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        
R10.0
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]9.6 3.83 4 16.9 9 1.87 8 2.64 7 16.1 11 1.33 8 3.02 3 10.7 3 1.33 15 2.79 18 18.9 24 1.11 18 4.82 1 6.85 1 1.73 2 4.13 4 14.6 3 2.27 2 0.52 24 5.08 57 0.00 1 0.28 3 1.04 3 0.04 2
OFLAF [77]9.7 3.84 5 17.2 11 1.99 13 2.48 5 14.1 5 1.41 9 2.96 2 10.1 2 1.17 11 2.36 9 14.7 8 0.82 10 5.15 3 7.90 7 2.15 4 6.43 34 18.2 12 4.98 18 0.27 2 2.42 4 0.07 15 0.79 10 1.88 8 1.81 26
MDP-Flow2 [68]11.5 3.86 7 17.2 11 1.90 10 2.06 1 12.6 1 1.04 2 3.22 5 11.0 4 1.16 10 3.27 29 21.7 35 1.19 23 6.35 16 8.86 13 3.12 10 5.40 14 15.7 4 5.11 20 0.38 11 3.75 26 0.02 3 0.49 6 1.80 7 0.13 7
NN-field [71]13.6 4.31 17 18.6 23 2.22 22 3.13 16 18.3 25 1.79 19 3.16 4 11.1 5 1.40 16 2.08 6 16.7 12 0.78 8 5.28 4 7.44 3 2.25 5 2.53 1 8.92 1 0.92 1 0.89 48 6.39 81 0.02 3 0.27 2 0.98 2 0.04 2
PMMST [114]14.7 4.02 10 16.5 7 1.46 1 3.86 33 16.9 17 3.33 49 3.91 10 12.6 9 2.82 40 2.18 8 9.47 2 1.30 29 5.68 9 7.88 6 2.78 7 5.25 12 13.7 2 4.29 10 0.53 26 5.11 58 0.02 3 0.26 1 0.94 1 0.04 2
nLayers [57]24.4 4.08 13 16.2 5 2.80 41 4.71 58 19.3 33 3.82 77 4.64 20 15.2 20 3.96 62 1.99 4 13.2 3 0.80 9 5.34 6 7.57 5 3.22 12 5.85 27 16.8 7 4.64 13 0.87 46 3.68 24 0.96 60 0.84 11 2.94 18 0.75 11
LME [70]25.8 3.70 3 16.1 4 1.69 2 2.13 2 13.0 2 1.19 4 5.91 47 15.4 21 7.43 91 3.23 25 22.4 40 1.19 23 6.60 23 9.12 16 4.39 46 6.11 29 20.8 21 6.60 55 0.52 24 4.96 55 0.07 15 1.09 16 3.28 26 1.86 29
ComponentFusion [96]25.8 4.03 11 17.7 15 2.19 21 2.17 4 13.1 3 1.26 5 3.86 9 13.2 11 1.58 18 2.85 21 18.0 17 1.03 16 6.68 24 9.59 23 4.14 37 8.35 76 27.3 75 8.34 90 0.60 29 4.03 33 0.52 47 0.76 9 2.22 12 1.09 14
SVFilterOh [111]26.9 4.36 19 15.9 3 2.01 16 3.04 14 16.3 13 1.78 18 3.31 6 11.3 6 1.20 12 2.02 5 13.6 5 0.57 2 5.94 12 8.69 12 2.12 3 6.61 37 19.3 14 6.32 51 5.10 113 12.9 126 10.0 124 0.75 8 2.20 11 1.32 16
FC-2Layers-FF [74]27.4 4.03 11 16.3 6 2.39 30 4.23 42 20.9 43 3.21 45 3.40 8 11.4 7 2.64 34 2.74 15 17.1 14 1.03 16 5.73 10 8.29 10 3.31 14 7.49 52 20.5 20 6.66 59 1.30 65 6.84 87 0.34 41 0.64 7 1.78 6 1.20 15
NNF-EAC [103]27.6 4.32 18 18.6 23 2.18 20 2.69 8 15.1 7 1.64 14 3.93 11 13.1 10 1.27 13 4.17 63 23.0 49 1.95 59 7.09 36 9.97 31 3.89 32 6.33 32 17.4 9 5.53 23 0.55 27 5.18 59 0.02 3 1.60 41 4.32 43 1.93 32
HAST [109]30.0 2.98 1 12.9 1 1.71 3 3.63 29 15.0 6 2.78 37 2.46 1 8.38 1 0.25 1 2.84 20 18.0 17 0.67 4 5.02 2 7.35 2 1.66 1 8.83 86 22.4 36 8.37 91 6.13 119 12.0 121 18.0 132 0.31 4 1.13 4 0.03 1
WLIF-Flow [93]30.1 3.97 9 17.0 10 2.12 18 3.53 23 18.5 27 2.37 30 4.60 19 15.1 18 2.34 30 3.40 32 20.3 30 1.50 34 7.69 60 11.4 71 4.79 61 6.67 38 17.8 11 5.53 23 0.40 14 3.68 24 0.07 15 1.59 40 3.82 36 2.63 50
FESL [72]32.1 3.91 8 16.6 8 2.13 19 5.68 83 23.5 62 4.23 84 5.17 31 16.8 27 2.99 43 2.41 11 15.8 10 0.89 13 5.76 11 8.62 11 4.05 35 5.81 23 17.6 10 5.32 22 1.09 56 5.68 72 1.21 67 1.35 25 2.89 17 1.72 23
RNLOD-Flow [121]32.2 3.58 2 15.7 2 1.83 6 3.60 27 19.9 36 2.06 23 5.53 41 18.1 43 2.42 32 2.75 16 17.7 15 1.01 15 6.01 13 9.09 15 3.98 34 7.21 44 20.0 16 6.87 68 2.59 88 9.67 103 1.95 79 1.06 15 2.66 15 1.79 25
Layers++ [37]32.5 4.39 21 17.8 16 3.14 49 3.70 30 18.0 22 2.84 38 3.37 7 11.5 8 2.65 35 2.38 10 14.1 7 0.82 10 5.33 5 7.52 4 3.78 30 7.58 55 22.0 32 6.13 44 1.81 82 7.08 90 0.54 48 1.45 32 2.46 14 4.56 90
3DFlow [135]32.5 4.65 27 19.4 27 1.86 7 3.01 13 18.5 27 1.32 7 4.17 12 14.5 14 0.62 2 1.38 1 7.93 1 0.72 6 6.90 28 10.3 44 3.76 28 11.3 106 30.0 89 10.5 108 1.63 77 4.03 33 5.22 109 0.35 5 1.27 5 0.06 5
ALD-Flow [66]33.8 4.22 14 18.2 19 1.93 12 3.20 19 16.8 16 1.59 13 5.21 32 17.4 34 1.13 9 3.70 42 22.9 47 1.26 25 6.54 22 9.31 19 3.14 11 5.25 12 21.5 27 4.98 18 0.88 47 4.67 45 4.48 105 2.69 66 6.66 65 4.79 92
TC/T-Flow [76]34.5 4.57 25 20.6 32 2.00 14 3.45 22 18.7 29 1.52 11 4.30 14 14.3 13 0.67 4 3.97 58 23.1 50 1.80 50 6.35 16 9.50 22 3.36 17 4.48 6 15.7 4 4.78 15 1.30 65 6.94 88 5.07 108 2.08 56 5.10 53 2.83 56
PMF [73]35.2 4.65 27 18.3 22 2.34 25 3.37 20 18.2 24 1.92 21 4.20 13 14.6 16 1.01 7 3.24 27 18.6 21 1.11 18 5.50 7 8.09 8 2.43 6 6.99 41 24.8 56 6.27 49 6.87 122 17.3 137 8.77 123 0.91 12 2.06 9 2.06 35
