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        
A75
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]16.0 2.17 4 5.35 5 1.92 4 1.56 5 6.39 19 1.67 10 1.51 7 3.67 8 1.61 8 1.20 36 4.36 17 1.02 37 2.30 4 3.18 3 1.73 7 2.16 39 6.35 8 2.39 65 2.54 24 4.18 12 2.17 31 0.81 9 1.50 17 0.67 4
NN-field [71]16.6 2.31 8 5.94 13 1.98 5 1.83 22 7.21 37 1.97 29 1.54 9 3.55 7 1.68 12 0.96 10 3.04 4 0.75 6 2.30 4 3.25 4 1.69 5 1.72 18 3.81 1 1.65 7 3.12 55 4.76 53 2.60 55 0.79 6 1.58 26 0.59 2
TC/T-Flow [76]19.8 2.06 1 7.42 30 1.55 1 1.61 11 6.77 28 1.52 3 1.46 5 4.33 18 1.56 5 0.88 3 6.96 44 0.69 2 2.91 20 4.35 26 1.88 11 1.47 5 6.12 7 1.61 6 2.22 7 3.98 4 4.00 99 1.06 41 1.99 45 1.19 52
ComponentFusion [96]20.0 2.12 3 6.18 16 1.80 3 1.67 14 4.82 4 1.91 24 1.34 2 4.01 11 1.47 3 0.88 3 4.74 18 0.72 4 2.99 24 4.35 26 1.96 14 2.03 31 11.2 75 1.96 27 2.90 46 4.62 47 1.90 18 0.93 26 1.56 25 0.89 16
ProFlow_ROB [147]20.2 2.44 11 7.85 39 2.01 6 1.54 3 7.07 33 1.55 4 1.53 8 7.16 55 1.43 2 0.81 1 5.26 25 0.67 1 3.48 42 4.95 47 1.69 5 1.46 4 8.54 34 1.53 4 1.92 3 4.48 32 2.01 22 0.93 26 2.14 51 0.94 26
ALD-Flow [66]23.0 2.26 6 5.81 10 2.07 7 1.56 5 5.71 13 1.66 8 1.46 5 4.64 24 1.66 11 0.95 9 7.15 48 0.80 12 3.18 34 4.57 36 1.76 8 1.51 6 7.63 20 1.60 5 2.61 27 4.27 17 3.90 95 1.04 38 2.22 58 1.18 49
WLIF-Flow [93]23.3 2.63 20 5.51 6 2.41 18 2.14 44 7.08 34 2.32 43 1.63 12 4.19 14 1.84 19 1.05 16 4.21 14 0.88 24 2.92 22 4.37 28 2.30 33 2.02 30 7.21 16 1.89 23 2.73 35 4.27 17 2.78 64 0.84 11 1.37 6 0.83 11
nLayers [57]24.5 2.33 9 5.14 3 2.17 10 2.75 92 7.22 39 3.07 94 1.69 21 4.04 12 2.21 64 0.88 3 2.83 2 0.70 3 2.08 2 3.25 4 1.30 1 1.88 21 6.06 6 1.85 14 2.89 45 4.59 42 2.28 36 0.92 23 1.48 15 0.94 26
OFLAF [77]24.9 2.77 36 5.70 8 2.49 20 1.76 17 5.35 9 1.84 21 1.54 9 2.69 2 1.72 14 1.30 41 3.55 10 1.12 51 2.30 4 3.62 7 1.64 4 2.23 45 5.93 3 2.06 37 2.81 39 4.29 20 2.99 70 1.15 50 1.69 31 1.18 49
MDP-Flow2 [68]25.3 3.08 41 6.23 17 2.73 45 1.55 4 4.80 3 1.64 7 1.63 12 3.27 4 1.61 8 1.37 52 5.15 23 1.15 56 2.91 20 4.19 20 2.20 21 2.24 47 6.43 9 2.17 47 2.62 28 4.35 24 1.88 17 1.08 43 1.66 30 0.95 30
RNLOD-Flow [121]26.1 2.19 5 4.96 2 2.19 11 1.79 19 7.20 36 1.76 16 1.42 3 4.31 16 1.56 5 0.97 11 3.42 9 0.84 17 2.75 15 4.16 17 2.01 16 1.86 20 7.24 17 1.95 26 4.02 94 6.41 110 4.48 114 0.90 18 1.51 18 0.85 12
OAR-Flow [125]27.1 2.55 14 7.57 32 2.36 15 1.81 20 7.94 45 1.94 28 1.72 28 8.40 61 1.95 27 0.94 8 5.90 35 0.79 9 3.49 44 4.83 45 1.84 10 1.16 2 7.84 25 1.22 2 1.93 4 3.63 1 2.26 34 1.10 46 2.16 54 1.34 61
AGIF+OF [85]28.5 2.60 15 6.24 18 2.45 19 2.49 72 9.30 67 2.63 71 1.68 19 4.79 30 2.08 48 1.05 16 4.34 16 0.81 13 2.77 17 4.05 14 2.10 19 1.92 24 7.48 19 1.74 12 2.69 32 4.48 32 2.69 61 0.87 12 1.40 7 0.95 30
Layers++ [37]28.7 2.70 31 6.40 20 2.83 52 2.33 61 6.62 25 2.54 68 1.65 16 3.24 3 2.02 37 0.92 6 2.48 1 0.75 6 2.12 3 3.11 1 1.50 3 2.06 34 8.25 28 1.94 25 3.59 79 5.41 79 3.21 73 0.89 15 1.32 4 0.90 19
LME [70]29.7 2.90 38 5.83 11 2.30 14 1.60 8 4.45 2 1.74 15 1.71 25 4.14 13 2.00 33 1.35 47 6.61 39 1.13 52 3.07 29 4.32 25 2.57 45 2.08 36 8.09 27 2.00 33 2.78 38 4.53 38 2.29 37 1.06 41 1.74 33 0.96 34
