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]11.6 6.84 15 15.1 24 4.48 12 6.28 5 15.5 18 3.00 4 7.42 3 13.5 17 2.39 3 7.71 7 22.7 21 2.48 4 4.26 1 5.09 1 2.83 1 6.52 2 14.9 2 4.55 4 1.74 22 3.32 58 1.23 10 5.63 14 10.7 14 2.48 16
PMMST [114]11.9 6.46 4 14.1 4 3.23 1 5.42 1 12.7 14 3.51 14 8.20 9 14.7 22 3.66 14 7.46 4 17.8 4 4.34 6 4.79 13 5.67 8 3.91 22 6.77 3 15.2 4 3.61 2 1.74 22 3.36 61 1.34 14 5.95 19 11.3 19 2.25 2
NN-field [71]15.3 7.29 35 16.0 50 4.74 24 6.15 2 15.2 17 3.02 6 7.77 7 14.1 21 2.71 6 7.56 5 22.8 22 1.96 3 4.49 2 5.36 2 3.09 3 5.72 1 14.1 1 1.96 1 1.96 41 3.34 59 1.32 13 5.70 15 10.8 15 2.49 17
OFLAF [77]18.2 6.75 12 14.9 17 4.44 10 7.07 11 17.5 28 3.10 7 8.45 10 15.5 24 2.50 5 13.0 47 35.0 96 6.38 19 4.57 3 5.57 5 3.12 4 7.63 7 15.9 7 5.90 16 1.68 16 2.86 16 1.43 23 5.83 18 11.0 17 2.79 18
MDP-Flow2 [68]25.7 6.66 7 14.7 14 4.53 14 6.79 8 17.0 22 3.23 8 8.68 11 15.8 25 2.90 7 13.4 57 33.7 83 6.89 46 4.95 29 5.84 26 4.15 45 8.49 18 18.7 29 7.72 44 1.64 12 3.08 29 1.27 12 6.77 22 12.8 24 3.33 24
nLayers [57]28.5 7.20 30 16.0 50 4.66 21 6.25 4 14.7 15 3.70 19 7.72 6 13.7 19 4.81 33 13.1 51 34.8 94 6.69 31 4.76 10 5.75 15 4.12 42 7.19 5 14.9 2 4.40 3 1.99 43 3.10 34 1.80 47 8.22 34 15.6 35 6.10 40
FC-2Layers-FF [74]28.5 7.07 24 15.5 35 4.91 30 8.30 33 19.7 48 4.30 23 7.61 5 13.6 18 4.29 25 11.8 21 30.2 42 6.20 17 4.60 4 5.54 3 3.52 7 9.20 32 18.3 24 6.27 23 2.20 62 3.42 70 1.85 48 7.54 28 14.3 30 4.12 31
3DFlow [135]32.6 6.97 18 15.1 24 3.90 3 8.12 28 19.7 48 3.79 20 13.6 64 24.2 73 3.63 12 4.18 1 12.4 1 1.73 2 4.97 31 5.98 47 3.83 19 10.5 52 18.9 45 8.87 61 2.38 70 3.11 36 2.45 73 5.82 17 11.1 18 3.00 20
ComponentFusion [96]33.9 7.22 31 15.9 46 4.61 19 7.60 17 19.2 42 3.30 9 9.70 16 17.6 30 3.77 16 11.1 16 31.0 51 4.45 7 4.96 30 5.88 31 4.25 49 10.9 57 23.7 72 9.40 69 1.90 38 3.08 29 1.69 41 8.00 32 15.1 33 4.57 33
FESL [72]36.6 6.97 18 15.3 31 4.47 11 9.74 61 21.4 69 5.49 56 11.4 40 20.2 42 4.25 24 12.5 30 31.5 58 6.81 36 4.72 7 5.71 11 3.72 15 7.03 4 16.0 8 4.81 5 2.21 64 3.49 77 1.94 52 11.1 56 17.6 48 10.1 56
AGIF+OF [85]37.4 7.17 28 15.6 37 4.93 31 10.2 71 22.1 78 5.16 43 12.5 53 21.2 53 4.88 35 12.5 30 31.7 63 6.76 33 4.78 12 5.73 13 3.91 22 7.85 10 16.3 10 5.20 7 1.83 32 3.10 34 1.71 42 10.8 53 17.6 48 11.0 59
PWC-Net_ROB [147]37.7 8.30 80 16.2 58 6.58 90 8.56 38 20.6 57 4.38 26 12.3 50 21.4 54 6.00 54 10.8 12 27.0 30 6.88 45 4.94 27 5.79 21 3.98 28 8.37 17 19.3 47 5.42 11 1.65 15 3.29 56 1.02 3 7.86 31 14.2 29 3.37 25
NNF-EAC [103]38.5 6.83 14 14.9 17 4.80 25 7.59 16 18.0 30 4.31 24 9.03 13 16.1 26 3.09 9 13.2 54 32.2 67 7.10 53 5.06 48 5.96 40 4.02 32 8.19 14 17.1 11 6.04 20 1.79 28 3.30 57 1.38 20 17.0 94 27.6 97 18.0 115
Layers++ [37]38.5 7.19 29 15.7 39 5.08 37 6.15 2 14.8 16 3.42 12 7.83 8 14.0 20 4.84 34 10.9 14 26.9 29 6.19 16 4.83 17 5.84 26 4.36 54 12.4 79 25.2 84 10.5 84 2.43 71 3.56 82 1.92 51 8.66 37 16.1 37 7.77 47
Correlation Flow [75]38.9 6.66 7 14.5 9 3.81 2 7.78 22 17.5 28 2.85 2 18.0 98 29.0 108 4.31 27 9.28 9 22.1 20 5.57 12 5.12 52 6.13 70 3.98 28 11.0 60 23.3 67 10.5 84 2.07 52 3.08 29 2.32 68 6.79 23 12.5 22 4.83 34
Efficient-NL [60]39.8 7.43 49 16.2 58 4.85 26 7.73 20 18.1 31 4.58 28 14.0 70 23.6 69 4.47 29 13.1 51 32.9 76 7.50 67 4.77 11 5.77 19 3.65 11 8.08 12 16.1 9 5.25 8 2.48 75 3.37 63 3.12 92 6.91 24 12.1 20 5.78 38
IROF++ [58]41.2 7.44 50 16.1 54 5.11 39 8.61 40 19.4 43 5.12 41 12.3 50 21.0 52 5.12 37 12.8 41 32.1 65 7.13 55 4.88 20 5.76 17 3.89 21 9.01 22 18.9 45 6.76 31 1.78 27 3.22 50 1.23 10 10.4 50 18.5 55 13.3 75
PH-Flow [101]41.3 7.38 43 15.9 46 5.22 44 9.30 51 19.5 44 5.71 59 9.62 15 17.2 28 5.09 36 13.4 57 34.5 89 7.10 53 4.82 14 5.73 13 3.82 18 8.36 16 17.1 11 5.35 10 2.66 80 3.43 72 3.42 101 7.13 27 13.3 27 5.33 37
LME [70]41.7 7.04 22 15.6 37 4.53 14 6.68 6 16.9 21 2.85 2 13.6 64 22.6 61 12.0 120 11.5 19 27.8 31 6.39 20 5.03 41 5.93 37 4.52 63 12.4 79 27.0 98 10.9 91 1.76 25 3.38 64 1.43 23 6.62 21 12.5 22 2.86 19
NL-TV-NCC [25]42.7 6.92 17 14.6 13 3.96 5 8.32 34 19.8 52 2.84 1 15.4 80 26.0 85 3.92 19 10.8 12 26.6 26 5.58 13 5.09 49 6.00 50 4.07 35 11.1 63 23.5 68 10.5 84 2.09 53 3.06 27 2.27 66 11.6 59 20.4 61 9.14 52
Classic+CPF [83]43.2 7.31 37 15.8 42 5.09 38 9.93 66 22.1 78 5.05 39 13.3 61 22.4 60 4.64 32 12.5 30 32.0 64 6.79 35 4.87 19 5.83 25 3.99 30 7.43 6 15.6 6 5.32 9 2.26 66 3.21 48 2.78 84 9.89 46 16.5 39 13.8 78
TC/T-Flow [76]43.3 6.31 2 13.3 2 4.85 26 11.5 100 23.6 93 6.67 76 13.4 63 23.2 67 3.00 8 14.2 72 36.9 115 6.33 18 4.72 7 5.64 6 3.64 10 7.70 8 17.1 11 5.61 15 2.00 44 3.45 75 2.86 86 10.9 55 18.2 53 3.59 27
LSM [39]43.3 7.06 23 15.2 29 5.21 43 9.65 59 21.2 68 5.48 55 11.9 46 20.2 42 5.33 42 12.0 22 30.0 40 6.84 40 5.14 57 6.13 70 4.62 69 9.12 28 18.1 21 6.53 27 2.13 58 3.11 36 2.11 58 8.09 33 14.3 30 6.76 44
CombBMOF [113]43.3 7.30 36 15.1 24 4.61 19 8.08 27 18.2 33 3.69 18 10.2 19 18.1 33 2.47 4 11.2 17 28.1 32 6.67 28 4.82 14 5.76 17 4.13 43 13.3 91 22.1 59 14.1 118 2.90 91 4.33 109 2.14 59 11.8 61 21.0 65 3.23 23
MLDP_OF [89]43.7 7.02 20 14.5 9 4.89 29 7.00 10 17.0 22 3.34 10 14.3 72 24.0 70 3.73 15 12.9 44 34.8 94 5.88 14 4.89 22 5.69 9 3.92 25 8.18 13 17.4 15 7.22 42 3.64 112 3.68 87 5.99 127 13.2 71 20.5 63 9.16 53
