 32.3 74 7.54 69 5.19 71 6.19 85 4.26 51 9.15 30 21.8 63 5.47 12 1.57 6 2.92 21 1.15 8 13.9 82 23.8 88 12.3 76
SimpleFlow [49]60.4 7.56 55 16.2 59 5.59 64 9.48 57 21.0 70 5.68 58 17.1 100 27.0 103 6.29 59 13.0 47 32.8 79 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 48 17.4 51 7.10 51
IROF-TV [53]61.1 7.55 54 16.1 55 5.46 60 9.23 51 21.8 80 5.88 63 13.3 67 22.2 66 5.50 52 12.8 41 31.6 65 7.28 61 5.12 53 6.09 66 4.67 79 13.3 94 29.6 124 9.97 81 1.60 7 3.12 42 1.06 5 11.5 63 21.3 72 11.5 66
SRR-TVOF-NL [91]61.4 7.83 60 15.4 33 5.99 77 13.2 124 26.1 117 8.61 98 13.2 65 22.0 65 6.78 66 13.6 64 30.3 47 7.34 65 4.72 7 5.56 5 4.04 35 9.87 41 19.8 54 8.30 56 3.25 105 3.73 94 3.18 97 6.93 29 12.9 29 4.92 41
HBM-GC [105]62.8 8.35 85 18.4 120 4.98 36 7.66 19 18.2 37 5.20 46 13.8 73 24.2 80 5.34 44 12.0 22 30.5 49 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 92 26.0 97 17.9 119
ACK-Prior [27]63.0 6.39 3 13.4 3 4.38 7 8.58 40 19.7 53 3.63 15 11.4 45 20.3 49 3.82 17 12.5 30 33.7 88 5.09 9 5.53 99 6.42 104 4.76 84 15.0 112 28.4 112 11.4 97 3.54 111 4.36 113 4.84 124 13.2 77 20.2 66 8.94 55
LiteFlowNet [142]63.2 9.19 98 16.6 86 7.02 99 8.23 30 18.9 46 4.53 28 12.9 60 21.5 62 6.23 58 12.0 22 26.7 31 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 19.2 113 24.7 91 21.9 144
2DHMM-SAS [92]64.9 7.39 46 15.9 47 5.25 48 10.7 98 23.4 96 5.43 52 18.0 105 27.0 103 7.95 104 13.1 51 32.7 77 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 81 22.4 81 15.5 94
Sparse Occlusion [54]65.4 7.38 44 15.8 43 5.28 49 8.25 31 19.9 60 4.71 34 15.5 90 26.3 97 4.63 31 13.5 63 33.3 87 6.92 48 5.25 78 6.26 93 4.11 41 9.70 38 21.1 58 5.94 18 4.85 136 5.95 139 3.71 114 10.8 58 20.0 65 8.01 54
DPOF [18]66.7 8.43 87 16.8 90 6.36 86 10.7 98 20.7 65 9.52 106 8.72 12 15.4 27 3.63 12 11.3 18 29.1 40 6.09 15 5.34 86 6.18 83 5.38 103 12.2 78 22.4 66 8.06 52 5.27 137 3.55 81 6.79 136 8.85 43 16.5 43 4.24 36
ResPWCR_ROB [144]67.5 8.30 81 14.5 10 7.12 101 8.82 43 19.6 52 5.91 64 11.8 49 19.3 45 7.90 103 12.4 29 28.5 37 7.89 75 5.18 68 5.97 42 5.36 101 10.9 60 23.9 82 8.84 63 2.85 90 3.65 87 2.34 71 14.7 85 21.8 75 16.2 106
ROF-ND [107]67.5 7.02 21 14.7 15 4.66 22 8.18 29 19.5 49 4.66 33 15.5 90 25.9 90 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 94 9.09 67 4.23 131 4.20 107 3.32 100 14.7 85 22.1 80 18.8 125
OFH [38]67.7 7.25 34 15.0 24 5.29 51 11.1 102 25.0 109 7.19 86 18.6 110 29.1 117 5.56 53 16.0 96 40.8 149 7.44 67 5.05 46 5.92 36 4.28 52 11.4 68 26.0 98 8.73 60 1.64 13 3.04 27 1.36 17 12.5 70 23.3 86 7.79 53
COFM [59]67.7 8.49 89 18.5 123 5.95 73 8.44 37 18.7 44 4.71 34 13.0 62 22.9 71 5.84 54 13.8 66 35.2 106 6.78 35 5.63 107 6.58 111 5.94 114 11.7 72 23.5 74 9.80 77 2.29 70 3.20 48 2.72 83 6.42 24 12.1 24 3.07 26
PGM-C [120]68.5 9.43 102 18.5 123 7.51 109 9.84 66 23.4 96 6.05 66 12.0 52 20.6 52 7.17 73 15.8 92 35.3 108 9.67 96 5.20 74 6.11 69 4.66 76 9.86 40 23.7 78 7.06 39 1.63 10 2.84 13 1.49 31 11.1 61 20.8 70 6.23 47
TCOF [69]69.0 7.46 52 15.1 25 5.70 67 9.13 49 21.1 72 5.43 52 19.6 116 29.8 122 8.31 108 12.9 44 31.0 55 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 39 15.9 40 3.80 34
S2D-Matching [84]69.8 8.25 78 18.0 117 5.76 70 10.9 100 22.8 91 5.71 60 17.3 101 28.5 110 6.38 63 12.1 25 30.3 47 6.65 28 5.15 62 6.13 73 4.63 72 9.18 32 19.5 53 6.69 29 2.66 82 3.35 62 3.50 105 11.6 64 19.9 64 14.7 88
OAR-Flow [125]70.2 8.08 72 16.8 90 6.19 82 17.4 138 28.9 136 12.3 135 16.3 96 26.7 102 7.01 70 15.1 85 35.2 106 7.31 63 5.17 65 6.16 78 4.24 49 9.51 36 22.9 72 5.52 14 1.54 5 2.98 24 1.59 39 9.10 46 17.1 50 3.69 32
ComplOF-FED-GPU [35]70.6 7.49 53 15.4 33 5.37 57 12.1 114 26.5 124 7.51 88 13.1 64 22.7 69 4.33 28 15.6 89 37.7 130 7.55 71 4.94 28 5.82 25 4.13 44 12.3 80 27.7 109 8.48 58 2.49 79 3.04 27 3.56 108 12.9 72 23.9 89 9.01 56
