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]9.8 6.84 15 15.1 24 4.48 12 6.28 5 15.5 11 3.00 4 7.42 3 13.5 10 2.39 3 7.71 7 22.7 14 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 7 10.7 7 2.48 9
PMMST [114]10.8 6.46 4 14.1 4 3.23 1 5.42 1 12.7 7 3.51 14 8.20 9 14.7 15 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 12 11.3 12 2.25 2
NN-field [71]13.6 7.29 35 16.0 50 4.74 24 6.15 2 15.2 10 3.02 6 7.77 7 14.1 14 2.71 6 7.56 5 22.8 15 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 8 10.8 8 2.49 10
OFLAF [77]16.4 6.75 12 14.9 17 4.44 10 7.07 11 17.5 21 3.10 7 8.45 10 15.5 17 2.50 5 13.0 47 35.0 89 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 11 11.0 10 2.79 11
MDP-Flow2 [68]23.9 6.66 7 14.7 14 4.53 14 6.79 8 17.0 15 3.23 8 8.68 11 15.8 18 2.90 7 13.4 57 33.7 76 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 15 12.8 17 3.33 17
nLayers [57]26.7 7.20 30 16.0 50 4.66 21 6.25 4 14.7 8 3.70 19 7.72 6 13.7 12 4.81 33 13.1 51 34.8 87 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 27 15.6 28 6.10 33
FC-2Layers-FF [74]26.7 7.07 24 15.5 35 4.91 30 8.30 33 19.7 41 4.30 23 7.61 5 13.6 11 4.29 25 11.8 21 30.2 35 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 21 14.3 23 4.12 24
3DFlow [135]30.6 6.97 18 15.1 24 3.90 3 8.12 28 19.7 41 3.79 20 13.6 57 24.2 66 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 38 8.87 61 2.38 70 3.11 36 2.45 73 5.82 10 11.1 11 3.00 13
ComponentFusion [96]31.9 7.22 31 15.9 46 4.61 19 7.60 17 19.2 35 3.30 9 9.70 16 17.6 23 3.77 16 11.1 16 31.0 44 4.45 7 4.96 30 5.88 31 4.25 49 10.9 57 23.7 65 9.40 69 1.90 38 3.08 29 1.69 41 8.00 25 15.1 26 4.57 26
FESL [72]34.6 6.97 18 15.3 31 4.47 11 9.74 61 21.4 62 5.49 56 11.4 33 20.2 35 4.25 24 12.5 30 31.5 51 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 49 17.6 41 10.1 49
AGIF+OF [85]35.3 7.17 28 15.6 37 4.93 31 10.2 71 22.1 71 5.16 43 12.5 46 21.2 46 4.88 35 12.5 30 31.7 56 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 46 17.6 41 11.0 52
PWC-Net_ROB [148]35.3 8.30 80 16.2 58 6.58 90 8.56 38 20.6 50 4.38 26 12.3 43 21.4 47 6.00 54 10.8 12 27.0 23 6.88 45 4.94 27 5.79 21 3.98 28 8.37 17 19.3 40 5.42 11 1.65 15 3.29 56 1.02 3 7.86 24 14.2 22 3.37 18
Layers++ [37]36.5 7.19 29 15.7 39 5.08 37 6.15 2 14.8 9 3.42 12 7.83 8 14.0 13 4.84 34 10.9 14 26.9 22 6.19 16 4.83 17 5.84 26 4.36 54 12.4 79 25.2 77 10.5 84 2.43 71 3.56 82 1.92 51 8.66 30 16.1 30 7.77 40
Correlation Flow [75]36.5 6.66 7 14.5 9 3.81 2 7.78 22 17.5 21 2.85 2 18.0 91 29.0 101 4.31 27 9.28 9 22.1 13 5.57 12 5.12 52 6.13 70 3.98 28 11.0 60 23.3 60 10.5 84 2.07 52 3.08 29 2.32 68 6.79 16 12.5 15 4.83 27
NNF-EAC [103]36.8 6.83 14 14.9 17 4.80 25 7.59 16 18.0 23 4.31 24 9.03 13 16.1 19 3.09 9 13.2 54 32.2 60 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 87 27.6 90 18.0 108
Efficient-NL [60]37.8 7.43 49 16.2 58 4.85 26 7.73 20 18.1 24 4.58 28 14.0 63 23.6 62 4.47 29 13.1 51 32.9 69 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 17 12.1 13 5.78 31
IROF++ [58]38.9 7.44 50 16.1 54 5.11 39 8.61 40 19.4 36 5.12 41 12.3 43 21.0 45 5.12 37 12.8 41 32.1 58 7.13 55 4.88 20 5.76 17 3.89 21 9.01 22 18.9 38 6.76 31 1.78 27 3.22 50 1.23 10 10.4 43 18.5 48 13.3 68
LME [70]39.0 7.04 22 15.6 37 4.53 14 6.68 6 16.9 14 2.85 2 13.6 57 22.6 54 12.0 113 11.5 19 27.8 24 6.39 20 5.03 41 5.93 37 4.52 63 12.4 79 27.0 91 10.9 91 1.76 25 3.38 64 1.43 23 6.62 14 12.5 15 2.86 12
PH-Flow [101]39.5 7.38 43 15.9 46 5.22 44 9.30 51 19.5 37 5.71 59 9.62 15 17.2 21 5.09 36 13.4 57 34.5 82 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 20 13.3 20 5.33 30
NL-TV-NCC [25]40.3 6.92 17 14.6 13 3.96 5 8.32 34 19.8 45 2.84 1 15.4 73 26.0 78 3.92 19 10.8 12 26.6 19 5.58 13 5.09 49 6.00 50 4.07 35 11.1 63 23.5 61 10.5 84 2.09 53 3.06 27 2.27 66 11.6 52 20.4 54 9.14 45
TC/T-Flow [76]41.0 6.31 2 13.3 2 4.85 26 11.5 93 23.6 86 6.67 76 13.4 56 23.2 60 3.00 8 14.2 72 36.9 108 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 48 18.2 46 3.59 20
Classic+CPF [83]41.2 7.31 37 15.8 42 5.09 38 9.93 66 22.1 71 5.05 39 13.3 54 22.4 53 4.64 32 12.5 30 32.0 57 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 39 16.5 32 13.8 71
