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        
A95
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]10.0 7.47 3 40.1 11 3.98 3 6.49 13 30.3 3 5.60 17 5.82 4 26.1 3 4.68 16 3.86 10 53.5 6 2.99 20 9.77 1 12.4 1 5.36 3 8.67 5 31.8 3 7.03 3 5.10 22 10.1 57 3.70 12 2.31 10 5.34 11 1.21 2
NN-field [71]13.6 8.38 14 43.1 27 4.19 4 7.34 24 28.7 2 6.26 28 5.82 4 28.9 6 4.68 16 2.94 2 54.1 7 2.16 3 10.4 4 13.2 4 5.24 2 6.12 1 17.5 1 4.46 1 6.24 56 10.6 72 4.10 13 2.35 14 6.44 21 1.14 1
MDP-Flow2 [68]16.0 8.02 8 38.6 6 5.75 20 5.17 2 31.1 4 4.55 3 5.48 3 30.8 9 4.22 9 4.49 20 99.9 56 3.27 28 11.3 13 13.4 6 8.04 21 10.8 14 54.4 37 10.5 21 4.84 11 9.33 37 4.31 18 2.69 28 4.85 6 2.20 4
OFLAF [77]17.4 7.70 5 39.8 8 4.74 8 6.40 12 32.5 7 5.82 23 4.73 2 25.3 2 3.96 5 4.47 19 99.9 56 3.55 45 10.2 3 13.0 2 6.29 7 13.3 35 42.1 19 9.90 18 5.10 22 8.01 10 4.66 28 2.75 29 5.59 15 6.33 38
PMMST [114]18.5 8.63 17 31.3 1 6.03 26 8.51 38 26.8 1 8.18 63 7.50 12 28.0 5 6.07 36 4.26 17 34.8 4 3.29 29 10.9 8 13.2 4 6.26 6 10.4 12 29.9 2 9.42 13 5.00 18 10.1 57 4.37 19 3.25 39 4.40 5 3.36 13
nLayers [57]26.1 8.19 11 45.3 53 4.62 6 9.65 62 31.7 6 8.88 82 8.87 20 33.6 11 8.22 64 3.62 6 99.9 56 2.93 17 10.5 5 13.6 8 6.52 8 11.3 20 33.4 4 9.45 15 6.02 51 8.56 16 4.99 36 2.31 10 6.80 26 5.53 34
NNF-EAC [103]26.7 8.80 19 40.8 14 6.14 28 6.13 7 39.3 27 5.36 11 6.97 9 35.1 12 4.73 18 5.83 41 87.9 38 3.49 41 12.1 28 14.6 20 8.87 32 12.5 31 41.2 15 11.8 38 5.35 31 10.1 57 4.61 26 3.19 37 7.62 37 3.99 23
ComponentFusion [96]28.1 8.30 13 49.1 74 5.87 23 5.69 5 35.4 15 5.40 12 7.24 10 35.3 13 4.99 22 3.69 7 99.9 56 2.32 6 11.7 19 14.1 13 8.75 30 15.8 64 66.6 60 15.0 77 5.71 39 8.88 23 5.09 41 2.64 25 5.25 10 3.68 18
FC-2Layers-FF [74]30.2 8.26 12 41.4 18 6.27 29 8.85 42 37.9 22 7.81 47 6.02 7 31.8 10 6.25 39 3.91 12 88.8 41 2.86 15 11.0 11 13.7 10 7.20 10 16.5 72 40.4 11 16.3 91 7.14 76 10.7 76 6.61 65 2.15 3 3.87 1 2.77 6
FESL [72]30.8 7.69 4 40.2 12 4.90 9 11.0 83 48.5 55 9.07 85 10.5 29 42.1 26 6.42 41 3.60 5 99.9 56 2.55 9 10.9 8 13.6 8 8.86 31 11.1 18 36.4 6 10.6 22 6.73 70 10.2 61 5.95 53 2.51 22 5.37 13 3.35 12
LME [70]31.5 7.85 7 42.7 25 6.01 25 5.33 3 34.6 10 4.91 7 14.6 51 54.5 52 40.7 112 4.66 22 73.0 14 3.25 25 11.5 16 13.8 11 9.65 57 11.6 22 70.4 70 12.1 43 5.14 24 9.97 55 4.51 25 2.86 30 6.45 22 4.29 28
TC/T-Flow [76]31.7 9.01 22 38.1 4 3.81 1 6.64 15 55.1 77 4.62 4 8.13 15 46.4 39 4.20 8 5.32 34 99.9 56 2.88 16 11.5 16 14.1 13 7.28 12 8.85 6 38.5 9 9.44 14 5.85 46 10.7 76 10.0 107 3.61 47 10.0 53 8.53 71
HAST [109]32.9 6.42 1 43.9 36 3.97 2 7.16 19 33.1 8 5.92 25 3.76 1 23.5 1 2.83 1 3.36 3 99.9 56 2.08 2 10.0 2 13.0 2 4.83 1 16.7 77 59.3 44 19.4 110 11.3 121 12.9 107 17.6 131 2.67 27 4.13 3 2.93 9
WLIF-Flow [93]34.3 8.04 9 40.7 13 5.53 17 7.98 33 34.6 10 7.20 40 8.75 19 40.5 21 5.74 33 4.27 18 96.8 53 2.94 18 13.4 85 16.1 93 9.77 61 13.5 39 41.3 17 11.8 38 5.65 37 9.12 29 5.96 54 2.29 9 7.30 30 6.96 48
PMF [73]34.7 9.38 30 48.9 72 4.67 7 7.10 17 37.5 19 5.58 16 7.91 13 30.0 8 4.06 6 4.89 30 99.9 56 3.29 29 10.6 7 14.0 12 5.76 5 12.4 30 54.8 38 11.5 33 11.2 120 17.9 139 11.1 112 2.06 1 4.95 9 4.00 24
ALD-Flow [66]34.9 8.18 10 41.6 23 4.51 5 6.32 10 54.8 75 5.03 9 10.7 33 61.8 60 4.24 10 4.24 16 99.9 56 2.61 10 11.7 19 14.3 15 7.21 11 10.8 14 61.4 47 9.93 19 5.96 49 9.55 42 9.77 106 3.87 52 15.7 63 9.38 84
Layers++ [37]35.4 9.07 23 44.4 39 8.41 65 8.47 37 31.5 5 8.03 56 5.85 6 37.9 15 6.02 35 3.76 9 62.6 8 2.79 12 10.5 5 13.5 7 8.22 26 17.6 85 55.0 39 14.5 74 7.44 81 10.9 80 5.70 52 2.27 8 4.86 7 9.14 76
3DFlow [135]35.8 9.37 28 41.4 18 5.02 11 7.10 17 38.0 23 5.51 15 7.41 11 53.2 50 3.81 4 4.74 23 14.8 1 4.00 57 12.0 26 15.2 45 8.89 34 19.9 103 60.3 45 18.1 107 8.06 89 9.24 34 10.1 108 2.26 6 4.12 2 2.04 3
Efficient-NL [60]36.5 8.40 15 43.6 33 5.38 15 9.12 46 37.4 18 7.83 49 11.1 37 56.6 54 6.16 37 5.71 38 99.9 56 3.32 32 11.3 13 14.7 24 7.66 13 16.6 76 37.6 7 12.7 51 6.93 74 10.8 78 5.98 57 2.89 32 5.47 14 2.90 8
RNLOD-Flow [121]37.4 7.26 2 38.7 7 5.25 14 7.65 29 43.0 36 6.20 27 12.7 44 75.2 67 4.59 14 3.52 4 99.9 56 2.46 7 11.4 15 14.9 33 7.74 15 16.2 66 40.2 10 16.2 88 8.20 91 12.2 97 7.63 84 2.49 21 5.98 18 7.10 52