SegFlow [160]70.8 9.47 105 18.6 126 7.51 109 10.2 73 24.1 105 6.22 69 12.2 53 21.0 57 7.22 74 16.1 97 36.3 118 9.76 99 5.21 77 6.12 71 4.69 82 10.1 47 24.2 85 7.76 47 1.66 17 2.89 19 1.50 32 9.31 47 17.5 52 4.27 37
AggregFlow [97]74.1 10.3 116 21.3 154 6.91 97 15.1 131 27.6 131 10.7 111 14.0 76 24.0 77 8.70 111 14.1 71 35.0 101 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 52 18.1 57 6.13 46
CompactFlow_ROB [159]76.4 11.5 126 20.6 148 8.79 147 8.99 47 18.8 45 6.75 79 14.8 81 21.3 60 14.7 133 14.0 69 32.1 69 9.13 86 5.17 65 6.02 57 4.82 87 10.4 53 22.8 70 7.73 46 1.63 10 2.68 4 0.88 3 19.0 110 24.6 90 24.3 149
CPM-Flow [116]77.0 9.46 104 18.6 126 7.51 109 10.0 70 23.7 100 6.20 68 12.2 53 20.9 56 7.13 71 15.8 92 35.6 111 9.71 98 5.20 74 6.12 71 4.65 75 10.9 60 23.7 78 8.90 65 1.73 23 3.15 45 1.51 35 14.5 84 26.0 97 13.6 82
EpicFlow [102]78.2 9.39 101 18.4 120 7.50 108 10.0 70 23.8 102 6.29 71 15.8 93 26.6 100 7.35 81 15.5 87 34.4 93 9.65 94 5.20 74 6.11 69 4.66 76 10.2 51 24.5 87 8.18 55 1.63 10 2.81 10 1.48 27 15.8 90 24.8 92 17.1 115
Aniso-Texture [82]79.8 6.49 5 14.2 8 4.54 16 7.83 24 19.5 49 4.37 25 22.0 143 33.6 156 8.47 109 10.3 11 25.4 28 5.55 11 5.19 71 6.10 67 4.45 61 18.7 134 33.0 149 20.1 158 4.07 129 4.62 121 2.47 78 20.1 120 28.5 106 20.7 136
Occlusion-TV-L1 [63]80.2 7.73 58 16.4 67 5.36 55 9.48 57 22.4 87 6.18 67 19.2 112 30.0 125 7.14 72 14.4 76 33.8 90 7.91 76 5.31 85 6.27 95 4.47 62 11.9 74 27.9 110 8.04 50 2.09 55 3.08 31 1.50 32 21.9 131 35.3 141 17.5 116
ContinualFlow_ROB [152]80.8 11.4 124 20.8 149 8.47 127 9.76 64 18.5 42 7.94 95 16.5 97 26.6 100 11.7 124 15.7 90 37.2 123 8.85 85 5.25 78 5.97 42 5.27 98 11.8 73 24.9 89 11.4 97 1.53 4 3.06 29 1.10 6 12.4 69 17.7 56 13.1 79
RFlow [90]81.3 7.10 26 14.9 18 5.40 58 8.98 46 21.9 82 5.19 45 18.5 109 29.3 119 5.35 46 18.1 132 44.9 167 9.86 102 5.12 53 6.01 54 4.38 56 13.0 91 29.3 121 9.93 80 2.28 69 2.85 14 3.52 106 20.3 122 33.3 131 16.1 104
FF++_ROB [145]81.8 9.92 111 19.4 134 7.55 113 8.87 44 20.9 68 5.83 62 15.3 86 25.3 86 7.95 104 11.0 15 25.4 28 7.23 60 5.19 71 6.10 67 4.80 85 17.1 121 25.3 93 13.2 113 1.88 36 2.96 23 2.77 84 18.7 107 27.2 102 25.3 151
DeepFlow2 [108]82.9 8.14 74 16.6 86 5.96 75 14.1 126 26.5 124 10.2 107 15.8 93 26.2 96 6.46 64 16.5 120 37.4 127 9.54 92 5.01 38 5.94 40 3.72 16 10.7 58 25.1 90 8.08 54 1.92 41 3.12 42 2.45 75 20.3 122 32.1 122 16.3 107
Adaptive [20]82.9 7.94 63 17.0 96 5.33 53 10.2 73 23.9 103 6.28 70 21.2 130 31.7 144 7.69 100 13.6 64 29.8 42 7.87 74 4.88 21 5.75 16 3.71 15 13.2 92 28.9 118 9.72 76 3.21 104 4.71 123 2.91 90 19.3 115 30.5 113 15.6 95
DMF_ROB [139]83.2 8.27 79 16.7 88 6.36 86 11.7 110 26.4 122 7.10 85 17.8 104 28.6 112 7.33 80 15.9 95 35.9 112 9.46 90 5.05 46 5.97 42 4.51 63 12.8 89 27.4 106 9.90 79 1.60 7 2.99 25 1.48 27 19.8 118 32.0 120 16.8 111
TF+OM [100]84.8 7.97 67 16.8 90 5.98 76 9.40 55 20.7 65 6.33 72 15.4 87 22.9 71 17.5 138 13.4 57 31.5 62 8.10 77 5.13 57 6.06 64 4.66 76 13.9 101 29.3 121 14.0 119 2.47 76 4.09 104 2.00 55 18.3 105 29.4 110 19.3 129
Steered-L1 [118]85.1 5.97 1 12.7 1 4.67 24 7.14 12 18.2 37 4.63 30 13.2 65 23.3 75 5.12 38 15.2 86 38.1 133 7.54 69 5.85 114 6.73 115 6.98 133 13.7 100 26.5 100 11.7 103 6.39 142 4.25 109 13.3 161 22.3 134 32.7 127 20.3 134
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
Aniso. Huber-L1 [22]85.8 7.96 66 16.3 65 6.10 80 11.4 104 24.7 107 6.77 80 20.6 123 29.6 121 7.26 76 13.2 54 29.2 41 7.77 73 5.52 98 6.58 111 4.29 53 12.4 82 26.7 103 8.83 62 2.93 96 3.68 89 3.10 93 16.5 96 27.4 103 13.9 84
OFRF [134]87.3 9.69 107 19.6 137 6.25 83 22.2 157 29.4 139 20.7 160 21.6 134 30.1 126 17.0 137 14.1 71 31.0 55 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 71 16.7 46 15.9 103