HAST [109]30.8 2.09 2 4.28 1 1.69 2 1.60 8 5.31 8 1.55 4 1.28 1 2.09 1 1.40 1 0.92 6 3.39 7 0.78 8 2.01 1 3.14 2 1.48 2 2.40 60 8.62 36 2.41 67 4.08 96 7.33 131 7.69 133 1.23 57 1.59 28 1.73 78
TC-Flow [46]31.1 2.45 12 6.60 22 2.39 17 1.25 1 5.24 6 1.32 1 1.45 4 4.40 21 1.50 4 1.15 33 8.13 55 1.04 39 3.22 35 4.77 43 2.06 18 1.94 25 8.65 37 2.09 41 2.33 18 4.51 35 3.82 93 1.24 58 2.18 56 1.50 73
PH-Flow [101]32.6 2.62 17 7.58 34 2.53 26 2.13 41 8.78 54 2.37 47 1.70 22 4.39 20 2.06 44 1.08 19 7.06 47 0.85 18 2.72 12 3.91 11 2.04 17 2.06 34 8.33 29 1.96 27 3.48 74 4.62 47 4.03 100 0.90 18 1.41 10 0.88 14
NNF-EAC [103]32.8 3.07 40 6.73 24 2.70 44 1.62 13 5.30 7 1.72 13 1.71 25 3.89 10 1.79 16 1.36 50 6.36 38 1.15 56 3.02 25 4.37 28 2.28 31 2.44 63 6.90 12 2.28 59 2.90 46 4.51 35 2.19 32 1.12 47 1.83 38 0.98 36
Classic+CPF [83]33.0 2.65 26 7.22 29 2.53 26 2.37 63 9.14 64 2.51 64 1.67 18 5.05 34 2.03 39 1.01 12 5.38 27 0.79 9 2.90 19 4.17 18 2.33 35 1.88 21 8.44 31 1.70 9 3.19 58 4.60 44 3.72 86 0.92 23 1.40 7 0.95 30
Sparse-NonSparse [56]33.1 2.62 17 7.58 34 2.60 34 2.18 50 8.74 52 2.46 60 1.68 19 4.86 31 2.00 33 1.04 14 7.97 53 0.81 13 3.13 31 4.45 32 2.42 40 1.98 28 8.53 33 1.87 18 3.13 56 4.32 23 3.51 80 0.88 13 1.41 10 0.91 20
FC-2Layers-FF [74]33.4 2.63 20 5.87 12 2.68 42 2.19 54 8.07 47 2.39 51 1.65 16 3.42 5 2.05 41 1.10 25 3.11 5 0.88 24 2.57 7 3.49 6 2.30 33 2.26 50 7.68 22 2.17 47 3.70 82 5.18 73 3.73 87 0.90 18 1.41 10 0.93 24
IROF++ [58]33.7 2.66 27 6.82 25 2.58 32 2.17 48 9.07 61 2.41 53 1.75 34 5.03 33 2.06 44 1.11 27 7.65 50 0.90 30 2.92 22 4.18 19 2.25 28 2.13 37 9.85 55 1.98 30 2.53 23 4.53 38 1.43 5 0.97 35 1.58 26 0.94 26
COFM [59]36.0 2.28 7 7.19 27 2.08 9 1.78 18 6.57 22 1.93 26 1.56 11 5.33 39 2.19 62 0.86 2 4.90 19 0.73 5 3.76 54 4.80 44 3.87 93 2.03 31 7.67 21 1.72 10 2.76 36 4.21 13 4.04 102 1.62 83 1.87 40 2.04 90
FESL [72]36.3 2.63 20 5.15 4 2.77 49 2.62 85 9.27 66 2.73 78 1.72 28 4.77 28 2.07 47 1.15 33 3.36 6 0.98 35 2.75 15 3.93 12 2.20 21 1.95 26 7.12 14 1.98 30 3.40 69 5.71 91 2.89 66 0.88 13 1.55 22 0.87 13
JOF [141]36.3 2.52 13 6.01 15 2.37 16 2.40 67 9.13 63 2.66 73 1.63 12 3.82 9 2.17 61 1.02 13 5.46 30 0.79 9 2.69 11 3.93 12 2.24 25 2.16 39 8.05 26 2.20 49 3.97 92 5.74 92 5.45 120 0.82 10 1.33 5 0.82 10
Efficient-NL [60]37.0 2.38 10 5.67 7 2.07 7 2.45 71 8.54 49 2.55 69 1.64 15 4.63 23 1.95 27 1.04 14 5.76 33 0.81 13 2.74 13 4.14 16 1.94 13 2.87 77 8.58 35 2.23 52 3.30 64 5.12 70 3.05 71 1.15 50 1.83 38 1.19 52
PMMST [114]38.0 3.55 63 6.48 21 3.33 73 2.18 50 6.49 21 2.47 63 1.93 46 4.28 15 2.09 49 1.60 71 2.84 3 1.43 78 2.60 8 3.72 9 1.91 12 2.22 44 6.05 5 2.13 45 2.70 34 4.48 32 2.08 26 1.18 56 1.91 42 1.09 45
LSM [39]38.6 2.60 15 7.70 38 2.61 36 2.19 54 8.77 53 2.44 58 1.70 22 4.78 29 2.06 44 1.08 19 8.13 55 0.86 20 3.05 27 4.30 23 2.47 41 2.18 42 8.66 40 2.08 39 3.56 77 4.68 52 3.74 88 0.90 18 1.43 13 0.93 24
Classic+NL [31]39.8 2.63 20 7.57 32 2.64 39 2.18 50 9.04 59 2.41 53 1.71 25 4.70 25 2.09 49 1.08 19 7.69 51 0.88 24 3.04 26 4.31 24 2.41 39 2.27 51 8.65 37 2.09 41 3.79 86 5.12 70 3.81 91 0.89 15 1.44 14 0.89 16