ProFlow_ROB [147]37.5 10.5 45 51.4 83 5.14 13 7.28 21 50.8 62 5.66 19 17.6 54 65.7 63 5.43 28 3.88 11 98.0 54 2.18 4 12.3 36 15.2 45 7.81 17 12.1 28 52.1 35 12.9 53 4.24 4 9.88 52 3.68 10 3.79 50 19.4 69 6.62 43
SVFilterOh [111]37.8 8.96 21 55.2 105 5.63 18 7.20 20 37.8 21 6.39 31 6.18 8 43.0 29 5.02 23 3.71 8 99.9 56 2.49 8 11.1 12 14.3 15 5.54 4 13.5 39 50.6 34 14.1 68 10.1 112 16.8 135 12.4 123 2.20 4 4.91 8 2.50 5
AGIF+OF [85]37.9 8.89 20 44.1 37 6.77 34 10.2 69 44.4 41 8.51 77 10.2 26 43.5 31 6.63 45 4.80 26 99.9 56 3.25 25 11.7 19 14.7 24 9.52 52 13.7 42 40.9 12 12.6 48 5.73 42 8.99 24 5.96 54 2.36 16 7.50 33 7.55 56
TC-Flow [46]38.3 8.59 16 41.0 16 5.12 12 5.47 4 45.6 45 4.31 2 10.2 26 94.7 82 3.49 2 6.08 47 99.9 56 3.50 42 11.9 24 14.5 18 7.90 19 11.9 27 61.7 49 11.5 33 5.72 40 9.85 50 11.5 117 4.02 55 15.0 61 9.14 76
IROF++ [58]40.4 9.29 27 45.0 51 6.30 30 9.55 58 43.0 36 8.20 64 10.8 34 43.1 30 7.57 56 6.28 52 99.9 56 3.90 52 12.2 32 14.8 29 9.41 50 15.2 61 44.1 28 14.5 74 5.27 26 9.48 40 3.69 11 2.62 24 6.48 23 4.14 25
PH-Flow [101]40.4 10.2 39 44.6 43 7.86 47 9.41 53 42.0 33 8.11 59 8.41 18 38.9 17 7.40 55 6.39 54 99.9 56 3.93 54 11.8 22 14.5 18 7.72 14 13.8 43 42.9 23 13.1 55 7.21 77 10.3 64 7.61 83 2.34 13 4.20 4 4.20 26
Correlation Flow [75]41.5 9.27 26 38.3 5 5.40 16 6.33 11 36.7 16 4.85 6 18.4 56 99.9 93 3.58 3 4.87 29 35.8 5 3.47 38 12.9 62 15.8 76 9.17 44 16.0 65 68.6 63 16.5 97 6.59 66 9.85 50 7.93 91 2.88 31 7.57 36 3.06 10
Classic+CPF [83]41.6 9.64 33 43.4 29 7.93 50 9.43 54 46.1 48 7.82 48 10.6 32 51.0 46 6.68 46 5.09 32 99.9 56 3.22 24 12.0 26 15.2 45 9.15 42 14.7 53 34.4 5 13.4 60 6.42 60 10.1 57 6.89 70 2.26 6 6.77 25 7.08 51
PWC-Net_ROB [148]42.7 17.5 97 49.3 77 9.65 88 9.55 58 42.8 34 8.41 69 19.6 58 46.1 38 10.6 71 6.18 51 74.3 15 3.39 35 12.4 39 15.4 57 8.92 35 11.8 25 45.5 29 11.5 33 4.32 6 9.79 46 2.49 3 3.08 34 6.38 20 2.86 7
JOF [141]43.5 8.67 18 45.9 55 6.43 31 10.3 71 48.5 55 8.94 84 8.37 17 39.4 19 7.19 50 4.81 27 99.9 56 2.79 12 11.9 24 14.6 20 8.03 20 13.9 46 43.0 24 10.8 23 9.32 105 11.4 87 11.3 116 2.21 5 7.25 28 7.07 50
CostFilter [40]44.3 10.5 45 46.8 64 6.98 38 7.51 26 38.1 24 6.31 30 9.22 21 29.7 7 4.74 19 5.86 43 99.9 56 3.97 56 10.9 8 14.3 15 6.77 9 13.4 36 56.1 40 12.3 45 11.6 124 20.5 143 14.2 125 2.12 2 8.52 43 6.71 45
OAR-Flow [125]46.0 11.1 52 48.8 71 5.85 21 9.88 64 82.9 116 6.47 32 27.3 77 99.9 93 8.06 60 6.75 60 99.9 56 2.80 14 12.4 39 15.1 43 8.20 25 10.3 10 58.1 42 8.37 9 4.07 2 8.06 12 5.45 49 4.81 65 9.74 52 6.36 39
ProbFlowFields [128]46.0 16.3 88 53.8 97 10.9 103 7.72 30 40.6 30 7.12 36 14.1 49 45.2 37 10.5 69 6.67 59 62.6 8 4.39 69 12.9 62 15.4 57 9.64 56 10.1 9 63.2 55 10.8 23 4.86 13 8.16 14 4.69 30 3.36 41 9.23 49 3.72 19
IIOF-NLDP [131]46.2 12.0 59 43.5 31 5.86 22 9.35 49 35.0 12 6.81 34 11.2 38 88.4 78 4.51 12 6.09 48 28.8 3 4.09 61 14.6 113 18.4 127 9.71 58 14.6 52 66.2 59 14.7 76 4.90 16 9.54 41 4.82 34 3.09 35 7.73 39 3.18 11
Sparse-NonSparse [56]47.0 9.96 34 44.2 38 8.85 73 9.39 52 50.6 61 8.08 58 10.1 25 43.7 33 7.21 51 6.10 49 88.2 39 3.41 36 12.5 45 15.5 67 8.96 36 16.3 68 41.9 18 16.2 88 6.48 62 9.05 26 6.27 61 2.33 12 7.33 31 7.76 64
MLDP_OF [89]47.4 11.8 58 41.7 24 8.40 64 6.97 16 35.2 14 5.88 24 11.3 41 65.3 62 5.23 26 4.76 25 99.9 56 3.09 21 12.2 32 14.8 29 8.87 32 13.4 36 48.1 31 17.2 104 10.0 111 10.9 80 18.1 132 3.58 46 8.07 42 4.53 32
LSM [39]47.8 10.0 37 42.9 26 8.48 66 9.36 51 49.6 59 7.99 53 10.5 29 43.6 32 6.80 47 5.80 39 88.6 40 3.38 34 12.5 45 15.4 57 9.03 38 16.5 72 42.3 21 16.3 91 6.94 75 9.84 47 6.71 66 2.42 19 7.96 41 7.72 61
Ramp [62]47.8 10.2 39 44.4 39 8.09 59 9.47 55 46.1 48 8.17 62 9.51 23 42.4 28 6.88 49 5.40 35 99.9 56 3.53 43 12.5 45 15.2 45 9.71 58 16.7 77 42.1 19 16.5 97 6.76 71 10.0 56 7.07 73 2.46 20 5.84 17 5.24 33
MDP-Flow [26]50.2 11.2 53 43.1 27 9.86 92 8.14 36 35.1 13 8.21 65 11.2 38 42.1 26 9.44 67 6.41 55 99.9 56 4.20 65 12.2 32 14.6 20 10.0 72 11.7 24 63.6 56 9.60 16 5.56 35 10.9 80 4.39 20 5.78 74 99.9 110 8.99 73