AugFNG_ROB [143]88.4 12.7 134 22.1 155 9.46 151 12.1 114 24.6 106 9.39 104 18.8 111 27.1 107 14.7 133 14.0 69 30.9 53 9.24 88 5.03 42 5.72 13 5.09 93 11.0 63 24.0 84 9.53 73 1.82 33 3.25 54 1.22 9 18.2 104 23.7 87 21.6 141
LocallyOriented [52]88.5 9.89 109 19.9 141 6.55 89 14.7 130 27.7 132 11.0 113 21.7 137 31.9 146 7.32 79 13.3 56 30.5 49 8.32 79 5.16 63 6.04 61 4.11 41 9.90 43 21.6 62 8.75 61 2.20 64 3.43 74 2.17 62 18.3 105 26.0 97 19.6 130
EAI-Flow [151]88.6 10.4 119 19.0 131 7.83 115 13.2 124 25.8 114 9.43 105 13.7 72 21.6 63 8.47 109 14.8 80 33.0 82 9.68 97 5.12 53 6.01 54 4.74 83 11.6 69 25.7 96 9.23 69 3.66 115 3.57 85 2.04 57 13.4 80 24.8 92 10.5 63
LFNet_ROB [149]91.4 10.1 114 17.0 96 8.16 123 9.48 57 21.8 80 6.00 65 16.8 98 26.1 94 11.1 121 13.4 57 29.9 43 8.73 84 5.40 94 6.20 86 5.58 108 13.3 94 29.4 123 10.0 83 2.04 51 3.21 50 1.85 50 22.7 138 35.6 142 21.8 143
SIOF [67]91.6 8.21 77 17.0 96 5.49 61 13.0 123 27.4 130 8.63 99 20.1 121 29.0 115 16.3 136 16.8 122 37.3 126 10.0 106 5.40 94 6.34 100 4.88 88 11.6 69 25.4 94 10.1 84 1.81 32 3.27 56 1.34 15 15.1 89 25.1 94 11.9 71
SegOF [10]92.5 9.43 102 17.7 111 8.06 120 12.0 113 22.9 94 10.4 110 17.0 99 26.1 94 12.6 128 13.8 66 26.8 32 11.2 114 5.53 99 6.26 93 6.06 117 19.0 135 35.6 161 18.8 137 1.37 2 2.60 2 0.83 2 16.4 94 30.0 111 14.0 85
TriangleFlow [30]92.7 8.08 72 17.0 96 5.12 41 11.7 110 26.1 117 6.98 84 19.5 114 30.3 129 6.34 62 12.9 44 33.0 82 6.71 33 7.00 138 8.16 142 6.63 130 12.8 89 24.5 87 10.5 87 3.59 112 5.17 134 3.27 99 12.9 72 21.9 77 12.1 73
DeepFlow [86]93.2 8.73 90 17.1 102 6.26 84 15.3 134 26.7 127 11.9 134 17.3 101 26.5 99 14.1 132 18.6 138 42.8 161 11.0 112 5.00 37 5.91 35 3.75 18 11.2 67 26.2 99 8.35 57 1.88 36 2.80 8 2.60 81 22.5 136 33.6 132 17.5 116
CRTflow [80]93.5 7.92 61 16.0 51 5.91 72 11.4 104 23.7 100 6.55 76 19.8 118 30.1 126 7.77 101 17.2 128 41.3 152 9.76 99 5.34 86 6.30 96 3.69 14 15.8 117 31.0 136 14.3 122 2.12 59 2.92 21 2.35 72 19.2 113 32.9 129 15.3 92
TriFlow [95]95.1 9.01 96 18.5 123 6.60 92 11.4 104 26.4 122 7.40 87 20.9 126 29.9 124 20.9 147 12.2 27 30.8 52 6.95 49 5.26 83 6.16 78 4.88 88 12.0 76 26.5 100 11.6 101 6.97 143 4.54 117 6.57 135 13.0 75 22.0 78 9.86 60
Brox et al. [5]96.4 8.46 88 16.7 88 6.56 90 11.3 103 26.2 119 6.94 83 15.0 84 25.4 87 6.89 69 17.4 129 38.8 137 9.80 101 5.99 118 6.88 122 6.26 122 14.1 104 31.1 139 12.0 105 2.03 50 3.41 71 1.14 7 19.1 112 30.3 112 12.1 73
Fusion [6]96.5 8.76 91 17.7 111 7.01 98 7.82 23 19.7 53 4.78 37 10.9 42 18.4 40 7.23 75 12.8 41 32.6 75 8.32 79 7.04 139 8.11 140 6.57 128 14.9 110 28.3 111 13.2 113 4.37 133 5.18 135 2.77 84 26.2 151 38.6 153 26.4 153
p-harmonic [29]96.9 8.15 76 16.2 59 6.50 88 9.66 62 22.6 89 6.57 77 21.2 130 31.2 137 9.65 114 15.7 90 33.9 91 10.0 106 5.18 68 6.04 61 5.31 100 14.3 106 30.3 131 12.2 109 3.10 101 3.55 81 1.91 52 23.1 141 34.8 139 17.8 118
CBF [12]98.0 7.23 33 14.9 18 5.16 42 9.95 69 21.9 82 7.69 91 17.6 103 27.0 103 7.28 78 16.4 119 39.3 141 9.18 87 6.34 131 7.35 136 6.11 120 13.4 97 28.4 112 8.52 59 5.54 139 5.11 131 6.41 133 18.7 107 30.8 114 16.4 108
EPMNet [133]99.2 11.6 128 20.5 146 8.03 119 17.7 140 28.9 136 13.2 140 12.9 60 20.3 49 10.7 117 15.5 87 37.4 127 9.48 91 5.36 90 6.23 89 4.94 90 14.0 102 29.9 127 12.2 109 2.97 97 5.82 138 2.01 56 10.1 53 18.8 61 3.51 30
CLG-TV [48]99.7 7.94 63 16.2 59 5.80 71 10.5 94 24.0 104 6.44 74 19.9 119 29.8 122 6.83 67 14.1 71 31.5 62 7.73 72 5.98 116 7.01 126 5.15 96 14.8 109 31.0 136 12.2 109 4.20 130 4.80 125 5.22 127 19.3 115 32.6 126 15.7 99
TV-L1-improved [17]99.8 7.64 57 16.2 59 5.67 66 10.1 72 23.4 96 6.38 73 21.3 132 32.0 149 9.27 113 17.5 130 42.1 156 9.54 92 5.25 78 6.13 73 4.07 36 14.5 107 30.4 133 11.4 97 3.38 107 5.02 128 2.99 92 19.6 117 32.1 122 16.6 110
FlowNet2 [122]100.0 12.8 135 23.3 160 8.09 121 16.8 137 28.5 133 12.5 136 13.9 74 21.6 63 12.0 126 15.0 84 34.0 92 9.98 105 5.36 90 6.23 89 4.94 90 14.0 102 29.9 127 12.2 109 3.36 106 6.60 144 2.24 66 8.83 42 16.6 45 3.02 25
