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]9.2 6.84 15 15.1 24 4.48 11 6.28 5 15.5 10 3.00 4 7.42 3 13.5 9 2.39 3 7.71 6 22.7 12 2.48 3 4.26 1 5.09 1 2.83 1 6.52 2 14.9 2 4.55 4 1.74 20 3.32 56 1.23 9 5.63 6 10.7 6 2.48 8
PMMST [114]10.2 6.46 4 14.1 4 3.23 1 5.42 1 12.7 6 3.51 13 8.20 9 14.7 14 3.66 14 7.46 3 17.8 3 4.34 5 4.79 13 5.67 8 3.91 22 6.77 3 15.2 4 3.61 2 1.74 20 3.36 59 1.34 13 5.95 11 11.3 11 2.25 2
NN-field [71]12.9 7.29 35 16.0 49 4.74 23 6.15 2 15.2 9 3.02 6 7.77 7 14.1 13 2.71 6 7.56 4 22.8 13 1.96 2 4.49 2 5.36 2 3.09 3 5.72 1 14.1 1 1.96 1 1.96 39 3.34 57 1.32 12 5.70 7 10.8 7 2.49 9
OFLAF [77]15.9 6.75 12 14.9 17 4.44 9 7.07 11 17.5 20 3.10 7 8.45 10 15.5 16 2.50 5 13.0 46 35.0 87 6.38 18 4.57 3 5.57 5 3.12 4 7.63 7 15.9 7 5.90 16 1.68 15 2.86 15 1.43 23 5.83 10 11.0 9 2.79 10
MDP-Flow2 [68]23.2 6.66 7 14.7 14 4.53 13 6.79 8 17.0 14 3.23 8 8.68 11 15.8 17 2.90 7 13.4 56 33.7 74 6.89 45 4.95 28 5.84 25 4.15 45 8.49 18 18.7 29 7.72 44 1.64 11 3.08 27 1.27 11 6.77 14 12.8 16 3.33 16
nLayers [57]26.0 7.20 30 16.0 49 4.66 20 6.25 4 14.7 7 3.70 18 7.72 6 13.7 11 4.81 33 13.1 50 34.8 85 6.69 30 4.76 10 5.75 15 4.12 42 7.19 5 14.9 2 4.40 3 1.99 41 3.10 32 1.80 46 8.22 26 15.6 27 6.10 32
FC-2Layers-FF [74]26.1 7.07 24 15.5 35 4.91 29 8.30 33 19.7 39 4.30 22 7.61 5 13.6 10 4.29 25 11.8 20 30.2 34 6.20 16 4.60 4 5.54 3 3.52 7 9.20 32 18.3 24 6.27 23 2.20 61 3.42 68 1.85 47 7.54 20 14.3 22 4.12 23
3DFlow [135]29.8 6.97 18 15.1 24 3.90 3 8.12 28 19.7 39 3.79 19 13.6 56 24.2 64 3.63 12 4.18 1 12.4 1 1.73 1 4.97 30 5.98 45 3.83 19 10.5 52 18.9 37 8.87 61 2.38 69 3.11 34 2.45 71 5.82 9 11.1 10 3.00 12
ComponentFusion [96]31.0 7.22 31 15.9 46 4.61 18 7.60 17 19.2 33 3.30 9 9.70 16 17.6 22 3.77 16 11.1 15 31.0 43 4.45 6 4.96 29 5.88 30 4.25 49 10.9 57 23.7 63 9.40 68 1.90 36 3.08 27 1.69 40 8.00 24 15.1 25 4.57 25
FESL [72]33.9 6.97 18 15.3 31 4.47 10 9.74 60 21.4 60 5.49 55 11.4 32 20.2 34 4.25 24 12.5 29 31.5 50 6.81 35 4.72 7 5.71 11 3.72 15 7.03 4 16.0 8 4.81 5 2.21 63 3.49 75 1.94 51 11.1 48 17.6 40 10.1 48
PWC-Net_ROB [148]34.5 8.30 79 16.2 57 6.58 89 8.56 38 20.6 48 4.38 25 12.3 42 21.4 46 6.00 54 10.8 11 27.0 21 6.88 44 4.94 26 5.79 21 3.98 28 8.37 17 19.3 39 5.42 11 1.65 14 3.29 54 1.02 3 7.86 23 14.2 21 3.37 17
AGIF+OF [85]34.5 7.17 28 15.6 37 4.93 30 10.2 70 22.1 69 5.16 42 12.5 45 21.2 45 4.88 35 12.5 29 31.7 55 6.76 32 4.78 12 5.73 13 3.91 22 7.85 10 16.3 10 5.20 7 1.83 30 3.10 32 1.71 41 10.8 45 17.6 40 11.0 50
Correlation Flow [75]35.5 6.66 7 14.5 9 3.81 2 7.78 22 17.5 20 2.85 2 18.0 89 29.0 99 4.31 27 9.28 8 22.1 11 5.57 11 5.12 51 6.13 67 3.98 28 11.0 60 23.3 58 10.5 83 2.07 51 3.08 27 2.32 66 6.79 15 12.5 14 4.83 26
Layers++ [37]35.6 7.19 29 15.7 39 5.08 36 6.15 2 14.8 8 3.42 12 7.83 8 14.0 12 4.84 34 10.9 13 26.9 20 6.19 15 4.83 17 5.84 25 4.36 54 12.4 77 25.2 74 10.5 83 2.43 70 3.56 80 1.92 50 8.66 29 16.1 29 7.77 39
NNF-EAC [103]35.8 6.83 14 14.9 17 4.80 24 7.59 16 18.0 22 4.31 23 9.03 13 16.1 18 3.09 9 13.2 53 32.2 59 7.10 52 5.06 47 5.96 39 4.02 32 8.19 14 17.1 11 6.04 20 1.79 26 3.30 55 1.38 19 17.0 84 27.6 87 18.0 106
Efficient-NL [60]37.0 7.43 48 16.2 57 4.85 25 7.73 20 18.1 23 4.58 27 14.0 61 23.6 60 4.47 29 13.1 50 32.9 68 7.50 66 4.77 11 5.77 19 3.65 11 8.08 12 16.1 9 5.25 8 2.48 74 3.37 61 3.12 90 6.91 16 12.1 12 5.78 30
LME [70]37.8 7.04 22 15.6 37 4.53 13 6.68 6 16.9 13 2.85 2 13.6 56 22.6 52 12.0 109 11.5 18 27.8 22 6.39 19 5.03 40 5.93 36 4.52 62 12.4 77 27.0 87 10.9 89 1.76 23 3.38 62 1.43 23 6.62 13 12.5 14 2.86 11
IROF++ [58]38.0 7.44 49 16.1 53 5.11 38 8.61 40 19.4 34 5.12 40 12.3 42 21.0 44 5.12 37 12.8 40 32.1 57 7.13 54 4.88 19 5.76 17 3.89 21 9.01 22 18.9 37 6.76 31 1.78 25 3.22 48 1.23 9 10.4 42 18.5 47 13.3 66
PH-Flow [101]38.8 7.38 43 15.9 46 5.22 43 9.30 51 19.5 35 5.71 58 9.62 15 17.2 20 5.09 36 13.4 56 34.5 80 7.10 52 4.82 14 5.73 13 3.82 18 8.36 16 17.1 11 5.35 10 2.66 79 3.43 70 3.42 99 7.13 19 13.3 19 5.33 29
NL-TV-NCC [25]39.4 6.92 17 14.6 13 3.96 4 8.32 34 19.8 43 2.84 1 15.4 71 26.0 77 3.92 19 10.8 11 26.6 17 5.58 12 5.09 48 6.00 48 4.07 35 11.1 63 23.5 59 10.5 83 2.09 52 3.06 26 2.27 64 11.6 51 20.4 53 9.14 44