Sparse-NonSparse [56]44.1 7.26 34 15.7 39 5.22 44 9.83 63 21.6 72 5.45 54 12.2 48 20.8 48 5.35 45 12.1 25 30.0 40 6.86 42 5.14 57 6.13 70 4.58 66 9.16 30 18.5 27 6.58 28 2.05 50 3.03 24 2.06 57 7.62 29 13.8 28 5.98 39
HAST [109]44.7 7.11 26 16.0 50 4.27 6 8.90 44 17.4 27 7.54 86 6.79 1 12.4 14 1.56 1 14.8 78 37.2 116 6.63 24 4.68 6 5.70 10 2.91 2 10.5 52 20.7 51 11.1 92 3.74 116 4.39 112 5.40 126 5.74 16 10.9 16 2.09 1
WLIF-Flow [93]44.9 6.80 13 14.9 17 4.60 18 6.93 9 16.7 20 4.11 22 10.3 20 18.2 34 4.11 23 12.7 39 30.9 49 6.67 28 6.60 132 7.87 136 5.60 106 8.54 19 17.4 15 6.03 19 1.85 33 3.18 45 1.67 39 14.4 77 23.2 78 15.3 86
Ramp [62]45.8 7.32 39 15.8 42 5.20 42 8.74 41 19.8 52 5.27 49 11.4 40 19.7 41 5.40 48 12.5 30 31.6 61 6.86 42 4.97 31 5.88 31 4.08 37 9.04 23 18.3 24 7.00 38 2.65 79 3.36 61 4.00 115 8.65 36 15.3 34 11.7 64
PMF [73]46.4 7.59 55 16.5 80 4.94 32 7.64 18 18.3 36 3.66 16 7.48 4 13.2 16 2.31 2 14.7 77 36.3 112 6.84 40 4.66 5 5.64 6 3.18 6 9.85 38 21.3 54 9.22 65 3.62 111 5.25 133 3.70 111 7.12 26 13.2 26 6.82 45
Classic+NL [31]47.4 7.40 46 16.1 54 5.36 54 9.49 58 20.9 62 5.44 53 12.3 50 20.8 48 5.20 40 12.5 30 31.3 57 6.82 37 5.03 41 5.98 47 4.18 47 8.94 21 17.5 17 5.91 17 2.29 68 3.44 74 2.17 60 9.88 45 17.0 45 11.9 66
FlowFields+ [130]48.2 8.95 93 17.2 98 7.26 102 7.52 15 17.3 25 5.15 42 10.4 21 17.6 30 6.16 55 10.1 10 24.5 23 6.49 22 5.11 51 6.00 50 4.57 65 9.28 33 22.2 60 6.70 30 1.77 26 3.20 46 1.51 33 13.1 70 21.8 69 15.6 89
CostFilter [40]48.6 7.36 41 15.7 39 4.96 34 7.76 21 18.1 31 3.83 21 7.07 2 12.4 14 3.12 10 14.6 76 36.3 112 6.57 23 4.82 14 5.81 23 3.54 8 12.4 79 20.5 50 10.3 82 3.86 121 5.96 137 4.36 118 8.86 40 16.7 42 3.72 29
FMOF [94]50.2 7.14 27 15.5 35 5.28 48 10.4 86 22.7 84 5.42 50 10.8 35 19.0 39 3.90 18 12.2 27 31.0 51 6.63 24 4.98 34 5.97 41 4.10 38 10.0 45 17.2 14 6.98 36 2.46 73 3.40 67 4.60 119 14.7 79 23.2 78 10.1 56
TV-L1-MCT [64]51.3 7.42 48 16.1 54 5.22 44 9.84 64 21.6 72 5.20 45 14.3 72 24.7 76 5.27 41 12.5 30 31.2 56 7.21 58 5.01 37 5.90 33 4.41 57 9.10 26 18.8 44 7.14 40 2.17 61 2.78 5 4.69 120 9.81 44 16.8 44 11.5 61
ProbFlowFields [128]51.7 8.84 91 17.9 110 6.90 95 7.20 13 17.3 25 4.75 35 11.6 43 20.5 46 6.31 59 8.48 8 22.0 19 5.26 10 5.25 75 6.24 89 4.67 78 9.96 43 23.9 76 6.99 37 1.64 12 2.80 7 1.41 21 14.7 79 25.5 88 14.7 82
WRT [150]51.8 7.40 46 15.9 46 3.93 4 9.33 52 21.1 66 3.42 12 21.1 122 31.0 128 6.88 67 4.33 2 13.0 3 1.43 1 4.84 18 5.80 22 4.44 59 13.6 95 21.4 56 10.8 89 1.71 20 2.85 13 1.65 38 16.7 91 20.4 61 20.8 132
RNLOD-Flow [121]51.9 6.72 10 14.9 17 4.39 8 9.09 46 21.0 64 5.06 40 15.2 78 25.8 81 5.42 49 12.6 37 32.2 67 6.64 26 5.46 94 6.48 105 4.34 53 8.35 15 17.8 19 6.16 22 2.82 86 3.90 98 3.36 99 9.02 41 16.1 37 9.83 54
SVFilterOh [111]52.0 7.94 62 17.5 104 4.94 32 8.27 32 19.8 52 3.66 16 9.83 18 17.7 32 4.59 30 13.4 57 34.5 89 6.82 37 4.89 22 5.93 37 3.15 5 10.4 51 22.7 62 9.35 68 3.51 108 4.72 122 4.17 116 7.68 30 14.3 30 4.90 35
IIOF-NLDP [131]52.2 7.31 37 15.4 32 4.42 9 8.37 35 19.9 55 3.01 5 15.4 80 25.9 83 4.00 21 7.56 5 18.6 18 4.73 8 6.04 118 7.28 130 5.15 93 10.1 46 21.3 54 9.54 71 1.74 22 2.90 18 1.50 31 15.8 84 21.6 68 20.5 129
Complementary OF [21]52.7 7.37 42 15.1 24 5.30 51 9.46 54 22.5 82 4.63 29 13.0 56 22.8 63 4.04 22 14.8 78 37.9 125 6.87 44 4.97 31 5.86 28 4.39 56 11.0 60 24.4 79 8.06 49 1.79 28 2.79 6 2.22 63 12.2 62 22.0 72 11.2 60
ALD-Flow [66]54.0 6.69 9 14.4 8 4.54 16 12.5 111 25.7 106 6.93 79 14.3 72 24.9 77 4.29 25 14.8 78 35.3 102 7.04 51 4.98 34 5.92 35 3.66 12 10.1 46 23.6 70 6.92 34 2.02 46 3.23 51 2.86 86 10.2 49 18.9 57 6.45 43
EPPM w/o HM [88]54.0 7.33 40 14.5 9 5.00 36 7.20 13 17.2 24 3.41 11 11.8 44 20.8 48 3.20 11 12.6 37 31.1 55 7.00 50 5.14 57 6.08 63 4.67 78 12.0 73 22.7 62 9.97 78 4.48 132 3.69 89 6.02 128 10.4 50 17.6 48 11.5 61
FlowFields [110]54.8 9.03 96 17.5 104 7.31 103 8.02 26 18.6 39 5.24 48 11.1 39 18.9 37 6.32 60 11.6 20 28.7 34 7.40 65 5.14 57 6.03 57 4.64 73 10.1 46 23.8 75 7.62 43 1.69 17 2.86 16 1.51 33 12.9 66 22.8 76 14.9 85
JOF [140]55.2 7.77 58 16.9 90 5.33 52 10.6 88 20.8 61 7.75 89 10.9 37 18.9 37 5.34 43 12.7 39 32.6 70 6.67 28 4.91 25 5.86 28 3.97 27 9.05 24 17.9 20 5.47 12 3.04 98 3.66 86 3.43 102 13.3 73 21.4 67 12.2 70
MDP-Flow [26]55.5 6.73 11 14.1 4 5.59 63 6.70 7 16.0 19 4.65 31 9.78 17 17.2 28 6.61 64 13.0 47 34.7 93 6.48 21 5.54 98 6.17 79 5.84 110 10.5 52 23.6 70 7.81 45 1.89 36 3.42 70 1.37 17 20.0 112 32.5 118 19.1 121
TC-Flow [46]56.0 6.56 6 14.1 4 4.48 12 9.25 50 21.4 69 5.03 38 14.9 76 25.8 81 3.93 20 14.5 75 35.9 106 6.97 49 5.01 37 5.97 41 3.63 9 9.98 44 22.8 65 6.83 33 2.11 55 3.25 52 3.61 109 16.7 91 26.8 94 20.0 127
S2F-IF [123]56.2 8.86 92 17.2 98 7.05 99 7.84 25 18.3 36 5.20 45 10.8 35 18.5 36 6.21 56 13.0 47 30.7 47 8.15 77 5.09 49 5.98 47 4.58 66 9.62 36 22.7 62 7.20 41 1.92 39 3.77 94 1.73 43 10.7 52 18.4 54 12.8 73
ProFlow_ROB [146]56.3 7.98 67 17.0 91 5.55 62 9.17 48 21.5 71 5.69 58 13.9 68 24.5 75 5.39 47 13.9 67 32.3 69 7.54 68 5.19 69 6.19 82 4.26 50 9.15 29 21.8 58 5.47 12 1.57 6 2.92 19 1.15 7 13.9 76 23.8 82 12.3 71