Correlation Flow [75]36.0 4.57 25 20.5 31 1.87 8 2.71 9 16.2 12 1.16 3 5.74 45 17.9 41 0.66 3 1.91 2 13.5 4 0.85 12 8.00 70 12.0 81 4.57 50 8.69 80 23.8 47 8.93 96 0.84 43 4.74 47 0.96 60 1.38 28 3.81 35 1.91 31
AGIF+OF [85]36.0 4.39 21 18.0 18 2.80 41 5.10 70 23.7 65 3.70 71 5.06 27 16.8 27 3.11 44 3.29 30 20.1 28 1.45 33 6.45 19 9.31 19 4.62 52 6.77 40 19.7 15 5.86 33 0.37 10 3.60 20 0.25 35 1.79 48 3.68 32 3.12 66
Efficient-NL [60]36.2 4.24 15 17.4 13 2.24 23 4.30 43 21.8 46 2.75 35 5.26 35 16.9 29 2.67 36 3.43 34 21.0 32 1.74 45 6.02 14 9.16 17 3.31 14 7.84 64 21.7 29 6.26 47 1.36 68 6.79 86 1.03 63 1.48 35 3.08 21 1.77 24
TC-Flow [46]38.2 4.27 16 19.0 26 1.91 11 2.85 10 16.6 15 1.45 10 5.05 26 16.9 29 0.80 6 4.05 59 23.9 59 1.74 45 6.73 25 9.68 25 2.93 9 5.83 24 22.9 41 5.68 30 1.39 70 4.87 52 7.32 119 2.46 63 6.13 60 4.49 86
ProFlow_ROB [147]38.3 5.24 45 22.0 45 2.36 28 3.71 32 20.5 40 2.17 27 6.59 54 21.5 57 2.88 42 3.48 35 22.0 37 1.14 22 6.88 27 9.84 28 3.61 21 5.84 25 23.0 42 6.06 40 0.50 23 4.91 53 0.15 25 2.29 59 6.62 64 2.50 49
OAR-Flow [125]39.0 5.41 48 21.6 43 2.61 35 4.96 66 22.3 49 2.88 39 7.90 64 23.8 62 4.19 66 4.45 70 22.7 46 1.90 54 7.03 33 10.1 35 3.39 18 5.10 10 22.3 34 4.56 12 0.29 4 2.64 8 0.17 27 1.58 39 4.89 52 1.68 21
Classic+CPF [83]40.1 4.77 32 19.7 29 2.99 44 4.59 49 23.3 60 3.08 43 5.24 33 17.2 32 2.81 39 3.32 31 21.3 33 1.57 39 6.51 21 9.49 21 4.24 42 7.39 49 21.5 27 6.27 49 1.02 51 5.33 63 1.40 70 1.47 34 3.19 24 2.47 47
IROF++ [58]42.8 4.68 29 19.4 27 2.70 38 4.66 53 23.1 55 3.42 58 5.25 34 17.2 32 3.79 58 3.95 56 23.2 52 2.05 64 6.97 31 9.84 28 4.64 53 7.99 68 24.6 53 7.05 72 0.44 17 4.30 40 0.00 1 1.37 27 3.26 25 2.83 56
ProbFlowFields [128]42.8 8.29 87 31.1 85 5.73 103 3.54 24 18.0 22 2.75 35 6.07 50 18.9 48 5.22 69 3.54 38 17.7 15 1.91 55 7.66 59 10.8 56 4.59 51 5.06 9 20.0 16 5.58 27 0.38 11 3.08 14 0.07 15 1.70 45 4.56 48 2.41 46
COFM [59]43.0 4.75 31 20.2 30 2.63 37 3.40 21 18.3 25 2.14 25 6.19 51 19.3 49 4.00 63 3.04 23 18.8 22 1.11 18 7.45 49 10.1 35 7.01 93 8.80 84 20.9 22 6.68 60 1.41 71 3.66 23 2.76 91 1.22 19 2.28 13 3.72 76
PH-Flow [101]43.0 5.11 39 21.0 34 3.62 63 4.59 49 22.4 50 3.37 53 4.37 15 14.5 14 3.45 50 3.93 55 22.5 42 2.07 67 6.34 15 9.00 14 3.74 26 7.28 47 21.7 29 6.39 53 1.61 76 5.58 70 1.58 73 1.15 18 2.12 10 3.39 71
HBM-GC [105]43.5 5.82 55 18.2 19 2.00 14 4.47 47 18.7 29 3.80 76 4.39 16 15.1 18 1.73 22 2.42 12 13.8 6 0.72 6 6.77 26 9.60 24 4.08 36 7.61 57 19.0 13 5.76 31 4.61 109 12.6 123 2.83 93 2.39 61 5.72 56 5.01 96
PWC-Net_ROB [148]44.3 9.12 95 32.2 91 4.81 89 4.68 55 22.6 51 3.66 68 7.60 61 25.0 72 5.34 70 2.47 13 15.4 9 0.97 14 7.07 34 9.98 32 3.95 33 6.32 31 25.4 62 6.26 47 0.47 20 4.66 44 0.17 27 0.98 13 3.17 23 0.31 9
Sparse-NonSparse [56]44.8 4.98 35 20.8 33 4.09 72 4.63 52 22.9 52 3.41 57 5.02 25 16.7 26 3.47 53 3.89 51 22.6 45 1.91 55 7.17 39 10.2 39 4.30 44 7.66 59 22.3 34 6.80 64 0.69 35 3.53 19 0.89 57 1.52 37 3.56 31 2.97 62
CostFilter [40]45.4 5.29 46 22.0 45 2.85 43 3.54 24 17.7 20 2.16 26 4.64 20 16.0 22 1.75 23 3.68 41 22.5 42 1.27 27 5.67 8 8.14 9 2.85 8 7.76 61 25.9 64 6.80 64 6.98 125 24.2 142 12.9 127 1.43 29 4.11 39 2.02 34
MLDP_OF [89]46.1 6.35 63 26.0 64 3.41 54 2.97 12 16.4 14 1.76 17 5.47 39 17.8 39 1.30 14 2.79 18 19.7 26 1.12 21 7.13 38 10.0 33 3.75 27 7.49 52 21.4 26 9.75 102 5.04 111 6.22 78 17.0 131 1.79 48 4.28 42 2.14 37
LSM [39]46.7 5.00 37 21.2 40 3.93 69 4.62 51 22.9 52 3.37 53 5.13 29 17.1 31 3.26 47 3.80 46 22.9 47 1.87 52 6.92 29 9.78 26 4.41 48 7.71 60 22.4 36 6.74 62 1.00 50 4.76 49 1.16 65 1.68 44 3.94 37 2.90 60
Classic+NL [31]46.8 5.07 38 21.0 34 4.22 76 4.70 57 23.4 61 3.27 47 4.98 24 16.5 24 3.48 54 3.75 45 22.5 42 1.68 42 7.21 42 10.2 39 4.32 45 7.82 62 22.4 36 6.71 61 1.47 72 6.39 81 1.18 66 1.12 17 2.87 16 2.27 41
FMOF [94]46.9 4.42 23 17.8 16 3.06 47 5.03 67 23.1 55 3.63 66 4.45 18 14.8 17 2.80 38 2.94 22 18.8 22 1.26 25 7.00 32 10.2 39 4.71 56 8.92 87 20.9 22 7.13 74 1.06 54 6.34 80 1.85 78 2.58 65 5.80 58 3.06 64