TC/T-Flow [76]40.1 6.31 2 13.3 2 4.85 25 11.5 91 23.6 84 6.67 75 13.4 55 23.2 58 3.00 8 14.2 72 36.9 106 6.33 17 4.72 7 5.64 6 3.64 10 7.70 8 17.1 11 5.61 15 2.00 42 3.45 73 2.86 84 10.9 47 18.2 45 3.59 19
LSM [39]40.2 7.06 23 15.2 29 5.21 42 9.65 58 21.2 58 5.48 54 11.9 38 20.2 34 5.33 42 12.0 21 30.0 32 6.84 39 5.14 55 6.13 67 4.62 68 9.12 28 18.1 21 6.53 27 2.13 57 3.11 34 2.11 56 8.09 25 14.3 22 6.76 36
Classic+CPF [83]40.2 7.31 37 15.8 42 5.09 37 9.93 64 22.1 69 5.05 38 13.3 53 22.4 51 4.64 32 12.5 29 32.0 56 6.79 34 4.87 18 5.83 24 3.99 30 7.43 6 15.6 6 5.32 9 2.26 65 3.21 46 2.78 82 9.89 38 16.5 31 13.8 69
CombBMOF [113]40.3 7.30 36 15.1 24 4.61 18 8.08 27 18.2 25 3.69 17 10.2 19 18.1 25 2.47 4 11.2 16 28.1 23 6.67 27 4.82 14 5.76 17 4.13 43 13.3 89 22.1 50 14.1 116 2.90 90 4.33 107 2.14 57 11.8 53 21.0 56 3.23 15
MLDP_OF [89]40.8 7.02 20 14.5 9 4.89 28 7.00 10 17.0 14 3.34 10 14.3 63 24.0 61 3.73 15 12.9 43 34.8 85 5.88 13 4.89 21 5.69 9 3.92 25 8.18 13 17.4 15 7.22 42 3.64 111 3.68 85 5.99 125 13.2 62 20.5 54 9.16 45
Sparse-NonSparse [56]41.0 7.26 34 15.7 39 5.22 43 9.83 61 21.6 63 5.45 53 12.2 40 20.8 40 5.35 45 12.1 24 30.0 32 6.86 41 5.14 55 6.13 67 4.58 65 9.16 30 18.5 27 6.58 28 2.05 48 3.03 23 2.06 55 7.62 21 13.8 20 5.98 31
WLIF-Flow [93]42.1 6.80 13 14.9 17 4.60 17 6.93 9 16.7 12 4.11 21 10.3 20 18.2 26 4.11 23 12.7 38 30.9 41 6.67 27 6.60 130 7.87 134 5.60 103 8.54 19 17.4 15 6.03 19 1.85 31 3.18 43 1.67 38 14.4 68 23.2 69 15.3 77
HAST [109]42.2 7.11 26 16.0 49 4.27 5 8.90 44 17.4 19 7.54 86 6.79 1 12.4 6 1.56 1 14.8 78 37.2 107 6.63 23 4.68 6 5.70 10 2.91 2 10.5 52 20.7 43 11.1 90 3.74 114 4.39 110 5.40 124 5.74 8 10.9 8 2.09 1
Ramp [62]43.0 7.32 39 15.8 42 5.20 41 8.74 41 19.8 43 5.27 48 11.4 32 19.7 33 5.40 48 12.5 29 31.6 53 6.86 41 4.97 30 5.88 30 4.08 37 9.04 23 18.3 24 7.00 38 2.65 78 3.36 59 4.00 113 8.65 28 15.3 26 11.7 55
PMF [73]43.3 7.59 54 16.5 71 4.94 31 7.64 18 18.3 28 3.66 15 7.48 4 13.2 8 2.31 2 14.7 77 36.3 103 6.84 39 4.66 5 5.64 6 3.18 6 9.85 38 21.3 46 9.22 65 3.62 110 5.25 131 3.70 109 7.12 18 13.2 18 6.82 37
Classic+NL [31]44.4 7.40 46 16.1 53 5.36 53 9.49 57 20.9 53 5.44 52 12.3 42 20.8 40 5.20 40 12.5 29 31.3 49 6.82 36 5.03 40 5.98 45 4.18 47 8.94 21 17.5 17 5.91 17 2.29 67 3.44 72 2.17 58 9.88 37 17.0 37 11.9 57
FlowFields+ [130]44.8 8.95 92 17.2 89 7.26 101 7.52 15 17.3 17 5.15 41 10.4 21 17.6 22 6.16 55 10.1 9 24.5 14 6.49 21 5.11 50 6.00 48 4.57 64 9.28 33 22.2 51 6.70 30 1.77 24 3.20 44 1.51 33 13.1 61 21.8 60 15.6 80
CostFilter [40]45.7 7.36 41 15.7 39 4.96 33 7.76 21 18.1 23 3.83 20 7.07 2 12.4 6 3.12 10 14.6 76 36.3 103 6.57 22 4.82 14 5.81 22 3.54 8 12.4 77 20.5 42 10.3 81 3.86 119 5.96 135 4.36 116 8.86 32 16.7 34 3.72 21
FMOF [94]46.9 7.14 27 15.5 35 5.28 47 10.4 77 22.7 75 5.42 49 10.8 27 19.0 31 3.90 18 12.2 26 31.0 43 6.63 23 4.98 33 5.97 40 4.10 38 10.0 45 17.2 14 6.98 36 2.46 72 3.40 65 4.60 117 14.7 70 23.2 69 10.1 48
ProbFlowFields [128]47.9 8.84 90 17.9 101 6.90 94 7.20 13 17.3 17 4.75 34 11.6 35 20.5 38 6.31 59 8.48 7 22.0 10 5.26 9 5.25 73 6.24 86 4.67 77 9.96 43 23.9 67 6.99 37 1.64 11 2.80 7 1.41 21 14.7 70 25.5 78 14.7 73
TV-L1-MCT [64]48.0 7.42 47 16.1 53 5.22 43 9.84 62 21.6 63 5.20 44 14.3 63 24.7 67 5.27 41 12.5 29 31.2 48 7.21 57 5.01 36 5.90 32 4.41 57 9.10 26 18.8 36 7.14 40 2.17 60 2.78 5 4.69 118 9.81 36 16.8 36 11.5 52
SVFilterOh [111]48.6 7.94 61 17.5 95 4.94 31 8.27 32 19.8 43 3.66 15 9.83 18 17.7 24 4.59 30 13.4 56 34.5 80 6.82 36 4.89 21 5.93 36 3.15 5 10.4 51 22.7 53 9.35 67 3.51 107 4.72 120 4.17 114 7.68 22 14.3 22 4.90 27
IIOF-NLDP [131]48.7 7.31 37 15.4 32 4.42 8 8.37 35 19.9 46 3.01 5 15.4 71 25.9 75 4.00 21 7.56 4 18.6 9 4.73 7 6.04 116 7.28 128 5.15 91 10.1 46 21.3 46 9.54 70 1.74 20 2.90 17 1.50 31 15.8 75 21.6 59 20.5 120
RNLOD-Flow [121]48.9 6.72 10 14.9 17 4.39 7 9.09 46 21.0 55 5.06 39 15.2 69 25.8 73 5.42 49 12.6 36 32.2 59 6.64 25 5.46 91 6.48 102 4.34 53 8.35 15 17.8 19 6.16 22 2.82 85 3.90 96 3.36 97 9.02 33 16.1 29 9.83 46
Complementary OF [21]49.3 7.37 42 15.1 24 5.30 50 9.46 53 22.5 73 4.63 28 13.0 48 22.8 54 4.04 22 14.8 78 37.9 115 6.87 43 4.97 30 5.86 27 4.39 56 11.0 60 24.4 70 8.06 49 1.79 26 2.79 6 2.22 61 12.2 54 22.0 63 11.2 51