SimpleFlow [49]57.9 7.56 54 16.2 58 5.59 63 9.48 55 21.0 64 5.68 57 17.1 93 27.0 96 6.29 58 13.0 47 32.8 74 7.09 52 5.18 66 6.16 75 4.62 69 8.75 20 17.6 18 6.81 32 2.13 58 3.50 78 2.30 67 9.78 43 17.4 47 7.10 46
IROF-TV [53]58.3 7.55 53 16.1 54 5.46 59 9.23 49 21.8 74 5.88 62 13.3 61 22.2 59 5.50 51 12.8 41 31.6 61 7.28 60 5.12 52 6.09 64 4.67 78 13.3 91 29.6 117 9.97 78 1.60 7 3.12 40 1.06 4 11.5 58 21.3 66 11.5 61
SRR-TVOF-NL [91]58.5 7.83 59 15.4 32 5.99 76 13.2 117 26.1 110 8.61 95 13.2 59 22.0 58 6.78 65 13.6 63 30.3 43 7.34 64 4.72 7 5.56 4 4.04 34 9.87 40 19.8 49 8.30 53 3.25 103 3.73 92 3.18 95 6.93 25 12.9 25 4.92 36
HBM-GC [105]60.2 8.35 84 18.4 115 4.98 35 7.66 19 18.2 33 5.20 45 13.8 67 24.2 73 5.34 43 12.0 22 30.5 45 6.83 39 5.04 44 6.02 56 4.43 58 9.34 34 15.5 5 7.92 46 3.03 97 4.57 117 2.51 78 16.1 86 26.0 90 17.9 113
ACK-Prior [27]60.3 6.39 3 13.4 3 4.38 7 8.58 39 19.7 48 3.63 15 11.4 40 20.3 44 3.82 17 12.5 30 33.7 83 5.09 9 5.53 96 6.42 101 4.76 82 15.0 109 28.4 105 11.4 94 3.54 109 4.36 111 4.84 122 13.2 71 20.2 60 8.94 50
LiteFlowNet [142]60.4 9.19 97 16.6 81 7.02 98 8.23 30 18.9 41 4.53 27 12.9 54 21.5 55 6.23 57 12.0 22 26.7 27 7.32 63 5.39 90 6.23 86 5.47 103 9.09 25 18.7 29 6.31 24 2.02 46 3.14 42 1.47 25 19.2 106 24.7 84 21.9 138
2DHMM-SAS [92]62.0 7.39 45 15.9 46 5.25 47 10.7 91 23.4 90 5.43 51 18.0 98 27.0 96 7.95 98 13.1 51 32.7 72 7.28 60 4.89 22 5.78 20 4.01 31 9.88 41 18.2 22 6.37 25 2.50 78 3.39 65 3.37 100 13.8 75 22.4 75 15.5 88
Sparse Occlusion [54]62.6 7.38 43 15.8 42 5.28 48 8.25 31 19.9 55 4.71 33 15.5 83 26.3 90 4.63 31 13.5 62 33.3 82 6.92 47 5.25 75 6.26 90 4.11 40 9.70 37 21.1 53 5.94 18 4.85 133 5.95 136 3.71 112 10.8 53 20.0 59 8.01 49
DPOF [18]63.7 8.43 86 16.8 85 6.36 85 10.7 91 20.7 59 9.52 103 8.72 12 15.4 23 3.63 12 11.3 18 29.1 36 6.09 15 5.34 83 6.18 80 5.38 100 12.2 75 22.4 61 8.06 49 5.27 134 3.55 79 6.79 133 8.85 39 16.5 39 4.24 32
OFH [38]64.2 7.25 33 15.0 23 5.29 50 11.1 95 25.0 102 7.19 83 18.6 103 29.1 110 5.56 52 16.0 94 40.8 142 7.44 66 5.05 45 5.92 35 4.28 51 11.4 65 26.0 91 8.73 57 1.64 12 3.04 25 1.36 16 12.5 64 23.3 80 7.79 48
ResPWCR_ROB [144]64.4 8.30 80 14.5 9 7.12 100 8.82 42 19.6 47 5.91 63 11.8 44 19.3 40 7.90 97 12.4 29 28.5 33 7.89 74 5.18 66 5.97 41 5.36 98 10.9 57 23.9 76 8.84 60 2.85 88 3.65 85 2.34 69 14.7 79 21.8 69 16.2 100
COFM [59]64.6 8.49 88 18.5 118 5.95 72 8.44 36 18.7 40 4.71 33 13.0 56 22.9 64 5.84 53 13.8 65 35.2 100 6.78 34 5.63 104 6.58 108 5.94 111 11.7 69 23.5 68 9.80 74 2.29 68 3.20 46 2.72 81 6.42 20 12.1 20 3.07 22
ROF-ND [107]64.6 7.02 20 14.7 14 4.66 21 8.18 29 19.5 44 4.66 32 15.5 83 25.9 83 5.47 50 4.68 3 12.6 2 2.76 5 5.93 112 7.12 127 5.27 95 12.2 75 25.4 87 9.09 64 4.23 129 4.20 105 3.32 98 14.7 79 22.1 74 18.8 119
PGM-C [120]65.7 9.43 101 18.5 118 7.51 108 9.84 64 23.4 90 6.05 65 12.0 47 20.6 47 7.17 72 15.8 90 35.3 102 9.67 94 5.20 72 6.11 67 4.66 75 9.86 39 23.7 72 7.06 39 1.63 10 2.84 12 1.49 30 11.1 56 20.8 64 6.23 42
TCOF [69]66.4 7.46 51 15.1 24 5.70 66 9.13 47 21.1 66 5.43 51 19.6 109 29.8 115 8.31 102 12.9 44 31.0 51 7.17 57 6.02 117 7.00 122 4.59 68 7.92 11 18.4 26 6.11 21 3.78 118 4.09 102 5.18 124 8.51 35 15.9 36 3.80 30
S2D-Matching [84]66.7 8.25 77 18.0 112 5.76 69 10.9 93 22.8 85 5.71 59 17.3 94 28.5 103 6.38 62 12.1 25 30.3 43 6.65 27 5.15 61 6.13 70 4.63 71 9.18 31 19.5 48 6.69 29 2.66 80 3.35 60 3.50 103 11.6 59 19.9 58 14.7 82
OAR-Flow [125]66.9 8.08 71 16.8 85 6.19 81 17.4 131 28.9 129 12.3 128 16.3 89 26.7 95 7.01 69 15.1 83 35.2 100 7.31 62 5.17 64 6.16 75 4.24 48 9.51 35 22.9 66 5.52 14 1.54 5 2.98 22 1.59 37 9.10 42 17.1 46 3.69 28
ComplOF-FED-GPU [35]67.2 7.49 52 15.4 32 5.37 56 12.1 107 26.5 117 7.51 85 13.1 58 22.7 62 4.33 28 15.6 87 37.7 123 7.55 70 4.94 27 5.82 24 4.13 43 12.3 77 27.7 102 8.48 55 2.49 77 3.04 25 3.56 106 12.9 66 23.9 83 9.01 51
AggregFlow [97]70.8 10.3 114 21.3 147 6.91 96 15.1 124 27.6 124 10.7 108 14.0 70 24.0 70 8.70 105 14.1 69 35.0 96 7.15 56 5.05 45 6.03 57 4.02 32 7.73 9 18.2 22 5.09 6 2.13 58 4.40 113 1.67 39 9.91 47 18.1 52 6.13 41
CPM-Flow [116]73.7 9.46 103 18.6 121 7.51 108 10.0 68 23.7 94 6.20 67 12.2 48 20.9 51 7.13 70 15.8 90 35.6 105 9.71 96 5.20 72 6.12 69 4.65 74 10.9 57 23.7 72 8.90 62 1.73 21 3.15 43 1.51 33 14.5 78 26.0 90 13.6 77
EpicFlow [102]74.8 9.39 100 18.4 115 7.50 107 10.0 68 23.8 96 6.29 69 15.8 86 26.6 93 7.35 79 15.5 85 34.4 88 9.65 92 5.20 72 6.11 67 4.66 75 10.2 49 24.5 80 8.18 52 1.63 10 2.81 9 1.48 26 15.8 84 24.8 85 17.1 109
Aniso-Texture [82]76.5 6.49 5 14.2 7 4.54 16 7.83 24 19.5 44 4.37 25 22.0 136 33.6 149 8.47 103 10.3 11 25.4 24 5.55 11 5.19 69 6.10 65 4.45 60 18.7 131 33.0 142 20.1 151 4.07 127 4.62 119 2.47 76 20.1 113 28.5 99 20.7 130
Occlusion-TV-L1 [63]76.8 7.73 57 16.4 66 5.36 54 9.48 55 22.4 81 6.18 66 19.2 105 30.0 118 7.14 71 14.4 74 33.8 85 7.91 75 5.31 82 6.27 92 4.47 61 11.9 71 27.9 103 8.04 47 2.09 53 3.08 29 1.50 31 21.9 124 35.3 134 17.5 110
ContinualFlow_ROB [152]77.1 11.4 122 20.8 142 8.47 125 9.76 62 18.5 38 7.94 92 16.5 90 26.6 93 11.7 118 15.7 88 37.2 116 8.85 84 5.25 75 5.97 41 5.27 95 11.8 70 24.9 82 11.4 94 1.53 4 3.06 27 1.10 5 12.4 63 17.7 51 13.1 74
RFlow [90]77.8 7.10 25 14.9 17 5.40 57 8.98 45 21.9 76 5.19 44 18.5 102 29.3 112 5.35 45 18.1 125 44.9 160 9.86 99 5.12 52 6.01 53 4.38 55 13.0 88 29.3 114 9.93 77 2.28 67 2.85 13 3.52 104 20.3 115 33.3 124 16.1 98