JOF [141]47.1 4.36 19 18.2 19 2.55 33 5.21 75 23.2 57 4.14 81 4.40 17 14.2 12 3.37 49 3.66 40 21.4 34 1.95 59 6.49 20 9.25 18 3.76 28 7.05 43 21.0 24 5.58 27 4.19 106 8.20 95 6.97 117 1.84 52 4.37 44 2.92 61
Ramp [62]47.4 5.12 40 21.1 38 3.82 68 4.68 55 23.2 57 3.47 61 4.89 23 16.3 23 3.46 51 3.83 48 22.3 39 1.93 58 7.23 43 10.2 39 4.80 62 7.61 57 22.1 33 6.80 64 1.20 61 5.04 56 1.43 71 1.36 26 2.98 19 2.31 45
IIOF-NLDP [131]47.8 6.16 59 25.7 62 2.54 32 4.55 48 23.7 65 2.40 31 5.35 38 17.6 37 1.06 8 2.78 17 17.0 13 1.54 35 8.90 91 13.4 109 4.73 57 8.04 69 22.8 39 7.69 84 0.64 33 4.61 42 0.25 35 1.81 51 4.16 41 2.72 52
Aniso-Texture [82]49.3 3.84 5 17.5 14 1.76 4 2.88 11 15.9 9 2.11 24 7.10 60 20.9 54 2.30 26 1.97 3 16.5 11 0.57 2 8.24 76 11.9 78 5.22 75 8.82 85 26.6 72 6.77 63 8.34 131 16.2 136 1.43 71 2.42 62 5.55 54 2.84 58
S2D-Matching [84]49.5 4.97 34 21.3 42 3.55 60 4.74 59 23.6 63 3.35 51 6.50 53 20.9 54 3.46 51 3.49 36 20.4 31 1.60 40 7.07 34 10.0 33 4.22 40 7.82 62 23.1 43 6.87 68 1.78 81 5.90 75 2.12 81 1.30 22 3.14 22 2.74 53
NL-TV-NCC [25]49.6 5.44 49 21.7 44 2.24 23 4.00 37 21.9 47 1.69 15 5.27 36 17.8 39 0.67 4 2.52 14 19.1 25 0.67 4 8.37 80 12.5 91 5.12 74 11.5 108 32.0 100 9.19 98 0.86 44 4.93 54 1.35 69 2.16 57 6.46 61 1.63 18
MDP-Flow [26]50.8 5.65 53 24.7 59 4.93 91 3.70 30 17.6 19 3.40 56 5.47 39 18.7 47 4.66 67 3.87 49 24.3 62 1.88 53 7.12 37 9.89 30 5.00 72 6.17 30 25.9 64 4.66 14 0.61 30 5.65 71 0.05 12 3.28 80 8.39 80 3.45 74
TV-L1-MCT [64]51.0 4.69 30 18.9 25 3.60 62 5.64 82 25.6 79 4.21 82 5.53 41 18.1 43 3.23 45 3.04 23 19.9 27 1.35 30 7.49 50 10.6 49 4.91 68 8.34 74 22.8 39 7.50 83 0.79 42 2.61 6 3.57 99 1.73 47 3.45 29 3.26 69
AggregFlow [97]51.4 6.17 60 23.3 53 2.58 34 7.01 93 28.0 98 5.29 94 8.46 69 24.2 64 7.66 94 3.73 43 20.2 29 1.73 44 7.25 44 10.6 49 3.52 19 4.43 5 16.4 6 4.80 17 0.75 39 5.43 66 0.25 35 1.92 53 4.46 46 4.12 80
IROF-TV [53]51.9 5.22 43 22.6 51 3.59 61 4.80 61 24.2 71 3.73 75 5.71 44 18.4 46 3.64 56 4.19 64 25.7 76 1.92 57 7.63 58 10.7 53 5.26 76 9.22 91 30.2 90 6.60 55 0.30 6 2.86 10 0.02 3 1.32 24 3.76 34 2.27 41
CombBMOF [113]54.6 6.51 65 28.6 74 2.61 35 3.98 36 18.7 29 2.29 29 5.29 37 17.4 34 2.33 29 5.12 80 26.1 83 3.28 86 6.35 16 9.81 27 3.34 16 12.0 112 28.4 80 15.1 124 3.73 100 12.8 125 0.76 54 0.98 13 3.00 20 0.09 6
OFH [38]54.9 6.38 64 25.7 62 4.69 85 3.90 34 20.6 41 2.24 28 7.85 63 24.2 64 2.27 25 4.11 62 25.1 67 1.72 43 7.44 48 10.4 45 4.69 54 8.13 70 28.9 82 8.44 94 0.44 17 4.25 37 0.12 22 2.80 68 8.82 90 2.74 53
Adaptive [20]55.4 5.12 40 22.0 45 2.34 25 4.82 63 23.2 57 3.50 62 8.67 74 24.5 69 3.56 55 4.19 64 25.3 73 1.83 51 7.40 47 10.6 49 3.63 22 5.84 25 23.2 45 3.75 8 3.25 96 8.86 98 0.89 57 2.87 71 6.69 66 3.14 68
Sparse Occlusion [54]55.8 4.99 36 21.1 38 2.79 40 4.13 40 20.1 39 3.00 42 5.94 49 19.4 50 2.15 24 3.41 33 21.8 36 1.35 30 8.17 75 12.1 84 4.74 58 7.87 66 25.6 63 6.34 52 11.4 136 17.7 138 2.71 90 1.64 43 4.70 51 1.81 26
Occlusion-TV-L1 [63]55.8 5.23 44 22.2 48 2.36 28 4.40 45 21.2 44 3.39 55 8.46 69 24.8 70 3.83 60 3.92 53 24.8 64 1.74 45 9.11 94 13.1 105 5.75 82 4.65 7 23.9 48 3.52 6 1.27 64 3.13 15 0.44 44 3.56 88 8.92 91 3.28 70
RFlow [90]57.2 5.85 56 24.8 61 4.44 82 3.18 17 17.9 21 1.88 20 7.81 62 24.4 68 2.32 28 3.25 28 23.4 55 1.55 36 7.94 64 11.6 74 4.86 64 8.23 71 28.0 79 6.64 58 1.16 60 2.13 2 1.13 64 4.10 99 9.22 98 6.81 105
2DHMM-SAS [92]57.7 5.14 42 21.0 34 3.79 67 5.26 76 25.2 76 3.45 59 6.97 59 20.2 51 4.18 65 4.06 60 23.3 54 2.10 68 7.18 40 10.2 39 4.92 69 8.29 72 23.7 46 7.16 75 1.26 62 5.41 65 1.63 74 1.71 46 3.75 33 2.74 53
SimpleFlow [49]58.2 5.65 53 22.4 50 4.93 91 5.47 81 24.5 74 4.28 85 6.88 58 21.0 56 3.95 61 4.74 73 25.2 69 3.02 79 7.19 41 10.1 35 4.70 55 8.34 74 23.1 43 7.16 75 1.02 51 4.61 42 0.89 57 1.29 21 3.44 27 2.47 47
ACK-Prior [27]58.9 5.49 51 24.0 56 1.81 5 2.55 6 15.7 8 0.83 1 5.07 28 17.7 38 1.52 17 2.14 7 18.1 19 0.50 1 8.64 83 11.6 74 7.10 96 14.6 123 30.7 92 11.7 113 8.46 132 11.5 117 19.5 134 3.68 92 7.25 70 2.64 51
S2F-IF [123]60.4 9.49 100 37.6 106 4.93 91 4.81 62 25.6 79 3.34 50 8.25 67 26.1 74 6.40 79 4.99 77 25.6 75 2.93 77 7.80 61 11.0 61 4.90 67 5.61 17 24.9 59 5.83 32 0.62 32 5.35 64 0.22 32 1.43 29 4.11 39 1.67 20