ALD-Flow [66]50.3 6.69 9 14.4 8 4.54 15 12.5 102 25.7 97 6.93 78 14.3 63 24.9 68 4.29 25 14.8 78 35.3 93 7.04 50 4.98 33 5.92 34 3.66 12 10.1 46 23.6 61 6.92 34 2.02 44 3.23 49 2.86 84 10.2 41 18.9 49 6.45 35
EPPM w/o HM [88]50.5 7.33 40 14.5 9 5.00 35 7.20 13 17.2 16 3.41 11 11.8 36 20.8 40 3.20 11 12.6 36 31.1 47 7.00 49 5.14 55 6.08 60 4.67 77 12.0 71 22.7 53 9.97 77 4.48 130 3.69 87 6.02 126 10.4 42 17.6 40 11.5 52
FlowFields [110]51.0 9.03 95 17.5 95 7.31 102 8.02 26 18.6 30 5.24 47 11.1 31 18.9 29 6.32 60 11.6 19 28.7 25 7.40 64 5.14 55 6.03 54 4.64 72 10.1 46 23.8 66 7.62 43 1.69 16 2.86 15 1.51 33 12.9 57 22.8 67 14.9 76
JOF [141]51.5 7.77 57 16.9 81 5.33 51 10.6 79 20.8 52 7.75 89 10.9 29 18.9 29 5.34 43 12.7 38 32.6 62 6.67 27 4.91 24 5.86 27 3.97 27 9.05 24 17.9 20 5.47 12 3.04 97 3.66 84 3.43 100 13.3 65 21.4 58 12.2 61
MDP-Flow [26]52.2 6.73 11 14.1 4 5.59 62 6.70 7 16.0 11 4.65 30 9.78 17 17.2 20 6.61 64 13.0 46 34.7 84 6.48 20 5.54 95 6.17 76 5.84 107 10.5 52 23.6 61 7.81 45 1.89 34 3.42 68 1.37 16 20.0 102 32.5 108 19.1 112
ProFlow_ROB [147]52.5 7.98 66 17.0 82 5.55 61 9.17 48 21.5 62 5.69 57 13.9 59 24.5 66 5.39 47 13.9 66 32.3 61 7.54 67 5.19 67 6.19 79 4.26 50 9.15 29 21.8 49 5.47 12 1.57 5 2.92 18 1.15 6 13.9 67 23.8 73 12.3 62
S2F-IF [123]52.5 8.86 91 17.2 89 7.05 98 7.84 25 18.3 28 5.20 44 10.8 27 18.5 28 6.21 56 13.0 46 30.7 39 8.15 76 5.09 48 5.98 45 4.58 65 9.62 36 22.7 53 7.20 41 1.92 37 3.77 92 1.73 42 10.7 44 18.4 46 12.8 64
TC-Flow [46]52.5 6.56 6 14.1 4 4.48 11 9.25 50 21.4 60 5.03 37 14.9 67 25.8 73 3.93 20 14.5 75 35.9 97 6.97 48 5.01 36 5.97 40 3.63 9 9.98 44 22.8 56 6.83 33 2.11 54 3.25 50 3.61 107 16.7 82 26.8 84 20.0 118
SimpleFlow [49]54.7 7.56 53 16.2 57 5.59 62 9.48 54 21.0 55 5.68 56 17.1 84 27.0 87 6.29 58 13.0 46 32.8 66 7.09 51 5.18 64 6.16 72 4.62 68 8.75 20 17.6 18 6.81 32 2.13 57 3.50 76 2.30 65 9.78 35 17.4 39 7.10 38
IROF-TV [53]54.7 7.55 52 16.1 53 5.46 58 9.23 49 21.8 65 5.88 61 13.3 53 22.2 50 5.50 51 12.8 40 31.6 53 7.28 59 5.12 51 6.09 61 4.67 77 13.3 89 29.6 107 9.97 77 1.60 6 3.12 38 1.06 4 11.5 50 21.3 57 11.5 52
SRR-TVOF-NL [91]54.9 7.83 58 15.4 32 5.99 75 13.2 108 26.1 100 8.61 94 13.2 51 22.0 49 6.78 65 13.6 62 30.3 35 7.34 63 4.72 7 5.56 4 4.04 34 9.87 40 19.8 41 8.30 53 3.25 102 3.73 90 3.18 93 6.93 17 12.9 17 4.92 28
ACK-Prior [27]56.6 6.39 3 13.4 3 4.38 6 8.58 39 19.7 39 3.63 14 11.4 32 20.3 36 3.82 17 12.5 29 33.7 74 5.09 8 5.53 93 6.42 98 4.76 80 15.0 107 28.4 95 11.4 92 3.54 108 4.36 109 4.84 120 13.2 62 20.2 52 8.94 42
HBM-GC [105]56.6 8.35 83 18.4 106 4.98 34 7.66 19 18.2 25 5.20 44 13.8 58 24.2 64 5.34 43 12.0 21 30.5 37 6.83 38 5.04 43 6.02 53 4.43 58 9.34 34 15.5 5 7.92 46 3.03 96 4.57 115 2.51 76 16.1 77 26.0 80 17.9 104
LiteFlowNet [143]56.7 9.19 96 16.6 72 7.02 97 8.23 30 18.9 32 4.53 26 12.9 46 21.5 47 6.23 57 12.0 21 26.7 18 7.32 62 5.39 87 6.23 83 5.47 100 9.09 25 18.7 29 6.31 24 2.02 44 3.14 40 1.47 25 19.2 96 24.7 75 21.9 128
2DHMM-SAS [92]58.2 7.39 45 15.9 46 5.25 46 10.7 82 23.4 81 5.43 50 18.0 89 27.0 87 7.95 89 13.1 50 32.7 64 7.28 59 4.89 21 5.78 20 4.01 31 9.88 41 18.2 22 6.37 25 2.50 77 3.39 63 3.37 98 13.8 66 22.4 66 15.5 79
Sparse Occlusion [54]59.2 7.38 43 15.8 42 5.28 47 8.25 31 19.9 46 4.71 32 15.5 74 26.3 82 4.63 31 13.5 61 33.3 73 6.92 46 5.25 73 6.26 87 4.11 40 9.70 37 21.1 45 5.94 18 4.85 131 5.95 134 3.71 110 10.8 45 20.0 51 8.01 41
DPOF [18]59.5 8.43 85 16.8 76 6.36 84 10.7 82 20.7 50 9.52 101 8.72 12 15.4 15 3.63 12 11.3 17 29.1 27 6.09 14 5.34 80 6.18 77 5.38 97 12.2 73 22.4 52 8.06 49 5.27 132 3.55 77 6.79 131 8.85 31 16.5 31 4.24 24
OFH [38]60.4 7.25 33 15.0 23 5.29 49 11.1 86 25.0 93 7.19 82 18.6 94 29.1 101 5.56 52 16.0 92 40.8 132 7.44 65 5.05 44 5.92 34 4.28 51 11.4 65 26.0 80 8.73 57 1.64 11 3.04 24 1.36 15 12.5 55 23.3 71 7.79 40
ResPWCR_ROB [145]60.5 8.30 79 14.5 9 7.12 99 8.82 42 19.6 38 5.91 62 11.8 36 19.3 32 7.90 88 12.4 28 28.5 24 7.89 73 5.18 64 5.97 40 5.36 95 10.9 57 23.9 67 8.84 60 2.85 87 3.65 83 2.34 67 14.7 70 21.8 60 16.2 91