FF++_ROB [145]78.2 9.92 109 19.4 128 7.55 111 8.87 43 20.9 62 5.83 61 15.3 79 25.3 79 7.95 98 11.0 15 25.4 24 7.23 59 5.19 69 6.10 65 4.80 83 17.1 118 25.3 86 13.2 110 1.88 34 2.96 21 2.77 82 18.7 101 27.2 95 25.3 144
DeepFlow2 [108]78.8 8.14 73 16.6 81 5.96 74 14.1 119 26.5 117 10.2 104 15.8 86 26.2 89 6.46 63 16.5 113 37.4 120 9.54 90 5.01 37 5.94 39 3.72 15 10.7 55 25.1 83 8.08 51 1.92 39 3.12 40 2.45 73 20.3 115 32.1 115 16.3 101
Adaptive [20]79.4 7.94 62 17.0 91 5.33 52 10.2 71 23.9 97 6.28 68 21.2 123 31.7 137 7.69 94 13.6 63 29.8 38 7.87 73 4.88 20 5.75 15 3.71 14 13.2 89 28.9 111 9.72 73 3.21 102 4.71 121 2.91 88 19.3 108 30.5 106 15.6 89
DMF_ROB [139]79.5 8.27 78 16.7 83 6.36 85 11.7 103 26.4 115 7.10 82 17.8 97 28.6 105 7.33 78 15.9 93 35.9 106 9.46 88 5.05 45 5.97 41 4.51 62 12.8 86 27.4 99 9.90 76 1.60 7 2.99 23 1.48 26 19.8 111 32.0 113 16.8 105
TF+OM [100]81.2 7.97 66 16.8 85 5.98 75 9.40 53 20.7 59 6.33 70 15.4 80 22.9 64 17.5 131 13.4 57 31.5 58 8.10 76 5.13 56 6.06 62 4.66 75 13.9 98 29.3 114 14.0 116 2.47 74 4.09 102 2.00 53 18.3 99 29.4 103 19.3 123
Steered-L1 [118]81.6 5.97 1 12.7 1 4.67 23 7.14 12 18.2 33 4.63 29 13.2 59 23.3 68 5.12 37 15.2 84 38.1 126 7.54 68 5.85 111 6.73 112 6.98 130 13.7 97 26.5 93 11.7 100 6.39 139 4.25 107 13.3 154 22.3 127 32.7 120 20.3 128
Aniso. Huber-L1 [22]82.3 7.96 65 16.3 64 6.10 79 11.4 97 24.7 100 6.77 77 20.6 116 29.6 114 7.26 74 13.2 54 29.2 37 7.77 72 5.52 95 6.58 108 4.29 52 12.4 79 26.7 96 8.83 59 2.93 94 3.68 87 3.10 91 16.5 90 27.4 96 13.9 79
OFRF [134]83.8 9.69 105 19.6 131 6.25 82 22.2 150 29.4 132 20.7 153 21.6 127 30.1 119 17.0 130 14.1 69 31.0 51 8.47 80 4.93 26 5.87 30 3.94 26 9.10 26 18.6 28 6.40 26 2.84 87 4.62 119 3.66 110 12.6 65 16.7 42 15.9 97
AdaConv-v1 [126]83.9 13.0 134 16.4 66 8.62 127 10.2 71 9.17 1 11.5 113 10.7 22 11.1 1 7.66 81 16.3 99 17.8 4 14.4 124 10.8 144 8.97 141 16.5 145 19.7 135 18.7 29 19.4 136 19.7 149 17.1 149 8.18 138 3.51 1 4.92 1 2.42 3
SepConv-v1 [127]83.9 13.0 134 16.4 66 8.62 127 10.2 71 9.17 1 11.5 113 10.7 22 11.1 1 7.66 81 16.3 99 17.8 4 14.4 124 10.8 144 8.97 141 16.5 145 19.7 135 18.7 29 19.4 136 19.7 149 17.1 149 8.18 138 3.51 1 4.92 1 2.42 3
SuperSlomo [132]83.9 13.0 134 16.4 66 8.62 127 10.2 71 9.17 1 11.5 113 10.7 22 11.1 1 7.66 81 16.3 99 17.8 4 14.4 124 10.8 144 8.97 141 16.5 145 19.7 135 18.7 29 19.4 136 19.7 149 17.1 149 8.18 138 3.51 1 4.92 1 2.42 3
CtxSyn [136]83.9 13.0 134 16.4 66 8.62 127 10.2 71 9.17 1 11.5 113 10.7 22 11.1 1 7.66 81 16.3 99 17.8 4 14.4 124 10.8 144 8.97 141 16.5 145 19.7 135 18.7 29 19.4 136 19.7 149 17.1 149 8.18 138 3.51 1 4.92 1 2.42 3
CyclicGen [153]83.9 13.0 134 16.4 66 8.62 127 10.2 71 9.17 1 11.5 113 10.7 22 11.1 1 7.66 81 16.3 99 17.8 4 14.4 124 10.8 144 8.97 141 16.5 145 19.7 135 18.7 29 19.4 136 19.7 149 17.1 149 8.18 138 3.51 1 4.92 1 2.42 3
TOF-M [154]83.9 13.0 134 16.4 66 8.62 127 10.2 71 9.17 1 11.5 113 10.7 22 11.1 1 7.66 81 16.3 99 17.8 4 14.4 124 10.8 144 8.97 141 16.5 145 19.7 135 18.7 29 19.4 136 19.7 149 17.1 149 8.18 138 3.51 1 4.92 1 2.42 3
MEMC-Net+ [155]83.9 13.0 134 16.4 66 8.62 127 10.2 71 9.17 1 11.5 113 10.7 22 11.1 1 7.66 81 16.3 99 17.8 4 14.4 124 10.8 144 8.97 141 16.5 145 19.7 135 18.7 29 19.4 136 19.7 149 17.1 149 8.18 138 3.51 1 4.92 1 2.42 3
CFRF [156]83.9 13.0 134 16.4 66 8.62 127 10.2 71 9.17 1 11.5 113 10.7 22 11.1 1 7.66 81 16.3 99 17.8 4 14.4 124 10.8 144 8.97 141 16.5 145 19.7 135 18.7 29 19.4 136 19.7 149 17.1 149 8.18 138 3.51 1 4.92 1 2.42 3
MPRN [157]83.9 13.0 134 16.4 66 8.62 127 10.2 71 9.17 1 11.5 113 10.7 22 11.1 1 7.66 81 16.3 99 17.8 4 14.4 124 10.8 144 8.97 141 16.5 145 19.7 135 18.7 29 19.4 136 19.7 149 17.1 149 8.18 138 3.51 1 4.92 1 2.42 3
DAIN [158]83.9 13.0 134 16.4 66 8.62 127 10.2 71 9.17 1 11.5 113 10.7 22 11.1 1 7.66 81 16.3 99 17.8 4 14.4 124 10.8 144 8.97 141 16.5 145 19.7 135 18.7 29 19.4 136 19.7 149 17.1 149 8.18 138 3.51 1 4.92 1 2.42 3
PyrWarp [159]83.9 13.0 134 16.4 66 8.62 127 10.2 71 9.17 1 11.5 113 10.7 22 11.1 1 7.66 81 16.3 99 17.8 4 14.4 124 10.8 144 8.97 141 16.5 145 19.7 135 18.7 29 19.4 136 19.7 149 17.1 149 8.18 138 3.51 1 4.92 1 2.42 3
InterpCNN [160]83.9 13.0 134 16.4 66 8.62 127 10.2 71 9.17 1 11.5 113 10.7 22 11.1 1 7.66 81 16.3 99 17.8 4 14.4 124 10.8 144 8.97 141 16.5 145 19.7 135 18.7 29 19.4 136 19.7 149 17.1 149 8.18 138 3.51 1 4.92 1 2.42 3
OFRI [161]83.9 13.0 134 16.4 66 8.62 127 10.2 71 9.17 1 11.5 113 10.7 22 11.1 1 7.66 81 16.3 99 17.8 4 14.4 124 10.8 144 8.97 141 16.5 145 19.7 135 18.7 29 19.4 136 19.7 149 17.1 149 8.18 138 3.51 1 4.92 1 2.42 3
AugFNG_ROB [143]84.2 12.7 131 22.1 148 9.46 144 12.1 107 24.6 99 9.39 101 18.8 104 27.1 100 14.7 127 14.0 68 30.9 49 9.24 86 5.03 41 5.72 12 5.09 90 11.0 60 24.0 78 9.53 70 1.82 31 3.25 52 1.22 8 18.2 98 23.7 81 21.6 135
EAI-Flow [151]84.6 10.4 117 19.0 125 7.83 113 13.2 117 25.8 107 9.43 102 13.7 66 21.6 56 8.47 103 14.8 78 33.0 77 9.68 95 5.12 52 6.01 53 4.74 81 11.6 66 25.7 89 9.23 66 3.66 113 3.57 83 2.04 55 13.4 74 24.8 85 10.5 58