Complementary OF [21]61.5 7.27 74 30.0 79 4.31 77 3.18 17 18.9 32 1.52 11 5.91 47 20.2 51 2.31 27 4.22 67 24.8 64 2.05 64 7.50 53 10.4 45 4.99 71 12.3 115 31.7 99 8.87 95 0.61 30 2.69 9 1.72 76 3.33 81 9.22 98 4.88 95
ROF-ND [107]62.7 6.70 66 27.6 70 3.53 58 3.08 15 16.0 10 1.73 16 5.81 46 18.3 45 1.58 18 3.81 47 18.4 20 2.20 69 9.45 99 14.0 120 6.31 89 11.3 106 29.6 87 7.27 79 9.92 134 10.8 108 7.29 118 1.53 38 3.44 27 1.64 19
TCOF [69]63.3 7.04 72 26.9 67 3.54 59 4.93 64 23.7 65 3.45 59 9.94 89 27.8 82 7.40 90 3.74 44 23.7 58 1.55 36 10.0 112 14.3 121 4.40 47 4.91 8 17.0 8 5.53 23 5.08 112 9.68 104 4.19 103 1.43 29 4.44 45 1.69 22
PGM-C [120]63.5 9.47 98 37.1 103 4.81 89 5.08 68 26.1 86 3.63 66 8.75 76 27.6 80 7.02 84 5.65 91 28.1 102 3.63 95 7.99 67 11.3 68 4.88 65 5.71 21 24.5 52 5.97 36 0.31 7 3.01 13 0.02 3 2.07 55 6.50 63 2.14 37
TF+OM [100]65.0 6.03 58 23.7 55 2.78 39 4.39 44 19.9 36 3.57 63 8.73 75 23.0 61 11.2 100 3.57 39 23.2 52 1.36 32 7.98 66 11.1 65 5.89 84 8.95 88 25.3 61 7.06 73 1.68 79 11.2 113 0.20 29 3.56 88 8.35 79 4.18 81
FlowFields [110]65.3 9.65 102 37.6 106 5.13 96 5.09 69 25.9 83 3.72 73 8.92 78 28.3 86 7.07 86 5.45 84 26.0 81 3.82 96 7.95 65 11.2 67 5.01 73 5.75 22 26.1 68 6.01 37 0.40 14 3.29 17 0.12 22 1.92 53 5.99 59 1.89 30
Steered-L1 [118]66.0 4.54 24 21.2 40 2.09 17 2.13 2 13.9 4 1.31 6 4.80 22 16.5 24 1.64 20 3.87 49 25.1 67 1.60 40 8.62 82 11.5 73 7.01 93 11.1 103 28.7 81 10.4 107 12.0 140 12.3 122 34.9 142 5.90 111 9.03 95 11.6 119
DMF_ROB [140]66.1 8.16 85 33.3 94 4.93 91 4.95 65 23.7 65 3.23 46 9.38 82 28.5 88 5.85 78 5.64 90 27.3 92 3.41 91 7.49 50 10.6 49 4.44 49 6.49 35 25.9 64 6.07 41 0.40 14 3.65 21 0.07 15 3.81 95 9.06 96 4.63 91
FlowFields+ [130]66.7 9.76 104 38.1 110 5.31 99 5.14 71 26.2 88 3.72 73 8.99 79 28.6 89 7.15 89 5.09 79 25.9 80 3.29 87 7.82 62 11.0 61 4.94 70 5.22 11 24.7 55 5.18 21 0.70 37 5.85 74 0.30 40 1.79 48 5.77 57 1.45 17
DeepFlow2 [108]67.0 6.80 68 28.5 73 2.99 44 5.20 74 22.9 52 3.60 65 8.88 77 26.2 75 5.75 75 5.76 93 26.8 90 3.41 91 7.34 46 10.7 53 3.58 20 5.86 28 24.8 56 6.22 46 1.02 51 3.78 28 3.08 97 4.35 102 9.84 103 5.80 100
EPPM w/o HM [88]67.3 8.62 91 33.5 95 3.62 63 3.58 26 19.7 34 1.93 22 6.19 51 20.5 53 1.64 20 4.64 72 25.2 69 2.54 72 7.60 57 10.4 45 5.81 83 11.2 104 31.6 97 9.82 103 6.91 124 8.93 99 15.9 130 1.48 35 4.06 38 2.01 33
CPM-Flow [116]67.4 9.47 98 37.1 103 4.79 87 5.15 72 26.3 89 3.67 69 8.59 73 27.1 78 7.00 83 5.59 88 27.8 99 3.57 93 7.99 67 11.3 68 4.74 58 5.70 20 24.1 50 6.05 39 0.48 21 4.29 39 0.02 3 2.76 67 7.63 74 4.11 79
EpicFlow [102]68.3 9.44 97 37.1 103 4.80 88 5.15 72 26.4 90 3.70 71 9.58 84 30.0 92 7.07 86 5.38 83 27.8 99 3.29 87 8.01 71 11.3 68 4.88 65 5.67 19 24.6 53 6.12 43 0.32 9 3.13 15 0.02 3 3.10 78 7.52 72 4.79 92
ComplOF-FED-GPU [35]70.0 6.96 70 30.7 82 3.33 52 4.74 59 24.9 75 2.66 33 6.71 56 22.4 58 2.45 33 4.44 69 26.2 84 2.05 64 7.50 53 10.7 53 4.20 39 9.78 93 34.0 108 9.47 100 2.42 87 4.74 47 6.63 115 3.09 76 9.17 97 3.91 78
SRR-TVOF-NL [91]71.0 7.45 78 28.6 74 3.09 48 6.20 86 26.1 86 3.90 78 9.82 87 28.4 87 5.78 76 3.96 57 23.5 56 1.55 36 7.55 55 10.8 56 5.27 77 9.21 90 26.7 73 7.25 78 5.74 116 11.5 117 4.01 101 1.30 22 3.49 30 2.19 40
F-TV-L1 [15]71.4 8.70 92 31.4 87 8.47 112 7.61 97 27.3 95 5.86 95 11.0 92 28.0 83 5.73 74 5.75 92 28.7 104 3.32 90 7.28 45 10.8 56 3.72 23 6.59 36 26.4 69 4.38 11 1.26 62 5.30 62 0.44 44 3.04 74 7.76 75 2.29 44
TV-L1-improved [17]72.2 5.52 52 23.4 54 3.42 55 4.13 40 20.8 42 2.96 40 8.29 68 24.2 64 3.64 56 4.06 60 24.4 63 1.77 48 8.34 79 12.1 84 4.15 38 13.7 119 38.4 121 14.9 121 4.40 108 10.1 106 2.14 82 3.33 81 8.42 81 3.40 72
SIOF [67]72.3 5.37 47 22.6 51 2.34 25 6.11 84 28.4 99 4.30 86 12.6 99 29.2 91 14.4 104 5.52 87 27.4 95 3.00 78 8.96 92 12.6 93 6.02 85 8.72 81 27.9 77 7.93 86 0.38 11 3.48 18 0.02 3 3.09 76 7.58 73 4.85 94
DPOF [18]73.0 9.01 94 34.7 97 3.68 66 6.16 85 25.4 78 4.32 87 5.55 43 17.9 41 3.36 48 3.92 53 25.3 73 2.00 62 8.14 74 11.0 61 6.05 86 10.5 98 27.9 77 8.16 88 9.33 133 6.19 77 21.0 136 1.46 33 4.57 49 0.80 12