FMOF [94]40.3 2.71 33 6.71 23 2.62 38 2.64 86 9.19 65 2.77 79 1.73 31 4.37 19 2.22 65 1.06 18 5.18 24 0.81 13 2.89 18 4.25 22 2.40 38 2.31 53 7.76 24 1.96 27 3.35 67 4.88 64 3.81 91 0.93 26 1.55 22 0.92 22
Ramp [62]40.5 2.64 25 7.64 37 2.56 30 2.20 57 8.90 57 2.46 60 1.73 31 4.74 27 2.09 49 1.11 27 6.81 43 0.88 24 3.07 29 4.46 33 2.38 37 2.28 52 8.52 32 2.15 46 3.40 69 4.25 14 4.16 109 0.94 29 1.53 20 0.97 35
ProbFlowFields [128]41.3 3.31 51 13.8 87 2.85 54 2.03 33 6.67 27 2.23 38 1.89 44 6.06 45 2.29 69 1.23 38 5.14 22 0.95 33 3.70 50 5.08 49 2.29 32 1.60 10 7.44 18 1.85 14 2.43 22 4.30 21 2.45 47 1.29 62 2.32 60 1.38 65
2DHMM-SAS [92]43.2 2.62 17 7.61 36 2.53 26 2.17 48 10.1 76 2.38 49 1.83 39 6.16 48 2.10 53 1.09 23 8.07 54 0.86 20 3.06 28 4.42 31 2.37 36 2.16 39 9.30 46 2.01 34 3.50 75 4.64 49 4.14 108 0.96 33 1.64 29 0.99 39
Adaptive [20]43.5 2.63 20 8.08 43 2.23 12 2.18 50 8.66 51 2.27 41 2.04 55 9.57 68 2.09 49 1.12 30 10.6 74 0.87 22 4.47 98 5.30 66 4.44 109 1.55 7 8.65 37 1.43 3 3.32 65 5.51 81 2.14 30 0.77 5 1.52 19 0.75 8
SVFilterOh [111]44.3 3.48 60 5.72 9 3.45 78 2.38 65 6.06 16 2.41 53 1.93 46 3.46 6 2.05 41 1.53 67 3.71 11 1.27 66 2.65 10 4.10 15 2.00 15 2.47 65 7.08 13 2.28 59 4.60 107 7.10 124 5.92 125 0.73 4 1.16 2 0.70 7
PMF [73]44.9 3.22 49 6.34 19 2.60 34 1.95 29 6.66 26 1.92 25 1.85 40 4.58 22 1.83 18 1.62 72 4.27 15 1.37 72 2.61 9 3.74 10 1.83 9 3.18 86 9.94 58 3.34 91 5.29 123 8.26 137 5.58 124 0.68 3 1.21 3 0.67 4
TV-L1-MCT [64]45.6 2.68 29 6.83 26 2.61 36 2.68 87 10.3 79 2.80 83 1.78 36 5.24 36 2.24 66 1.13 31 5.44 29 0.87 22 3.39 41 4.69 41 2.96 63 2.45 64 9.14 44 2.31 63 2.64 29 4.37 26 2.04 24 1.08 43 1.74 33 1.36 63
S2D-Matching [84]45.7 2.69 30 7.86 41 2.68 42 2.19 54 9.11 62 2.44 58 1.77 35 6.11 47 2.04 40 1.13 31 5.86 34 0.91 31 3.17 33 4.41 30 2.50 42 2.41 61 9.09 43 2.25 56 4.00 93 5.16 72 4.07 103 0.91 22 1.40 7 0.95 30
SimpleFlow [49]47.4 2.74 34 8.28 47 2.73 45 2.50 73 9.73 74 2.83 88 1.89 44 6.81 53 2.35 71 1.11 27 10.4 71 0.89 29 3.27 36 4.47 34 2.63 47 3.03 80 8.91 42 2.39 65 3.10 54 4.25 14 2.76 63 0.89 15 1.49 16 0.89 16
Occlusion-TV-L1 [63]47.9 3.15 43 8.42 49 2.50 21 2.03 33 7.42 41 2.14 35 2.24 66 9.79 70 2.16 59 1.35 47 9.59 64 1.11 47 4.10 77 5.77 97 3.22 74 1.68 17 9.21 45 2.08 39 2.69 32 4.59 42 1.70 13 1.05 39 2.36 63 0.98 36
IROF-TV [53]48.0 2.89 37 8.67 52 2.81 51 2.25 59 9.54 72 2.51 64 1.79 38 5.50 41 2.15 58 1.53 67 11.5 82 1.27 66 3.33 37 4.62 37 2.85 55 2.78 72 13.5 96 2.57 70 2.15 6 4.14 10 1.37 4 0.94 29 1.55 22 0.94 26
MDP-Flow [26]48.4 3.14 42 9.81 59 2.83 52 2.06 36 6.10 17 2.43 56 1.87 42 6.10 46 2.10 53 1.44 57 8.90 60 1.15 56 3.37 39 4.62 37 2.54 44 2.35 56 10.4 64 2.23 52 2.88 43 4.83 57 1.94 20 1.27 61 2.62 68 1.09 45
Correlation Flow [75]49.0 3.18 45 7.85 39 2.85 54 1.74 15 5.77 14 1.69 12 1.94 48 5.25 37 1.70 13 1.47 61 5.67 32 1.26 65 3.66 47 5.20 60 2.53 43 3.06 82 9.57 50 3.10 86 3.42 72 4.94 66 4.03 100 1.17 54 1.80 35 1.16 47
3DFlow [135]49.8 3.21 47 7.43 31 2.64 39 1.92 27 7.04 30 1.85 22 2.03 54 4.31 16 1.84 19 1.65 77 3.41 8 1.33 68 3.14 32 4.51 35 2.24 25 3.66 94 11.8 81 3.87 104 4.19 99 4.93 65 5.46 121 1.05 39 1.54 21 1.02 41