LocallyOriented [52]84.9 9.89 107 19.9 135 6.55 88 14.7 123 27.7 125 11.0 110 21.7 130 31.9 139 7.32 77 13.3 56 30.5 45 8.32 78 5.16 62 6.04 59 4.11 40 9.90 42 21.6 57 8.75 58 2.20 62 3.43 72 2.17 60 18.3 99 26.0 90 19.6 124
SIOF [67]87.1 8.21 76 17.0 91 5.49 60 13.0 116 27.4 123 8.63 96 20.1 114 29.0 108 16.3 129 16.8 115 37.3 119 10.0 103 5.40 91 6.34 97 4.88 85 11.6 66 25.4 87 10.1 81 1.81 30 3.27 54 1.34 14 15.1 83 25.1 87 11.9 66
LFNet_ROB [149]87.6 10.1 112 17.0 91 8.16 121 9.48 55 21.8 74 6.00 64 16.8 91 26.1 87 11.1 115 13.4 57 29.9 39 8.73 83 5.40 91 6.20 83 5.58 105 13.3 91 29.4 116 10.0 80 2.04 49 3.21 48 1.85 48 22.7 131 35.6 135 21.8 137
SegOF [10]88.7 9.43 101 17.7 106 8.06 118 12.0 106 22.9 88 10.4 107 17.0 92 26.1 87 12.6 122 13.8 65 26.8 28 11.2 111 5.53 96 6.26 90 6.06 114 19.0 132 35.6 154 18.8 134 1.37 2 2.60 2 0.83 2 16.4 88 30.0 104 14.0 80
DeepFlow [86]88.8 8.73 89 17.1 97 6.26 83 15.3 127 26.7 120 11.9 127 17.3 94 26.5 92 14.1 126 18.6 131 42.8 154 11.0 109 5.00 36 5.91 34 3.75 17 11.2 64 26.2 92 8.35 54 1.88 34 2.80 7 2.60 79 22.5 129 33.6 125 17.5 110
TriangleFlow [30]88.9 8.08 71 17.0 91 5.12 40 11.7 103 26.1 110 6.98 81 19.5 107 30.3 122 6.34 61 12.9 44 33.0 77 6.71 32 7.00 135 8.16 139 6.63 127 12.8 86 24.5 80 10.5 84 3.59 110 5.17 131 3.27 97 12.9 66 21.9 71 12.1 68
CRTflow [80]89.4 7.92 60 16.0 50 5.91 71 11.4 97 23.7 94 6.55 74 19.8 111 30.1 119 7.77 95 17.2 121 41.3 145 9.76 97 5.34 83 6.30 93 3.69 13 15.8 114 31.0 129 14.3 119 2.12 57 2.92 19 2.35 70 19.2 106 32.9 122 15.3 86
TriFlow [95]91.1 9.01 95 18.5 118 6.60 91 11.4 97 26.4 115 7.40 84 20.9 119 29.9 117 20.9 140 12.2 27 30.8 48 6.95 48 5.26 80 6.16 75 4.88 85 12.0 73 26.5 93 11.6 98 6.97 140 4.54 115 6.57 132 13.0 69 22.0 72 9.86 55
Brox et al. [5]92.1 8.46 87 16.7 83 6.56 89 11.3 96 26.2 112 6.94 80 15.0 77 25.4 80 6.89 68 17.4 122 38.8 130 9.80 98 5.99 115 6.88 119 6.26 119 14.1 101 31.1 132 12.0 102 2.03 48 3.41 69 1.14 6 19.1 105 30.3 105 12.1 68
Fusion [6]93.1 8.76 90 17.7 106 7.01 97 7.82 23 19.7 48 4.78 36 10.9 37 18.4 35 7.23 73 12.8 41 32.6 70 8.32 78 7.04 136 8.11 137 6.57 125 14.9 107 28.3 104 13.2 110 4.37 131 5.18 132 2.77 82 26.2 144 38.6 146 26.4 146
p-harmonic [29]93.2 8.15 75 16.2 58 6.50 87 9.66 60 22.6 83 6.57 75 21.2 123 31.2 130 9.65 108 15.7 88 33.9 86 10.0 103 5.18 66 6.04 59 5.31 97 14.3 103 30.3 124 12.2 106 3.10 99 3.55 79 1.91 50 23.1 134 34.8 132 17.8 112
CBF [12]94.0 7.23 32 14.9 17 5.16 41 9.95 67 21.9 76 7.69 88 17.6 96 27.0 96 7.28 76 16.4 112 39.3 134 9.18 85 6.34 128 7.35 133 6.11 117 13.4 94 28.4 105 8.52 56 5.54 136 5.11 128 6.41 130 18.7 101 30.8 107 16.4 102
EPMNet [133]95.0 11.6 125 20.5 140 8.03 117 17.7 133 28.9 129 13.2 133 12.9 54 20.3 44 10.7 111 15.5 85 37.4 120 9.48 89 5.36 87 6.23 86 4.94 87 14.0 99 29.9 120 12.2 106 2.97 95 5.82 135 2.01 54 10.1 48 18.8 56 3.51 26
FlowNet2 [122]95.8 12.8 132 23.3 153 8.09 119 16.8 130 28.5 126 12.5 129 13.9 68 21.6 56 12.0 120 15.0 82 34.0 87 9.98 102 5.36 87 6.23 86 4.94 87 14.0 99 29.9 120 12.2 106 3.36 104 6.60 141 2.24 64 8.83 38 16.6 41 3.02 21
TV-L1-improved [17]95.8 7.64 56 16.2 58 5.67 65 10.1 70 23.4 90 6.38 71 21.3 125 32.0 142 9.27 107 17.5 123 42.1 149 9.54 90 5.25 75 6.13 70 4.07 35 14.5 104 30.4 126 11.4 94 3.38 105 5.02 126 2.99 90 19.6 110 32.1 115 16.6 104
CLG-TV [48]96.0 7.94 62 16.2 58 5.80 70 10.5 87 24.0 98 6.44 72 19.9 112 29.8 115 6.83 66 14.1 69 31.5 58 7.73 71 5.98 113 7.01 123 5.15 93 14.8 106 31.0 129 12.2 106 4.20 128 4.80 123 5.22 125 19.3 108 32.6 119 15.7 93
WOLF_ROB [148]96.2 9.97 110 18.4 115 7.33 104 20.8 141 34.8 157 13.9 135 22.2 138 30.7 126 10.9 112 17.0 120 33.2 81 12.3 118 5.16 62 6.01 53 5.11 92 10.2 49 20.7 51 9.05 63 1.97 42 3.28 55 2.48 77 17.9 97 23.1 77 21.3 134
Local-TV-L1 [65]97.6 9.74 106 17.9 110 6.89 94 18.4 136 29.4 132 14.9 137 24.4 142 30.8 127 20.2 138 19.4 136 42.4 152 12.7 120 5.35 86 6.00 50 4.10 38 13.6 95 28.9 111 9.26 67 1.62 9 2.58 1 1.48 26 20.3 115 32.0 113 16.4 102
Classic++ [32]98.0 8.05 69 17.4 103 6.09 78 11.5 100 26.3 114 6.91 78 18.1 100 28.7 106 8.18 100 16.2 95 39.0 132 8.57 81 5.36 87 6.33 95 4.54 64 15.0 109 30.4 126 11.6 98 2.70 83 3.55 79 2.94 89 21.9 124 34.0 128 17.9 113
SuperFlow [81]98.3 9.27 99 17.3 101 6.63 92 11.7 103 22.8 85 8.84 98 19.3 106 28.0 102 18.4 135 16.9 117 38.2 127 9.89 100 5.44 93 6.32 94 5.61 107 11.9 71 26.6 95 9.56 72 2.92 92 4.08 101 1.79 45 20.1 113 32.4 117 15.8 95
Rannacher [23]99.5 8.07 70 16.8 85 6.15 80 10.6 88 24.8 101 6.51 73 21.9 134 32.6 148 10.9 112 18.4 128 43.3 156 10.5 105 5.27 81 6.18 80 4.17 46 15.5 112 32.3 139 12.0 102 2.69 82 3.57 83 2.68 80 17.8 96 31.0 108 16.1 98
F-TV-L1 [15]100.3 8.41 85 16.8 85 6.31 84 18.0 135 29.7 134 12.8 130 21.6 127 30.5 123 10.1 110 18.2 126 42.3 151 9.65 92 5.02 40 5.97 41 3.91 22 14.1 101 30.8 128 10.6 88 2.79 84 4.90 124 2.35 70 20.5 118 32.7 120 15.6 89
BriefMatch [124]102.5 6.91 16 14.8 16 4.85 26 11.0 94 22.8 85 8.24 93 9.42 14 16.6 27 5.13 39 16.7 114 40.7 141 8.61 82 9.76 142 10.6 156 14.1 143 18.2 128 31.0 129 17.4 130 9.26 144 6.60 141 20.9 160 28.0 148 36.5 138 34.9 153
StereoOF-V1MT [119]103.0 8.14 73 15.8 42 5.42 58 17.6 132 34.3 155 10.3 105 21.6 127 31.5 134 7.27 75 15.8 90 32.7 72 10.7 106 5.62 103 6.40 99 6.00 113 16.6 117 30.0 122 15.5 121 2.01 45 3.08 29 3.15 93 33.6 154 44.0 155 32.8 151