WOLF_ROB [148]100.5 9.97 112 18.4 120 7.33 105 20.8 148 34.8 164 13.9 142 22.2 145 30.7 133 10.9 118 17.0 127 33.2 86 12.3 121 5.16 63 6.01 54 5.11 95 10.2 51 20.7 56 9.05 66 1.97 44 3.28 57 2.48 79 17.9 103 23.1 83 21.3 140
Local-TV-L1 [65]102.0 9.74 108 17.9 115 6.89 95 18.4 143 29.4 139 14.9 144 24.4 149 30.8 134 20.2 145 19.4 143 42.4 159 12.7 123 5.35 89 6.00 51 4.10 39 13.6 98 28.9 118 9.26 70 1.62 9 2.58 1 1.48 27 20.3 122 32.0 120 16.4 108
Classic++ [32]102.2 8.05 70 17.4 108 6.09 79 11.5 107 26.3 121 6.91 81 18.1 107 28.7 113 8.18 106 16.2 98 39.0 139 8.57 82 5.36 90 6.33 98 4.54 65 15.0 112 30.4 133 11.6 101 2.70 85 3.55 81 2.94 91 21.9 131 34.0 135 17.9 119
SuperFlow [81]102.9 9.27 100 17.3 106 6.63 93 11.7 110 22.8 91 8.84 101 19.3 113 28.0 109 18.4 142 16.9 124 38.2 134 9.89 103 5.44 96 6.32 97 5.61 110 11.9 74 26.6 102 9.56 75 2.92 94 4.08 103 1.79 47 20.1 120 32.4 124 15.8 101
Rannacher [23]103.8 8.07 71 16.8 90 6.15 81 10.6 95 24.8 108 6.51 75 21.9 141 32.6 155 10.9 118 18.4 135 43.3 163 10.5 108 5.27 84 6.18 83 4.17 47 15.5 115 32.3 146 12.0 105 2.69 84 3.57 85 2.68 82 17.8 102 31.0 115 16.1 104
F-TV-L1 [15]104.7 8.41 86 16.8 90 6.31 85 18.0 142 29.7 141 12.8 137 21.6 134 30.5 130 10.1 116 18.2 133 42.3 158 9.65 94 5.02 41 5.97 42 3.91 23 14.1 104 30.8 135 10.6 91 2.79 86 4.90 126 2.35 72 20.5 125 32.7 127 15.6 95
BriefMatch [124]106.6 6.91 17 14.8 17 4.85 27 11.0 101 22.8 91 8.24 96 9.42 14 16.6 31 5.13 40 16.7 121 40.7 148 8.61 83 9.76 145 10.6 163 14.1 146 18.2 131 31.0 136 17.4 133 9.26 147 6.60 144 20.9 167 28.0 155 36.5 145 34.9 160
StereoOF-V1MT [119]106.9 8.14 74 15.8 43 5.42 59 17.6 139 34.3 162 10.3 108 21.6 134 31.5 141 7.27 77 15.8 92 32.7 77 10.7 109 5.62 106 6.40 102 6.00 116 16.6 120 30.0 129 15.5 124 2.01 47 3.08 31 3.15 95 33.6 161 44.0 162 32.8 158
DF-Auto [115]108.7 10.7 122 19.8 140 7.42 107 16.3 136 25.3 110 13.1 139 19.5 114 28.5 110 17.8 140 16.9 124 37.2 123 10.8 110 6.76 137 8.12 141 5.56 107 10.8 59 25.2 91 6.95 35 3.69 117 4.92 127 1.48 27 17.7 101 27.9 105 14.6 87
Dynamic MRF [7]109.2 8.32 84 17.3 106 5.95 73 12.3 116 28.5 133 7.75 92 19.6 116 31.8 145 7.56 82 18.4 135 42.2 157 11.6 118 5.25 78 6.16 78 4.80 85 17.7 125 34.4 157 16.6 129 1.89 38 2.63 3 3.21 98 30.3 157 43.6 161 29.0 155
Bartels [41]109.2 8.31 83 17.7 111 5.51 62 8.46 38 20.6 62 4.89 38 14.8 81 26.0 92 7.89 102 18.5 137 43.6 164 11.1 113 6.18 124 6.51 110 8.63 141 15.6 116 32.6 148 13.9 118 3.86 123 4.56 118 7.09 137 22.5 136 36.5 145 18.4 123
Shiralkar [42]110.9 7.92 61 15.2 30 5.73 68 14.6 129 30.3 142 9.04 102 21.7 137 31.2 137 9.77 115 19.6 145 41.5 153 13.2 125 5.17 65 6.04 61 4.63 72 18.0 130 31.1 139 14.7 123 3.67 116 3.40 69 4.74 123 23.9 146 36.6 147 18.9 126
GraphCuts [14]111.5 9.24 99 17.2 103 7.53 112 22.1 155 33.0 156 16.8 152 15.9 95 23.1 73 15.6 135 14.2 74 28.9 39 9.34 89 5.83 113 6.82 118 6.25 121 18.5 133 29.7 125 12.0 105 2.85 90 3.39 67 3.52 106 23.8 145 36.1 143 19.1 127
Second-order prior [8]114.0 8.04 69 16.3 65 6.01 78 12.5 118 26.5 124 9.10 103 21.0 127 31.1 136 9.23 112 16.2 98 36.2 117 9.93 104 5.70 110 6.67 114 5.09 93 20.7 157 34.1 155 21.0 159 3.76 119 3.89 99 4.25 119 18.9 109 31.8 119 19.9 132
Filter Flow [19]114.7 10.5 120 19.4 134 8.33 124 12.5 118 25.8 114 8.69 100 19.9 119 27.0 103 21.7 150 19.0 140 33.1 85 15.9 146 5.34 86 6.21 87 5.37 102 16.2 119 26.7 103 15.5 124 3.46 109 4.48 116 2.26 67 23.3 144 31.5 118 18.5 124
CNN-flow-warp+ref [117]115.8 9.91 110 19.6 137 7.85 116 10.6 95 22.9 94 8.55 97 21.3 132 32.1 151 11.9 125 18.7 139 42.0 155 11.3 115 5.56 102 6.34 100 6.08 119 12.3 80 27.6 107 10.8 92 2.06 53 3.69 91 3.16 96 33.3 159 40.4 156 34.7 159