FMOF [94]51.1 9.17 24 43.6 33 8.04 56 10.0 67 48.1 52 8.48 75 8.35 16 38.3 16 6.49 43 5.08 31 99.9 56 3.45 37 12.6 51 15.4 57 9.19 45 18.1 91 41.2 15 15.5 82 6.67 69 10.6 72 7.47 80 3.00 33 16.1 64 7.74 62
Classic+NL [31]51.3 10.1 38 44.9 49 8.90 74 9.49 56 51.6 66 7.87 50 9.93 24 43.9 35 7.31 54 6.07 46 99.9 56 3.78 50 12.5 45 15.3 53 9.06 39 17.1 81 41.0 13 15.8 85 7.32 80 10.8 78 6.80 69 2.35 14 5.62 16 7.69 60
IROF-TV [53]51.7 10.4 43 44.5 42 8.16 60 9.69 63 51.1 65 8.44 70 12.6 43 46.8 40 7.27 53 6.80 61 87.5 37 3.93 54 13.0 68 15.7 72 10.4 77 18.3 93 86.9 102 13.7 64 4.44 7 7.40 5 3.05 6 2.60 23 7.55 35 7.56 57
TV-L1-MCT [64]52.0 9.57 31 44.7 45 8.66 69 10.9 82 48.1 52 9.11 86 11.8 42 58.1 56 6.61 44 4.74 23 99.9 56 3.34 33 12.9 62 15.2 45 9.89 66 17.8 89 47.8 30 16.0 87 5.28 27 8.09 13 7.71 85 3.33 40 7.26 29 7.53 55
CombBMOF [113]52.2 12.5 64 41.3 17 6.50 33 8.58 40 36.9 17 6.88 35 10.9 35 35.9 14 5.21 25 10.4 80 85.0 35 5.90 90 11.6 18 15.2 45 8.15 23 27.3 117 60.9 46 35.6 131 9.20 102 14.7 123 6.75 68 3.17 36 7.53 34 4.20 26
OFH [38]52.3 12.6 65 43.4 29 9.45 82 7.30 23 64.4 87 5.27 10 27.6 78 99.9 93 4.87 21 6.60 58 99.9 56 3.74 48 12.4 39 14.7 24 9.62 54 15.5 63 74.1 77 15.6 84 4.60 8 9.39 38 4.64 27 5.39 70 26.0 78 6.68 44
NL-TV-NCC [25]52.6 10.7 48 40.8 14 6.45 32 8.52 39 41.1 31 6.30 29 11.2 38 93.6 81 4.18 7 5.99 45 75.9 19 4.02 58 13.2 75 16.2 99 10.1 74 16.7 77 70.9 71 16.3 91 6.56 65 9.91 54 7.05 72 4.76 63 16.9 65 3.56 16
COFM [59]52.8 9.37 28 55.5 107 6.86 36 7.28 21 44.2 40 6.17 26 14.3 50 47.6 43 8.22 64 4.15 15 99.9 56 2.23 5 13.2 75 16.2 99 12.2 103 17.6 85 75.4 79 15.5 82 6.20 55 8.77 21 7.35 77 3.62 48 5.35 12 6.43 41
Adaptive [20]53.7 10.2 39 46.1 57 4.95 10 9.63 60 55.4 78 7.80 46 36.7 94 99.9 93 7.64 57 6.15 50 78.7 21 2.96 19 12.1 28 14.8 29 9.09 40 12.3 29 85.8 100 6.06 2 8.72 96 12.5 103 4.97 35 3.55 45 34.8 82 9.13 75
AggregFlow [97]55.0 13.2 67 62.1 128 6.79 35 14.9 95 73.1 97 10.6 94 26.8 76 55.1 53 20.5 96 5.48 36 99.9 56 3.67 46 12.5 45 15.0 37 7.76 16 8.55 4 38.2 8 8.90 11 5.78 43 10.6 72 4.74 32 5.43 71 8.53 44 7.58 58
S2F-IF [123]55.2 20.0 101 51.4 83 9.91 93 9.64 61 48.3 54 7.93 51 19.7 59 41.7 24 13.6 84 9.98 77 84.3 31 5.40 83 12.8 59 15.3 53 9.92 69 10.9 17 62.4 53 10.9 27 5.00 18 10.4 67 5.30 47 3.71 49 8.55 45 3.87 21
FlowFields+ [130]55.9 20.3 102 52.0 87 10.3 99 10.3 71 44.8 43 8.44 70 19.5 57 40.2 20 14.1 85 10.2 79 66.6 11 6.28 95 12.8 59 15.4 57 9.97 70 10.3 10 61.8 50 10.2 20 4.85 12 10.9 80 4.79 33 3.97 54 12.8 57 3.85 20
Sparse Occlusion [54]56.6 9.98 36 41.5 22 7.82 46 9.00 45 40.5 29 8.28 67 13.5 47 85.5 75 5.96 34 5.82 40 99.9 56 3.90 52 13.0 68 15.9 78 9.77 61 13.8 43 49.9 33 12.3 45 13.6 135 15.7 131 7.81 88 3.51 42 9.05 46 6.42 40
Complementary OF [21]56.8 13.6 71 46.2 58 9.35 79 6.20 8 50.4 60 4.92 8 12.8 45 58.8 58 5.45 29 7.89 68 99.9 56 5.59 85 12.3 36 14.6 20 9.99 71 18.9 98 69.9 67 14.3 72 5.44 32 7.80 7 7.78 87 6.13 78 26.9 79 9.66 92
S2D-Matching [84]56.9 9.96 34 53.0 93 8.51 67 9.53 57 53.0 68 7.94 52 20.5 61 99.9 93 6.80 47 5.30 33 83.0 24 3.53 43 12.4 39 15.2 45 9.16 43 17.3 82 41.1 14 16.8 102 7.75 85 10.5 70 7.90 90 2.36 16 6.34 19 9.58 89
RFlow [90]57.0 11.5 56 45.3 53 8.80 72 6.22 9 49.2 58 5.41 13 26.2 74 99.9 93 5.04 24 4.14 14 99.9 56 3.11 22 12.6 51 15.0 37 9.87 64 16.5 72 83.2 95 13.8 67 6.62 67 8.58 17 6.16 58 6.33 81 99.9 110 12.0 105
FlowFields [110]57.0 20.3 102 52.3 89 10.2 95 10.2 69 49.0 57 8.46 73 20.3 60 40.5 21 14.7 86 10.8 84 76.6 20 6.16 93 12.9 62 15.4 57 10.0 72 11.1 18 69.9 67 11.0 29 4.97 17 8.63 18 5.12 43 4.04 57 14.0 58 3.98 22
HBM-GC [105]58.0 10.9 50 57.5 116 7.03 40 9.35 49 40.2 28 8.80 80 8.09 14 52.3 48 6.42 41 6.91 63 84.3 31 6.17 94 11.8 22 14.7 24 8.40 27 14.7 53 43.2 25 12.6 48 9.81 110 17.8 138 8.50 97 3.54 44 10.1 54 10.1 96
2DHMM-SAS [92]58.3 10.3 42 44.8 47 8.03 55 10.5 77 52.4 67 8.21 65 21.6 63 97.4 87 8.20 63 6.88 62 99.9 56 3.86 51 12.4 39 15.0 37 9.87 64 17.7 87 43.3 26 15.9 86 6.81 72 10.2 61 7.15 76 2.65 26 7.68 38 7.29 53
Occlusion-TV-L1 [63]58.7 10.4 43 44.9 49 6.90 37 8.77 41 53.3 70 7.54 42 33.8 90 99.9 93 7.96 58 5.88 44 99.9 56 3.48 40 13.6 94 16.3 102 10.6 80 9.50 7 80.1 86 8.60 10 6.12 53 8.69 19 4.39 20 6.52 84 99.9 110 9.37 81