DF-Auto [115]104.1 10.7 120 19.8 134 7.42 106 16.3 129 25.3 103 13.1 132 19.5 107 28.5 103 17.8 133 16.9 117 37.2 116 10.8 107 6.76 134 8.12 138 5.56 104 10.8 56 25.2 84 6.95 35 3.69 115 4.92 125 1.48 26 17.7 95 27.9 98 14.6 81
Dynamic MRF [7]104.9 8.32 83 17.3 101 5.95 72 12.3 109 28.5 126 7.75 89 19.6 109 31.8 138 7.56 80 18.4 128 42.2 150 11.6 115 5.25 75 6.16 75 4.80 83 17.7 122 34.4 150 16.6 126 1.89 36 2.63 3 3.21 96 30.3 150 43.6 154 29.0 148
Bartels [41]105.1 8.31 82 17.7 106 5.51 61 8.46 37 20.6 57 4.89 37 14.8 75 26.0 85 7.89 96 18.5 130 43.6 157 11.1 110 6.18 121 6.51 107 8.63 138 15.6 113 32.6 141 13.9 115 3.86 121 4.56 116 7.09 134 22.5 129 36.5 138 18.4 117
Shiralkar [42]106.7 7.92 60 15.2 29 5.73 67 14.6 122 30.3 135 9.04 99 21.7 130 31.2 130 9.77 109 19.6 138 41.5 146 13.2 122 5.17 64 6.04 59 4.63 71 18.0 127 31.1 132 14.7 120 3.67 114 3.40 67 4.74 121 23.9 139 36.6 140 18.9 120
GraphCuts [14]107.0 9.24 98 17.2 98 7.53 110 22.1 148 33.0 149 16.8 145 15.9 88 23.1 66 15.6 128 14.2 72 28.9 35 9.34 87 5.83 110 6.82 115 6.25 118 18.5 130 29.7 118 12.0 102 2.85 88 3.39 65 3.52 104 23.8 138 36.1 136 19.1 121
Second-order prior [8]109.5 8.04 68 16.3 64 6.01 77 12.5 111 26.5 117 9.10 100 21.0 120 31.1 129 9.23 106 16.2 95 36.2 111 9.93 101 5.70 107 6.67 111 5.09 90 20.7 150 34.1 148 21.0 152 3.76 117 3.89 97 4.25 117 18.9 103 31.8 112 19.9 126
Filter Flow [19]109.9 10.5 118 19.4 128 8.33 122 12.5 111 25.8 107 8.69 97 19.9 112 27.0 96 21.7 143 19.0 133 33.1 80 15.9 139 5.34 83 6.21 84 5.37 99 16.2 116 26.7 96 15.5 121 3.46 107 4.48 114 2.26 65 23.3 137 31.5 111 18.5 118
StereoFlow [44]110.8 16.2 155 22.6 151 13.9 157 22.1 148 31.6 141 18.8 150 24.7 143 30.6 125 21.2 142 23.3 150 39.9 135 19.6 150 5.98 113 6.22 85 7.11 132 11.6 66 27.6 100 8.05 48 1.36 1 2.85 13 0.65 1 20.7 119 33.7 126 17.0 108
CNN-flow-warp+ref [117]111.2 9.91 108 19.6 131 7.85 114 10.6 88 22.9 88 8.55 94 21.3 125 32.1 144 11.9 119 18.7 132 42.0 148 11.3 112 5.56 99 6.34 97 6.08 116 12.3 77 27.6 100 10.8 89 2.06 51 3.69 89 3.16 94 33.3 152 40.4 149 34.7 152
FlowNetS+ft+v [112]111.9 8.96 94 17.8 109 6.83 93 14.2 120 26.2 112 11.1 111 22.3 139 32.2 145 12.7 123 16.8 115 36.1 110 10.9 108 6.31 127 7.29 131 6.26 119 12.5 83 28.8 109 9.88 75 3.84 120 6.75 143 6.30 129 16.4 88 29.0 101 14.7 82
IAOF2 [51]112.2 10.0 111 19.9 135 7.91 116 14.4 121 26.7 120 10.9 109 22.0 136 32.2 145 17.6 132 19.1 134 33.0 77 17.1 143 5.81 109 6.86 117 4.94 87 12.6 84 25.9 90 11.9 101 4.26 130 4.11 104 7.75 137 16.2 87 26.5 93 13.5 76
Ad-TV-NDC [36]115.6 12.1 129 18.6 121 10.7 149 25.5 154 32.0 145 22.2 154 29.3 156 34.3 154 22.8 147 16.9 117 32.8 74 12.2 117 5.99 115 7.20 129 3.83 19 12.6 84 28.5 107 10.3 82 2.79 84 4.07 100 1.78 44 24.1 140 31.4 110 25.1 143
TVL1_ROB [138]115.9 12.9 133 20.8 142 9.80 147 21.3 145 30.9 138 17.9 149 27.9 150 33.6 149 23.5 151 20.5 140 37.8 124 16.7 141 5.57 100 6.47 104 5.46 102 14.5 104 32.1 138 12.1 105 1.69 17 2.81 9 1.22 8 22.9 132 36.3 137 18.3 116
LDOF [28]117.7 9.66 104 18.9 124 7.13 101 15.1 124 29.1 131 11.3 112 15.6 85 25.1 78 10.9 112 20.9 143 43.1 155 14.9 137 6.12 119 7.01 123 6.26 119 16.0 115 31.2 134 13.2 110 3.89 123 5.61 134 8.96 151 19.0 104 33.0 123 11.7 64
2D-CLG [1]118.1 15.2 153 24.5 157 11.2 151 15.1 124 25.9 109 13.5 134 27.5 149 33.9 151 24.7 156 22.2 147 38.3 128 19.0 149 5.67 105 6.44 102 6.29 122 17.5 120 34.3 149 16.4 125 1.47 3 2.68 4 1.54 36 21.7 123 34.6 131 16.9 107
Nguyen [33]119.0 11.4 122 19.6 131 8.44 124 21.0 144 31.7 143 17.7 147 29.8 158 36.3 158 24.1 155 18.2 126 34.6 92 13.9 123 6.28 123 6.85 116 7.51 135 15.4 111 33.0 142 14.0 116 2.24 65 3.11 36 1.79 45 21.6 122 33.9 127 15.8 95
UnFlow [129]119.6 16.0 154 25.1 158 11.3 152 12.7 115 22.2 80 11.7 126 20.4 115 27.6 101 13.6 124 20.8 141 36.0 108 17.9 146 6.34 128 6.89 120 7.74 136 17.7 122 33.5 145 17.1 129 2.92 92 4.33 109 1.37 17 20.7 119 37.3 144 15.6 89
IAOF [50]119.8 10.1 112 18.6 121 7.89 115 22.2 150 33.7 152 15.9 141 33.0 160 39.2 161 23.7 152 16.2 95 32.1 65 11.6 115 5.80 108 6.87 118 5.39 101 17.8 124 30.1 123 11.4 94 3.13 101 3.69 89 3.88 114 22.4 128 29.3 102 21.6 135
SPSA-learn [13]121.0 11.3 121 19.4 128 8.52 126 20.9 142 34.2 154 16.2 144 26.5 147 33.9 151 22.4 146 22.5 149 39.9 135 18.9 148 5.59 101 6.41 100 5.94 111 17.8 124 31.4 136 18.3 133 2.11 55 3.11 36 1.37 17 24.3 141 35.1 133 19.7 125
Learning Flow [11]121.1 8.28 79 17.0 91 5.75 68 12.3 109 28.5 126 7.79 91 18.4 101 28.7 106 8.29 101 22.2 147 40.6 140 17.3 144 8.52 137 10.3 155 7.04 131 19.9 148 35.1 152 16.8 128 3.11 100 4.59 118 3.59 108 26.9 146 40.0 148 20.9 133
HBpMotionGpu [43]122.2 12.2 130 22.1 148 8.34 123 17.9 134 31.4 140 14.7 136 29.2 155 37.8 160 20.6 139 19.1 134 44.6 159 11.5 114 5.60 102 6.45 103 6.06 114 13.2 89 28.8 109 11.1 92 3.45 106 3.97 99 2.04 55 23.1 134 34.1 129 20.7 130
Modified CLG [34]125.5 11.6 125 20.5 140 9.14 143 12.6 114 25.4 105 10.3 105 27.4 148 34.4 155 23.8 153 21.8 145 42.7 153 16.7 141 6.18 121 7.06 126 6.57 125 14.9 107 33.0 142 13.4 113 2.45 72 3.80 95 3.81 113 22.0 126 36.6 140 16.8 105