COFM [59]60.5 8.49 87 18.5 109 5.95 71 8.44 36 18.7 31 4.71 32 13.0 48 22.9 55 5.84 53 13.8 64 35.2 91 6.78 33 5.63 101 6.58 106 5.94 108 11.7 68 23.5 59 9.80 73 2.29 67 3.20 44 2.72 79 6.42 12 12.1 12 3.07 14
ROF-ND [107]61.2 7.02 20 14.7 14 4.66 20 8.18 29 19.5 35 4.66 31 15.5 74 25.9 75 5.47 50 4.68 2 12.6 2 2.76 4 5.93 109 7.12 125 5.27 93 12.2 73 25.4 77 9.09 64 4.23 127 4.20 103 3.32 96 14.7 70 22.1 65 18.8 110
PGM-C [120]61.8 9.43 100 18.5 109 7.51 107 9.84 62 23.4 81 6.05 64 12.0 39 20.6 39 7.17 71 15.8 88 35.3 93 9.67 92 5.20 70 6.11 64 4.66 74 9.86 39 23.7 63 7.06 39 1.63 9 2.84 12 1.49 30 11.1 48 20.8 55 6.23 34
OAR-Flow [125]62.2 8.08 70 16.8 76 6.19 80 17.4 121 28.9 119 12.3 118 16.3 80 26.7 86 7.01 68 15.1 82 35.2 91 7.31 61 5.17 62 6.16 72 4.24 48 9.51 35 22.9 57 5.52 14 1.54 4 2.98 21 1.59 37 9.10 34 17.1 38 3.69 20
S2D-Matching [84]62.5 8.25 76 18.0 103 5.76 68 10.9 84 22.8 76 5.71 58 17.3 85 28.5 94 6.38 62 12.1 24 30.3 35 6.65 26 5.15 59 6.13 67 4.63 70 9.18 31 19.5 40 6.69 29 2.66 79 3.35 58 3.50 101 11.6 51 19.9 50 14.7 73
TCOF [69]62.8 7.46 50 15.1 24 5.70 65 9.13 47 21.1 57 5.43 50 19.6 100 29.8 106 8.31 93 12.9 43 31.0 43 7.17 56 6.02 114 7.00 120 4.59 67 7.92 11 18.4 26 6.11 21 3.78 116 4.09 100 5.18 122 8.51 27 15.9 28 3.80 22
ComplOF-FED-GPU [35]63.3 7.49 51 15.4 32 5.37 55 12.1 98 26.5 107 7.51 85 13.1 50 22.7 53 4.33 28 15.6 86 37.7 113 7.55 69 4.94 26 5.82 23 4.13 43 12.3 75 27.7 92 8.48 55 2.49 76 3.04 24 3.56 104 12.9 57 23.9 74 9.01 43
AggregFlow [97]66.5 10.3 113 21.3 136 6.91 95 15.1 114 27.6 114 10.7 106 14.0 61 24.0 61 8.70 95 14.1 69 35.0 87 7.15 55 5.05 44 6.03 54 4.02 32 7.73 9 18.2 22 5.09 6 2.13 57 4.40 111 1.67 38 9.91 39 18.1 44 6.13 33
CPM-Flow [116]69.5 9.46 102 18.6 112 7.51 107 10.0 66 23.7 85 6.20 66 12.2 40 20.9 43 7.13 69 15.8 88 35.6 96 9.71 93 5.20 70 6.12 66 4.65 73 10.9 57 23.7 63 8.90 62 1.73 19 3.15 41 1.51 33 14.5 69 26.0 80 13.6 68
EpicFlow [102]70.8 9.39 99 18.4 106 7.50 106 10.0 66 23.8 87 6.29 68 15.8 77 26.6 85 7.35 78 15.5 84 34.4 79 9.65 90 5.20 70 6.11 64 4.66 74 10.2 49 24.5 71 8.18 52 1.63 9 2.81 9 1.48 26 15.8 75 24.8 76 17.1 100
Aniso-Texture [82]71.8 6.49 5 14.2 7 4.54 15 7.83 24 19.5 35 4.37 24 22.0 126 33.6 139 8.47 94 10.3 10 25.4 15 5.55 10 5.19 67 6.10 62 4.45 59 18.7 129 33.0 132 20.1 141 4.07 125 4.62 117 2.47 74 20.1 103 28.5 89 20.7 121
Occlusion-TV-L1 [63]72.9 7.73 56 16.4 65 5.36 53 9.48 54 22.4 72 6.18 65 19.2 96 30.0 109 7.14 70 14.4 74 33.8 76 7.91 74 5.31 79 6.27 89 4.47 60 11.9 69 27.9 93 8.04 47 2.09 52 3.08 27 1.50 31 21.9 114 35.3 124 17.5 101
FF++_ROB [146]73.3 9.92 108 19.4 118 7.55 110 8.87 43 20.9 53 5.83 60 15.3 70 25.3 70 7.95 89 11.0 14 25.4 15 7.23 58 5.19 67 6.10 62 4.80 81 17.1 116 25.3 76 13.2 107 1.88 32 2.96 20 2.77 80 18.7 91 27.2 85 25.3 134
RFlow [90]73.7 7.10 25 14.9 17 5.40 56 8.98 45 21.9 67 5.19 43 18.5 93 29.3 103 5.35 45 18.1 115 44.9 150 9.86 97 5.12 51 6.01 51 4.38 55 13.0 86 29.3 104 9.93 76 2.28 66 2.85 13 3.52 102 20.3 105 33.3 114 16.1 89
DeepFlow2 [108]73.9 8.14 72 16.6 72 5.96 73 14.1 109 26.5 107 10.2 102 15.8 77 26.2 81 6.46 63 16.5 103 37.4 110 9.54 88 5.01 36 5.94 38 3.72 15 10.7 55 25.1 73 8.08 51 1.92 37 3.12 38 2.45 71 20.3 105 32.1 105 16.3 92
Adaptive [20]74.8 7.94 61 17.0 82 5.33 51 10.2 70 23.9 88 6.28 67 21.2 113 31.7 127 7.69 85 13.6 62 29.8 29 7.87 72 4.88 19 5.75 15 3.71 14 13.2 87 28.9 101 9.72 72 3.21 101 4.71 119 2.91 86 19.3 98 30.5 96 15.6 80
DMF_ROB [140]74.9 8.27 77 16.7 74 6.36 84 11.7 94 26.4 105 7.10 81 17.8 88 28.6 96 7.33 77 15.9 91 35.9 97 9.46 86 5.05 44 5.97 40 4.51 61 12.8 84 27.4 89 9.90 75 1.60 6 2.99 22 1.48 26 19.8 101 32.0 103 16.8 96
TF+OM [100]76.5 7.97 65 16.8 76 5.98 74 9.40 52 20.7 50 6.33 69 15.4 71 22.9 55 17.5 121 13.4 56 31.5 50 8.10 75 5.13 54 6.06 59 4.66 74 13.9 96 29.3 104 14.0 113 2.47 73 4.09 100 2.00 52 18.3 89 29.4 93 19.3 114
Steered-L1 [118]77.2 5.97 1 12.7 1 4.67 22 7.14 12 18.2 25 4.63 28 13.2 51 23.3 59 5.12 37 15.2 83 38.1 116 7.54 67 5.85 108 6.73 110 6.98 127 13.7 95 26.5 82 11.7 97 6.39 137 4.25 105 13.3 144 22.3 117 32.7 110 20.3 119
Aniso. Huber-L1 [22]78.0 7.96 64 16.3 63 6.10 78 11.4 88 24.7 91 6.77 76 20.6 107 29.6 105 7.26 73 13.2 53 29.2 28 7.77 71 5.52 92 6.58 106 4.29 52 12.4 77 26.7 85 8.83 59 2.93 93 3.68 85 3.10 89 16.5 81 27.4 86 13.9 70