SimpleFlow [49]59.5 11.3 55 46.6 60 9.79 91 10.7 80 45.0 44 9.15 87 23.1 66 99.9 93 8.38 66 8.00 70 99.9 56 3.72 47 12.7 56 15.5 67 9.36 49 16.3 68 42.6 22 15.3 81 5.91 48 9.61 43 5.39 48 2.39 18 7.08 27 9.41 85
Aniso-Texture [82]59.6 7.75 6 40.0 10 5.87 23 7.36 25 41.5 32 7.19 39 41.3 104 99.9 93 6.22 38 2.73 1 65.4 10 1.92 1 12.9 62 15.3 53 10.1 74 29.2 119 99.9 117 16.5 97 11.8 127 14.9 127 8.22 94 3.80 51 12.6 56 8.58 72
ACK-Prior [27]60.4 10.7 48 37.9 3 7.90 49 6.01 6 38.5 25 4.80 5 10.2 26 41.5 23 4.35 11 4.56 21 99.9 56 3.75 49 13.2 75 15.9 78 11.3 91 27.3 117 82.2 89 23.1 117 11.6 124 14.9 127 16.2 129 6.43 82 15.5 62 6.11 36
EPPM w/o HM [88]60.8 15.3 83 41.4 18 8.08 58 7.60 27 33.9 9 5.66 19 13.0 46 47.0 41 5.57 30 8.73 74 99.9 56 4.81 78 12.6 51 15.7 72 10.8 84 18.6 95 62.9 54 16.4 95 11.9 130 12.5 103 17.2 130 3.20 38 7.49 32 6.00 35
PGM-C [120]60.8 20.6 105 54.2 100 9.59 86 10.1 68 60.8 82 8.47 74 22.3 65 44.3 36 14.8 88 10.7 83 99.9 56 4.15 63 13.1 73 15.4 57 9.90 67 11.8 25 64.6 58 12.0 42 4.86 13 7.96 8 5.01 38 4.78 64 14.4 59 7.01 49
ROF-ND [107]62.9 12.0 59 39.9 9 8.22 63 6.49 13 45.6 45 5.49 14 13.5 47 92.7 79 4.83 20 8.05 71 23.7 2 5.54 84 14.2 107 17.5 115 11.2 89 20.1 105 72.0 73 15.0 77 13.0 133 13.3 113 10.5 111 3.52 43 6.67 24 3.36 13
ComplOF-FED-GPU [35]63.8 13.2 67 44.7 45 7.95 51 9.18 47 82.6 115 5.63 18 15.3 52 58.5 57 5.67 31 7.59 66 99.9 56 4.68 74 12.3 36 14.8 29 9.20 46 18.2 92 83.8 96 16.4 95 7.54 83 9.84 47 11.1 112 5.44 72 31.6 81 7.74 62
CPM-Flow [116]65.3 20.6 105 54.3 101 9.58 84 10.3 71 62.5 85 8.50 76 21.9 64 43.8 34 14.7 86 10.6 82 99.9 56 4.06 59 13.2 75 15.4 57 9.85 63 12.6 32 68.9 64 13.3 57 5.02 20 9.16 32 5.04 40 5.27 67 19.2 67 9.63 91
EpicFlow [102]66.1 20.6 105 54.1 99 9.59 86 10.3 71 62.9 86 8.55 78 26.3 75 99.4 92 15.1 90 10.4 80 99.9 56 4.07 60 13.1 73 15.4 57 9.90 67 11.6 22 67.3 61 11.9 41 4.86 13 7.97 9 4.99 36 5.34 69 19.2 67 9.74 94
DMF_ROB [140]66.4 16.2 87 49.6 79 9.96 94 9.93 66 75.9 101 7.56 43 30.5 83 99.9 93 11.8 76 16.5 100 99.9 56 4.36 68 12.6 51 14.9 33 9.62 54 12.9 34 76.3 81 11.5 33 4.68 9 8.80 22 5.10 42 7.02 92 91.0 107 9.62 90
SRR-TVOF-NL [91]66.9 14.4 79 46.7 61 8.18 62 13.1 89 74.0 99 8.44 70 24.1 70 63.2 61 11.9 78 6.51 57 85.1 36 3.25 25 12.1 28 15.0 37 10.3 76 17.5 83 61.6 48 13.4 60 10.4 116 12.3 99 8.92 100 5.52 73 7.83 40 7.58 58
Steered-L1 [118]66.9 9.19 25 36.3 2 6.06 27 4.59 1 39.2 26 4.30 1 9.30 22 52.3 48 4.57 13 4.86 28 99.9 56 3.30 31 13.6 94 15.9 78 12.3 104 24.7 116 77.0 82 20.2 111 15.1 138 13.7 118 40.0 140 14.7 117 91.5 108 20.9 119
DeepFlow2 [108]67.1 14.3 76 47.4 67 7.03 40 10.4 75 77.1 103 8.01 54 23.3 67 99.9 93 11.8 76 16.1 96 99.9 56 4.41 70 12.4 39 15.0 37 8.16 24 13.4 36 68.4 62 14.2 69 5.65 37 9.07 28 8.50 97 8.52 100 92.9 109 10.6 100
TCOF [69]68.4 13.6 71 44.8 47 8.02 54 9.90 65 54.6 74 8.02 55 31.3 86 99.9 93 15.4 92 6.49 56 82.4 23 4.76 76 14.9 117 18.0 124 9.50 51 9.71 8 48.3 32 12.6 48 10.1 112 12.7 105 8.96 101 4.29 58 9.21 48 6.80 46
DPOF [18]69.4 17.4 96 49.1 74 7.77 45 12.3 85 45.6 45 8.91 83 10.9 35 26.6 4 8.09 61 7.81 67 99.3 55 5.31 80 13.5 90 16.0 89 11.0 87 17.5 83 61.8 50 12.2 44 13.1 134 10.9 80 18.1 132 5.04 66 9.50 51 4.49 30
F-TV-L1 [15]70.0 15.6 84 47.4 67 13.4 109 18.8 105 99.1 125 11.6 95 43.1 108 99.9 93 11.3 75 14.7 92 99.9 56 7.03 99 12.2 32 14.9 33 9.00 37 13.5 39 99.9 117 7.56 6 6.41 59 10.5 70 4.23 16 3.91 53 80.3 96 3.38 15
TF+OM [100]70.6 12.1 61 51.3 82 7.13 42 8.92 44 44.4 41 8.13 61 33.8 90 54.4 51 45.8 115 6.28 52 90.1 43 4.63 73 12.7 56 15.2 45 10.6 80 18.9 98 99.9 117 11.3 31 7.81 86 14.2 120 6.33 62 7.09 93 43.5 84 8.22 67
Aniso. Huber-L1 [22]70.8 11.7 57 43.8 35 8.16 60 13.6 91 66.3 89 12.0 97 35.9 92 99.9 93 10.5 69 10.0 78 72.9 13 5.00 79 13.4 85 16.3 102 9.61 53 15.1 59 63.7 57 7.96 7 8.96 99 11.6 91 7.95 92 4.02 55 26.9 79 7.97 66
LiteFlowNet [143]71.8 24.0 119 51.5 85 13.3 108 11.7 84 43.1 38 9.98 90 21.5 62 47.6 43 13.0 80 10.9 86 71.9 12 6.87 98 13.3 83 16.2 99 11.5 93 18.7 96 52.2 36 16.7 100 6.18 54 9.32 36 4.21 15 5.83 76 24.4 76 7.46 54