AggregFlow [97]51.3 3.29 50 8.49 50 3.14 65 2.70 89 12.2 97 2.68 75 2.32 70 9.03 63 2.88 87 1.44 57 4.19 13 1.25 64 3.48 42 5.09 50 2.19 20 1.55 7 5.36 2 1.68 8 2.56 26 4.78 55 1.77 15 1.54 79 2.15 52 2.16 96
IIOF-NLDP [131]52.1 3.19 46 10.4 63 2.50 21 2.43 70 9.32 69 2.32 43 1.98 51 5.55 42 1.81 17 1.48 63 6.12 37 1.23 63 3.75 52 5.55 85 2.25 28 3.03 80 9.30 46 3.02 82 2.66 31 4.83 57 2.60 55 1.24 58 1.97 44 1.17 48
Aniso-Texture [82]53.5 2.75 35 6.00 14 3.09 62 2.13 41 5.64 11 2.52 67 1.78 36 6.80 52 2.20 63 1.08 19 4.01 12 0.92 32 4.08 74 5.44 76 3.26 78 2.31 53 11.8 81 2.26 57 5.87 130 8.09 136 4.24 110 0.80 8 1.70 32 0.67 4
OFH [38]53.8 3.60 71 10.3 62 3.80 89 1.58 7 7.05 31 1.66 8 1.70 22 9.23 64 1.58 7 1.19 35 10.1 67 1.08 43 3.98 60 5.22 62 3.57 83 2.80 73 12.6 88 3.12 87 2.30 14 4.60 44 2.35 39 1.41 74 2.90 81 1.75 79
CostFilter [40]55.2 3.59 68 8.35 48 3.26 69 2.12 39 6.60 23 2.16 36 2.00 53 5.56 43 2.01 35 2.04 90 7.05 46 1.89 91 2.74 13 3.70 8 2.27 30 3.29 87 10.3 63 3.33 90 5.22 121 9.79 142 6.16 127 0.38 1 1.08 1 0.35 1
Classic++ [32]55.2 2.66 27 8.18 46 2.65 41 2.13 41 7.96 46 2.43 56 1.85 40 9.39 67 2.10 53 1.09 23 10.4 71 0.88 24 3.97 58 5.60 90 2.89 58 2.36 57 13.6 99 2.10 43 4.03 95 5.20 74 4.33 111 0.99 37 2.05 47 0.92 22
DeepFlow2 [108]55.5 3.44 56 12.6 77 3.36 76 1.98 30 8.60 50 2.10 33 2.38 73 11.1 75 2.60 78 1.34 44 14.6 93 1.11 47 3.53 45 5.09 50 2.23 24 1.66 16 9.90 57 1.77 13 2.76 36 4.06 7 3.40 77 1.72 89 3.21 92 2.13 94
S2F-IF [123]56.0 3.54 62 19.2 114 2.58 32 2.41 68 10.4 80 2.59 70 2.57 78 10.6 74 2.59 76 1.29 40 10.5 73 0.98 35 4.07 72 5.38 71 2.90 59 1.65 15 9.94 58 1.85 14 2.27 9 4.26 16 2.35 39 1.33 65 2.49 66 1.32 58
FlowFields+ [130]57.4 3.58 66 19.0 110 2.56 30 2.57 78 10.8 85 2.78 80 2.72 84 11.9 81 2.78 85 1.32 42 10.9 76 1.03 38 3.97 58 5.34 68 2.74 48 1.64 14 9.79 54 1.87 18 2.26 8 4.30 21 2.35 39 1.35 66 2.62 68 1.34 61
CPM-Flow [116]58.3 3.47 58 19.0 110 2.52 23 2.59 80 11.0 90 2.82 85 2.56 76 11.3 77 2.75 81 1.34 44 15.7 98 1.06 40 4.02 65 5.42 73 2.78 50 1.59 9 9.39 48 1.87 18 2.30 14 4.17 11 2.36 42 1.35 66 2.69 74 1.39 67
RFlow [90]58.6 3.62 73 9.91 60 3.53 82 1.83 22 5.50 10 1.93 26 2.14 61 9.57 68 1.86 22 1.32 42 6.75 40 1.14 54 3.98 60 5.35 69 3.24 75 2.39 59 11.7 80 2.24 54 3.45 73 4.60 44 3.63 81 1.64 85 2.90 81 1.91 86
PGM-C [120]59.0 3.48 60 19.0 110 2.52 23 2.59 80 10.8 85 2.82 85 2.59 79 11.8 80 2.75 81 1.34 44 16.5 102 1.06 40 4.03 67 5.46 78 2.78 50 1.60 10 9.63 52 1.88 21 2.28 10 3.98 4 2.36 42 1.37 69 2.69 74 1.45 69
EpicFlow [102]60.7 3.47 58 18.9 108 2.52 23 2.59 80 10.9 88 2.82 85 2.64 81 14.2 91 2.75 81 1.35 47 15.5 96 1.06 40 4.04 69 5.48 79 2.88 57 1.62 13 9.70 53 1.91 24 2.28 10 4.08 9 2.36 42 1.39 73 2.71 76 1.51 74
FlowFields [110]61.0 3.56 65 19.0 110 2.54 29 2.57 78 10.6 83 2.79 81 2.72 84 11.7 79 2.76 84 1.42 54 10.9 76 1.13 52 4.08 74 5.43 75 2.92 61 1.60 10 10.5 66 1.86 17 2.28 10 4.35 24 2.46 49 1.38 72 2.62 68 1.36 63
MLDP_OF [89]61.5 4.16 91 10.4 63 4.04 91 2.04 35 6.61 24 2.04 31 2.36 72 6.60 51 2.05 41 1.43 55 5.65 31 1.18 60 3.75 52 4.86 46 2.96 63 2.96 78 8.71 41 3.47 93 4.20 100 5.51 81 7.24 130 1.16 53 1.87 40 1.21 54