StereoFlow [44]116.1 16.2 162 22.6 158 13.9 164 22.1 155 31.6 148 18.8 157 24.7 150 30.6 132 21.2 149 23.3 157 39.9 142 19.6 157 5.98 116 6.22 88 7.11 135 11.6 69 27.6 107 8.05 51 1.36 1 2.85 14 0.65 1 20.7 126 33.7 133 17.0 114
FlowNetS+ft+v [112]116.5 8.96 95 17.8 114 6.83 94 14.2 127 26.2 119 11.1 114 22.3 146 32.2 152 12.7 129 16.8 122 36.1 116 10.9 111 6.31 130 7.29 134 6.26 122 12.5 86 28.8 116 9.88 78 3.84 122 6.75 146 6.30 132 16.4 94 29.0 108 14.7 88
IAOF2 [51]117.0 10.0 113 19.9 141 7.91 118 14.4 128 26.7 127 10.9 112 22.0 143 32.2 152 17.6 139 19.1 141 33.0 82 17.1 150 5.81 112 6.86 120 4.94 90 12.6 87 25.9 97 11.9 104 4.26 132 4.11 106 7.75 140 16.2 93 26.5 100 13.5 81
Ad-TV-NDC [36]120.5 12.1 132 18.6 126 10.7 156 25.5 161 32.0 152 22.2 161 29.3 163 34.3 161 22.8 154 16.9 124 32.8 79 12.2 120 5.99 118 7.20 132 3.83 20 12.6 87 28.5 114 10.3 85 2.79 86 4.07 102 1.78 46 24.1 147 31.4 117 25.1 150
TVL1_ROB [138]121.1 12.9 136 20.8 149 9.80 154 21.3 152 30.9 145 17.9 156 27.9 157 33.6 156 23.5 158 20.5 147 37.8 131 16.7 148 5.57 103 6.47 107 5.46 105 14.5 107 32.1 145 12.1 108 1.69 19 2.81 10 1.22 9 22.9 139 36.3 144 18.3 122
LDOF [28]122.7 9.66 106 18.9 130 7.13 102 15.1 131 29.1 138 11.3 115 15.6 92 25.1 85 10.9 118 20.9 150 43.1 162 14.9 144 6.12 122 7.01 126 6.26 122 16.0 118 31.2 141 13.2 113 3.89 125 5.61 137 8.96 158 19.0 110 33.0 130 11.7 69
2D-CLG [1]123.5 15.2 160 24.5 164 11.2 158 15.1 131 25.9 116 13.5 141 27.5 156 33.9 158 24.7 163 22.2 154 38.3 135 19.0 156 5.67 108 6.44 105 6.29 125 17.5 123 34.3 156 16.4 128 1.47 3 2.68 4 1.54 38 21.7 130 34.6 138 16.9 113
Nguyen [33]123.8 11.4 124 19.6 137 8.44 126 21.0 151 31.7 150 17.7 154 29.8 165 36.3 165 24.1 162 18.2 133 34.6 97 13.9 126 6.28 126 6.85 119 7.51 138 15.4 114 33.0 149 14.0 119 2.24 67 3.11 38 1.79 47 21.6 129 33.9 134 15.8 101
IAOF [50]124.4 10.1 114 18.6 126 7.89 117 22.2 157 33.7 159 15.9 148 33.0 167 39.2 168 23.7 159 16.2 98 32.1 69 11.6 118 5.80 111 6.87 121 5.39 104 17.8 127 30.1 130 11.4 97 3.13 103 3.69 91 3.88 116 22.4 135 29.3 109 21.6 141
UnFlow [129]124.9 16.0 161 25.1 165 11.3 159 12.7 122 22.2 86 11.7 133 20.4 122 27.6 108 13.6 130 20.8 148 36.0 114 17.9 153 6.34 131 6.89 123 7.74 139 17.7 125 33.5 152 17.1 132 2.92 94 4.33 111 1.37 18 20.7 126 37.3 151 15.6 95
SPSA-learn [13]126.0 11.3 123 19.4 134 8.52 128 20.9 149 34.2 161 16.2 151 26.5 154 33.9 158 22.4 153 22.5 156 39.9 142 18.9 155 5.59 104 6.41 103 5.94 114 17.8 127 31.4 143 18.3 136 2.11 57 3.11 38 1.37 18 24.3 148 35.1 140 19.7 131
Learning Flow [11]126.2 8.28 80 17.0 96 5.75 69 12.3 116 28.5 133 7.79 94 18.4 108 28.7 113 8.29 107 22.2 154 40.6 147 17.3 151 8.52 140 10.3 162 7.04 134 19.9 155 35.1 159 16.8 131 3.11 102 4.59 120 3.59 110 26.9 153 40.0 155 20.9 139
HBpMotionGpu [43]127.2 12.2 133 22.1 155 8.34 125 17.9 141 31.4 147 14.7 143 29.2 162 37.8 167 20.6 146 19.1 141 44.6 166 11.5 117 5.60 105 6.45 106 6.06 117 13.2 92 28.8 116 11.1 95 3.45 108 3.97 101 2.04 57 23.1 141 34.1 136 20.7 136
Modified CLG [34]130.6 11.6 128 20.5 146 9.14 150 12.6 121 25.4 112 10.3 108 27.4 155 34.4 162 23.8 160 21.8 152 42.7 160 16.7 148 6.18 124 7.06 129 6.57 128 14.9 110 33.0 149 13.4 116 2.45 74 3.80 97 3.81 115 22.0 133 36.6 147 16.8 111
Black & Anandan [4]132.2 10.5 120 18.0 117 8.14 122 21.4 154 32.8 155 16.1 150 26.1 153 32.3 154 21.8 151 20.8 148 38.9 138 16.1 147 6.29 128 7.41 137 5.62 111 17.1 121 31.2 141 13.7 117 4.06 128 5.11 131 2.37 74 23.1 141 34.1 136 15.7 99
GroupFlow [9]133.5 11.5 126 21.2 153 8.71 146 20.5 146 33.0 156 15.7 147 23.6 147 31.6 142 20.1 144 16.2 98 34.5 94 11.3 115 8.86 141 9.84 161 6.50 127 18.2 131 30.3 131 17.4 133 3.82 121 5.05 129 6.55 134 21.1 128 28.8 107 22.4 147
2bit-BM-tele [98]133.6 10.3 116 20.1 143 7.40 106 11.5 107 26.7 127 7.57 90 20.6 123 32.0 149 11.4 123 17.9 131 40.3 145 12.3 121 6.29 128 6.80 117 6.93 132 21.0 158 32.0 144 18.0 135 7.61 144 6.57 143 11.1 160 27.5 154 39.4 154 29.2 156