AugFNG_ROB [144]78.9 12.7 129 22.1 138 9.46 134 12.1 98 24.6 90 9.39 100 18.8 95 27.1 91 14.7 117 14.0 68 30.9 41 9.24 84 5.03 40 5.72 12 5.09 88 11.0 60 24.0 69 9.53 69 1.82 29 3.25 50 1.22 7 18.2 88 23.7 72 21.6 125
OFRF [134]79.1 9.69 104 19.6 121 6.25 81 22.2 140 29.4 122 20.7 143 21.6 117 30.1 110 17.0 120 14.1 69 31.0 43 8.47 79 4.93 25 5.87 29 3.94 26 9.10 26 18.6 28 6.40 26 2.84 86 4.62 117 3.66 108 12.6 56 16.7 34 15.9 88
LocallyOriented [52]80.2 9.89 106 19.9 125 6.55 87 14.7 113 27.7 115 11.0 108 21.7 120 31.9 129 7.32 76 13.3 55 30.5 37 8.32 77 5.16 60 6.04 56 4.11 40 9.90 42 21.6 48 8.75 58 2.20 61 3.43 70 2.17 58 18.3 89 26.0 80 19.6 115
SIOF [67]81.6 8.21 75 17.0 82 5.49 59 13.0 107 27.4 113 8.63 95 20.1 105 29.0 99 16.3 119 16.8 105 37.3 109 10.0 101 5.40 88 6.34 94 4.88 83 11.6 66 25.4 77 10.1 80 1.81 28 3.27 52 1.34 13 15.1 74 25.1 77 11.9 57
AdaConv-v1 [126]82.6 13.0 132 16.4 65 8.62 124 10.2 70 9.17 1 11.5 111 10.7 22 11.1 1 7.66 80 16.3 97 17.8 3 14.4 122 10.8 142 8.97 139 16.5 143 19.7 133 18.7 29 19.4 134 19.7 147 17.1 147 8.18 136 3.51 1 4.92 1 2.42 3
SepConv-v1 [127]82.6 13.0 132 16.4 65 8.62 124 10.2 70 9.17 1 11.5 111 10.7 22 11.1 1 7.66 80 16.3 97 17.8 3 14.4 122 10.8 142 8.97 139 16.5 143 19.7 133 18.7 29 19.4 134 19.7 147 17.1 147 8.18 136 3.51 1 4.92 1 2.42 3
SuperSlomo [132]82.6 13.0 132 16.4 65 8.62 124 10.2 70 9.17 1 11.5 111 10.7 22 11.1 1 7.66 80 16.3 97 17.8 3 14.4 122 10.8 142 8.97 139 16.5 143 19.7 133 18.7 29 19.4 134 19.7 147 17.1 147 8.18 136 3.51 1 4.92 1 2.42 3
FGIK [136]82.6 13.0 132 16.4 65 8.62 124 10.2 70 9.17 1 11.5 111 10.7 22 11.1 1 7.66 80 16.3 97 17.8 3 14.4 122 10.8 142 8.97 139 16.5 143 19.7 133 18.7 29 19.4 134 19.7 147 17.1 147 8.18 136 3.51 1 4.92 1 2.42 3
CtxSyn [137]82.6 13.0 132 16.4 65 8.62 124 10.2 70 9.17 1 11.5 111 10.7 22 11.1 1 7.66 80 16.3 97 17.8 3 14.4 122 10.8 142 8.97 139 16.5 143 19.7 133 18.7 29 19.4 134 19.7 147 17.1 147 8.18 136 3.51 1 4.92 1 2.42 3
LFNet_ROB [151]82.8 10.1 111 17.0 82 8.16 119 9.48 54 21.8 65 6.00 63 16.8 82 26.1 79 11.1 105 13.4 56 29.9 31 8.73 82 5.40 88 6.20 80 5.58 102 13.3 89 29.4 106 10.0 79 2.04 47 3.21 46 1.85 47 22.7 121 35.6 125 21.8 127
DeepFlow [86]83.1 8.73 88 17.1 88 6.26 82 15.3 117 26.7 110 11.9 117 17.3 85 26.5 84 14.1 116 18.6 121 42.8 144 11.0 107 5.00 35 5.91 33 3.75 17 11.2 64 26.2 81 8.35 54 1.88 32 2.80 7 2.60 77 22.5 119 33.6 115 17.5 101
SegOF [10]83.6 9.43 100 17.7 97 8.06 116 12.0 97 22.9 79 10.4 105 17.0 83 26.1 79 12.6 112 13.8 64 26.8 19 11.2 109 5.53 93 6.26 87 6.06 111 19.0 130 35.6 144 18.8 132 1.37 2 2.60 2 0.83 2 16.4 79 30.0 94 14.0 71
CRTflow [80]84.2 7.92 59 16.0 49 5.91 70 11.4 88 23.7 85 6.55 73 19.8 102 30.1 110 7.77 86 17.2 111 41.3 135 9.76 94 5.34 80 6.30 90 3.69 13 15.8 112 31.0 119 14.3 117 2.12 56 2.92 18 2.35 68 19.2 96 32.9 112 15.3 77
TriangleFlow [30]84.3 8.08 70 17.0 82 5.12 39 11.7 94 26.1 100 6.98 80 19.5 98 30.3 113 6.34 61 12.9 43 33.0 69 6.71 31 7.00 133 8.16 137 6.63 124 12.8 84 24.5 71 10.5 83 3.59 109 5.17 129 3.27 95 12.9 57 21.9 62 12.1 59
ContFlow_ROB [150]84.3 12.2 127 21.3 136 9.20 133 10.1 68 21.3 59 7.33 83 16.7 81 25.7 72 12.2 111 13.9 66 29.8 29 9.83 96 6.03 115 6.56 105 7.20 131 13.4 92 27.2 88 14.0 113 2.06 49 3.57 81 1.38 19 13.2 62 17.8 43 12.9 65
TriFlow [95]85.9 9.01 94 18.5 109 6.60 90 11.4 88 26.4 105 7.40 84 20.9 110 29.9 108 20.9 130 12.2 26 30.8 40 6.95 47 5.26 77 6.16 72 4.88 83 12.0 71 26.5 82 11.6 95 6.97 138 4.54 113 6.57 130 13.0 60 22.0 63 9.86 47
Brox et al. [5]86.7 8.46 86 16.7 74 6.56 88 11.3 87 26.2 102 6.94 79 15.0 68 25.4 71 6.89 67 17.4 112 38.8 120 9.80 95 5.99 112 6.88 117 6.26 116 14.1 99 31.1 122 12.0 99 2.03 46 3.41 67 1.14 5 19.1 95 30.3 95 12.1 59
p-harmonic [29]88.5 8.15 74 16.2 57 6.50 86 9.66 59 22.6 74 6.57 74 21.2 113 31.2 120 9.65 98 15.7 87 33.9 77 10.0 101 5.18 64 6.04 56 5.31 94 14.3 101 30.3 114 12.2 103 3.10 98 3.55 77 1.91 49 23.1 124 34.8 122 17.8 103
Fusion [6]88.7 8.76 89 17.7 97 7.01 96 7.82 23 19.7 39 4.78 35 10.9 29 18.4 27 7.23 72 12.8 40 32.6 62 8.32 77 7.04 134 8.11 135 6.57 122 14.9 105 28.3 94 13.2 107 4.37 129 5.18 130 2.77 80 26.2 134 38.6 136 26.4 136