LSM [39]41.3 7.06 23 15.2 29 5.21 43 9.65 59 21.2 61 5.48 55 11.9 39 20.2 35 5.33 42 12.0 22 30.0 33 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 26 14.3 23 6.76 37
CombBMOF [113]41.3 7.30 36 15.1 24 4.61 19 8.08 27 18.2 26 3.69 18 10.2 19 18.1 26 2.47 4 11.2 17 28.1 25 6.67 28 4.82 14 5.76 17 4.13 43 13.3 91 22.1 52 14.1 118 2.90 91 4.33 109 2.14 59 11.8 54 21.0 58 3.23 16
MLDP_OF [89]41.6 7.02 20 14.5 9 4.89 29 7.00 10 17.0 15 3.34 10 14.3 65 24.0 63 3.73 15 12.9 44 34.8 87 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 64 20.5 56 9.16 46
Sparse-NonSparse [56]42.1 7.26 34 15.7 39 5.22 44 9.83 63 21.6 65 5.45 54 12.2 41 20.8 41 5.35 45 12.1 25 30.0 33 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 22 13.8 21 5.98 32
HAST [109]43.0 7.11 26 16.0 50 4.27 6 8.90 44 17.4 20 7.54 86 6.79 1 12.4 7 1.56 1 14.8 78 37.2 109 6.63 24 4.68 6 5.70 10 2.91 2 10.5 52 20.7 44 11.1 92 3.74 116 4.39 112 5.40 126 5.74 9 10.9 9 2.09 1
WLIF-Flow [93]43.1 6.80 13 14.9 17 4.60 18 6.93 9 16.7 13 4.11 22 10.3 20 18.2 27 4.11 23 12.7 39 30.9 42 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 70 23.2 71 15.3 79
Ramp [62]43.8 7.32 39 15.8 42 5.20 42 8.74 41 19.8 45 5.27 49 11.4 33 19.7 34 5.40 48 12.5 30 31.6 54 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 29 15.3 27 11.7 57
PMF [73]44.1 7.59 55 16.5 73 4.94 32 7.64 18 18.3 29 3.66 16 7.48 4 13.2 9 2.31 2 14.7 77 36.3 105 6.84 40 4.66 5 5.64 6 3.18 6 9.85 38 21.3 47 9.22 65 3.62 111 5.25 133 3.70 111 7.12 19 13.2 19 6.82 38
Classic+NL [31]45.3 7.40 46 16.1 54 5.36 54 9.49 58 20.9 55 5.44 53 12.3 43 20.8 41 5.20 40 12.5 30 31.3 50 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 38 17.0 38 11.9 59
FlowFields+ [130]45.9 8.95 93 17.2 91 7.26 102 7.52 15 17.3 18 5.15 42 10.4 21 17.6 23 6.16 55 10.1 10 24.5 16 6.49 22 5.11 51 6.00 50 4.57 65 9.28 33 22.2 53 6.70 30 1.77 26 3.20 46 1.51 33 13.1 63 21.8 62 15.6 82
CostFilter [40]46.6 7.36 41 15.7 39 4.96 34 7.76 21 18.1 24 3.83 21 7.07 2 12.4 7 3.12 10 14.6 76 36.3 105 6.57 23 4.82 14 5.81 23 3.54 8 12.4 79 20.5 43 10.3 82 3.86 121 5.96 137 4.36 118 8.86 33 16.7 35 3.72 22
FMOF [94]47.8 7.14 27 15.5 35 5.28 48 10.4 79 22.7 77 5.42 50 10.8 28 19.0 32 3.90 18 12.2 27 31.0 44 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 72 23.2 71 10.1 49
TV-L1-MCT [64]49.0 7.42 48 16.1 54 5.22 44 9.84 64 21.6 65 5.20 45 14.3 65 24.7 69 5.27 41 12.5 30 31.2 49 7.21 58 5.01 37 5.90 33 4.41 57 9.10 26 18.8 37 7.14 40 2.17 61 2.78 5 4.69 120 9.81 37 16.8 37 11.5 54
ProbFlowFields [128]49.1 8.84 91 17.9 103 6.90 95 7.20 13 17.3 18 4.75 35 11.6 36 20.5 39 6.31 59 8.48 8 22.0 12 5.26 10 5.25 75 6.24 89 4.67 78 9.96 43 23.9 69 6.99 37 1.64 12 2.80 7 1.41 21 14.7 72 25.5 81 14.7 75
SVFilterOh [111]49.6 7.94 62 17.5 97 4.94 32 8.27 32 19.8 45 3.66 16 9.83 18 17.7 25 4.59 30 13.4 57 34.5 82 6.82 37 4.89 22 5.93 37 3.15 5 10.4 51 22.7 55 9.35 68 3.51 108 4.72 122 4.17 116 7.68 23 14.3 23 4.90 28
WRT [151]49.8 7.40 46 15.9 46 3.93 4 9.33 52 21.1 59 3.42 12 21.1 115 31.0 121 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 49 10.8 89 1.71 20 2.85 13 1.65 38 16.7 84 20.4 54 20.8 125
IIOF-NLDP [131]49.8 7.31 37 15.4 32 4.42 9 8.37 35 19.9 48 3.01 5 15.4 73 25.9 76 4.00 21 7.56 5 18.6 11 4.73 8 6.04 118 7.28 130 5.15 93 10.1 46 21.3 47 9.54 71 1.74 22 2.90 18 1.50 31 15.8 77 21.6 61 20.5 122
RNLOD-Flow [121]49.9 6.72 10 14.9 17 4.39 8 9.09 46 21.0 57 5.06 40 15.2 71 25.8 74 5.42 49 12.6 37 32.2 60 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 34 16.1 30 9.83 47
Complementary OF [21]50.3 7.37 42 15.1 24 5.30 51 9.46 54 22.5 75 4.63 29 13.0 49 22.8 56 4.04 22 14.8 78 37.9 118 6.87 44 4.97 31 5.86 28 4.39 56 11.0 60 24.4 72 8.06 49 1.79 28 2.79 6 2.22 63 12.2 55 22.0 65 11.2 53
ALD-Flow [66]51.4 6.69 9 14.4 8 4.54 16 12.5 104 25.7 99 6.93 79 14.3 65 24.9 70 4.29 25 14.8 78 35.3 95 7.04 51 4.98 34 5.92 35 3.66 12 10.1 46 23.6 63 6.92 34 2.02 46 3.23 51 2.86 86 10.2 42 18.9 50 6.45 36
EPPM w/o HM [88]51.7 7.33 40 14.5 9 5.00 36 7.20 13 17.2 17 3.41 11 11.8 37 20.8 41 3.20 11 12.6 37 31.1 48 7.00 50 5.14 57 6.08 63 4.67 78 12.0 73 22.7 55 9.97 78 4.48 132 3.69 89 6.02 128 10.4 43 17.6 41 11.5 54