FF++_ROB [146]72.5 21.4 111 55.5 107 10.2 95 10.6 79 54.1 72 8.70 79 24.1 70 59.5 59 16.2 94 11.5 88 74.8 17 7.42 102 13.0 68 15.7 72 10.6 80 14.7 53 70.0 69 13.7 64 5.31 30 8.76 20 7.53 82 4.57 60 14.8 60 13.9 109
TV-L1-improved [17]73.8 10.9 50 45.2 52 7.42 43 8.12 34 54.0 71 6.79 33 36.5 93 99.9 93 7.26 52 5.84 42 99.9 56 3.15 23 13.2 75 15.9 78 9.11 41 22.1 109 99.9 117 20.8 112 9.59 108 13.3 113 9.04 102 6.19 79 88.8 103 9.71 93
SIOF [67]74.9 10.6 47 49.7 80 7.01 39 14.8 94 85.9 118 8.40 68 49.7 117 98.3 89 49.2 118 12.0 89 99.9 56 5.88 88 13.5 90 15.9 78 10.8 84 16.3 68 74.2 78 13.6 63 5.51 34 9.02 25 4.42 23 6.52 84 19.5 72 9.85 95
CRTflow [80]76.2 15.0 81 46.3 59 7.89 48 8.87 43 54.9 76 7.15 37 30.1 80 99.9 93 8.03 59 9.30 76 99.9 56 4.50 72 13.0 68 15.7 72 8.05 22 32.5 123 99.9 117 34.3 130 6.62 67 9.72 45 7.52 81 9.30 104 99.9 110 14.7 111
DeepFlow [86]76.5 14.7 80 49.0 73 9.78 90 12.9 87 79.3 107 9.80 89 30.1 80 96.1 85 24.4 101 21.4 108 99.9 56 5.36 82 12.5 45 15.1 43 8.59 28 14.0 47 71.9 72 15.1 80 5.46 33 8.01 10 8.73 99 14.2 115 99.9 110 15.7 115
Brox et al. [5]76.6 16.0 85 49.2 76 12.0 105 12.3 85 80.4 108 10.3 92 23.7 69 73.1 66 13.2 81 24.2 109 99.9 56 4.23 66 14.7 114 16.8 108 15.4 127 10.7 13 96.7 110 9.71 17 5.88 47 9.05 26 3.01 5 8.78 101 67.7 92 9.37 81
LocallyOriented [52]77.8 17.0 95 55.7 109 8.00 53 17.0 102 82.3 114 12.1 98 42.4 107 99.9 93 14.8 88 9.13 75 89.2 42 4.79 77 13.4 85 16.1 93 9.20 46 10.8 14 58.1 42 11.8 38 6.89 73 10.6 72 7.14 75 7.78 98 74.9 93 9.42 86
BriefMatch [124]78.9 9.63 32 44.4 39 5.74 19 7.64 28 51.0 63 5.70 21 10.5 29 39.2 18 4.63 15 3.95 13 99.9 56 2.72 11 16.2 129 17.6 119 33.0 141 41.4 135 99.4 116 43.4 137 12.7 132 13.2 111 67.6 144 79.5 135 99.9 110 99.9 141
Dynamic MRF [7]79.7 14.0 75 50.7 81 9.58 84 7.75 31 85.7 117 5.76 22 31.5 87 99.9 93 5.23 26 7.97 69 99.9 56 4.10 62 13.0 68 15.6 70 10.7 83 30.4 122 99.9 117 29.5 127 5.64 36 7.52 6 9.61 105 67.3 133 99.9 110 66.7 133
Classic++ [32]80.4 11.2 53 49.4 78 9.13 75 9.34 48 68.4 92 8.11 59 30.7 84 95.1 84 10.2 68 5.59 37 99.9 56 3.47 38 13.5 90 16.1 93 10.4 77 19.7 102 99.9 117 17.6 106 8.38 92 11.5 90 8.30 96 7.20 96 99.9 110 9.54 88
ResPWCR_ROB [145]82.8 23.4 117 46.7 61 16.7 119 14.7 93 42.9 35 13.2 100 23.4 68 48.7 45 22.0 99 16.4 99 84.5 33 11.3 114 13.2 75 15.8 76 12.6 109 15.2 61 72.1 74 16.3 91 9.13 101 12.3 99 7.37 78 7.09 93 17.6 66 9.31 80
Rannacher [23]82.8 13.8 74 47.5 69 10.8 102 10.5 77 62.0 84 8.84 81 41.1 103 99.9 93 11.0 73 8.49 72 99.9 56 4.28 67 13.5 90 16.1 93 9.72 60 22.5 111 99.9 117 17.0 103 7.66 84 9.88 52 7.82 89 4.72 62 75.1 94 9.37 81
SuperFlow [81]83.0 14.3 76 47.0 66 9.26 77 19.5 107 58.7 81 17.9 108 45.9 111 99.9 93 56.1 121 19.0 106 99.9 56 5.88 88 13.3 83 16.1 93 12.6 109 11.5 21 74.0 76 8.27 8 9.24 103 12.9 107 4.70 31 8.27 99 89.2 105 8.28 68
CBF [12]83.5 12.2 63 41.4 18 8.65 68 16.5 99 47.1 51 16.6 106 24.7 72 88.1 77 12.9 79 11.0 87 99.9 56 4.18 64 14.9 117 17.5 115 14.0 122 15.0 58 79.8 85 8.97 12 14.9 137 15.1 129 15.9 128 5.78 74 63.0 91 10.1 96
AugFNG_ROB [144]83.9 34.3 131 65.6 134 20.9 125 25.8 113 66.4 90 24.3 116 40.9 101 99.9 93 40.6 111 15.2 94 96.0 50 9.61 107 13.4 85 15.6 70 12.3 104 15.1 59 73.5 75 14.2 69 5.29 28 11.2 86 2.87 4 5.30 68 19.4 69 4.51 31
p-harmonic [29]84.2 15.1 82 48.5 70 14.1 111 10.4 75 53.1 69 9.31 88 41.9 105 99.9 93 15.1 90 19.4 107 99.9 56 10.6 110 12.7 56 14.9 33 11.8 95 18.0 90 85.6 99 18.4 109 7.85 87 10.4 67 5.46 50 6.98 91 99.9 110 9.28 79
Local-TV-L1 [65]85.0 16.5 90 52.3 89 11.7 104 27.7 115 96.9 122 22.5 114 68.8 125 99.9 93 47.5 116 34.6 119 99.9 56 7.04 100 12.6 51 15.0 37 9.25 48 17.7 87 84.7 97 13.7 64 5.09 21 7.36 4 5.03 39 20.7 120 88.8 103 29.4 125
CLG-TV [48]85.3 12.1 61 43.5 31 9.42 81 14.1 92 60.9 83 13.2 100 33.2 89 99.9 93 11.2 74 10.8 84 84.7 34 5.82 87 14.8 116 17.9 122 12.1 101 13.8 43 99.9 117 11.3 31 10.9 118 14.2 120 9.22 103 6.69 88 99.9 110 8.52 70
TriFlow [95]86.1 16.1 86 57.1 114 7.97 52 13.3 90 65.2 88 12.3 99 48.8 114 99.9 93 61.8 125 7.03 64 91.4 45 5.33 81 13.4 85 15.3 53 11.4 92 14.3 51 76.1 80 13.3 57 22.7 143 14.3 122 26.7 136 5.93 77 11.8 55 7.86 65