Heeger++ [104]135.7 11.7 130 18.3 119 9.04 149 23.3 160 37.0 167 17.4 153 21.0 127 29.1 117 11.1 121 27.0 161 40.5 146 24.4 160 5.69 109 6.33 98 5.80 112 25.9 164 37.5 164 26.3 164 2.48 77 3.88 98 2.20 64 37.6 164 46.0 165 41.6 167
HCIC-L [99]136.1 14.6 157 21.1 151 9.67 152 42.7 168 36.7 166 46.6 168 21.8 139 30.5 130 17.9 141 21.1 151 35.1 103 18.6 154 6.42 133 6.58 111 7.35 137 17.8 127 28.6 115 16.6 129 12.8 150 14.3 150 15.3 163 16.8 99 25.7 96 12.7 77
H+S_ROB [137]137.3 16.6 164 23.6 162 11.9 161 19.1 144 30.6 144 15.6 146 25.1 151 30.2 128 23.4 156 29.1 162 36.3 118 27.9 163 13.4 165 15.7 165 12.2 143 27.2 165 38.8 166 27.8 165 1.70 21 2.81 10 1.42 23 32.2 158 41.3 159 30.2 157
BlockOverlap [61]137.4 10.3 116 19.1 132 7.74 114 15.4 135 25.3 110 13.0 138 24.3 148 31.9 146 21.0 148 19.5 144 43.8 165 13.1 124 9.14 142 7.60 138 13.9 145 19.0 135 29.0 120 15.7 126 11.0 148 8.77 148 24.8 168 23.0 140 31.3 116 25.9 152
TI-DOFE [24]138.5 14.6 157 21.1 151 11.7 160 22.4 159 31.6 148 19.6 158 28.6 160 31.2 137 26.3 164 26.3 160 36.0 114 25.1 161 6.43 134 7.34 135 6.67 131 19.1 137 33.8 153 18.9 138 2.88 92 3.15 45 2.82 87 25.7 150 36.6 147 22.3 146
Horn & Schunck [3]140.0 11.8 131 19.3 133 8.85 148 20.1 145 33.5 158 15.3 145 25.5 152 31.2 137 24.0 161 26.1 159 38.6 136 23.5 158 6.12 122 6.99 124 6.34 126 19.9 155 33.9 154 19.6 156 3.95 127 4.28 110 2.46 77 25.3 149 37.5 152 22.0 145
FFV1MT [106]147.2 13.9 156 23.4 161 10.8 157 20.9 149 34.5 163 16.0 149 21.8 139 29.5 120 13.8 131 31.0 166 41.7 154 29.4 165 9.97 146 6.78 116 17.9 165 23.8 161 35.3 160 25.0 163 2.99 98 4.24 108 3.57 109 37.6 164 46.0 165 41.6 167
SILK [79]148.4 13.2 154 22.4 157 10.2 155 20.5 146 32.2 154 17.7 154 29.0 161 34.1 160 23.4 156 22.0 153 40.8 149 17.3 151 6.28 126 7.17 131 7.12 136 21.7 159 35.8 162 19.6 156 5.44 138 3.45 77 10.8 159 29.3 156 40.6 158 26.7 154
Adaptive flow [45]149.0 13.2 154 20.2 144 9.78 153 27.3 163 31.9 151 25.4 162 28.3 159 31.6 142 30.5 167 19.7 146 37.6 129 15.3 145 11.2 164 12.6 164 8.93 142 17.6 124 29.8 126 15.8 127 13.1 151 11.0 149 18.3 164 26.4 152 36.8 150 22.7 148
PGAM+LK [55]149.4 14.9 159 22.8 159 14.1 165 25.5 161 31.3 146 26.6 163 21.9 141 26.4 98 22.2 152 26.0 158 39.1 140 24.0 159 9.61 144 6.49 109 14.1 146 24.3 162 35.0 158 23.0 161 6.19 141 6.24 142 7.26 138 34.3 162 40.4 156 40.8 166
SLK [47]149.8 17.2 166 24.0 163 18.2 166 21.3 152 30.4 143 20.1 159 27.9 157 31.9 146 23.3 155 31.4 167 39.9 142 30.0 167 6.60 135 7.04 128 8.37 140 22.8 160 36.4 163 21.6 160 3.90 126 3.75 95 5.02 125 33.3 159 41.7 160 35.2 161
AVG_FLOW_ROB [141]155.2 32.4 168 34.1 168 37.7 168 35.1 167 33.7 159 37.0 167 20.7 125 24.1 79 19.4 143 34.1 168 35.1 103 34.8 168 39.6 167 37.0 167 44.9 167 40.6 168 42.2 167 38.5 168 11.3 149 15.3 151 7.36 139 46.5 168 52.3 168 38.9 163
FOLKI [16]158.5 16.2 162 25.9 166 12.7 163 32.5 165 35.6 165 34.7 165 29.4 164 35.1 164 26.9 165 29.1 162 41.0 151 27.9 163 9.58 143 8.90 143 13.5 144 25.7 163 38.3 165 24.5 162 7.71 145 5.13 133 14.5 162 36.5 163 44.4 163 36.1 162
Pyramid LK [2]159.1 17.0 165 20.4 145 19.4 167 31.7 164 32.1 153 32.5 164 32.9 166 34.8 163 29.9 166 29.4 164 35.3 108 29.9 166 31.7 166 35.5 166 29.8 166 29.9 166 32.3 146 28.0 166 9.01 146 7.93 147 18.9 165 39.9 166 45.4 164 39.0 164
Periodicity [78]164.4 18.0 167 30.5 167 12.3 162 34.0 166 41.4 168 35.6 166 36.5 168 36.5 166 35.2 168 29.7 165 46.6 168 26.8 162 51.8 168 56.5 168 45.5 168 36.7 167 42.4 168 37.1 167 5.99 140 6.16 141 19.3 166 40.1 167 51.1 167 40.4 165
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

Methodtime*framescolor Reference and notes
[1] 2D-CLG 844 2 gray The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences.