Aniso. Huber-L1 [22]73.0 5.98 57 24.2 57 3.23 51 8.53 101 27.3 95 7.91 100 9.64 85 25.6 73 5.52 72 5.00 78 25.7 76 2.75 75 8.66 84 12.8 99 4.74 58 7.60 56 24.8 56 3.51 5 3.65 99 7.24 91 3.00 96 2.57 64 6.69 66 2.86 59
Classic++ [32]75.0 5.46 50 22.2 48 4.35 79 4.66 53 22.1 48 3.57 63 8.00 65 24.3 67 5.06 68 4.21 66 25.2 69 2.01 63 8.77 87 12.7 97 5.47 78 9.03 89 30.2 90 7.29 80 2.92 94 7.73 93 3.10 98 3.83 96 8.53 82 3.87 77
LocallyOriented [52]75.2 8.05 84 30.6 81 3.63 65 8.09 99 30.8 107 6.17 97 12.3 98 32.3 99 7.04 85 4.88 76 25.2 69 2.88 76 8.80 89 12.7 97 4.27 43 5.41 15 20.4 18 6.07 41 1.35 67 6.03 76 0.99 62 3.73 94 8.62 85 4.18 81
BriefMatch [124]75.8 4.78 33 21.0 34 2.40 31 4.00 37 19.8 35 2.68 34 5.13 29 17.5 36 2.41 31 3.23 25 22.1 38 1.28 28 9.81 107 12.0 81 13.1 131 17.2 126 33.8 105 17.8 128 7.84 127 12.7 124 22.3 137 8.01 123 10.5 109 16.1 130
DeepFlow [86]77.8 7.55 79 29.3 77 4.67 84 6.29 88 23.7 65 4.86 89 10.0 90 28.0 83 8.76 99 6.15 100 27.3 92 3.83 97 7.49 50 10.8 56 3.72 23 6.40 33 26.8 74 6.85 67 1.12 57 2.92 12 3.94 100 7.07 116 11.2 114 12.7 121
FF++_ROB [146]77.8 9.90 107 38.2 111 5.12 95 5.32 79 26.0 84 4.01 79 9.76 86 30.0 92 7.58 92 5.48 85 26.2 84 3.88 99 7.83 63 11.0 61 5.63 80 7.26 45 24.3 51 7.33 81 0.78 41 3.65 21 2.88 94 2.92 73 6.46 61 6.17 103
CRTflow [80]78.2 7.63 81 31.8 90 3.42 55 4.40 45 21.2 44 2.97 41 8.99 79 26.6 76 4.11 64 4.86 75 26.5 86 2.57 73 7.99 67 11.7 76 3.26 13 18.0 130 40.2 124 22.2 133 1.47 72 4.45 41 2.51 88 4.73 104 11.4 115 7.30 106
TriFlow [95]78.4 7.87 83 30.1 80 3.19 50 7.12 94 24.4 73 7.15 99 13.9 103 31.4 96 20.0 110 3.50 37 22.4 40 1.77 48 8.70 85 11.7 76 7.03 95 7.51 54 21.9 31 6.63 57 28.6 143 14.7 133 78.3 145 2.16 57 5.57 55 2.14 37
Rannacher [23]80.5 6.99 71 27.1 68 5.36 101 5.27 77 24.3 72 4.22 83 9.51 83 27.1 78 5.54 73 4.76 74 25.7 76 2.58 74 8.80 89 12.9 102 4.82 63 11.0 101 35.7 112 9.36 99 2.33 86 4.76 49 2.39 87 2.82 70 8.01 76 3.13 67
Brox et al. [5]80.6 8.32 88 32.6 92 6.95 106 6.23 87 26.9 94 5.23 92 9.13 81 27.6 80 6.55 81 5.85 95 28.2 103 3.26 84 10.2 114 12.9 102 11.0 125 5.43 16 29.3 86 4.79 16 0.86 44 4.00 31 0.12 22 4.32 100 10.2 106 4.54 89
Local-TV-L1 [65]81.1 9.60 101 30.8 83 7.89 111 12.7 110 30.2 106 13.3 110 15.9 110 32.3 99 17.3 107 6.19 101 28.0 101 3.84 98 7.55 55 10.9 60 4.22 40 7.48 51 26.4 69 6.02 38 0.28 3 1.87 1 0.15 25 9.10 125 10.8 111 20.5 131
Bartels [41]81.8 6.83 69 26.2 65 5.19 98 3.93 35 17.4 18 3.30 48 6.63 55 22.6 59 3.25 46 4.45 70 23.9 59 2.48 71 9.12 95 12.1 84 8.25 108 10.6 99 31.1 93 12.3 116 5.74 116 10.4 107 18.9 133 5.34 106 9.52 100 8.47 112
Dynamic MRF [7]81.8 7.74 82 31.6 89 4.44 82 4.12 39 23.6 63 2.47 32 8.49 71 28.0 83 2.83 41 4.25 68 27.4 95 2.41 70 8.61 81 12.0 81 6.08 87 14.5 122 43.2 128 14.9 121 0.64 33 2.35 3 4.51 106 9.85 128 15.6 131 15.3 128
SuperFlow [81]82.8 7.15 73 27.4 69 3.52 57 10.4 106 27.8 97 11.2 107 14.5 108 31.5 98 22.4 112 5.93 96 31.6 111 3.23 83 8.77 87 11.9 78 8.59 113 5.61 17 25.9 64 3.72 7 3.76 103 11.1 112 0.37 43 3.59 90 8.96 93 3.01 63
LiteFlowNet [143]84.1 15.0 115 50.3 127 7.15 107 6.37 89 25.8 82 4.98 90 11.5 95 36.2 110 6.96 82 5.48 85 23.1 50 3.06 82 9.02 93 12.3 89 7.10 96 11.7 111 33.8 105 9.65 101 0.44 17 4.00 31 0.20 29 3.07 75 6.97 69 4.52 88
CBF [12]87.1 6.32 61 26.2 65 3.35 53 11.1 107 25.6 79 13.7 111 8.51 72 24.1 63 7.12 88 5.12 80 26.0 81 3.04 81 10.3 115 13.6 114 9.59 121 7.85 65 26.4 69 4.25 9 11.8 137 13.8 128 14.2 129 3.54 87 8.06 77 5.32 98
OFRF [134]87.4 7.28 75 24.5 58 4.75 86 14.7 114 29.6 104 15.2 112 14.3 105 29.0 90 15.9 106 6.64 103 25.7 76 5.02 108 6.95 30 10.1 35 3.72 23 8.44 77 23.9 48 7.17 77 3.30 97 6.51 83 10.8 125 9.99 129 9.82 102 24.2 134
CLG-TV [48]88.1 6.33 62 24.7 59 4.13 73 9.08 104 26.6 91 9.31 106 9.85 88 26.8 77 5.82 77 5.30 82 26.5 86 3.03 80 10.4 117 14.6 125 7.57 101 7.95 67 31.1 93 6.51 54 5.92 118 11.4 114 4.36 104 3.41 84 8.81 89 3.06 64
TriangleFlow [30]88.9 7.35 76 28.2 72 4.31 77 5.35 80 25.2 76 3.36 52 8.00 65 24.8 70 2.70 37 3.90 52 24.1 61 1.97 61 12.9 132 17.8 138 10.7 123 13.1 117 32.3 102 13.9 119 4.71 110 16.1 135 4.04 102 3.65 91 8.73 87 5.69 99
DF-Auto [115]90.1 9.74 103 34.1 96 4.36 80 14.1 113 31.9 111 15.4 114 15.6 109 33.1 105 23.6 114 5.94 97 27.3 92 3.59 94 10.4 117 14.8 128 6.97 92 3.80 3 21.1 25 2.46 3 5.25 115 11.4 114 0.49 46 4.33 101 10.4 107 4.33 83