Black & Anandan [4]127.2 10.5 118 18.0 112 8.14 120 21.4 147 32.8 148 16.1 143 26.1 146 32.3 147 21.8 144 20.8 141 38.9 131 16.1 140 6.29 125 7.41 134 5.62 108 17.1 118 31.2 134 13.7 114 4.06 126 5.11 128 2.37 72 23.1 134 34.1 129 15.7 93
GroupFlow [9]128.5 11.5 124 21.2 146 8.71 140 20.5 139 33.0 149 15.7 140 23.6 140 31.6 135 20.1 137 16.2 95 34.5 89 11.3 112 8.86 138 9.84 154 6.50 124 18.2 128 30.3 124 17.4 130 3.82 119 5.05 127 6.55 131 21.1 121 28.8 100 22.4 141
2bit-BM-tele [98]128.5 10.3 114 20.1 137 7.40 105 11.5 100 26.7 120 7.57 87 20.6 116 32.0 142 11.4 117 17.9 124 40.3 138 12.3 118 6.29 125 6.80 114 6.93 129 21.0 151 32.0 137 18.0 132 7.61 141 6.57 140 11.1 153 27.5 147 39.4 147 29.2 149
Heeger++ [104]130.1 11.7 127 18.3 114 9.04 142 23.3 153 37.0 160 17.4 146 21.0 120 29.1 110 11.1 115 27.0 154 40.5 139 24.4 153 5.69 106 6.33 95 5.80 109 25.9 157 37.5 157 26.3 157 2.48 75 3.88 96 2.20 62 37.6 157 46.0 158 41.6 160
HCIC-L [99]130.5 14.6 150 21.1 144 9.67 145 42.7 161 36.7 159 46.6 161 21.8 132 30.5 123 17.9 134 21.1 144 35.1 98 18.6 147 6.42 130 6.58 108 7.35 134 17.8 124 28.6 108 16.6 126 12.8 147 14.3 147 15.3 156 16.8 93 25.7 89 12.7 72
H+S_ROB [137]131.2 16.6 157 23.6 155 11.9 154 19.1 137 30.6 137 15.6 139 25.1 144 30.2 121 23.4 149 29.1 155 36.3 112 27.9 156 13.4 158 15.7 158 12.2 140 27.2 158 38.8 159 27.8 158 1.70 19 2.81 9 1.42 22 32.2 151 41.3 152 30.2 150
BlockOverlap [61]132.2 10.3 114 19.1 126 7.74 112 15.4 128 25.3 103 13.0 131 24.3 141 31.9 139 21.0 141 19.5 137 43.8 158 13.1 121 9.14 139 7.60 135 13.9 142 19.0 132 29.0 113 15.7 123 11.0 145 8.77 145 24.8 161 23.0 133 31.3 109 25.9 145
TI-DOFE [24]133.0 14.6 150 21.1 144 11.7 153 22.4 152 31.6 141 19.6 151 28.6 153 31.2 130 26.3 157 26.3 153 36.0 108 25.1 154 6.43 131 7.34 132 6.67 128 19.1 134 33.8 146 18.9 135 2.88 90 3.15 43 2.82 85 25.7 143 36.6 140 22.3 140
Horn & Schunck [3]134.4 11.8 128 19.3 127 8.85 141 20.1 138 33.5 151 15.3 138 25.5 145 31.2 130 24.0 154 26.1 152 38.6 129 23.5 151 6.12 119 6.99 121 6.34 123 19.9 148 33.9 147 19.6 149 3.95 125 4.28 108 2.46 75 25.3 142 37.5 145 22.0 139
FFV1MT [106]141.2 13.9 149 23.4 154 10.8 150 20.9 142 34.5 156 16.0 142 21.8 132 29.5 113 13.8 125 31.0 159 41.7 147 29.4 158 9.97 143 6.78 113 17.9 158 23.8 154 35.3 153 25.0 156 2.99 96 4.24 106 3.57 107 37.6 157 46.0 158 41.6 160
SILK [79]142.3 13.2 147 22.4 150 10.2 148 20.5 139 32.2 147 17.7 147 29.0 154 34.1 153 23.4 149 22.0 146 40.8 142 17.3 144 6.28 123 7.17 128 7.12 133 21.7 152 35.8 155 19.6 149 5.44 135 3.45 75 10.8 152 29.3 149 40.6 151 26.7 147
Adaptive flow [45]142.9 13.2 147 20.2 138 9.78 146 27.3 156 31.9 144 25.4 155 28.3 152 31.6 135 30.5 160 19.7 139 37.6 122 15.3 138 11.2 157 12.6 157 8.93 139 17.6 121 29.8 119 15.8 124 13.1 148 11.0 146 18.3 157 26.4 145 36.8 143 22.7 142
PGAM+LK [55]143.4 14.9 152 22.8 152 14.1 158 25.5 154 31.3 139 26.6 156 21.9 134 26.4 91 22.2 145 26.0 151 39.1 133 24.0 152 9.61 141 6.49 106 14.1 143 24.3 155 35.0 151 23.0 154 6.19 138 6.24 139 7.26 135 34.3 155 40.4 149 40.8 159
SLK [47]143.9 17.2 159 24.0 156 18.2 159 21.3 145 30.4 136 20.1 152 27.9 150 31.9 139 23.3 148 31.4 160 39.9 135 30.0 160 6.60 132 7.04 125 8.37 137 22.8 153 36.4 156 21.6 153 3.90 124 3.75 93 5.02 123 33.3 152 41.7 153 35.2 154
AVG_FLOW_ROB [141]148.8 32.4 161 34.1 161 37.7 161 35.1 160 33.7 152 37.0 160 20.7 118 24.1 72 19.4 136 34.1 161 35.1 98 34.8 161 39.6 160 37.0 160 44.9 160 40.6 161 42.2 160 38.5 161 11.3 146 15.3 148 7.36 136 46.5 161 52.3 161 38.9 156
FOLKI [16]152.3 16.2 155 25.9 159 12.7 156 32.5 158 35.6 158 34.7 158 29.4 157 35.1 157 26.9 158 29.1 155 41.0 144 27.9 156 9.58 140 8.90 140 13.5 141 25.7 156 38.3 158 24.5 155 7.71 142 5.13 130 14.5 155 36.5 156 44.4 156 36.1 155
Pyramid LK [2]152.5 17.0 158 20.4 139 19.4 160 31.7 157 32.1 146 32.5 157 32.9 159 34.8 156 29.9 159 29.4 157 35.3 102 29.9 159 31.7 159 35.5 159 29.8 159 29.9 159 32.3 139 28.0 159 9.01 143 7.93 144 18.9 158 39.9 159 45.4 157 39.0 157
Periodicity [78]157.7 18.0 160 30.5 160 12.3 155 34.0 159 41.4 161 35.6 159 36.5 161 36.5 159 35.2 161 29.7 158 46.6 161 26.8 155 51.8 161 56.5 161 45.5 161 36.7 160 42.4 161 37.1 160 5.99 137 6.16 138 19.3 159 40.1 160 51.1 160 40.4 158
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

Methodtime*framescolor Reference and notes
[1] 2D-CLG 844 2 gray The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences.
[2] Pyramid LK 12 2 color A modification of Bouguet's pyramidal implementation of Lucas-Kanade.
[3] Horn & Schunck 49 2 gray A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data.
[4] Black & Anandan 328 2 gray A modern Matlab implementation of the Black & Anandan method by Deqing Sun.
[5] Brox et al. 18 2 color T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.)
[6] Fusion 2,666 2 color V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008.
[7] Dynamic MRF 366 2 gray B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.)
[8] Second-order prior 14 2 gray W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[9] GroupFlow 600 2 gray X. Ren. Local Grouping for Optical Flow. CVPR 2008.
[10] SegOF 60 2 color L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available.
[11] Learning Flow 825 2 gray D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008.