DMF_ROB [140]63.0 3.70 75 15.2 96 3.34 74 2.21 58 9.03 58 2.40 52 2.84 89 13.7 90 2.65 80 1.41 53 16.9 105 1.10 45 3.92 56 5.17 58 3.14 71 2.01 29 10.6 67 2.11 44 2.37 20 3.72 3 2.62 58 1.49 78 2.74 77 1.68 76
TV-L1-improved [17]63.3 2.70 31 9.05 54 2.29 13 1.85 24 7.06 32 1.97 29 1.94 48 9.28 66 1.90 26 1.10 25 8.96 61 0.85 18 4.07 72 5.60 90 2.75 49 5.44 124 17.3 116 6.29 128 4.75 115 6.82 116 4.73 117 1.13 48 2.68 73 1.06 44
BriefMatch [124]63.7 3.03 39 7.96 42 2.73 45 1.75 16 6.88 29 1.73 14 1.72 28 4.70 25 1.73 15 1.51 66 5.38 27 1.39 76 4.01 63 5.27 64 3.72 88 5.57 125 15.9 108 6.02 127 4.65 108 6.85 117 8.98 137 0.95 31 2.30 59 1.77 80
Steered-L1 [118]63.8 3.21 47 8.15 45 3.11 64 1.39 2 4.13 1 1.51 2 1.73 31 5.20 35 1.65 10 1.28 39 10.3 70 1.11 47 4.05 71 5.35 69 3.55 81 3.10 83 12.6 88 2.59 71 6.15 135 6.90 118 13.1 142 1.73 90 3.04 89 2.39 100
CombBMOF [113]64.6 3.55 63 11.6 72 2.79 50 2.52 74 7.21 37 2.51 64 1.88 43 5.63 44 1.84 19 1.67 80 11.2 80 1.51 83 3.68 48 4.62 37 3.07 69 4.08 101 11.4 78 4.79 116 4.72 112 6.58 113 3.82 93 0.92 23 1.82 37 0.88 14
PWC-Net_ROB [148]64.7 4.74 103 14.6 91 3.51 81 2.88 95 8.88 56 2.92 92 2.75 86 9.98 72 3.27 95 1.65 77 4.91 20 1.35 69 4.10 77 5.12 55 2.91 60 2.66 70 10.2 62 2.67 72 1.69 2 4.65 51 1.13 2 1.26 60 2.06 48 1.29 57
Sparse Occlusion [54]65.7 3.36 52 8.08 43 2.90 56 2.61 84 7.68 42 3.01 93 2.10 57 6.40 50 2.13 56 1.45 59 6.80 41 1.14 54 4.01 63 5.31 67 2.81 53 2.55 67 10.4 64 2.21 51 6.70 138 8.26 137 4.34 112 1.15 50 2.08 49 0.99 39
DeepFlow [86]66.4 3.94 83 12.7 78 4.14 95 2.12 39 9.06 60 2.28 42 2.84 89 12.5 85 3.16 92 1.68 81 15.6 97 1.44 80 3.58 46 5.10 52 2.20 21 1.78 19 11.1 73 1.88 21 2.65 30 4.07 8 3.40 77 2.08 107 3.59 108 3.09 111
EPPM w/o HM [88]67.2 4.03 88 13.7 86 3.25 68 1.91 26 7.71 43 1.83 19 2.14 61 7.85 59 1.96 29 1.80 83 10.2 68 1.63 87 3.72 51 4.62 37 3.24 75 3.93 99 13.2 94 3.79 102 4.35 104 5.68 90 7.45 131 0.97 35 1.93 43 0.98 36
Complementary OF [21]69.8 4.47 99 12.4 76 4.63 104 1.60 8 6.16 18 1.67 10 2.10 57 6.85 54 2.16 59 2.27 95 9.76 65 2.19 100 4.00 62 5.10 52 3.71 86 3.96 100 12.9 91 3.32 89 2.83 40 4.46 31 3.08 72 2.04 105 3.33 98 2.86 105
FF++_ROB [146]70.1 3.75 77 20.6 116 2.92 57 2.60 83 10.6 83 2.79 81 2.97 96 13.2 89 3.18 93 1.62 72 11.2 80 1.38 75 4.12 79 5.52 83 2.99 66 2.24 47 9.58 51 2.30 62 2.31 16 4.40 29 2.39 45 1.36 68 2.55 67 1.44 68
HBM-GC [105]70.2 5.52 107 7.21 28 5.03 111 2.96 96 7.15 35 3.23 96 2.79 88 4.90 32 2.88 87 3.12 109 4.92 21 2.97 111 3.37 39 4.23 21 3.46 79 3.80 98 6.63 10 3.52 94 5.86 129 7.23 129 4.53 115 0.64 2 2.02 46 0.64 3
TF+OM [100]71.5 3.58 66 9.07 55 2.75 48 2.07 37 6.43 20 2.37 47 1.99 52 7.56 58 2.78 85 2.07 91 7.02 45 2.07 98 4.19 84 5.12 55 4.32 104 3.15 85 10.1 61 3.00 81 4.10 97 6.00 98 3.92 96 1.54 79 2.98 86 1.94 87
Rannacher [23]71.8 3.60 71 11.3 69 3.27 70 2.41 68 9.53 71 2.63 71 2.60 80 11.9 81 2.58 75 1.36 50 12.1 84 1.09 44 4.22 85 5.90 103 3.14 71 3.63 93 16.1 111 2.75 76 3.72 83 5.24 76 3.70 85 0.96 33 2.16 54 0.91 20