[2] Pyramid LK 12 2 color A modification of Bouguet's pyramidal implementation of Lucas-Kanade.
[3] Horn & Schunck 49 2 gray A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data.
[4] Black & Anandan 328 2 gray A modern Matlab implementation of the Black & Anandan method by Deqing Sun.
[5] Brox et al. 18 2 color T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.)
[6] Fusion 2,666 2 color V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008.
[7] Dynamic MRF 366 2 gray B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.)
[8] Second-order prior 14 2 gray W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[9] GroupFlow 600 2 gray X. Ren. Local Grouping for Optical Flow. CVPR 2008.
[10] SegOF 60 2 color L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available.
[11] Learning Flow 825 2 gray D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008.
[12] CBF 69 2 color W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[13] SPSA-learn 200 2 color Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008.
[14] GraphCuts 1,200 2 color T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008.
[15] F-TV-L1 8 2 gray A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008.
[16] FOLKI 1.4 2 gray G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005.
[17] TV-L1-improved 2.9 2 gray A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision.
[18] DPOF 287 2 color C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.)
[19] Filter Flow 34,000 2 color S. Seitz and S. Baker. Filter flow. ICCV 2009.
[20] Adaptive 9.2 2 gray A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009.
[21] Complementary OF 44 2 color H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[22] Aniso. Huber-L1 2 2 gray M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision.
[23] Rannacher 0.12 2 gray J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009.
[24] TI-DOFE 260 2 gray C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009.
[25] NL-TV-NCC 20 2 color M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010.
[26] MDP-Flow 188 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010.
[27] ACK-Prior 5872 2 color K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010.
[28] LDOF 122 2 color T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011.
[29] p-harmonic 565 2 gray J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010.
[30] TriangleFlow 4200 2 gray B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010.
[31] Classic+NL 972 2 color D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code.
[32] Classic++ 486 2 gray A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010.
[33] Nguyen 33 2 gray D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011.
[34] Modified CLG 133 2 gray R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010.
[35] ComplOF-FED-GPU 0.97 2 color P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010.
[36] Ad-TV-NDC 35 2 gray M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010.
[37] Layers++ 18206 2 color D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010.
[38] OFH 620 3 color H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011.
[39] LSM 1615 2 color K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011.
[40] CostFilter 55 2 color C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011.
[41] Bartels 0.15 2 gray C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU.
[42] Shiralkar 600 2 gray M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242.
[43] HBpMotionGpu 1000 5 gray S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.)
[44] StereoFlow 7200 2 color G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772.
[45] Adaptive flow 121 2 gray T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011.
[46] TC-Flow 2500 5 color S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011.
[47] SLK 300 2 gray T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011.
[48] CLG-TV 29 2 gray M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code.
[49] SimpleFlow 1.7 2 color M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012.
[50] IAOF 57 2 gray D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011.
[51] IAOF2 56 2 gray D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011.
[52] LocallyOriented 9541 2 gray Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012.
[53] IROF-TV 261 2 color H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop.
[54] Sparse Occlusion 2312 2 color A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011.
[55] PGAM+LK 0.37 2 gray A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010.
[56] Sparse-NonSparse 713 2 color L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013.
[57] nLayers 36150 4 color D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012.
[58] IROF++ 187 2 color H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013.
[59] COFM 600 3 color M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013.
[60] Efficient-NL 400 2 color P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012.
[61] BlockOverlap 2 2 gray M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to MMSP 2012.
[62] Ramp 1200 2 color A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012.
[63] Occlusion-TV-L1 538 3 gray C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012.
[64] TV-L1-MCT 90 2 color M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012.
[65] Local-TV-L1 500 2 gray L. Raket. Local smoothness for global optical flow. ICIP 2012.
[66] ALD-Flow 61 2 color M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012.
[67] SIOF 234 2 color L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012.
[68] MDP-Flow2 342 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available.
[69] TCOF 1421 all gray J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013.
[70] LME 476 2 color W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013.
[71] NN-field 362 2 color L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[72] FESL 3310 2 color W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013.
[73] PMF 35 2 color J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013.
[74] FC-2Layers-FF 2662 4 color D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013.
[75] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[76] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[77] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[78] Periodicity 8000 4 color G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013.
[79] SILK 572 2 gray P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP.
[80] CRTflow 13 3 color O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013.
[81] SuperFlow 178 2 color Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507.
[82] Aniso-Texture 300 2 color Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267.
[83] Classic+CPF 640 2 gray Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013.
[84] S2D-Matching 1200 2 color Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479.
[85] AGIF+OF 438 2 gray Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015.
[86] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[87] NNF-Local 673 2 color Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014.
[88] EPPM w/o HM 2.5 2 color L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014.
[89] MLDP_OF 165 2 gray M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014.
[90] RFlow 20 2 gray S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014.
[91] SRR-TVOF-NL 32 all color P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014.
[92] 2DHMM-SAS 157 2 color M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission.