FlowFields [110]52.2 9.03 96 17.5 97 7.31 103 8.02 26 18.6 32 5.24 48 11.1 32 18.9 30 6.32 60 11.6 20 28.7 27 7.40 65 5.14 57 6.03 57 4.64 73 10.1 46 23.8 68 7.62 43 1.69 17 2.86 16 1.51 33 12.9 59 22.8 69 14.9 78
JOF [141]52.5 7.77 58 16.9 83 5.33 52 10.6 81 20.8 54 7.75 89 10.9 30 18.9 30 5.34 43 12.7 39 32.6 63 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 66 21.4 60 12.2 63
MDP-Flow [26]53.5 6.73 11 14.1 4 5.59 63 6.70 7 16.0 12 4.65 31 9.78 17 17.2 21 6.61 64 13.0 47 34.7 86 6.48 21 5.54 98 6.17 79 5.84 110 10.5 52 23.6 63 7.81 45 1.89 36 3.42 70 1.37 17 20.0 105 32.5 111 19.1 114
S2F-IF [123]53.6 8.86 92 17.2 91 7.05 99 7.84 25 18.3 29 5.20 45 10.8 28 18.5 29 6.21 56 13.0 47 30.7 40 8.15 77 5.09 49 5.98 47 4.58 66 9.62 36 22.7 55 7.20 41 1.92 39 3.77 94 1.73 43 10.7 45 18.4 47 12.8 66
TC-Flow [46]53.6 6.56 6 14.1 4 4.48 12 9.25 50 21.4 62 5.03 38 14.9 69 25.8 74 3.93 20 14.5 75 35.9 99 6.97 49 5.01 37 5.97 41 3.63 9 9.98 44 22.8 58 6.83 33 2.11 55 3.25 52 3.61 109 16.7 84 26.8 87 20.0 120
ProFlow_ROB [147]53.7 7.98 67 17.0 84 5.55 62 9.17 48 21.5 64 5.69 58 13.9 61 24.5 68 5.39 47 13.9 67 32.3 62 7.54 68 5.19 69 6.19 82 4.26 50 9.15 29 21.8 51 5.47 12 1.57 6 2.92 19 1.15 7 13.9 69 23.8 75 12.3 64
SimpleFlow [49]55.9 7.56 54 16.2 58 5.59 63 9.48 55 21.0 57 5.68 57 17.1 86 27.0 89 6.29 58 13.0 47 32.8 67 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 36 17.4 40 7.10 39
SRR-TVOF-NL [91]55.9 7.83 59 15.4 32 5.99 76 13.2 110 26.1 103 8.61 95 13.2 52 22.0 51 6.78 65 13.6 63 30.3 36 7.34 64 4.72 7 5.56 4 4.04 34 9.87 40 19.8 42 8.30 53 3.25 103 3.73 92 3.18 95 6.93 18 12.9 18 4.92 29
IROF-TV [53]56.0 7.55 53 16.1 54 5.46 59 9.23 49 21.8 67 5.88 62 13.3 54 22.2 52 5.50 51 12.8 41 31.6 54 7.28 60 5.12 52 6.09 64 4.67 78 13.3 91 29.6 110 9.97 78 1.60 7 3.12 40 1.06 4 11.5 51 21.3 59 11.5 54
HBM-GC [105]57.8 8.35 84 18.4 108 4.98 35 7.66 19 18.2 26 5.20 45 13.8 60 24.2 66 5.34 43 12.0 22 30.5 38 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 79 26.0 83 17.9 106
ACK-Prior [27]58.0 6.39 3 13.4 3 4.38 7 8.58 39 19.7 41 3.63 15 11.4 33 20.3 37 3.82 17 12.5 30 33.7 76 5.09 9 5.53 96 6.42 101 4.76 82 15.0 109 28.4 98 11.4 94 3.54 109 4.36 111 4.84 122 13.2 64 20.2 53 8.94 43
LiteFlowNet [143]58.1 9.19 97 16.6 74 7.02 98 8.23 30 18.9 34 4.53 27 12.9 47 21.5 48 6.23 57 12.0 22 26.7 20 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 99 24.7 77 21.9 131
2DHMM-SAS [92]59.3 7.39 45 15.9 46 5.25 47 10.7 84 23.4 83 5.43 51 18.0 91 27.0 89 7.95 91 13.1 51 32.7 65 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 68 22.4 68 15.5 81
Sparse Occlusion [54]60.2 7.38 43 15.8 42 5.28 48 8.25 31 19.9 48 4.71 33 15.5 76 26.3 83 4.63 31 13.5 62 33.3 75 6.92 47 5.25 75 6.26 90 4.11 40 9.70 37 21.1 46 5.94 18 4.85 133 5.95 136 3.71 112 10.8 46 20.0 52 8.01 42
DPOF [18]61.1 8.43 86 16.8 78 6.36 85 10.7 84 20.7 52 9.52 103 8.72 12 15.4 16 3.63 12 11.3 18 29.1 29 6.09 15 5.34 83 6.18 80 5.38 100 12.2 75 22.4 54 8.06 49 5.27 134 3.55 79 6.79 133 8.85 32 16.5 32 4.24 25
OFH [38]61.6 7.25 33 15.0 23 5.29 50 11.1 88 25.0 95 7.19 83 18.6 96 29.1 103 5.56 52 16.0 94 40.8 135 7.44 66 5.05 45 5.92 35 4.28 51 11.4 65 26.0 84 8.73 57 1.64 12 3.04 25 1.36 16 12.5 57 23.3 73 7.79 41
ResPWCR_ROB [145]61.8 8.30 80 14.5 9 7.12 100 8.82 42 19.6 40 5.91 63 11.8 37 19.3 33 7.90 90 12.4 29 28.5 26 7.89 74 5.18 66 5.97 41 5.36 98 10.9 57 23.9 69 8.84 60 2.85 88 3.65 85 2.34 69 14.7 72 21.8 62 16.2 93
COFM [59]62.0 8.49 88 18.5 111 5.95 72 8.44 36 18.7 33 4.71 33 13.0 49 22.9 57 5.84 53 13.8 65 35.2 93 6.78 34 5.63 104 6.58 108 5.94 111 11.7 69 23.5 61 9.80 74 2.29 68 3.20 46 2.72 81 6.42 13 12.1 13 3.07 15
ROF-ND [107]62.5 7.02 20 14.7 14 4.66 21 8.18 29 19.5 37 4.66 32 15.5 76 25.9 76 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 80 9.09 64 4.23 129 4.20 105 3.32 98 14.7 72 22.1 67 18.8 112
PGM-C [120]63.0 9.43 101 18.5 111 7.51 108 9.84 64 23.4 83 6.05 65 12.0 40 20.6 40 7.17 72 15.8 90 35.3 95 9.67 94 5.20 72 6.11 67 4.66 75 9.86 39 23.7 65 7.06 39 1.63 10 2.84 12 1.49 30 11.1 49 20.8 57 6.23 35