p-harmonic [29]90.7 8.47 89 36.3 101 7.17 108 5.27 77 24.1 70 4.39 88 11.2 94 31.4 96 8.13 98 7.18 107 32.4 113 5.24 109 8.04 72 11.1 65 6.89 91 9.82 94 36.4 115 10.6 109 2.61 89 5.51 68 0.54 48 4.07 98 9.01 94 4.34 84
CNN-flow-warp+ref [117]90.8 9.81 106 35.7 99 7.67 110 8.14 100 26.0 84 8.55 102 14.3 105 35.8 108 15.7 105 6.69 104 30.3 107 4.31 103 9.17 97 12.2 87 8.71 115 7.03 42 29.6 87 5.55 26 0.69 35 3.77 27 2.00 80 7.79 121 12.1 119 8.13 111
FlowNet2 [122]93.7 21.7 127 43.8 115 13.5 118 24.6 129 42.3 128 27.3 129 19.8 115 40.5 114 29.9 123 8.21 114 23.6 57 5.39 111 9.85 109 12.6 93 8.54 110 8.76 82 28.9 82 5.89 34 2.77 91 15.5 134 0.81 56 1.28 20 4.68 50 0.26 8
FlowNetS+ft+v [112]94.5 7.57 80 29.4 78 3.96 70 7.50 96 26.6 91 6.48 98 14.3 105 32.7 103 17.5 108 7.55 108 31.3 109 5.28 110 10.5 119 14.7 126 7.49 100 6.75 39 27.8 76 6.97 71 4.01 105 8.84 97 6.77 116 3.52 86 9.71 101 3.61 75
LDOF [28]96.0 8.22 86 31.4 87 4.08 71 7.64 98 29.4 101 5.87 96 10.7 91 30.3 94 7.99 97 7.80 111 36.8 120 4.86 107 9.14 96 12.4 90 8.24 107 8.58 78 32.0 100 8.38 92 1.75 80 5.26 61 5.02 107 5.52 108 12.9 123 6.04 102
SegOF [10]96.1 12.6 111 34.9 98 7.20 109 21.3 123 36.9 120 25.3 127 21.6 119 40.5 114 31.8 127 14.1 125 37.7 122 10.8 120 10.3 115 12.5 91 12.6 130 10.2 96 40.2 124 11.2 111 0.29 4 2.91 11 0.07 15 2.90 72 8.68 86 2.07 36
AugFNG_ROB [144]96.3 18.1 119 47.6 121 10.8 115 23.9 127 39.8 126 28.6 130 22.8 123 49.1 125 29.3 121 7.57 109 25.0 66 4.54 106 9.90 111 12.8 99 8.92 116 8.31 73 33.8 105 8.19 89 0.76 40 7.01 89 0.25 35 2.80 68 7.45 71 1.85 28
Fusion [6]96.4 8.51 90 37.6 106 6.69 105 3.62 28 20.0 38 3.08 43 6.82 57 22.6 59 6.47 80 5.78 94 31.3 109 4.29 102 11.2 127 14.7 126 10.6 122 14.0 120 35.2 110 15.0 123 7.88 128 14.3 131 2.22 83 5.35 107 11.0 112 8.56 113
EPMNet [133]97.5 21.3 126 48.9 125 14.5 121 23.2 126 44.2 130 25.1 126 18.8 114 37.9 112 28.4 119 8.92 117 27.5 98 5.90 114 9.85 109 12.6 93 8.54 110 8.76 82 28.9 82 5.89 34 1.98 83 11.4 114 0.59 50 2.36 60 8.59 84 0.63 10
WOLF_ROB [149]98.7 11.7 108 48.4 122 5.18 97 12.5 109 38.6 123 8.94 103 18.0 113 43.3 120 13.5 102 7.96 112 30.5 108 5.97 116 8.25 77 11.4 71 6.75 90 10.9 100 36.1 114 10.2 104 0.72 38 4.15 35 1.28 68 5.67 109 11.0 112 10.2 117
ResPWCR_ROB [145]98.7 18.8 120 53.9 130 13.5 118 8.80 102 29.4 101 8.15 101 12.6 99 36.0 109 12.1 101 7.61 110 32.2 112 5.71 113 8.07 73 10.4 45 8.08 104 9.68 92 34.5 109 10.3 105 3.74 102 9.01 100 1.82 77 3.35 83 8.20 78 4.45 85
Learning Flow [11]99.2 6.74 67 28.1 71 3.03 46 6.37 89 28.7 100 5.02 91 11.8 96 32.6 102 7.93 96 6.87 106 33.2 117 4.32 104 12.5 131 17.4 136 7.78 102 9.98 95 35.2 110 8.41 93 2.66 90 10.9 110 2.24 84 6.76 115 13.7 125 6.41 104
StereoFlow [44]101.1 58.0 145 76.4 145 63.7 142 51.8 144 66.9 145 48.3 140 51.0 145 73.0 144 41.6 137 63.5 144 83.4 145 56.7 142 13.3 134 13.7 115 19.1 137 3.63 2 20.4 18 2.73 4 0.26 1 2.49 5 0.05 12 4.06 97 8.57 83 5.81 101
Second-order prior [8]101.5 7.35 76 31.2 86 4.16 74 6.80 92 29.5 103 5.27 93 11.8 96 33.3 106 7.78 95 6.05 98 27.2 91 3.90 100 9.67 104 13.8 118 5.74 81 14.0 120 41.8 127 11.7 113 6.86 121 9.72 105 7.61 121 4.72 103 10.1 105 7.78 109
Ad-TV-NDC [36]102.0 21.2 125 36.8 102 34.1 136 25.9 131 38.5 122 29.9 131 23.5 125 41.0 116 27.1 115 13.3 122 32.4 113 13.3 125 8.75 86 13.2 106 3.82 31 7.43 50 25.1 60 6.92 70 1.50 74 4.84 51 0.34 41 17.1 139 15.9 135 37.2 143
ContFlow_ROB [150]102.1 23.4 129 49.2 126 13.8 120 16.7 118 33.7 114 18.3 118 22.2 120 47.7 124 27.9 117 8.46 115 26.6 88 5.51 112 12.2 129 15.8 132 11.8 127 15.8 125 37.4 117 16.2 127 1.12 57 9.28 102 0.22 32 1.63 42 4.47 47 0.82 13
HBpMotionGpu [43]102.9 11.7 108 32.8 93 6.34 104 18.9 120 35.4 118 22.0 123 22.3 121 42.7 119 31.1 126 5.62 89 26.7 89 3.31 89 9.47 100 13.0 104 8.55 112 8.68 79 31.2 95 5.58 27 6.88 123 11.9 119 0.64 51 7.67 120 11.4 115 15.2 126
StereoOF-V1MT [119]104.7 9.29 96 44.8 117 4.17 75 7.22 95 34.5 115 3.68 70 13.7 102 42.6 118 3.80 59 6.06 99 38.5 124 3.27 85 11.0 124 15.1 130 9.55 120 15.1 124 49.9 134 14.0 120 1.08 55 5.51 68 5.44 110 9.33 127 15.5 130 9.73 116