[12] CBF 69 2 color W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[13] SPSA-learn 200 2 color Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008.
[14] GraphCuts 1,200 2 color T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008.
[15] F-TV-L1 8 2 gray A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008.
[16] FOLKI 1.4 2 gray G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005.
[17] TV-L1-improved 2.9 2 gray A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision.
[18] DPOF 287 2 color C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.)
[19] Filter Flow 34,000 2 color S. Seitz and S. Baker. Filter flow. ICCV 2009.
[20] Adaptive 9.2 2 gray A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009.
[21] Complementary OF 44 2 color H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[22] Aniso. Huber-L1 2 2 gray M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision.
[23] Rannacher 0.12 2 gray J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009.
[24] TI-DOFE 260 2 gray C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009.
[25] NL-TV-NCC 20 2 color M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010.
[26] MDP-Flow 188 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010.
[27] ACK-Prior 5872 2 color K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010.
[28] LDOF 122 2 color T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011.
[29] p-harmonic 565 2 gray J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010.
[30] TriangleFlow 4200 2 gray B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010.
[31] Classic+NL 972 2 color D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code.
[32] Classic++ 486 2 gray A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010.
[33] Nguyen 33 2 gray D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011.
[34] Modified CLG 133 2 gray R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010.
[35] ComplOF-FED-GPU 0.97 2 color P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010.
[36] Ad-TV-NDC 35 2 gray M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010.
[37] Layers++ 18206 2 color D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010.
[38] OFH 620 3 color H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011.
[39] LSM 1615 2 color K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011.
[40] CostFilter 55 2 color C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011.
[41] Bartels 0.15 2 gray C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU.
[42] Shiralkar 600 2 gray M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242.
[43] HBpMotionGpu 1000 5 gray S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.)
[44] StereoFlow 7200 2 color G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772.
[45] Adaptive flow 121 2 gray T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011.
[46] TC-Flow 2500 5 color S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011.
[47] SLK 300 2 gray T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011.
[48] CLG-TV 29 2 gray M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code.
[49] SimpleFlow 1.7 2 color M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012.
[50] IAOF 57 2 gray D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011.
[51] IAOF2 56 2 gray D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011.
[52] LocallyOriented 9541 2 gray Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012.
[53] IROF-TV 261 2 color H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop.
[54] Sparse Occlusion 2312 2 color A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011.
[55] PGAM+LK 0.37 2 gray A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010.
[56] Sparse-NonSparse 713 2 color L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013.
[57] nLayers 36150 4 color D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012.
[58] IROF++ 187 2 color H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013.
[59] COFM 600 3 color M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013.
[60] Efficient-NL 400 2 color P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012.
[61] BlockOverlap 2 2 gray M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to MMSP 2012.
[62] Ramp 1200 2 color A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012.
[63] Occlusion-TV-L1 538 3 gray C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012.
[64] TV-L1-MCT 90 2 color M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012.
[65] Local-TV-L1 500 2 gray L. Raket. Local smoothness for global optical flow. ICIP 2012.
[66] ALD-Flow 61 2 color M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012.
[67] SIOF 234 2 color L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012.
[68] MDP-Flow2 342 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available.
[69] TCOF 1421 all gray J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013.
[70] LME 476 2 color W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013.
[71] NN-field 362 2 color L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[72] FESL 3310 2 color W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013.
[73] PMF 35 2 color J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013.
[74] FC-2Layers-FF 2662 4 color D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013.
[75] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[76] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[77] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[78] Periodicity 8000 4 color G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013.
[79] SILK 572 2 gray P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP.
[80] CRTflow 13 3 color O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013.
[81] SuperFlow 178 2 color Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507.
[82] Aniso-Texture 300 2 color Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267.
[83] Classic+CPF 640 2 gray Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013.
[84] S2D-Matching 1200 2 color Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479.
[85] AGIF+OF 438 2 gray Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015.
[86] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[87] NNF-Local 673 2 color Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014.
[88] EPPM w/o HM 2.5 2 color L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014.
[89] MLDP_OF 165 2 gray M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014.
[90] RFlow 20 2 gray S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014.
[91] SRR-TVOF-NL 32 all color P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014.
[92] 2DHMM-SAS 157 2 color M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission.
[93] WLIF-Flow 700 2 color Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014.
[94] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[95] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[96] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[97] AggregFlow 1642 2 color D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759.
[98] 2bit-BM-tele 124 2 gray R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013.
[99] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[100] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[101] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[102] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[103] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[104] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[105] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[106] FFV1MT 358 5 gray F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015.
[107] ROF-ND 4 2 color S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015.
[108] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[109] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[110] FlowFields 15 2 color C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015.
[111] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[112] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[113] CombBMOF 51 2 color M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.)
[114] PMMST 182 2 color F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015.
[115] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[116] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[117] CNN-flow-warp+ref 1.4 3 color D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016.
[118] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[119] StereoOF-V1MT 343 2 gray Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132.
[120] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[121] RNLOD-Flow 1040 2 gray C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. IEEE TIP 26(8):4055-4067, 2017.
[122] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[123] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[124] BriefMatch 0.068 2 gray G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62.
[125] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[126] AdaConv-v1 2.8 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[127] SepConv-v1 0.2 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[128] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[129] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[130] FlowFields+ 10.5 2 color C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017.
[131] IIOF-NLDP 150 2 color D.-H. Trinh, W. Blondel, and C. Daul. A general form of illumination-invariant descriptors in variational optical flow estimation. ICIP 2017.
[132] SuperSlomo 0.5 2 color Anonymous. (Interpolation results only.) Super SloMo: High quality estimation of multiple intermediate frames for video interpolation. CVPR 2018 submission 325.
[133] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[134] OFRF 90 2 color T. Mai, M. Gouiffes, and S. Bouchafa. Optical Flow refinement using iterative propagation under color, proximity and flow reliability constraints. Submitted to Signal, Image and Video Processing 2017.
[135] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
[136] CtxSyn 0.07 2 color S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[137] H+S_ROB 5 2 color ROB 2018 baseline submission, based on: E. Meinhardt-Llopis, J. Sanchez, and D. Kondermann. Horn-Schunck optical flow with a multi-scale strategy. Image Processing On Line 3:151–172, 2013.
[138] TVL1_ROB 1 2 color ROB 2018 baseline submission, based on: J. Sanchez, E. Meinhardt-Llopis, and G. Facciolo. TV-L1 optical flow estimation. Image Processing On Line 3:137-150, 2013.
[139] DMF_ROB 10 2 color ROB 2018 baseline submission, based on: P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[140] JOF 657 2 gray C. Zhang, L. Ge, Z. Chen, M. Li, W. Liu, and H. Chen. Refined TV-L1 optical flow estimation using joint filtering. Submitted to IEEE TMM, 2018.
[141] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[142] LiteFlowNet 0.06 2 color T.-W. Hui, X. Tang, and C. C. Loy. LiteFlowNet: A lightweight convolutional neural network for optical flow estimation. CVPR 2018.
[143] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[144] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[145] FF++_ROB 17.43 2 color R. Schuster, C. Bailer, O. Wasenmueller, D. Stricker. FlowFields++: Accurate optical flow correspondences meet robust interpolation. ICIP 2018. Submitted to ROB 2018.
[146] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[147] PWC-Net_ROB 0.069 2 color D. Sun, X. Yang, M.-Y. Liu, and J. Kautz. PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. CVPR 2018.
[148] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[149] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
[150] WRT 9 2 color L. Mei, J. Lai, X. Xie, J. Zhu, and J. Chen. Illumination-invariance optical flow estimation using weighted regularization transform. Submitted to IEEE TCSVT 2018.
[151] EAI-Flow 2.1 2 color Anonymous. Hierarchical coherency sensitive hashing and interpolation with RANSAC for large displacement optical flow. CVIU 2018 submission 17-678.
[152] ContinualFlow_ROB 0.5 all color M Neoral, J. Sochman, and J. Matas. Continual occlusions and optical flow estimation. ACCV 2018.
[153] CyclicGen 0.088 2 color Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
[154] TOF-M 0.393 2 color T. Xue, B. Chen, J. Wu, D. Wei, and W. Freeman. Video enhancement with task-oriented flow. arXiv 1711.09078, 2017.
[155] MEMC-Net+ 0.16 2 color W. Bao, W.-S. Lai, X. Zhang, Z. Gao, and M.-H. Yang. (Interpolation results only.) MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement. Submitted to TPAMI 2018.
[156] CFRF 0.128 2 color Anonymous. (Interpolation results only.) Coarse-to-fine refinement framework for video frame interpolation. CVPR 2019 submission 1992.
[157] MPRN 0.32 4 color Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[158] DAIN 0.13 2 color Anonymous. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019 submission 1769.
[159] PyrWarp 0.14 2 color Anonymous. (Interpolation results only.) Feature pyramid warping for video frame interpolation. CVPR 2019 submission 868.
[160] InterpCNN 0.65 2 color Anonymous. (Interpolation results only.) Video frame interpolation with a stack of synthesis networks and intermediate optical flows. CVPR 2019 submission 6533.
[161] OFRI 0.31 2 color Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
* 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.