FlowNet2 [122]86.1 32.0 128 68.0 140 14.9 113 35.2 120 77.9 106 29.8 125 32.9 88 51.2 47 35.4 108 16.3 97 99.9 56 10.5 109 13.2 75 15.9 78 12.0 97 14.1 48 99.9 117 10.8 23 8.84 98 20.1 140 4.66 28 4.49 59 9.46 50 3.65 17
OFRF [134]86.8 13.1 66 58.6 120 9.77 89 49.6 133 99.9 126 43.7 134 49.2 115 99.9 93 32.0 106 16.3 97 96.4 51 10.0 108 12.1 28 14.7 24 7.87 18 14.9 57 43.6 27 13.3 57 8.66 95 12.0 96 11.8 120 21.9 123 19.7 73 36.6 127
DF-Auto [115]87.3 20.5 104 55.9 111 9.21 76 22.7 110 74.8 100 19.3 111 44.7 110 93.5 80 57.8 123 27.1 113 99.9 56 5.70 86 15.0 120 18.9 134 11.8 95 7.13 2 57.9 41 7.09 4 10.2 115 13.9 119 4.23 16 8.94 102 54.0 89 9.21 78
SegOF [10]87.4 22.8 116 54.8 102 15.4 115 27.9 116 56.0 79 27.4 120 39.3 97 87.9 76 33.2 107 37.5 120 75.4 18 22.3 120 14.4 111 16.3 102 14.7 125 21.7 107 99.9 117 24.5 120 4.09 3 7.28 2 2.18 2 6.79 89 48.3 87 6.93 47
EPMNet [133]87.8 29.4 125 62.1 128 16.4 118 36.2 121 95.3 121 29.0 124 30.2 82 47.4 42 30.9 105 18.3 103 99.9 56 11.1 112 13.2 75 15.9 78 12.0 97 14.1 48 99.9 117 10.8 23 8.19 90 16.9 136 4.18 14 6.63 87 19.4 69 6.18 37
TriangleFlow [30]88.6 13.2 67 46.8 64 9.41 80 10.8 81 73.2 98 7.30 41 26.1 73 99.9 93 5.70 32 7.23 65 99.9 56 4.46 71 17.0 134 21.3 139 15.2 126 23.0 112 69.8 66 22.9 116 9.71 109 16.1 132 9.40 104 6.89 90 23.8 74 11.5 103
Bartels [41]88.7 13.3 70 55.0 103 10.2 95 8.13 35 43.2 39 7.67 44 18.1 55 69.0 65 6.30 40 8.49 72 99.9 56 6.05 92 13.9 101 16.1 93 13.9 120 21.8 108 99.9 117 21.5 115 10.6 117 13.5 115 20.3 134 12.3 110 99.9 110 26.9 123
WOLF_ROB [149]89.7 21.5 112 55.2 105 10.2 95 37.6 123 99.9 126 17.3 107 54.7 120 99.9 93 23.9 100 25.1 110 99.9 56 12.8 115 12.8 59 15.4 57 11.2 89 18.5 94 61.8 50 17.2 104 5.80 45 9.26 35 6.20 60 11.4 108 24.3 75 15.7 115
Fusion [6]90.0 16.3 88 53.8 97 12.5 106 7.93 32 37.7 20 7.75 45 15.6 53 41.8 25 13.2 81 13.5 90 83.1 25 7.77 104 15.4 122 18.5 128 14.2 124 33.1 124 89.0 103 24.8 122 11.8 127 14.7 123 8.27 95 11.4 108 99.9 110 13.3 107
ContFlow_ROB [150]91.0 34.9 133 63.8 131 15.9 116 22.1 109 51.0 63 21.1 112 37.8 95 98.0 88 38.4 109 15.8 95 79.3 22 10.6 110 15.4 122 17.8 121 15.4 127 23.7 113 90.7 106 24.2 119 5.98 50 12.3 99 3.56 8 4.70 61 9.12 47 4.33 29
LFNet_ROB [151]92.3 28.9 124 53.4 95 17.2 120 15.3 97 46.9 50 13.7 103 31.0 85 96.3 86 21.7 98 18.4 104 92.1 46 14.4 117 13.7 99 16.6 106 12.0 97 18.8 97 90.4 105 16.7 100 6.48 62 10.9 80 5.97 56 6.22 80 99.9 110 10.3 98
CNN-flow-warp+ref [117]92.5 21.3 110 57.3 115 15.1 114 16.8 101 54.4 73 15.9 105 41.0 102 99.9 93 28.8 102 28.6 115 99.9 56 7.45 103 14.0 104 15.9 78 14.0 122 16.5 72 84.8 98 10.9 27 5.30 29 8.23 15 8.13 93 99.9 141 99.9 110 99.9 141
StereoFlow [44]93.8 48.0 141 74.6 149 41.1 142 61.0 138 99.9 126 51.6 137 71.4 126 99.9 93 63.9 127 65.6 135 99.9 56 61.2 135 16.2 129 15.9 78 22.6 135 7.22 3 77.8 84 7.39 5 3.38 1 7.35 3 1.99 1 7.18 95 99.9 110 11.4 102
LDOF [28]94.4 17.9 99 53.5 96 8.72 70 18.7 104 92.6 120 11.8 96 29.5 79 67.1 64 20.9 97 29.0 116 99.9 56 8.92 106 14.2 107 16.4 105 13.7 117 18.9 98 97.5 114 15.0 77 6.26 58 10.3 64 10.1 108 10.4 106 99.9 110 10.3 98
StereoOF-V1MT [119]94.9 16.5 90 46.0 56 9.27 78 18.9 106 99.9 126 7.16 38 40.5 99 99.9 93 8.18 62 14.7 92 96.4 51 6.30 96 14.1 106 16.8 108 12.9 112 29.9 120 91.4 107 27.0 125 5.78 43 10.4 67 10.4 110 99.9 141 99.9 110 99.9 141
Shiralkar [42]95.8 16.8 93 44.6 43 9.46 83 16.5 99 98.8 124 8.05 57 42.0 106 99.9 93 10.8 72 18.4 104 99.9 56 8.02 105 12.9 62 15.5 67 10.4 77 30.2 121 99.9 117 25.1 123 11.4 123 11.8 94 15.8 127 22.2 124 99.9 110 17.5 118
FlowNetS+ft+v [112]95.8 16.5 90 52.1 88 8.06 57 17.4 103 76.9 102 13.4 102 46.3 112 99.9 93 30.4 104 29.8 117 99.9 56 13.8 116 15.5 124 18.5 128 13.8 119 12.7 33 89.5 104 11.7 37 9.24 103 13.5 115 12.1 121 7.39 97 57.9 90 9.52 87
Learning Flow [11]96.3 13.7 73 52.8 91 7.67 44 12.9 87 87.1 119 10.0 91 40.5 99 95.0 83 13.4 83 38.1 121 99.9 56 4.74 75 17.1 136 21.7 140 12.5 108 24.2 115 99.9 117 13.5 62 7.95 88 12.7 105 6.98 71 23.9 126 99.9 110 14.9 112