EPMNet [133]89.3 11.6 122 20.5 130 8.03 115 17.7 123 28.9 119 13.2 123 12.9 46 20.3 36 10.7 101 15.5 84 37.4 110 9.48 87 5.36 84 6.23 83 4.94 85 14.0 97 29.9 110 12.2 103 2.97 94 5.82 133 2.01 53 10.1 40 18.8 48 3.51 18
CBF [12]89.6 7.23 32 14.9 17 5.16 40 9.95 65 21.9 67 7.69 88 17.6 87 27.0 87 7.28 75 16.4 102 39.3 124 9.18 83 6.34 126 7.35 131 6.11 114 13.4 92 28.4 95 8.52 56 5.54 134 5.11 126 6.41 128 18.7 91 30.8 97 16.4 93
FlowNet2 [122]90.1 12.8 130 23.3 143 8.09 117 16.8 120 28.5 116 12.5 119 13.9 59 21.6 48 12.0 109 15.0 81 34.0 78 9.98 100 5.36 84 6.23 83 4.94 85 14.0 97 29.9 110 12.2 103 3.36 103 6.60 139 2.24 62 8.83 30 16.6 33 3.02 13
WOLF_ROB [149]90.4 9.97 109 18.4 106 7.33 103 20.8 131 34.8 147 13.9 125 22.2 128 30.7 117 10.9 102 17.0 110 33.2 72 12.3 116 5.16 60 6.01 51 5.11 90 10.2 49 20.7 43 9.05 63 1.97 40 3.28 53 2.48 75 17.9 87 23.1 68 21.3 124
TV-L1-improved [17]90.8 7.64 55 16.2 57 5.67 64 10.1 68 23.4 81 6.38 70 21.3 115 32.0 132 9.27 97 17.5 113 42.1 139 9.54 88 5.25 73 6.13 67 4.07 35 14.5 102 30.4 116 11.4 92 3.38 104 5.02 124 2.99 88 19.6 100 32.1 105 16.6 95
CLG-TV [48]91.6 7.94 61 16.2 57 5.80 69 10.5 78 24.0 89 6.44 71 19.9 103 29.8 106 6.83 66 14.1 69 31.5 50 7.73 70 5.98 110 7.01 121 5.15 91 14.8 104 31.0 119 12.2 103 4.20 126 4.80 121 5.22 123 19.3 98 32.6 109 15.7 84
Local-TV-L1 [65]91.8 9.74 105 17.9 101 6.89 93 18.4 126 29.4 122 14.9 127 24.4 132 30.8 118 20.2 128 19.4 126 42.4 142 12.7 118 5.35 83 6.00 48 4.10 38 13.6 94 28.9 101 9.26 66 1.62 8 2.58 1 1.48 26 20.3 105 32.0 103 16.4 93
Classic++ [32]92.7 8.05 68 17.4 94 6.09 77 11.5 91 26.3 104 6.91 77 18.1 91 28.7 97 8.18 91 16.2 93 39.0 122 8.57 80 5.36 84 6.33 92 4.54 63 15.0 107 30.4 116 11.6 95 2.70 82 3.55 77 2.94 87 21.9 114 34.0 118 17.9 104
SuperFlow [81]92.7 9.27 98 17.3 92 6.63 91 11.7 94 22.8 76 8.84 97 19.3 97 28.0 93 18.4 125 16.9 107 38.2 117 9.89 98 5.44 90 6.32 91 5.61 104 11.9 69 26.6 84 9.56 71 2.92 91 4.08 99 1.79 44 20.1 103 32.4 107 15.8 86
Rannacher [23]93.8 8.07 69 16.8 76 6.15 79 10.6 79 24.8 92 6.51 72 21.9 124 32.6 138 10.9 102 18.4 118 43.3 146 10.5 103 5.27 78 6.18 77 4.17 46 15.5 110 32.3 129 12.0 99 2.69 81 3.57 81 2.68 78 17.8 86 31.0 98 16.1 89
F-TV-L1 [15]94.4 8.41 84 16.8 76 6.31 83 18.0 125 29.7 124 12.8 120 21.6 117 30.5 114 10.1 100 18.2 116 42.3 141 9.65 90 5.02 39 5.97 40 3.91 22 14.1 99 30.8 118 10.6 87 2.79 83 4.90 122 2.35 68 20.5 108 32.7 110 15.6 80
BriefMatch [124]97.4 6.91 16 14.8 16 4.85 25 11.0 85 22.8 76 8.24 92 9.42 14 16.6 19 5.13 39 16.7 104 40.7 131 8.61 81 9.76 140 10.6 146 14.1 141 18.2 126 31.0 119 17.4 128 9.26 142 6.60 139 20.9 150 28.0 138 36.5 128 34.9 143
StereoOF-V1MT [119]98.1 8.14 72 15.8 42 5.42 57 17.6 122 34.3 145 10.3 103 21.6 117 31.5 124 7.27 74 15.8 88 32.7 64 10.7 104 5.62 100 6.40 96 6.00 110 16.6 115 30.0 112 15.5 119 2.01 43 3.08 27 3.15 91 33.6 144 44.0 145 32.8 141
DF-Auto [115]98.2 10.7 118 19.8 124 7.42 105 16.3 119 25.3 94 13.1 122 19.5 98 28.5 94 17.8 123 16.9 107 37.2 107 10.8 105 6.76 132 8.12 136 5.56 101 10.8 56 25.2 74 6.95 35 3.69 113 4.92 123 1.48 26 17.7 85 27.9 88 14.6 72
Dynamic MRF [7]99.6 8.32 82 17.3 92 5.95 71 12.3 100 28.5 116 7.75 89 19.6 100 31.8 128 7.56 79 18.4 118 42.2 140 11.6 113 5.25 73 6.16 72 4.80 81 17.7 120 34.4 140 16.6 124 1.89 34 2.63 3 3.21 94 30.3 140 43.6 144 29.0 138
Bartels [41]99.9 8.31 81 17.7 97 5.51 60 8.46 37 20.6 48 4.89 36 14.8 66 26.0 77 7.89 87 18.5 120 43.6 147 11.1 108 6.18 119 6.51 104 8.63 136 15.6 111 32.6 131 13.9 112 3.86 119 4.56 114 7.09 132 22.5 119 36.5 128 18.4 108
Shiralkar [42]101.3 7.92 59 15.2 29 5.73 66 14.6 112 30.3 125 9.04 98 21.7 120 31.2 120 9.77 99 19.6 128 41.5 136 13.2 120 5.17 62 6.04 56 4.63 70 18.0 125 31.1 122 14.7 118 3.67 112 3.40 65 4.74 119 23.9 129 36.6 130 18.9 111
GraphCuts [14]101.3 9.24 97 17.2 89 7.53 109 22.1 138 33.0 139 16.8 135 15.9 79 23.1 57 15.6 118 14.2 72 28.9 26 9.34 85 5.83 107 6.82 113 6.25 115 18.5 128 29.7 108 12.0 99 2.85 87 3.39 63 3.52 102 23.8 128 36.1 126 19.1 112