Shiralkar [42]104.8 9.76 104 46.6 119 4.40 81 6.53 91 31.3 109 4.04 80 12.7 101 37.5 111 5.34 70 6.47 102 32.9 116 4.34 105 8.33 78 11.9 78 5.58 79 17.4 129 43.3 130 15.5 125 6.82 120 8.77 96 14.0 128 7.36 118 15.7 134 7.83 110
LFNet_ROB [151]104.9 20.5 124 60.8 135 12.8 117 10.1 105 31.7 110 9.00 104 20.6 117 53.4 128 14.0 103 9.26 118 32.6 115 7.53 117 9.83 108 13.2 106 8.22 106 11.5 108 37.7 118 11.3 112 1.13 59 6.72 84 0.74 53 3.50 85 8.77 88 5.19 97
SPSA-learn [13]106.0 15.7 117 48.8 123 16.5 123 16.6 116 35.0 117 17.5 117 21.4 118 42.3 117 29.7 122 12.6 120 37.4 121 12.3 123 9.64 102 12.8 99 9.16 117 11.0 101 37.9 120 12.2 115 0.98 49 3.88 29 0.05 12 8.38 124 11.6 117 15.2 126
Filter Flow [19]108.1 14.6 113 38.2 111 8.96 114 12.4 108 34.6 116 11.3 108 20.2 116 38.3 113 30.1 124 19.2 127 43.4 128 18.6 128 10.0 112 13.4 109 9.43 119 10.3 97 31.4 96 9.08 97 8.21 130 19.6 139 0.79 55 3.72 93 6.85 68 3.41 73
Modified CLG [34]108.8 15.7 117 43.7 114 12.2 116 19.1 121 33.3 113 23.7 124 25.1 126 47.4 123 35.6 132 13.2 121 35.5 119 11.1 121 10.7 121 14.4 123 9.36 118 7.26 45 35.8 113 6.19 45 1.66 78 5.21 60 6.43 113 5.94 112 13.8 127 7.73 108
GraphCuts [14]109.4 12.6 111 36.1 100 5.46 102 14.7 114 39.4 125 12.5 109 17.8 112 35.6 107 29.1 120 6.86 105 33.7 118 4.15 101 9.33 98 12.6 93 8.69 114 23.0 135 31.6 97 15.5 125 3.52 98 7.38 92 11.7 126 5.33 105 9.87 104 8.75 114
IAOF2 [51]109.5 8.72 93 30.9 84 5.32 100 13.9 112 31.1 108 15.4 114 14.1 104 33.0 104 18.2 109 30.8 136 42.2 127 36.4 138 9.74 106 13.8 118 6.09 88 12.0 112 33.4 103 7.96 87 7.92 129 13.9 129 7.49 120 5.69 110 10.6 110 4.51 87
2D-CLG [1]110.3 24.4 130 51.8 129 19.4 127 27.4 132 38.7 124 33.8 134 34.6 133 57.7 132 42.2 139 33.4 138 57.1 139 32.9 137 9.64 102 12.2 87 11.0 125 11.2 104 40.2 124 12.8 117 0.31 7 2.62 7 0.25 35 6.33 113 13.7 125 7.33 107
TVL1_ROB [139]111.2 36.9 137 55.3 131 54.3 141 36.5 136 40.3 127 46.0 138 36.6 135 59.4 135 43.5 142 30.0 135 49.3 132 31.8 135 9.70 105 13.7 115 7.19 99 7.34 48 33.4 103 7.88 85 0.56 28 3.98 30 0.10 21 15.1 136 15.9 135 33.3 141
BlockOverlap [61]112.9 12.3 110 29.2 76 8.49 113 13.7 111 29.6 104 15.3 113 16.2 111 32.5 101 20.0 110 8.87 116 27.4 95 7.62 118 10.9 123 13.4 109 12.5 129 13.3 118 29.1 85 10.3 105 11.8 137 14.4 132 23.8 138 10.6 130 8.92 91 24.8 135
IAOF [50]115.2 14.7 114 37.8 109 14.8 122 17.3 119 33.2 112 18.7 119 22.7 122 44.3 121 23.3 113 20.9 129 38.7 125 24.5 132 9.60 101 13.3 108 8.28 109 13.0 116 38.8 122 7.37 82 4.20 107 7.90 94 2.59 89 14.5 135 13.4 124 32.0 140
Black & Anandan [4]116.7 15.1 116 45.4 118 18.1 126 16.6 116 36.3 119 16.9 116 23.3 124 44.9 122 27.8 116 13.5 123 38.1 123 13.1 124 11.1 126 15.7 131 7.97 103 11.6 110 39.6 123 11.0 110 5.17 114 9.06 101 2.27 85 7.28 117 12.3 120 10.2 117
2bit-BM-tele [98]116.8 20.3 123 39.1 113 26.1 131 8.84 103 26.8 93 9.29 105 11.1 93 30.7 95 7.60 93 8.06 113 29.9 106 5.91 115 11.0 124 13.7 115 11.8 127 18.0 130 37.1 116 19.8 132 17.1 141 20.4 141 30.8 141 6.54 114 11.7 118 11.8 120
UnFlow [129]118.2 45.7 142 58.8 132 25.7 130 28.2 133 44.0 129 31.2 133 38.6 140 68.3 142 37.0 134 19.4 128 46.0 129 16.6 127 13.8 136 14.9 129 18.2 136 20.9 133 49.2 133 23.5 134 2.86 92 6.76 85 0.22 32 3.12 79 10.4 107 2.27 41
GroupFlow [9]118.7 22.9 128 47.1 120 26.7 134 28.4 134 50.0 136 30.8 132 25.4 127 52.4 127 30.6 125 9.32 119 29.6 105 8.14 119 10.7 121 13.4 109 7.16 98 23.0 135 46.3 131 27.8 138 1.56 75 5.72 73 2.76 91 8.00 122 12.5 121 15.3 128
Nguyen [33]119.0 20.0 122 44.7 116 17.4 125 39.5 140 37.5 121 52.5 141 34.0 132 56.0 131 38.8 135 35.6 139 47.9 131 41.1 139 12.1 128 14.3 121 16.5 134 12.0 112 37.8 119 13.8 118 1.37 69 4.27 38 0.71 52 11.6 133 14.5 129 20.8 132
SILK [79]124.6 26.9 131 51.7 128 36.6 138 22.3 125 45.5 132 24.5 125 28.8 128 54.7 130 34.2 128 18.4 126 41.6 126 15.8 126 13.1 133 16.5 133 16.1 133 19.1 132 47.8 132 19.3 131 2.87 93 4.22 36 6.53 114 15.9 137 19.1 137 25.8 136
Heeger++ [104]125.8 42.8 140 66.4 144 26.2 132 25.0 130 60.7 144 19.8 122 38.4 139 66.9 139 28.0 118 23.5 131 49.3 132 19.7 129 10.6 120 13.4 109 8.12 105 40.8 143 67.2 145 45.1 143 2.04 85 10.9 110 1.70 75 11.2 131 15.6 131 12.8 122