Ad-TV-NDC [36]97.8 31.0 126 53.3 94 33.1 138 70.2 139 99.9 126 49.0 136 93.2 142 99.9 93 54.0 120 38.9 122 95.0 48 29.4 123 13.8 100 17.3 114 8.71 29 14.7 53 77.1 83 13.0 54 6.24 56 9.84 47 5.19 46 46.4 131 76.4 95 54.0 131
Second-order prior [8]98.4 14.3 76 46.7 61 8.79 71 15.2 96 72.5 96 10.5 93 39.2 96 99.9 93 16.6 95 17.5 101 99.9 56 6.01 91 14.4 111 17.5 115 10.8 84 38.6 133 99.9 117 24.7 121 11.3 121 12.2 97 11.2 114 9.13 103 89.5 106 15.6 114
Filter Flow [19]98.7 21.6 114 57.7 117 14.4 112 24.6 112 77.5 105 18.1 109 54.3 119 80.8 68 66.3 131 52.8 128 91.0 44 46.5 129 13.6 94 16.0 89 12.3 104 17.0 80 69.6 65 14.2 69 12.0 131 16.1 132 7.39 79 6.58 86 37.5 83 8.36 69
TVL1_ROB [139]99.7 31.2 127 59.9 125 29.1 134 48.6 132 99.9 126 41.9 132 91.6 141 99.9 93 71.5 134 52.0 127 99.9 56 44.1 128 14.2 107 16.9 110 12.0 97 14.2 50 99.9 117 13.2 56 4.83 10 9.14 31 3.56 8 21.0 121 99.9 110 22.5 121
GraphCuts [14]101.3 21.7 115 52.8 91 10.4 100 39.2 125 99.9 126 23.1 115 39.7 98 58.0 55 49.6 119 25.6 112 74.6 16 7.31 101 13.6 94 15.9 78 13.2 115 37.8 130 97.6 115 16.2 88 9.36 106 11.4 87 11.7 118 10.3 105 99.9 110 15.0 113
2D-CLG [1]102.2 46.1 139 67.5 139 28.2 133 39.5 126 77.3 104 38.9 128 93.9 144 99.9 93 74.9 138 53.6 129 99.9 56 51.0 131 13.9 101 15.9 78 13.5 116 24.0 114 99.9 117 21.2 113 4.28 5 7.24 1 4.50 24 12.7 111 99.9 110 11.6 104
HBpMotionGpu [43]102.7 19.5 100 63.6 130 13.5 110 31.0 117 99.9 126 27.4 120 99.9 147 99.9 93 59.3 124 18.2 102 99.9 56 6.69 97 13.6 94 16.0 89 12.4 107 16.2 66 91.5 108 11.1 30 11.1 119 13.0 110 6.73 67 21.3 122 99.9 110 21.6 120
IAOF2 [51]103.1 16.8 93 59.5 123 10.5 101 20.1 108 69.0 94 18.1 109 53.3 118 99.9 93 56.8 122 55.3 132 95.0 48 54.7 133 14.2 107 17.2 113 11.0 87 19.2 101 81.1 87 14.3 72 11.8 127 13.2 111 13.0 124 13.5 112 45.0 85 9.00 74
SPSA-learn [13]103.6 23.6 118 55.7 109 20.1 124 32.9 119 99.9 126 25.2 117 91.2 140 99.9 93 64.5 129 49.6 125 99.9 56 31.2 124 14.0 104 16.0 89 13.0 114 19.9 103 99.9 117 23.3 118 6.53 64 9.13 30 4.40 22 15.8 118 99.9 110 16.5 117
Modified CLG [34]105.4 27.9 122 58.6 120 23.4 128 26.5 114 71.1 95 26.2 119 93.4 143 99.9 93 73.1 136 49.2 124 99.9 56 22.6 121 15.2 121 18.1 125 13.7 117 16.3 68 99.9 117 12.8 52 6.43 61 10.2 61 11.7 118 11.3 107 99.9 110 11.3 101
UnFlow [129]106.8 49.8 142 69.9 146 23.3 127 32.8 118 57.8 80 33.0 126 49.4 116 98.6 90 39.8 110 53.6 129 99.9 56 52.1 132 16.2 129 18.5 128 20.6 132 35.3 127 99.9 117 38.4 133 8.81 97 11.4 87 3.08 7 6.46 83 99.9 110 6.47 42
IAOF [50]106.9 20.6 105 55.0 103 17.4 121 36.6 122 99.9 126 27.6 122 99.9 147 99.9 93 75.5 139 32.7 118 93.3 47 25.5 122 13.9 101 16.6 106 12.1 101 36.5 128 92.3 109 12.3 45 9.40 107 11.7 92 7.13 74 26.2 127 47.4 86 28.8 124
GroupFlow [9]109.5 27.3 121 66.8 137 21.6 126 41.1 127 99.9 126 35.1 127 71.4 126 99.9 93 61.8 125 25.1 110 99.9 56 14.4 117 14.7 114 17.9 122 11.7 94 40.6 134 97.2 113 40.6 135 5.72 40 11.7 92 6.48 63 16.4 119 53.8 88 23.0 122
Black & Anandan [4]109.9 21.5 112 51.7 86 19.8 123 38.6 124 99.9 126 25.8 118 81.3 130 99.9 93 65.5 130 50.4 126 99.9 56 31.6 125 15.5 124 19.1 135 12.8 111 22.4 110 96.8 112 18.2 108 10.1 112 12.4 102 5.16 45 13.9 114 99.9 110 12.9 106
Nguyen [33]110.5 27.2 120 56.2 112 18.7 122 46.7 131 99.9 126 44.1 135 97.7 146 99.9 93 74.1 137 45.7 123 99.9 56 38.0 126 16.4 132 17.7 120 21.8 134 20.8 106 99.9 117 21.2 113 7.21 77 9.42 39 5.61 51 14.6 116 99.9 110 14.2 110
2bit-BM-tele [98]113.6 20.8 109 59.0 122 16.3 117 16.4 98 68.5 93 15.3 104 43.9 109 99.9 93 15.4 92 14.6 91 99.9 56 11.2 113 15.6 126 17.5 115 16.8 130 34.9 126 99.9 117 31.1 128 18.8 141 20.4 142 30.8 137 23.7 125 99.9 110 61.9 132
BlockOverlap [61]115.5 17.6 98 56.5 113 13.1 107 24.0 111 66.9 91 21.5 113 67.6 124 99.9 93 49.0 117 28.2 114 99.9 56 15.2 119 17.6 138 18.3 126 32.7 140 38.1 131 81.6 88 26.6 124 14.5 136 15.5 130 67.6 144 39.8 129 82.5 97 84.7 134
Heeger++ [104]117.1 33.0 129 58.3 119 23.6 129 60.7 136 99.9 126 39.4 129 59.1 121 99.9 93 30.1 103 86.5 147 99.9 56 70.5 137 14.9 117 17.1 111 12.9 112 76.5 142 99.9 117 79.8 142 7.49 82 12.9 107 6.59 64 99.9 141 99.9 110 99.9 141