OAR-Flow [125]63.7 8.08 71 16.8 78 6.19 81 17.4 124 28.9 122 12.3 121 16.3 82 26.7 88 7.01 69 15.1 83 35.2 93 7.31 62 5.17 64 6.16 75 4.24 48 9.51 35 22.9 59 5.52 14 1.54 5 2.98 22 1.59 37 9.10 35 17.1 39 3.69 21
S2D-Matching [84]63.8 8.25 77 18.0 105 5.76 69 10.9 86 22.8 78 5.71 59 17.3 87 28.5 96 6.38 62 12.1 25 30.3 36 6.65 27 5.15 61 6.13 70 4.63 71 9.18 31 19.5 41 6.69 29 2.66 80 3.35 60 3.50 103 11.6 52 19.9 51 14.7 75
TCOF [69]64.0 7.46 51 15.1 24 5.70 66 9.13 47 21.1 59 5.43 51 19.6 102 29.8 108 8.31 95 12.9 44 31.0 44 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 28 15.9 29 3.80 23
ComplOF-FED-GPU [35]64.6 7.49 52 15.4 32 5.37 56 12.1 100 26.5 110 7.51 85 13.1 51 22.7 55 4.33 28 15.6 87 37.7 116 7.55 70 4.94 27 5.82 24 4.13 43 12.3 77 27.7 95 8.48 55 2.49 77 3.04 25 3.56 106 12.9 59 23.9 76 9.01 44
AggregFlow [97]67.9 10.3 114 21.3 140 6.91 96 15.1 117 27.6 117 10.7 108 14.0 63 24.0 63 8.70 98 14.1 69 35.0 89 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 40 18.1 45 6.13 34
CPM-Flow [116]71.1 9.46 103 18.6 114 7.51 108 10.0 68 23.7 87 6.20 67 12.2 41 20.9 44 7.13 70 15.8 90 35.6 98 9.71 96 5.20 72 6.12 69 4.65 74 10.9 57 23.7 65 8.90 62 1.73 21 3.15 43 1.51 33 14.5 71 26.0 83 13.6 70
EpicFlow [102]72.2 9.39 100 18.4 108 7.50 107 10.0 68 23.8 89 6.29 69 15.8 79 26.6 86 7.35 79 15.5 85 34.4 81 9.65 92 5.20 72 6.11 67 4.66 75 10.2 49 24.5 73 8.18 52 1.63 10 2.81 9 1.48 26 15.8 77 24.8 78 17.1 102
Aniso-Texture [82]73.6 6.49 5 14.2 7 4.54 16 7.83 24 19.5 37 4.37 25 22.0 129 33.6 142 8.47 96 10.3 11 25.4 17 5.55 11 5.19 69 6.10 65 4.45 60 18.7 131 33.0 135 20.1 144 4.07 127 4.62 119 2.47 76 20.1 106 28.5 92 20.7 123
ContinualFlow_ROB [153]74.2 11.4 122 20.8 135 8.47 125 9.76 62 18.5 31 7.94 92 16.5 83 26.6 86 11.7 111 15.7 88 37.2 109 8.85 84 5.25 75 5.97 41 5.27 95 11.8 70 24.9 75 11.4 94 1.53 4 3.06 27 1.10 5 12.4 56 17.7 44 13.1 67
Occlusion-TV-L1 [63]74.5 7.73 57 16.4 66 5.36 54 9.48 55 22.4 74 6.18 66 19.2 98 30.0 111 7.14 71 14.4 74 33.8 78 7.91 75 5.31 82 6.27 92 4.47 61 11.9 71 27.9 96 8.04 47 2.09 53 3.08 29 1.50 31 21.9 117 35.3 127 17.5 103
RFlow [90]75.2 7.10 25 14.9 17 5.40 57 8.98 45 21.9 69 5.19 44 18.5 95 29.3 105 5.35 45 18.1 118 44.9 153 9.86 99 5.12 52 6.01 53 4.38 55 13.0 88 29.3 107 9.93 77 2.28 67 2.85 13 3.52 104 20.3 108 33.3 117 16.1 91
FF++_ROB [146]75.2 9.92 109 19.4 121 7.55 111 8.87 43 20.9 55 5.83 61 15.3 72 25.3 72 7.95 91 11.0 15 25.4 17 7.23 59 5.19 69 6.10 65 4.80 83 17.1 118 25.3 79 13.2 110 1.88 34 2.96 21 2.77 82 18.7 94 27.2 88 25.3 137
DeepFlow2 [108]75.6 8.14 73 16.6 74 5.96 74 14.1 112 26.5 110 10.2 104 15.8 79 26.2 82 6.46 63 16.5 106 37.4 113 9.54 90 5.01 37 5.94 39 3.72 15 10.7 55 25.1 76 8.08 51 1.92 39 3.12 40 2.45 73 20.3 108 32.1 108 16.3 94
Adaptive [20]76.5 7.94 62 17.0 84 5.33 52 10.2 71 23.9 90 6.28 68 21.2 116 31.7 130 7.69 87 13.6 63 29.8 31 7.87 73 4.88 20 5.75 15 3.71 14 13.2 89 28.9 104 9.72 73 3.21 102 4.71 121 2.91 88 19.3 101 30.5 99 15.6 82
DMF_ROB [140]76.5 8.27 78 16.7 76 6.36 85 11.7 96 26.4 108 7.10 82 17.8 90 28.6 98 7.33 78 15.9 93 35.9 99 9.46 88 5.05 45 5.97 41 4.51 62 12.8 86 27.4 92 9.90 76 1.60 7 2.99 23 1.48 26 19.8 104 32.0 106 16.8 98
TF+OM [100]78.3 7.97 66 16.8 78 5.98 75 9.40 53 20.7 52 6.33 70 15.4 73 22.9 57 17.5 124 13.4 57 31.5 51 8.10 76 5.13 56 6.06 62 4.66 75 13.9 98 29.3 107 14.0 116 2.47 74 4.09 102 2.00 53 18.3 92 29.4 96 19.3 116
Steered-L1 [118]79.0 5.97 1 12.7 1 4.67 23 7.14 12 18.2 26 4.63 29 13.2 52 23.3 61 5.12 37 15.2 84 38.1 119 7.54 68 5.85 111 6.73 112 6.98 130 13.7 97 26.5 86 11.7 100 6.39 139 4.25 107 13.3 147 22.3 120 32.7 113 20.3 121
Aniso. Huber-L1 [22]79.7 7.96 65 16.3 64 6.10 79 11.4 90 24.7 93 6.77 77 20.6 109 29.6 107 7.26 74 13.2 54 29.2 30 7.77 72 5.52 95 6.58 108 4.29 52 12.4 79 26.7 89 8.83 59 2.93 94 3.68 87 3.10 91 16.5 83 27.4 89 13.9 72
OFRF [134]80.6 9.69 105 19.6 124 6.25 82 22.2 143 29.4 125 20.7 146 21.6 120 30.1 112 17.0 123 14.1 69 31.0 44 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 58 16.7 35 15.9 90
AugFNG_ROB [144]80.7 12.7 131 22.1 141 9.46 137 12.1 100 24.6 92 9.39 101 18.8 97 27.1 93 14.7 120 14.0 68 30.9 42 9.24 86 5.03 41 5.72 12 5.09 90 11.0 60 24.0 71 9.53 70 1.82 31 3.25 52 1.22 8 18.2 91 23.7 74 21.6 128