Aniso. Huber-L1 [22]72.8 3.17 44 9.57 57 3.05 60 3.72 100 11.5 94 4.38 102 2.86 92 10.5 73 3.80 99 1.70 82 11.6 83 1.42 77 4.04 69 5.58 87 2.98 65 2.34 55 9.88 56 2.05 36 4.49 106 5.91 96 3.42 79 1.08 43 2.10 50 1.02 41
F-TV-L1 [15]73.4 5.69 109 13.3 81 6.62 116 2.71 90 12.0 96 2.86 90 2.76 87 12.6 86 2.43 73 2.41 100 16.3 101 2.02 97 4.17 82 5.27 64 3.74 89 2.41 61 10.8 71 2.49 69 3.04 52 4.84 62 2.26 34 0.79 6 1.81 36 0.76 9
ComplOF-FED-GPU [35]73.4 4.09 90 12.8 79 4.09 94 1.61 11 9.86 75 1.62 6 2.12 59 8.39 60 1.87 24 1.85 85 12.4 87 1.70 90 3.95 57 5.25 63 3.25 77 3.54 91 15.1 107 3.60 98 3.93 89 4.83 57 4.60 116 1.55 81 2.93 85 1.80 81
TCOF [69]73.6 3.95 84 11.0 67 4.20 96 2.56 77 9.31 68 2.68 75 2.71 83 12.8 88 3.34 96 2.30 96 6.80 41 2.33 102 4.50 100 6.28 120 2.58 46 1.89 23 6.02 4 2.06 37 4.72 112 6.30 104 2.58 52 1.37 69 2.63 71 1.22 56
NL-TV-NCC [25]74.0 3.89 81 8.49 50 3.34 74 2.52 74 8.44 48 2.38 49 2.25 67 5.49 40 1.99 31 1.87 86 7.61 49 1.53 84 4.36 92 5.91 104 2.78 50 4.12 105 13.0 92 3.58 97 3.85 87 5.74 92 3.79 90 1.63 84 2.81 79 1.46 70
ACK-Prior [27]74.6 4.28 93 9.53 56 3.85 90 1.87 25 5.68 12 1.83 19 1.97 50 5.25 37 1.96 29 1.98 89 5.26 25 1.65 88 4.08 74 5.12 55 3.79 92 4.53 114 13.0 92 3.61 99 5.63 125 6.40 108 8.50 135 1.92 101 2.90 81 2.64 102
ROF-ND [107]75.0 4.03 88 11.1 68 3.48 80 2.33 61 5.09 5 2.22 37 2.19 64 6.22 49 2.02 37 2.30 96 5.92 36 1.68 89 4.23 86 6.03 110 2.94 62 3.70 96 12.2 84 3.05 84 6.21 136 6.93 120 5.53 122 1.43 75 2.21 57 1.32 58
LDOF [28]79.5 3.72 76 14.9 94 3.59 85 2.38 65 14.0 107 2.46 60 2.69 82 14.4 92 2.55 74 1.48 63 33.9 126 1.10 45 4.24 88 5.59 89 3.75 90 2.04 33 16.4 114 1.99 32 2.83 40 4.83 57 2.43 46 2.28 115 4.02 120 3.38 114
CRTflow [80]79.5 3.65 74 14.0 89 3.10 63 2.16 46 7.88 44 2.23 38 2.25 67 11.2 76 1.99 31 1.56 69 12.7 88 1.35 69 4.02 65 5.53 84 3.01 67 6.86 131 19.6 127 8.64 133 3.29 62 5.53 84 3.23 74 2.05 106 3.95 119 2.71 103
DPOF [18]80.2 4.32 94 16.2 98 3.30 71 2.69 88 10.2 77 2.69 77 2.44 75 7.17 56 2.61 79 1.95 88 10.2 68 1.55 85 3.85 55 5.20 60 3.03 68 2.84 75 11.1 73 2.67 72 4.71 111 4.83 57 8.84 136 1.73 90 3.03 88 1.86 83
SRR-TVOF-NL [91]80.2 4.62 102 12.2 75 3.55 83 2.32 60 10.8 85 2.34 45 2.56 76 12.4 84 2.59 76 1.49 65 8.56 58 1.17 59 4.12 79 5.10 52 3.51 80 2.63 68 10.9 72 2.26 57 5.64 126 6.92 119 4.13 107 2.19 112 2.87 80 2.86 105
LocallyOriented [52]80.6 3.46 57 14.6 91 3.01 59 2.84 94 13.3 102 2.85 89 2.92 94 17.6 101 3.05 91 1.63 75 10.6 74 1.43 78 4.23 86 5.79 98 3.19 73 2.48 66 7.69 23 2.87 78 3.41 71 5.63 88 3.25 75 1.65 86 3.48 102 1.86 83
SIOF [67]81.2 4.00 86 8.74 53 3.46 79 2.00 32 13.6 103 2.13 34 3.02 99 15.7 97 3.38 97 2.55 104 13.5 92 2.50 105 4.27 89 5.70 93 3.70 85 3.55 92 11.5 79 4.01 105 3.17 57 4.64 49 2.12 29 1.85 99 3.29 97 2.15 95
Second-order prior [8]82.0 3.40 53 13.6 83 3.19 66 2.16 46 13.8 106 2.34 45 2.43 74 17.1 99 2.26 67 1.20 36 15.7 98 0.96 34 4.44 96 6.10 114 3.08 70 3.41 90 19.7 128 2.67 72 5.42 124 6.02 101 5.40 119 1.44 76 3.44 101 1.48 71
Brox et al. [5]82.1 4.01 87 14.7 93 4.49 102 2.75 92 11.5 94 3.21 95 2.33 71 12.2 83 2.34 70 1.46 60 19.9 109 1.19 61 4.62 105 5.71 94 4.89 116 2.13 37 13.3 95 2.28 59 2.87 42 4.78 55 1.55 10 2.30 117 3.68 112 3.31 112