H+S_ROB [138]118.8 50.3 143 65.4 133 33.8 139 46.6 130 99.9 126 43.6 133 78.1 128 99.9 93 71.7 135 95.5 148 99.9 56 91.4 148 24.6 143 28.4 143 32.4 139 80.6 143 99.9 117 83.7 149 5.16 25 9.70 44 5.15 44 99.9 141 99.9 110 95.7 140
SILK [79]119.2 33.3 130 64.6 132 29.2 136 46.3 129 99.9 126 39.4 129 95.0 145 99.9 93 66.5 132 56.7 133 99.9 56 50.2 130 16.1 128 18.7 132 17.2 131 48.7 137 99.9 117 37.3 132 7.26 79 9.22 33 14.5 126 70.9 134 99.9 110 51.7 130
Horn & Schunck [3]119.5 28.8 123 57.7 117 25.3 130 41.1 127 99.9 126 28.2 123 80.0 129 99.9 93 75.9 140 75.5 136 99.9 56 66.3 136 15.7 127 18.5 128 13.9 120 41.9 136 99.9 117 41.4 136 11.6 124 13.6 117 6.16 58 45.4 130 99.9 110 39.5 128
TI-DOFE [24]121.6 40.2 135 61.2 127 38.6 141 60.2 135 99.9 126 53.7 138 90.4 139 99.9 93 78.2 142 83.9 145 99.9 56 82.8 146 16.6 133 19.4 137 16.4 129 38.1 131 99.9 117 38.7 134 8.51 94 10.3 64 7.75 86 56.3 132 99.9 110 49.7 129
HCIC-L [99]123.8 44.4 138 66.7 136 29.1 134 99.9 148 99.9 126 99.9 148 47.8 113 99.9 93 44.6 114 58.5 134 99.9 56 55.7 134 20.3 140 20.6 138 24.0 137 33.9 125 86.5 101 33.6 129 38.0 145 49.5 145 36.0 138 13.7 113 25.8 77 13.7 108
FFV1MT [106]126.2 36.4 134 71.0 147 25.8 131 50.3 134 99.9 126 39.7 131 65.6 123 99.1 91 41.6 113 99.9 149 99.9 56 97.4 150 20.2 139 19.3 136 33.1 142 62.5 139 99.9 117 71.1 141 9.04 100 14.8 125 11.2 114 99.9 141 99.9 110 99.9 141
SLK [47]126.8 53.1 144 66.3 135 59.5 150 60.9 137 98.1 123 58.6 139 89.7 137 99.9 93 67.7 133 99.9 149 99.9 56 95.1 149 17.0 134 18.8 133 23.5 136 56.6 138 99.9 117 51.2 138 8.43 93 11.9 95 12.2 122 99.9 141 99.9 110 99.9 141
PGAM+LK [55]127.9 43.6 136 67.1 138 43.7 143 73.8 140 99.9 126 77.5 140 61.9 122 82.9 74 63.9 127 76.6 137 99.9 56 72.5 138 17.1 136 17.1 111 31.6 138 66.2 140 99.9 117 64.8 140 18.9 142 20.3 141 22.1 135 99.9 141 99.9 110 99.9 141
Adaptive flow [45]128.1 34.4 132 59.7 124 29.7 137 84.5 146 99.9 126 77.7 141 87.6 136 99.9 93 92.8 149 54.9 131 99.9 56 39.3 127 20.6 141 23.8 142 20.9 133 37.5 129 96.7 110 29.2 126 35.2 144 30.1 144 58.6 143 38.1 128 99.9 110 33.0 126
AdaConv-v1 [126]128.8 66.7 146 69.5 141 54.6 144 80.0 141 82.0 109 79.5 142 81.7 131 82.0 69 80.9 143 82.3 139 83.1 25 82.6 141 85.8 144 85.9 144 85.2 144 88.2 145 83.0 90 82.9 144 75.7 147 67.1 147 77.8 147 85.1 136 86.4 98 84.8 135
SepConv-v1 [127]128.8 66.7 146 69.5 141 54.6 144 80.0 141 82.0 109 79.5 142 81.7 131 82.0 69 80.9 143 82.3 139 83.1 25 82.6 141 85.8 144 85.9 144 85.2 144 88.2 145 83.0 90 82.9 144 75.7 147 67.1 147 77.8 147 85.1 136 86.4 98 84.8 135
SuperSlomo [132]128.8 66.7 146 69.5 141 54.6 144 80.0 141 82.0 109 79.5 142 81.7 131 82.0 69 80.9 143 82.3 139 83.1 25 82.6 141 85.8 144 85.9 144 85.2 144 88.2 145 83.0 90 82.9 144 75.7 147 67.1 147 77.8 147 85.1 136 86.4 98 84.8 135
FGIK [136]128.8 66.7 146 69.5 141 54.6 144 80.0 141 82.0 109 79.5 142 81.7 131 82.0 69 80.9 143 82.3 139 83.1 25 82.6 141 85.8 144 85.9 144 85.2 144 88.2 145 83.0 90 82.9 144 75.7 147 67.1 147 77.8 147 85.1 136 86.4 98 84.8 135
CtxSyn [137]128.8 66.7 146 69.5 141 54.6 144 80.0 141 82.0 109 79.5 142 81.7 131 82.0 69 80.9 143 82.3 139 83.1 25 82.6 141 85.8 144 85.9 144 85.2 144 88.2 145 83.0 90 82.9 144 75.7 147 67.1 147 77.8 147 85.1 136 86.4 98 84.8 135
Periodicity [78]131.4 54.4 145 84.3 150 26.5 132 99.9 148 99.9 126 99.9 148 99.9 147 99.9 93 99.9 150 81.4 138 99.9 56 76.3 139 99.9 150 99.9 149 99.9 150 99.9 150 99.9 117 99.9 150 6.06 52 14.8 125 70.6 146 99.9 141 99.9 110 99.9 141
FOLKI [16]133.0 43.8 137 74.4 148 38.0 140 99.9 148 99.9 126 99.9 148 89.7 137 99.9 93 76.2 141 85.0 146 99.9 56 81.0 140 23.2 142 22.5 141 38.8 143 66.2 140 99.9 117 62.7 139 17.0 140 17.6 137 42.6 141 99.9 141 99.9 110 99.9 141
Pyramid LK [2]134.5 47.7 140 60.7 126 56.1 149 88.6 147 99.9 126 91.9 147 99.9 147 99.9 93 89.4 148 83.0 144 99.9 56 83.2 147 98.4 149 99.9 149 87.9 149 87.4 144 99.9 117 81.4 143 16.9 139 16.6 134 57.0 142 99.9 141 99.9 110 99.9 141
AVG_FLOW_ROB [142]137.9 99.9 151 99.9 151 99.9 151 99.9 148 99.9 126 99.9 148 99.9 147 99.9 93 99.9 150 99.9 149 99.9 56 99.9 151 99.9 150 99.9 149 99.9 150 99.9 150 99.9 117 99.9 150 48.6 146 52.0 146 38.2 139 99.9 141 99.9 110 99.9 141
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.