[93] WLIF-Flow 700 2 color Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014.
[94] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[95] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[96] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[97] AggregFlow 1642 2 color D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759.
[98] 2bit-BM-tele 124 2 gray R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013.
[99] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[100] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[101] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[102] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[103] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[104] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[105] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[106] FFV1MT 358 5 gray F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015.
[107] ROF-ND 4 2 color S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015.
[108] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[109] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[110] FlowFields 15 2 color C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015.
[111] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[112] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[113] CombBMOF 51 2 color M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.)
[114] PMMST 182 2 color F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015.
[115] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[116] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[117] CNN-flow-warp+ref 1.4 3 color D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016.
[118] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[119] StereoOF-V1MT 343 2 gray Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132.
[120] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[121] RNLOD-Flow 1040 2 gray C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. IEEE TIP 26(8):4055-4067, 2017.
[122] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[123] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[124] BriefMatch 0.068 2 gray G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62.
[125] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[126] AdaConv-v1 2.8 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[127] SepConv-v1 0.2 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[128] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[129] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[130] FlowFields+ 10.5 2 color C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017.
[131] IIOF-NLDP 150 2 color D.-H. Trinh, W. Blondel, and C. Daul. A general form of illumination-invariant descriptors in variational optical flow estimation. ICIP 2017.
[132] SuperSlomo 0.5 2 color Anonymous. (Interpolation results only.) Super SloMo: High quality estimation of multiple intermediate frames for video interpolation. CVPR 2018 submission 325.
[133] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[134] OFRF 90 2 color T. Mai, M. Gouiffes, and S. Bouchafa. Optical Flow refinement using iterative propagation under color, proximity and flow reliability constraints. Submitted to Signal, Image and Video Processing 2017.
[135] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
[136] CtxSyn 0.07 2 color S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[137] H+S_ROB 5 2 color ROB 2018 baseline submission, based on: E. Meinhardt-Llopis, J. Sanchez, and D. Kondermann. Horn-Schunck optical flow with a multi-scale strategy. Image Processing On Line 3:151–172, 2013.
[138] TVL1_ROB 1 2 color ROB 2018 baseline submission, based on: J. Sanchez, E. Meinhardt-Llopis, and G. Facciolo. TV-L1 optical flow estimation. Image Processing On Line 3:137-150, 2013.
[139] DMF_ROB 10 2 color ROB 2018 baseline submission, based on: P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[140] JOF 657 2 gray C. Zhang, L. Ge, Z. Chen, M. Li, W. Liu, and H. Chen. Refined TV-L1 optical flow estimation using joint filtering. Submitted to IEEE TMM, 2018.
[141] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[142] LiteFlowNet 0.06 2 color T.-W. Hui, X. Tang, and C. C. Loy. LiteFlowNet: A lightweight convolutional neural network for optical flow estimation. CVPR 2018.
[143] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[144] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[145] FF++_ROB 17.43 2 color R. Schuster, C. Bailer, O. Wasenmueller, D. Stricker. FlowFields++: Accurate optical flow correspondences meet robust interpolation. ICIP 2018. Submitted to ROB 2018.
[146] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[147] PWC-Net_ROB 0.069 2 color D. Sun, X. Yang, M.-Y. Liu, and J. Kautz. PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. CVPR 2018.
[148] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[149] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
[150] WRT 9 2 color L. Mei, J. Lai, X. Xie, J. Zhu, and J. Chen. Illumination-invariance optical flow estimation using weighted regularization transform. Submitted to IEEE TCSVT 2018.
[151] EAI-Flow 2.1 2 color Anonymous. Hierarchical coherency sensitive hashing and interpolation with RANSAC for large displacement optical flow. CVIU 2018 submission 17-678.
[152] ContinualFlow_ROB 0.5 all color M Neoral, J. Sochman, and J. Matas. Continual occlusions and optical flow estimation. ACCV 2018.
[153] CyclicGen 0.088 2 color Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
[154] TOF-M 0.393 2 color T. Xue, B. Chen, J. Wu, D. Wei, and W. Freeman. Video enhancement with task-oriented flow. arXiv 1711.09078, 2017.
[155] MPRN 0.32 4 color Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[156] DAIN 0.13 2 color Anonymous. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019 submission 1769.
[157] FRUCnet 0.65 2 color V. T. Nguyen, K. Lee, and H.-J. Lee. (Interpolation results only.) A stacked deep MEMC network for frame rate up conversion and its application to HEVC. Submitted to IEEE TCSVT 2019.
[158] OFRI 0.31 2 color Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
[159] CompactFlow_ROB 0.05 2 color Anonymous. CompactFlow: spatially shiftable window revisited. CVPR 2019 submission 1387.
[160] SegFlow 3.2 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. Efficient segmentation-based PatchMatch for large displacement optical flow estimation. IEEE TCSVT 2018.
[161] PyrWarp 0.14 2 color Anonymous. (Interpolation results only.) Video frame interpolation using differentiable forward-warping of feature pyramids. ICCV 2019 submission 741.
[162] HCFN 0.18 2 color Anonymous. Practical coarse-to-fine optical flow with deep networks. ICCV 2019 submission 116.
[163] FGME 0.23 2 color Anonymous. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. ICCV 2019 submission 4327.
[164] MS-PFT 0.44 2 color X. Cheng and Z. Chen. (Interpolation results only.) A multi-scale position feature transform network for video frame interpolation. Submitted to TCSVT 2019.
[165] MEMC-Net+ 0.12 2 color W. Bao, W.-S. Lai, X. Zhang, Z. Gao, and M.-H. Yang. (Interpolation results only.) MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement. Submitted to TPAMI 2018.
[166] ADC 0.01 2 color Anonymous. (Interpolation results only.) Learning spatial transform for video frame interpolation. ICCV 2019 submission 5424.
[167] DSepConv 0.3 2 color Anonymous. (Interpolation results only.) Video frame interpolation via deformable separable convolution. AAAI 2020 submission 2271.
[168] MAF-net 0.3 2 color Anonymous. (Interpolation results only.) MAF-net: Motion attention feedback network for video frame interpolation. AAAI 2020 submission 9862.
* The "time" column lists the reported runtime in seconds on the "Urban" sequence. Note that these runtimes are not normalized by processor speed or type.