H+S_ROB [138]127.0 35.2 135 65.0 141 26.4 133 38.8 139 57.8 143 44.7 137 46.2 144 74.1 145 43.1 141 64.3 145 66.9 142 69.3 144 17.9 141 19.2 141 29.2 143 30.3 141 59.6 142 34.1 140 0.49 22 4.67 45 0.20 29 22.3 143 23.4 140 21.4 133
Horn & Schunck [3]127.3 19.9 121 61.0 137 23.3 128 19.4 122 44.3 131 19.1 120 29.5 129 58.8 134 34.9 130 21.0 130 49.9 134 21.2 130 12.3 130 16.5 133 10.8 124 17.3 128 50.6 136 18.0 129 7.23 126 11.9 119 2.34 86 13.4 134 22.2 139 14.9 125
Periodicity [78]131.3 30.6 134 48.8 123 16.7 124 24.1 128 49.8 134 26.2 128 39.1 141 54.5 129 39.5 136 13.6 124 47.1 130 12.0 122 37.5 145 48.2 145 33.6 144 38.5 142 66.9 144 36.0 142 2.02 84 10.8 108 8.18 122 20.8 140 35.9 144 30.1 138
FFV1MT [106]132.0 39.5 138 59.3 133 25.4 129 21.8 124 56.3 142 19.1 120 38.0 138 67.0 140 34.9 130 24.3 132 55.7 138 22.2 131 17.7 140 18.9 140 25.5 141 41.8 144 66.3 143 45.5 144 3.73 100 12.9 126 6.35 112 11.2 131 15.6 131 12.8 122
TI-DOFE [24]132.4 44.7 141 66.3 143 66.5 144 44.2 142 50.5 137 54.8 143 43.5 143 72.0 143 44.7 143 48.6 141 63.3 140 54.0 141 13.6 135 17.7 137 15.1 132 17.2 126 50.3 135 19.0 130 3.07 95 5.50 67 2.93 95 21.5 141 24.7 142 33.9 142
SLK [47]133.7 28.9 133 63.3 140 36.4 137 42.3 141 54.0 141 52.8 142 36.6 135 67.7 141 42.5 140 51.4 142 54.3 137 60.0 143 14.5 138 16.7 135 20.8 139 21.5 134 53.4 140 24.1 135 3.92 104 6.27 79 5.91 111 21.7 142 23.7 141 31.5 139
Adaptive flow [45]136.5 49.6 143 62.1 138 66.8 145 37.4 137 46.5 133 43.1 136 34.9 134 58.6 133 41.7 138 27.3 134 53.5 136 28.7 133 16.1 139 18.2 139 17.6 135 25.3 139 52.9 138 25.1 137 45.4 144 38.1 144 74.4 143 9.25 126 14.4 128 13.9 124
PGAM+LK [55]137.1 35.2 135 65.7 142 44.1 140 31.5 135 51.1 138 36.1 135 30.9 130 60.0 137 36.8 133 33.0 137 72.3 144 32.7 136 13.8 136 14.4 123 22.6 140 24.6 137 53.2 139 24.6 136 27.1 142 32.6 143 26.2 139 17.0 138 20.4 138 28.4 137
FOLKI [16]137.4 27.4 132 59.9 134 40.6 139 37.4 137 51.5 139 46.6 139 32.4 131 61.6 138 34.2 128 26.3 133 50.6 135 30.2 134 18.2 143 19.7 142 26.3 142 24.6 137 56.6 141 28.8 139 10.3 135 13.9 129 26.7 140 27.1 144 26.9 143 45.3 144
HCIC-L [99]137.9 51.6 144 60.9 136 30.9 135 58.4 145 53.4 140 73.0 145 39.8 142 50.8 126 52.8 145 63.4 143 71.0 143 69.9 145 18.1 142 20.6 143 20.5 138 29.9 140 43.2 128 34.1 140 73.0 145 62.0 145 76.4 144 7.45 119 12.5 121 8.87 115
Pyramid LK [2]141.2 41.0 139 62.5 139 66.4 143 47.2 143 49.9 135 59.7 144 37.5 137 59.5 136 45.5 144 43.8 140 65.1 141 49.5 140 36.5 144 43.8 144 42.6 145 43.3 145 52.8 137 45.9 145 11.8 137 20.2 140 20.7 135 40.0 145 46.5 145 59.5 145
AVG_FLOW_ROB [142]146.2 99.3 146 98.3 151 99.2 146 99.8 146 100.0 146 99.7 146 99.9 146 99.9 146 99.9 146 98.3 146 96.8 146 98.0 146 96.2 146 96.6 146 93.9 146 87.7 146 86.6 146 88.2 146 96.9 146 84.2 146 98.7 146 93.0 146 98.4 146 95.3 146
AdaConv-v1 [126]146.8 99.3 146 97.8 146 99.8 147 99.9 147 100.0 146 99.8 147 99.9 146 99.9 146 99.9 146 99.5 147 99.9 147 99.9 147 99.9 147 99.9 147 99.9 147 99.1 147 98.9 147 99.7 147 98.5 147 93.0 147 100.0 147 99.9 147 99.9 147 99.9 147
SepConv-v1 [127]146.8 99.3 146 97.8 146 99.8 147 99.9 147 100.0 146 99.8 147 99.9 146 99.9 146 99.9 146 99.5 147 99.9 147 99.9 147 99.9 147 99.9 147 99.9 147 99.1 147 98.9 147 99.7 147 98.5 147 93.0 147 100.0 147 99.9 147 99.9 147 99.9 147
SuperSlomo [132]146.8 99.3 146 97.8 146 99.8 147 99.9 147 100.0 146 99.8 147 99.9 146 99.9 146 99.9 146 99.5 147 99.9 147 99.9 147 99.9 147 99.9 147 99.9 147 99.1 147 98.9 147 99.7 147 98.5 147 93.0 147 100.0 147 99.9 147 99.9 147 99.9 147
FGIK [136]146.8 99.3 146 97.8 146 99.8 147 99.9 147 100.0 146 99.8 147 99.9 146 99.9 146 99.9 146 99.5 147 99.9 147 99.9 147 99.9 147 99.9 147 99.9 147 99.1 147 98.9 147 99.7 147 98.5 147 93.0 147 100.0 147 99.9 147 99.9 147 99.9 147
CtxSyn [137]146.8 99.3 146 97.8 146 99.8 147 99.9 147 100.0 146 99.8 147 99.9 146 99.9 146 99.9 146 99.5 147 99.9 147 99.9 147 99.9 147 99.9 147 99.9 147 99.1 147 98.9 147 99.7 147 98.5 147 93.0 147 100.0 147 99.9 147 99.9 147 99.9 147
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.