Filter Flow [19]103.7 10.5 116 19.4 118 8.33 120 12.5 102 25.8 98 8.69 96 19.9 103 27.0 87 21.7 133 19.0 123 33.1 71 15.9 129 5.34 80 6.21 81 5.37 96 16.2 114 26.7 85 15.5 119 3.46 106 4.48 112 2.26 63 23.3 127 31.5 101 18.5 109
Second-order prior [8]103.8 8.04 67 16.3 63 6.01 76 12.5 102 26.5 107 9.10 99 21.0 111 31.1 119 9.23 96 16.2 93 36.2 102 9.93 99 5.70 104 6.67 109 5.09 88 20.7 140 34.1 138 21.0 142 3.76 115 3.89 95 4.25 115 18.9 93 31.8 102 19.9 117
StereoFlow [44]103.8 16.2 145 22.6 141 13.9 147 22.1 138 31.6 131 18.8 140 24.7 133 30.6 116 21.2 132 23.3 140 39.9 125 19.6 140 5.98 110 6.22 82 7.11 129 11.6 66 27.6 90 8.05 48 1.36 1 2.85 13 0.65 1 20.7 109 33.7 116 17.0 99
CNN-flow-warp+ref [117]105.2 9.91 107 19.6 121 7.85 112 10.6 79 22.9 79 8.55 93 21.3 115 32.1 134 11.9 108 18.7 122 42.0 138 11.3 110 5.56 96 6.34 94 6.08 113 12.3 75 27.6 90 10.8 88 2.06 49 3.69 87 3.16 92 33.3 142 40.4 139 34.7 142
IAOF2 [51]106.0 10.0 110 19.9 125 7.91 114 14.4 111 26.7 110 10.9 107 22.0 126 32.2 135 17.6 122 19.1 124 33.0 69 17.1 133 5.81 106 6.86 115 4.94 85 12.6 82 25.9 79 11.9 98 4.26 128 4.11 102 7.75 135 16.2 78 26.5 83 13.5 67
FlowNetS+ft+v [112]106.2 8.96 93 17.8 100 6.83 92 14.2 110 26.2 102 11.1 109 22.3 129 32.2 135 12.7 113 16.8 105 36.1 101 10.9 106 6.31 125 7.29 129 6.26 116 12.5 81 28.8 99 9.88 74 3.84 118 6.75 141 6.30 127 16.4 79 29.0 91 14.7 73
TVL1_ROB [139]108.9 12.9 131 20.8 132 9.80 137 21.3 135 30.9 128 17.9 139 27.9 140 33.6 139 23.5 141 20.5 130 37.8 114 16.7 131 5.57 97 6.47 101 5.46 99 14.5 102 32.1 128 12.1 102 1.69 16 2.81 9 1.22 7 22.9 122 36.3 127 18.3 107
Ad-TV-NDC [36]109.2 12.1 126 18.6 112 10.7 139 25.5 144 32.0 135 22.2 144 29.3 146 34.3 144 22.8 137 16.9 107 32.8 66 12.2 115 5.99 112 7.20 127 3.83 19 12.6 82 28.5 97 10.3 81 2.79 83 4.07 98 1.78 43 24.1 130 31.4 100 25.1 133
2D-CLG [1]111.0 15.2 143 24.5 147 11.2 141 15.1 114 25.9 99 13.5 124 27.5 139 33.9 141 24.7 146 22.2 137 38.3 118 19.0 139 5.67 102 6.44 99 6.29 119 17.5 118 34.3 139 16.4 123 1.47 3 2.68 4 1.54 36 21.7 113 34.6 121 16.9 98
LDOF [28]111.2 9.66 103 18.9 115 7.13 100 15.1 114 29.1 121 11.3 110 15.6 76 25.1 69 10.9 102 20.9 133 43.1 145 14.9 127 6.12 117 7.01 121 6.26 116 16.0 113 31.2 124 13.2 107 3.89 121 5.61 132 8.96 141 19.0 94 33.0 113 11.7 55
UnFlow [129]112.6 16.0 144 25.1 148 11.3 142 12.7 106 22.2 71 11.7 116 20.4 106 27.6 92 13.6 114 20.8 131 36.0 99 17.9 136 6.34 126 6.89 118 7.74 134 17.7 120 33.5 135 17.1 127 2.92 91 4.33 107 1.37 16 20.7 109 37.3 134 15.6 80
Nguyen [33]112.8 11.4 120 19.6 121 8.44 122 21.0 134 31.7 133 17.7 137 29.8 148 36.3 148 24.1 145 18.2 116 34.6 83 13.9 121 6.28 121 6.85 114 7.51 133 15.4 109 33.0 132 14.0 113 2.24 64 3.11 34 1.79 44 21.6 112 33.9 117 15.8 86
IAOF [50]114.0 10.1 111 18.6 112 7.89 113 22.2 140 33.7 142 15.9 131 33.0 150 39.2 151 23.7 142 16.2 93 32.1 57 11.6 113 5.80 105 6.87 116 5.39 98 17.8 122 30.1 113 11.4 92 3.13 100 3.69 87 3.88 112 22.4 118 29.3 92 21.6 125
SPSA-learn [13]114.2 11.3 119 19.4 118 8.52 123 20.9 132 34.2 144 16.2 134 26.5 137 33.9 141 22.4 136 22.5 139 39.9 125 18.9 138 5.59 98 6.41 97 5.94 108 17.8 122 31.4 126 18.3 131 2.11 54 3.11 34 1.37 16 24.3 131 35.1 123 19.7 116
Learning Flow [11]114.5 8.28 78 17.0 82 5.75 67 12.3 100 28.5 116 7.79 91 18.4 92 28.7 97 8.29 92 22.2 137 40.6 130 17.3 134 8.52 135 10.3 145 7.04 128 19.9 138 35.1 142 16.8 126 3.11 99 4.59 116 3.59 106 26.9 136 40.0 138 20.9 123
HBpMotionGpu [43]115.9 12.2 127 22.1 138 8.34 121 17.9 124 31.4 130 14.7 126 29.2 145 37.8 150 20.6 129 19.1 124 44.6 149 11.5 112 5.60 99 6.45 100 6.06 111 13.2 87 28.8 99 11.1 90 3.45 105 3.97 97 2.04 54 23.1 124 34.1 119 20.7 121
Modified CLG [34]118.8 11.6 122 20.5 130 9.14 132 12.6 105 25.4 96 10.3 103 27.4 138 34.4 145 23.8 143 21.8 135 42.7 143 16.7 131 6.18 119 7.06 124 6.57 122 14.9 105 33.0 132 13.4 110 2.45 71 3.80 93 3.81 111 22.0 116 36.6 130 16.8 96
Black & Anandan [4]120.5 10.5 116 18.0 103 8.14 118 21.4 137 32.8 138 16.1 133 26.1 136 32.3 137 21.8 134 20.8 131 38.9 121 16.1 130 6.29 123 7.41 132 5.62 105 17.1 116 31.2 124 13.7 111 4.06 124 5.11 126 2.37 70 23.1 124 34.1 119 15.7 84