EAI-Flow [152]81.4 10.4 117 19.0 118 7.83 113 13.2 110 25.8 100 9.43 102 13.7 59 21.6 49 8.47 96 14.8 78 33.0 70 9.68 95 5.12 52 6.01 53 4.74 81 11.6 66 25.7 82 9.23 66 3.66 113 3.57 83 2.04 55 13.4 67 24.8 78 10.5 51
LocallyOriented [52]82.0 9.89 107 19.9 128 6.55 88 14.7 116 27.7 118 11.0 110 21.7 123 31.9 132 7.32 77 13.3 56 30.5 38 8.32 78 5.16 62 6.04 59 4.11 40 9.90 42 21.6 50 8.75 58 2.20 62 3.43 72 2.17 60 18.3 92 26.0 83 19.6 117
SIOF [67]83.6 8.21 76 17.0 84 5.49 60 13.0 109 27.4 116 8.63 96 20.1 107 29.0 101 16.3 122 16.8 108 37.3 112 10.0 103 5.40 91 6.34 97 4.88 85 11.6 66 25.4 80 10.1 81 1.81 30 3.27 54 1.34 14 15.1 76 25.1 80 11.9 59
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
FGIK [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
CtxSyn [137]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 [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
LFNet_ROB [150]84.7 10.1 112 17.0 84 8.16 121 9.48 55 21.8 67 6.00 64 16.8 84 26.1 80 11.1 108 13.4 57 29.9 32 8.73 83 5.40 91 6.20 83 5.58 105 13.3 91 29.4 109 10.0 80 2.04 49 3.21 48 1.85 48 22.7 124 35.6 128 21.8 130
DeepFlow [86]85.0 8.73 89 17.1 90 6.26 83 15.3 120 26.7 113 11.9 120 17.3 87 26.5 85 14.1 119 18.6 124 42.8 147 11.0 109 5.00 36 5.91 34 3.75 17 11.2 64 26.2 85 8.35 54 1.88 34 2.80 7 2.60 79 22.5 122 33.6 118 17.5 103
SegOF [10]85.5 9.43 101 17.7 99 8.06 118 12.0 99 22.9 81 10.4 107 17.0 85 26.1 80 12.6 115 13.8 65 26.8 21 11.2 111 5.53 96 6.26 90 6.06 114 19.0 132 35.6 147 18.8 134 1.37 2 2.60 2 0.83 2 16.4 81 30.0 97 14.0 73
TriangleFlow [30]86.0 8.08 71 17.0 84 5.12 40 11.7 96 26.1 103 6.98 81 19.5 100 30.3 115 6.34 61 12.9 44 33.0 70 6.71 32 7.00 135 8.16 139 6.63 127 12.8 86 24.5 73 10.5 84 3.59 110 5.17 131 3.27 97 12.9 59 21.9 64 12.1 61
CRTflow [80]86.2 7.92 60 16.0 50 5.91 71 11.4 90 23.7 87 6.55 74 19.8 104 30.1 112 7.77 88 17.2 114 41.3 138 9.76 97 5.34 83 6.30 93 3.69 13 15.8 114 31.0 122 14.3 119 2.12 57 2.92 19 2.35 70 19.2 99 32.9 115 15.3 79
TriFlow [95]87.9 9.01 95 18.5 111 6.60 91 11.4 90 26.4 108 7.40 84 20.9 112 29.9 110 20.9 133 12.2 27 30.8 41 6.95 48 5.26 80 6.16 75 4.88 85 12.0 73 26.5 86 11.6 98 6.97 140 4.54 115 6.57 132 13.0 62 22.0 65 9.86 48
Brox et al. [5]88.9 8.46 87 16.7 76 6.56 89 11.3 89 26.2 105 6.94 80 15.0 70 25.4 73 6.89 68 17.4 115 38.8 123 9.80 98 5.99 115 6.88 119 6.26 119 14.1 101 31.1 125 12.0 102 2.03 48 3.41 69 1.14 6 19.1 98 30.3 98 12.1 61
Fusion [6]90.5 8.76 90 17.7 99 7.01 97 7.82 23 19.7 41 4.78 36 10.9 30 18.4 28 7.23 73 12.8 41 32.6 63 8.32 78 7.04 136 8.11 137 6.57 125 14.9 107 28.3 97 13.2 110 4.37 131 5.18 132 2.77 82 26.2 137 38.6 139 26.4 139
p-harmonic [29]90.6 8.15 75 16.2 58 6.50 87 9.66 60 22.6 76 6.57 75 21.2 116 31.2 123 9.65 101 15.7 88 33.9 79 10.0 103 5.18 66 6.04 59 5.31 97 14.3 103 30.3 117 12.2 106 3.10 99 3.55 79 1.91 50 23.1 127 34.8 125 17.8 105
CBF [12]91.4 7.23 32 14.9 17 5.16 41 9.95 67 21.9 69 7.69 88 17.6 89 27.0 89 7.28 76 16.4 105 39.3 127 9.18 85 6.34 128 7.35 133 6.11 117 13.4 94 28.4 98 8.52 56 5.54 136 5.11 128 6.41 130 18.7 94 30.8 100 16.4 95
EPMNet [133]91.5 11.6 125 20.5 133 8.03 117 17.7 126 28.9 122 13.2 126 12.9 47 20.3 37 10.7 104 15.5 85 37.4 113 9.48 89 5.36 87 6.23 86 4.94 87 14.0 99 29.9 113 12.2 106 2.97 95 5.82 135 2.01 54 10.1 41 18.8 49 3.51 19
FlowNet2 [122]92.2 12.8 132 23.3 146 8.09 119 16.8 123 28.5 119 12.5 122 13.9 61 21.6 49 12.0 113 15.0 82 34.0 80 9.98 102 5.36 87 6.23 86 4.94 87 14.0 99 29.9 113 12.2 106 3.36 104 6.60 141 2.24 64 8.83 31 16.6 34 3.02 14
WOLF_ROB [149]92.4 9.97 110 18.4 108 7.33 104 20.8 134 34.8 150 13.9 128 22.2 131 30.7 119 10.9 105 17.0 113 33.2 74 12.3 118 5.16 62 6.01 53 5.11 92 10.2 49 20.7 44 9.05 63 1.97 42 3.28 55 2.48 77 17.9 90 23.1 70 21.3 127
TV-L1-improved [17]92.9 7.64 56 16.2 58 5.67 65 10.1 70 23.4 83 6.38 71 21.3 118 32.0 135 9.27 100 17.5 116 42.1 142 9.54 90 5.25 75 6.13 70 4.07 35 14.5 104 30.4 119 11.4 94 3.38 105 5.02 126 2.99 90 19.6 103 32.1 108 16.6 97