Bartels [41]83.0 4.23 92 10.7 66 4.70 107 2.37 63 5.83 15 2.66 73 2.21 65 7.42 57 2.42 72 2.59 105 8.46 57 2.53 106 4.33 91 5.50 81 4.37 106 3.69 95 14.6 105 4.80 117 4.75 115 6.30 104 7.59 132 1.13 48 2.33 62 1.32 58
Dynamic MRF [7]83.4 4.55 101 13.6 83 5.02 109 1.81 20 8.86 55 1.82 18 2.13 60 12.6 86 1.87 24 1.62 72 13.2 90 1.45 81 4.61 103 5.80 101 4.32 104 4.14 106 21.3 130 4.42 109 3.22 60 4.41 30 5.01 118 2.11 108 3.92 118 3.51 115
CLG-TV [48]84.5 3.59 68 9.91 60 3.24 67 4.16 104 11.1 91 4.96 104 3.12 100 11.5 78 3.97 100 2.31 98 13.0 89 1.99 96 4.56 102 6.11 115 3.95 95 2.85 76 12.2 84 2.78 77 4.23 103 5.87 95 2.86 65 1.17 54 2.45 65 1.04 43
TriangleFlow [30]84.8 3.96 85 11.5 70 4.08 93 2.14 44 10.2 77 2.07 32 2.16 63 9.80 71 1.86 22 1.47 61 9.22 62 1.11 47 5.37 126 7.25 133 4.72 112 4.49 113 13.7 101 4.62 114 3.78 85 7.33 131 4.11 105 1.73 90 3.48 102 2.30 97
p-harmonic [29]85.5 4.47 99 14.4 90 4.52 103 2.71 90 9.33 70 2.89 91 3.40 101 15.0 94 3.02 90 1.93 87 24.1 116 1.59 86 4.15 81 5.18 59 3.66 84 3.37 89 16.0 109 3.54 95 3.90 88 5.36 78 2.71 62 1.29 62 2.41 64 1.38 65
Local-TV-L1 [65]85.8 4.95 104 13.2 80 5.40 112 4.37 106 14.6 110 5.04 106 4.59 108 17.8 103 5.96 108 2.42 101 16.9 105 2.25 101 3.68 48 5.03 48 2.82 54 2.25 49 10.6 67 2.24 54 2.55 25 4.37 26 2.91 69 2.73 124 4.10 122 7.77 130
FlowNetS+ft+v [112]86.0 3.42 55 13.4 82 3.39 77 2.54 76 11.2 92 2.80 83 2.94 95 18.6 106 4.76 102 1.43 55 27.4 119 1.20 62 4.67 108 6.35 122 3.71 86 1.96 27 12.3 86 2.01 34 4.10 97 6.00 98 4.11 105 1.76 93 3.49 105 2.37 99
CBF [12]86.7 3.59 68 10.5 65 3.68 87 4.72 108 10.4 80 6.02 113 2.28 69 9.24 65 2.96 89 1.63 75 12.2 85 1.36 71 4.48 99 5.75 96 3.99 97 2.70 71 10.7 70 2.48 68 6.13 134 7.02 121 5.92 125 1.45 77 2.65 72 1.66 75
CNN-flow-warp+ref [117]86.7 3.90 82 19.8 115 3.73 88 3.40 99 10.9 88 4.21 101 3.85 105 23.8 118 6.07 109 1.65 77 22.4 114 1.37 72 4.38 95 5.58 87 4.08 98 2.23 45 13.8 102 2.33 64 2.41 21 4.27 17 2.24 33 2.43 121 3.66 111 3.64 119
DF-Auto [115]86.8 3.88 80 17.6 102 2.93 58 5.44 114 14.7 111 6.44 114 4.54 107 16.8 98 9.38 114 2.22 94 15.0 95 1.95 93 4.32 90 6.00 108 3.88 94 1.44 3 7.14 15 1.73 11 4.20 100 6.78 115 1.70 13 2.42 120 4.04 121 3.34 113
SuperFlow [81]89.2 3.40 53 11.5 70 3.31 72 3.97 102 12.2 97 5.00 105 3.01 98 17.9 104 7.70 112 2.66 106 18.1 108 2.64 108 4.17 82 5.42 73 4.16 102 2.19 43 10.6 67 2.20 49 4.22 102 6.11 103 2.45 47 2.12 110 3.64 110 3.59 117
OFRF [134]90.3 4.35 95 9.74 58 4.34 97 5.12 112 13.1 101 5.68 111 3.74 104 14.7 93 5.10 103 2.91 108 11.0 78 2.84 109 3.34 38 4.74 42 2.24 25 3.34 88 9.46 49 3.23 88 3.67 81 5.54 85 5.56 123 3.05 128 3.88 116 9.53 135
StereoFlow [44]93.2 21.8 144 37.8 139 27.4 144 24.3 142 37.6 144 22.4 140 28.3 144 39.2 139 28.8 139 24.0 142 47.7 136 21.6 141 5.15 121 5.49 80 6.01 131 0.95 1 6.87 11 1.06 1 1.68 1 3.70 2 0.92 1 1.29 62 2.32 60 1.49 72
LiteFlowNet [143]93.5 6.43 112 24.0 121 4.45 100 3.74 101 10.4 80 3.78 98 4.32 106 15.2 96 3.78 98 2.36 99 8.74 59 1.97 95 4.88 115 6.06 111 4.38 107 4.23 109 14.0 103 3.68 100 3.56 77 5.59 87 1.98 21 1.70 88 2.79 78 1.83 82