GroupFlow [9]121.7 11.5 121 21.2 135 8.71 129 20.5 129 33.0 139 15.7 130 23.6 130 31.6 125 20.1 127 16.2 93 34.5 80 11.3 110 8.86 136 9.84 144 6.50 121 18.2 126 30.3 114 17.4 128 3.82 117 5.05 125 6.55 129 21.1 111 28.8 90 22.4 131
2bit-BM-tele [98]122.0 10.3 113 20.1 127 7.40 104 11.5 91 26.7 110 7.57 87 20.6 107 32.0 132 11.4 107 17.9 114 40.3 128 12.3 116 6.29 123 6.80 112 6.93 126 21.0 141 32.0 127 18.0 130 7.61 139 6.57 138 11.1 143 27.5 137 39.4 137 29.2 139
Heeger++ [104]122.4 11.7 124 18.3 105 9.04 131 23.3 143 37.0 150 17.4 136 21.0 111 29.1 101 11.1 105 27.0 144 40.5 129 24.4 143 5.69 103 6.33 92 5.80 106 25.9 147 37.5 147 26.3 147 2.48 74 3.88 94 2.20 60 37.6 147 46.0 148 41.6 150
H+S_ROB [138]122.9 16.6 147 23.6 145 11.9 144 19.1 127 30.6 127 15.6 129 25.1 134 30.2 112 23.4 139 29.1 145 36.3 103 27.9 146 13.4 148 15.7 148 12.2 138 27.2 148 38.8 149 27.8 148 1.70 18 2.81 9 1.42 22 32.2 141 41.3 142 30.2 140
HCIC-L [99]122.9 14.6 140 21.1 133 9.67 135 42.7 151 36.7 149 46.6 151 21.8 122 30.5 114 17.9 124 21.1 134 35.1 89 18.6 137 6.42 128 6.58 106 7.35 132 17.8 122 28.6 98 16.6 124 12.8 145 14.3 145 15.3 146 16.8 83 25.7 79 12.7 63
BlockOverlap [61]125.7 10.3 113 19.1 116 7.74 111 15.4 118 25.3 94 13.0 121 24.3 131 31.9 129 21.0 131 19.5 127 43.8 148 13.1 119 9.14 137 7.60 133 13.9 140 19.0 130 29.0 103 15.7 121 11.0 143 8.77 143 24.8 151 23.0 123 31.3 99 25.9 135
TI-DOFE [24]125.7 14.6 140 21.1 133 11.7 143 22.4 142 31.6 131 19.6 141 28.6 143 31.2 120 26.3 147 26.3 143 36.0 99 25.1 144 6.43 129 7.34 130 6.67 125 19.1 132 33.8 136 18.9 133 2.88 89 3.15 41 2.82 83 25.7 133 36.6 130 22.3 130
Horn & Schunck [3]126.6 11.8 125 19.3 117 8.85 130 20.1 128 33.5 141 15.3 128 25.5 135 31.2 120 24.0 144 26.1 142 38.6 119 23.5 141 6.12 117 6.99 119 6.34 120 19.9 138 33.9 137 19.6 139 3.95 123 4.28 106 2.46 73 25.3 132 37.5 135 22.0 129
FFV1MT [106]132.9 13.9 139 23.4 144 10.8 140 20.9 132 34.5 146 16.0 132 21.8 122 29.5 104 13.8 115 31.0 149 41.7 137 29.4 148 9.97 141 6.78 111 17.9 148 23.8 144 35.3 143 25.0 146 2.99 95 4.24 104 3.57 105 37.6 147 46.0 148 41.6 150
SILK [79]133.9 13.2 137 22.4 140 10.2 138 20.5 129 32.2 137 17.7 137 29.0 144 34.1 143 23.4 139 22.0 136 40.8 132 17.3 134 6.28 121 7.17 126 7.12 130 21.7 142 35.8 145 19.6 139 5.44 133 3.45 73 10.8 142 29.3 139 40.6 141 26.7 137
Adaptive flow [45]134.6 13.2 137 20.2 128 9.78 136 27.3 146 31.9 134 25.4 145 28.3 142 31.6 125 30.5 150 19.7 129 37.6 112 15.3 128 11.2 147 12.6 147 8.93 137 17.6 119 29.8 109 15.8 122 13.1 146 11.0 144 18.3 147 26.4 135 36.8 133 22.7 132
PGAM+LK [55]135.5 14.9 142 22.8 142 14.1 148 25.5 144 31.3 129 26.6 146 21.9 124 26.4 83 22.2 135 26.0 141 39.1 123 24.0 142 9.61 139 6.49 103 14.1 141 24.3 145 35.0 141 23.0 144 6.19 136 6.24 137 7.26 133 34.3 145 40.4 139 40.8 149
SLK [47]135.9 17.2 149 24.0 146 18.2 149 21.3 135 30.4 126 20.1 142 27.9 140 31.9 129 23.3 138 31.4 150 39.9 125 30.0 150 6.60 130 7.04 123 8.37 135 22.8 143 36.4 146 21.6 143 3.90 122 3.75 91 5.02 121 33.3 142 41.7 143 35.2 144
AVG_FLOW_ROB [142]139.9 32.4 151 34.1 151 37.7 151 35.1 150 33.7 142 37.0 150 20.7 109 24.1 63 19.4 126 34.1 151 35.1 89 34.8 151 39.6 150 37.0 150 44.9 150 40.6 151 42.2 150 38.5 151 11.3 144 15.3 146 7.36 134 46.5 151 52.3 151 38.9 146
Pyramid LK [2]143.2 17.0 148 20.4 129 19.4 150 31.7 147 32.1 136 32.5 147 32.9 149 34.8 146 29.9 149 29.4 147 35.3 93 29.9 149 31.7 149 35.5 149 29.8 149 29.9 149 32.3 129 28.0 149 9.01 141 7.93 142 18.9 148 39.9 149 45.4 147 39.0 147
FOLKI [16]144.0 16.2 145 25.9 149 12.7 146 32.5 148 35.6 148 34.7 148 29.4 147 35.1 147 26.9 148 29.1 145 41.0 134 27.9 146 9.58 138 8.90 138 13.5 139 25.7 146 38.3 148 24.5 145 7.71 140 5.13 128 14.5 145 36.5 146 44.4 146 36.1 145
Periodicity [78]148.4 18.0 150 30.5 150 12.3 145 34.0 149 41.4 151 35.6 149 36.5 151 36.5 149 35.2 151 29.7 148 46.6 151 26.8 145 51.8 151 56.5 151 45.5 151 36.7 150 42.4 151 37.1 150 5.99 135 6.16 136 19.3 149 40.1 150 51.1 150 40.4 148
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] ContFlow_ROB 0.45 all color Anonymous. Continual Flow. ROB 2018 submission.
[151] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
* 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.