CLG-TV [48]93.4 7.94 62 16.2 58 5.80 70 10.5 80 24.0 91 6.44 72 19.9 105 29.8 108 6.83 66 14.1 69 31.5 51 7.73 71 5.98 113 7.01 123 5.15 93 14.8 106 31.0 122 12.2 106 4.20 128 4.80 123 5.22 125 19.3 101 32.6 112 15.7 86
Local-TV-L1 [65]93.8 9.74 106 17.9 103 6.89 94 18.4 129 29.4 125 14.9 130 24.4 135 30.8 120 20.2 131 19.4 129 42.4 145 12.7 120 5.35 86 6.00 50 4.10 38 13.6 95 28.9 104 9.26 67 1.62 9 2.58 1 1.48 26 20.3 108 32.0 106 16.4 95
Classic++ [32]94.8 8.05 69 17.4 96 6.09 78 11.5 93 26.3 107 6.91 78 18.1 93 28.7 99 8.18 93 16.2 95 39.0 125 8.57 81 5.36 87 6.33 95 4.54 64 15.0 109 30.4 119 11.6 98 2.70 83 3.55 79 2.94 89 21.9 117 34.0 121 17.9 106
SuperFlow [81]94.8 9.27 99 17.3 94 6.63 92 11.7 96 22.8 78 8.84 98 19.3 99 28.0 95 18.4 128 16.9 110 38.2 120 9.89 100 5.44 93 6.32 94 5.61 107 11.9 71 26.6 88 9.56 72 2.92 92 4.08 101 1.79 45 20.1 106 32.4 110 15.8 88
Rannacher [23]96.0 8.07 70 16.8 78 6.15 80 10.6 81 24.8 94 6.51 73 21.9 127 32.6 141 10.9 105 18.4 121 43.3 149 10.5 105 5.27 81 6.18 80 4.17 46 15.5 112 32.3 132 12.0 102 2.69 82 3.57 83 2.68 80 17.8 89 31.0 101 16.1 91
F-TV-L1 [15]96.5 8.41 85 16.8 78 6.31 84 18.0 128 29.7 127 12.8 123 21.6 120 30.5 116 10.1 103 18.2 119 42.3 144 9.65 92 5.02 40 5.97 41 3.91 22 14.1 101 30.8 121 10.6 88 2.79 84 4.90 124 2.35 70 20.5 111 32.7 113 15.6 82
BriefMatch [124]99.2 6.91 16 14.8 16 4.85 26 11.0 87 22.8 78 8.24 93 9.42 14 16.6 20 5.13 39 16.7 107 40.7 134 8.61 82 9.76 142 10.6 149 14.1 143 18.2 128 31.0 122 17.4 130 9.26 144 6.60 141 20.9 153 28.0 141 36.5 131 34.9 146
DF-Auto [115]100.3 10.7 120 19.8 127 7.42 106 16.3 122 25.3 96 13.1 125 19.5 100 28.5 96 17.8 126 16.9 110 37.2 109 10.8 107 6.76 134 8.12 138 5.56 104 10.8 56 25.2 77 6.95 35 3.69 115 4.92 125 1.48 26 17.7 88 27.9 91 14.6 74
StereoOF-V1MT [119]100.3 8.14 73 15.8 42 5.42 58 17.6 125 34.3 148 10.3 105 21.6 120 31.5 127 7.27 75 15.8 90 32.7 65 10.7 106 5.62 103 6.40 99 6.00 113 16.6 117 30.0 115 15.5 121 2.01 45 3.08 29 3.15 93 33.6 147 44.0 148 32.8 144
Dynamic MRF [7]101.7 8.32 83 17.3 94 5.95 72 12.3 102 28.5 119 7.75 89 19.6 102 31.8 131 7.56 80 18.4 121 42.2 143 11.6 115 5.25 75 6.16 75 4.80 83 17.7 122 34.4 143 16.6 126 1.89 36 2.63 3 3.21 96 30.3 143 43.6 147 29.0 141
Bartels [41]101.9 8.31 82 17.7 99 5.51 61 8.46 37 20.6 50 4.89 37 14.8 68 26.0 78 7.89 89 18.5 123 43.6 150 11.1 110 6.18 121 6.51 107 8.63 138 15.6 113 32.6 134 13.9 115 3.86 121 4.56 116 7.09 134 22.5 122 36.5 131 18.4 110
Shiralkar [42]103.5 7.92 60 15.2 29 5.73 67 14.6 115 30.3 128 9.04 99 21.7 123 31.2 123 9.77 102 19.6 131 41.5 139 13.2 122 5.17 64 6.04 59 4.63 71 18.0 127 31.1 125 14.7 120 3.67 114 3.40 67 4.74 121 23.9 132 36.6 133 18.9 113
GraphCuts [14]103.5 9.24 98 17.2 91 7.53 110 22.1 141 33.0 142 16.8 138 15.9 81 23.1 59 15.6 121 14.2 72 28.9 28 9.34 87 5.83 110 6.82 115 6.25 118 18.5 130 29.7 111 12.0 102 2.85 88 3.39 65 3.52 104 23.8 131 36.1 129 19.1 114
Second-order prior [8]106.0 8.04 68 16.3 64 6.01 77 12.5 104 26.5 110 9.10 100 21.0 113 31.1 122 9.23 99 16.2 95 36.2 104 9.93 101 5.70 107 6.67 111 5.09 90 20.7 143 34.1 141 21.0 145 3.76 117 3.89 97 4.25 117 18.9 96 31.8 105 19.9 119
Filter Flow [19]106.1 10.5 118 19.4 121 8.33 122 12.5 104 25.8 100 8.69 97 19.9 105 27.0 89 21.7 136 19.0 126 33.1 73 15.9 132 5.34 83 6.21 84 5.37 99 16.2 116 26.7 89 15.5 121 3.46 107 4.48 114 2.26 65 23.3 130 31.5 104 18.5 111
StereoFlow [44]106.1 16.2 148 22.6 144 13.9 150 22.1 141 31.6 134 18.8 143 24.7 136 30.6 118 21.2 135 23.3 143 39.9 128 19.6 143 5.98 113 6.22 85 7.11 132 11.6 66 27.6 93 8.05 48 1.36 1 2.85 13 0.65 1 20.7 112 33.7 119 17.0 101
CNN-flow-warp+ref [117]107.7 9.91 108 19.6 124 7.85 114 10.6 81 22.9 81 8.55 94 21.3 118 32.1 137 11.9 112 18.7 125 42.0 141 11.3 112 5.56 99 6.34 97 6.08 116 12.3 77 27.6 93 10.8 89 2.06 51 3.69 89 3.16 94 33.3 145 40.4 142 34.7 145
FlowNetS+ft+v [112]108.4 8.96 94 17.8 102 6.83 93 14.2 113 26.2 105 11.1 111 22.3 132 32.2 138 12.7 116 16.8 108 36.1 103 10.9 108 6.31 127 7.29 131 6.26 119 12.5 83 28.8 102 9.88 75 3.84 120 6.75 143 6.30 129 16.4 81 29.0 94 14.7 75
IAOF2 [51]108.5 10.0 111 19.9 128 7.91 116 14.4 114 26.7 113 10.9 109 22.0 129 32.2 138 17.6 125 19.1 127 33.0 70 17.1 136 5.81 109 6.86 117 4.94 87 12.6 84 25.9 83 11.9 101 4.26 130 4.11 104 7.75 137 16.2 80 26.5 86 13.5 69
Ad-TV-NDC [36]111.5 12.1 129 18.6 114 10.7 142 25.5 147 32.0 138 22.2 147 29.3 149 34.3 147 22.8 140 16.9 110 32.8 67 12.2 117 5.99 115 7.20 129 3.83 19 12.6 84 28.5 100 10.3 82 2.79 84 4.07 100 1.78 44 24.1 133 31.4 103 25.1 136
TVL1_ROB [139]111.5 12.9 133 20.8 135 9.80 140 21.3 138 30.9 131 17.9 142 27.9 143 33.6 142 23.5 144 20.5 133 37.8 117 16.7 134 5.57 100 6.47 104 5.46 102 14.5 104 32.1 131 12.1 105 1.69 17 2.81 9 1.22 8 22.9 125 36.3 130 18.3 109
2D-CLG [1]113.5 15.2 146 24.5 150 11.2 144 15.1 117 25.9 102 13.5 127 27.5 142 33.9 144 24.7 149 22.2 140 38.3 121 19.0 142 5.67 105 6.44 102 6.29 122 17.5 120 34.3 142 16.4 125 1.47 3 2.68 4 1.54 36 21.7 116 34.6 124 16.9 100
LDOF [28]113.6 9.66 104 18.9 117 7.13 101 15.1 117 29.1 124 11.3 112 15.6 78 25.1 71 10.9 105 20.9 136 43.1 148 14.9 130 6.12 119 7.01 123 6.26 119 16.0 115 31.2 127 13.2 110 3.89 123 5.61 134 8.96 144 19.0 97 33.0 116 11.7 57
UnFlow [129]114.9 16.0 147 25.1 151 11.3 145 12.7 108 22.2 73 11.7 119 20.4 108 27.6 94 13.6 117 20.8 134 36.0 101 17.9 139 6.34 128 6.89 120 7.74 136 17.7 122 33.5 138 17.1 129 2.92 92 4.33 109 1.37 17 20.7 112 37.3 137 15.6 82
Nguyen [33]115.2 11.4 122 19.6 124 8.44 124 21.0 137 31.7 136 17.7 140 29.8 151 36.3 151 24.1 148 18.2 119 34.6 85 13.9 123 6.28 123 6.85 116 7.51 135 15.4 111 33.0 135 14.0 116 2.24 65 3.11 36 1.79 45 21.6 115 33.9 120 15.8 88
IAOF [50]116.3 10.1 112 18.6 114 7.89 115 22.2 143 33.7 145 15.9 134 33.0 153 39.2 154 23.7 145 16.2 95 32.1 58 11.6 115 5.80 108 6.87 118 5.39 101 17.8 124 30.1 116 11.4 94 3.13 101 3.69 89 3.88 114 22.4 121 29.3 95 21.6 128
Learning Flow [11]116.8 8.28 79 17.0 84 5.75 68 12.3 102 28.5 119 7.79 91 18.4 94 28.7 99 8.29 94 22.2 140 40.6 133 17.3 137 8.52 137 10.3 148 7.04 131 19.9 141 35.1 145 16.8 128 3.11 100 4.59 118 3.59 108 26.9 139 40.0 141 20.9 126
SPSA-learn [13]116.9 11.3 121 19.4 121 8.52 126 20.9 135 34.2 147 16.2 137 26.5 140 33.9 144 22.4 139 22.5 142 39.9 128 18.9 141 5.59 101 6.41 100 5.94 111 17.8 124 31.4 129 18.3 133 2.11 55 3.11 36 1.37 17 24.3 134 35.1 126 19.7 118
HBpMotionGpu [43]118.5 12.2 130 22.1 141 8.34 123 17.9 127 31.4 133 14.7 129 29.2 148 37.8 153 20.6 132 19.1 127 44.6 152 11.5 114 5.60 102 6.45 103 6.06 114 13.2 89 28.8 102 11.1 92 3.45 106 3.97 99 2.04 55 23.1 127 34.1 122 20.7 123
Modified CLG [34]121.4 11.6 125 20.5 133 9.14 136 12.6 107 25.4 98 10.3 105 27.4 141 34.4 148 23.8 146 21.8 138 42.7 146 16.7 134 6.18 121 7.06 126 6.57 125 14.9 107 33.0 135 13.4 113 2.45 72 3.80 95 3.81 113 22.0 119 36.6 133 16.8 98
Black & Anandan [4]123.1 10.5 118 18.0 105 8.14 120 21.4 140 32.8 141 16.1 136 26.1 139 32.3 140 21.8 137 20.8 134 38.9 124 16.1 133 6.29 125 7.41 134 5.62 108 17.1 118 31.2 127 13.7 114 4.06 126 5.11 128 2.37 72 23.1 127 34.1 122 15.7 86
GroupFlow [9]124.4 11.5 124 21.2 139 8.71 133 20.5 132 33.0 142 15.7 133 23.6 133 31.6 128 20.1 130 16.2 95 34.5 82 11.3 112 8.86 138 9.84 147 6.50 124 18.2 128 30.3 117 17.4 130 3.82 119 5.05 127 6.55 131 21.1 114 28.8 93 22.4 134
2bit-BM-tele [98]124.4 10.3 114 20.1 130 7.40 105 11.5 93 26.7 113 7.57 87 20.6 109 32.0 135 11.4 110 17.9 117 40.3 131 12.3 118 6.29 125 6.80 114 6.93 129 21.0 144 32.0 130 18.0 132 7.61 141 6.57 140 11.1 146 27.5 140 39.4 140 29.2 142
Heeger++ [104]125.1 11.7 127 18.3 107 9.04 135 23.3 146 37.0 153 17.4 139 21.0 113 29.1 103 11.1 108 27.0 147 40.5 132 24.4 146 5.69 106 6.33 95 5.80 109 25.9 150 37.5 150 26.3 150 2.48 75 3.88 96 2.20 62 37.6 150 46.0 151 41.6 153
H+S_ROB [138]125.4 16.6 150 23.6 148 11.9 147 19.1 130 30.6 130 15.6 132 25.1 137 30.2 114 23.4 142 29.1 148 36.3 105 27.9 149 13.4 151 15.7 151 12.2 140 27.2 151 38.8 152 27.8 151 1.70 19 2.81 9 1.42 22 32.2 144 41.3 145 30.2 143
HCIC-L [99]125.5 14.6 143 21.1 137 9.67 138 42.7 154 36.7 152 46.6 154 21.8 125 30.5 116 17.9 127 21.1 137 35.1 91 18.6 140 6.42 130 6.58 108 7.35 134 17.8 124 28.6 101 16.6 126 12.8 147 14.3 147 15.3 149 16.8 86 25.7 82 12.7 65
BlockOverlap [61]128.1 10.3 114 19.1 119 7.74 112 15.4 121 25.3 96 13.0 124 24.3 134 31.9 132 21.0 134 19.5 130 43.8 151 13.1 121 9.14 139 7.60 135 13.9 142 19.0 132 29.0 106 15.7 123 11.0 145 8.77 145 24.8 154 23.0 126 31.3 102 25.9 138
TI-DOFE [24]128.4 14.6 143 21.1 137 11.7 146 22.4 145 31.6 134 19.6 144 28.6 146 31.2 123 26.3 150 26.3 146 36.0 101 25.1 147 6.43 131 7.34 132 6.67 128 19.1 134 33.8 139 18.9 135 2.88 90 3.15 43 2.82 85 25.7 136 36.6 133 22.3 133
Horn & Schunck [3]129.4 11.8 128 19.3 120 8.85 134 20.1 131 33.5 144 15.3 131 25.5 138 31.2 123 24.0 147 26.1 145 38.6 122 23.5 144 6.12 119 6.99 121 6.34 123 19.9 141 33.9 140 19.6 142 3.95 125 4.28 108 2.46 75 25.3 135 37.5 138 22.0 132
FFV1MT [106]135.6 13.9 142 23.4 147 10.8 143 20.9 135 34.5 149 16.0 135 21.8 125 29.5 106 13.8 118 31.0 152 41.7 140 29.4 151 9.97 143 6.78 113 17.9 151 23.8 147 35.3 146 25.0 149 2.99 96 4.24 106 3.57 107 37.6 150 46.0 151 41.6 153
SILK [79]136.8 13.2 140 22.4 143 10.2 141 20.5 132 32.2 140 17.7 140 29.0 147 34.1 146 23.4 142 22.0 139 40.8 135 17.3 137 6.28 123 7.17 128 7.12 133 21.7 145 35.8 148 19.6 142 5.44 135 3.45 75 10.8 145 29.3 142 40.6 144 26.7 140
Adaptive flow [45]137.4 13.2 140 20.2 131 9.78 139 27.3 149 31.9 137 25.4 148 28.3 145 31.6 128 30.5 153 19.7 132 37.6 115 15.3 131 11.2 150 12.6 150 8.93 139 17.6 121 29.8 112 15.8 124 13.1 148 11.0 146 18.3 150 26.4 138 36.8 136 22.7 135
PGAM+LK [55]138.2 14.9 145 22.8 145 14.1 151 25.5 147 31.3 132 26.6 149 21.9 127 26.4 84 22.2 138 26.0 144 39.1 126 24.0 145 9.61 141 6.49 106 14.1 143 24.3 148 35.0 144 23.0 147 6.19 138 6.24 139 7.26 135 34.3 148 40.4 142 40.8 152
SLK [47]138.7 17.2 152 24.0 149 18.2 152 21.3 138 30.4 129 20.1 145 27.9 143 31.9 132 23.3 141 31.4 153 39.9 128 30.0 153 6.60 132 7.04 125 8.37 137 22.8 146 36.4 149 21.6 146 3.90 124 3.75 93 5.02 123 33.3 145 41.7 146 35.2 147
AVG_FLOW_ROB [142]142.7 32.4 154 34.1 154 37.7 154 35.1 153 33.7 145 37.0 153 20.7 111 24.1 65 19.4 129 34.1 154 35.1 91 34.8 154 39.6 153 37.0 153 44.9 153 40.6 154 42.2 153 38.5 154 11.3 146 15.3 148 7.36 136 46.5 154 52.3 154 38.9 149
Pyramid LK [2]146.1 17.0 151 20.4 132 19.4 153 31.7 150 32.1 139 32.5 150 32.9 152 34.8 149 29.9 152 29.4 150 35.3 95 29.9 152 31.7 152 35.5 152 29.8 152 29.9 152 32.3 132 28.0 152 9.01 143 7.93 144 18.9 151 39.9 152 45.4 150 39.0 150
FOLKI [16]146.8 16.2 148 25.9 152 12.7 149 32.5 151 35.6 151 34.7 151 29.4 150 35.1 150 26.9 151 29.1 148 41.0 137 27.9 149 9.58 140 8.90 140 13.5 141 25.7 149 38.3 151 24.5 148 7.71 142 5.13 130 14.5 148 36.5 149 44.4 149 36.1 148
Periodicity [78]151.3 18.0 153 30.5 153 12.3 148 34.0 152 41.4 154 35.6 152 36.5 154 36.5 152 35.2 154 29.7 151 46.6 154 26.8 148 51.8 154 56.5 154 45.5 154 36.7 153 42.4 154 37.1 153 5.99 137 6.16 138 19.3 152 40.1 153 51.1 153 40.4 151
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] FGIK 0.18 2 color Anonymous. (Interpolation results only.) Learning flow-guided interpolation kernels for video frame synthesis. ECCV 2018 submission 433.
[137] CtxSyn 0.07 2 color S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[138] 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.
[139] 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.
[140] 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.
[141] 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.
[142] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[143] 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.
[144] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[145] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[146] 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.
[147] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[148] 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.
[149] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[150] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
[151] 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.
[152] 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.
[153] ContinualFlow_ROB 0.5 all color Anonymous. Continual Flow. ACCV 2018 submission 273.
[154] CyclicGen 0.088 2 color Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
* 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.