TriFlow [95]94.2 4.44 96 13.8 87 3.62 86 3.16 98 9.65 73 3.81 99 2.89 93 19.6 109 6.36 110 2.48 103 7.88 52 2.33 102 4.37 94 5.44 76 4.28 103 2.98 79 8.42 30 3.07 85 11.7 143 7.70 134 21.5 143 1.76 93 2.98 86 1.94 87
Learning Flow [11]94.6 3.80 79 11.9 73 3.58 84 3.02 97 13.0 100 3.34 97 2.84 89 17.9 104 3.18 93 1.82 84 34.6 129 1.50 82 5.44 128 7.32 134 4.61 111 3.10 83 18.8 123 3.04 83 3.94 90 6.38 107 3.65 83 1.37 69 3.38 99 1.18 49
Fusion [6]94.8 3.76 78 16.9 99 4.07 92 1.99 31 7.37 40 2.26 40 2.07 56 8.51 62 2.28 68 1.59 70 24.8 117 1.37 72 5.00 119 6.36 123 4.98 121 4.70 117 16.2 113 5.01 120 6.00 133 7.50 133 4.38 113 2.97 127 3.74 115 3.55 116
Shiralkar [42]96.1 4.46 97 18.3 105 4.36 98 1.93 28 16.4 112 1.87 23 2.99 97 17.6 101 2.01 35 2.10 92 21.0 111 1.96 94 4.36 92 5.72 95 3.55 81 5.65 126 19.4 125 5.11 123 4.90 119 5.57 86 7.14 129 2.11 108 4.71 128 2.53 101
StereoOF-V1MT [119]98.4 4.46 97 18.0 104 4.46 101 2.09 38 18.6 118 1.79 17 3.70 103 20.6 112 2.13 56 2.18 93 25.0 118 1.91 92 5.52 130 6.98 130 4.82 114 5.01 122 25.8 135 4.73 115 3.21 59 5.27 77 3.64 82 2.32 118 4.64 126 2.83 104
SegOF [10]99.7 5.62 108 17.1 100 3.08 61 8.33 124 20.9 120 10.1 127 7.44 117 21.7 114 13.3 123 5.42 125 21.0 111 4.47 120 4.81 114 5.51 82 5.74 130 4.97 120 17.1 115 4.83 118 2.12 5 4.38 28 1.46 6 2.17 111 3.23 93 3.74 121
WOLF_ROB [149]101.5 5.28 106 22.2 118 4.65 106 4.15 103 21.9 124 3.81 99 6.02 113 23.6 117 5.35 106 2.47 102 16.5 102 2.33 102 4.50 100 5.65 92 4.12 100 4.15 107 14.8 106 3.83 103 3.00 51 4.84 62 2.67 60 2.25 114 4.11 123 3.66 120
Ad-TV-NDC [36]102.9 8.75 124 15.3 97 12.3 135 10.5 131 24.2 130 12.3 131 8.96 125 28.2 122 11.5 117 5.31 124 22.8 115 5.55 125 4.03 67 5.79 98 2.86 56 2.80 73 10.0 60 2.87 78 3.04 52 4.52 37 2.66 59 4.62 135 5.79 135 30.9 143
AugFNG_ROB [144]103.4 7.79 119 28.5 129 5.02 109 9.56 128 18.5 117 11.3 130 8.78 124 26.2 119 17.3 130 3.46 112 9.97 66 2.86 110 5.26 124 6.24 119 4.77 113 4.44 111 14.5 104 4.15 106 2.99 50 5.22 75 1.30 3 1.85 99 3.18 91 2.10 93
ContFlow_ROB [150]107.2 9.53 129 30.8 132 6.83 118 7.01 119 14.4 108 7.66 120 8.67 122 21.5 113 11.4 116 3.99 115 11.0 78 3.23 113 6.14 134 7.16 132 6.10 132 6.22 128 16.1 111 5.95 126 3.26 61 6.01 100 1.48 7 1.66 87 3.27 96 1.70 77
Modified CLG [34]107.4 6.79 115 24.7 122 6.63 117 7.09 120 17.4 113 9.40 124 10.1 126 29.2 124 16.6 128 4.48 121 27.5 120 3.86 116 4.80 112 6.31 121 4.48 110 2.65 69 17.6 118 2.69 75 2.92 48 4.94 66 2.07 25 3.19 130 5.17 131 5.78 126
Filter Flow [19]107.5 6.76 114 17.6 102 4.37 99 5.01 110 17.6 114 5.49 110 5.98 112 26.3 120 18.4 132 7.23 127 29.9 123 6.91 128 5.12 120 6.23 117 5.36 125 5.23 123 11.9 83 4.95 119 6.64 137 8.75 140 3.75 89 0.95 31 2.15 52 1.21 54
LFNet_ROB [151]107.5 8.41 123 29.9 131 5.80 114 5.03 111 13.7 105 5.06 108 7.93 120 22.4 116 5.30 105 3.31 110 14.9 94 2.56 107 5.26 124 6.39 124 4.98 121 4.56 116 17.8 119 4.51 113 3.73 84 5.99 97 2.59 54 1.82 98 3.26 95 2.08 92
ResPWCR_ROB [145]108.4 8.23 121 22.9 119 6.93 119 4.20 105 12.3 99 4.43 103 5.27 110 15.1 95 5.64 107 3.74 114 17.2 107 3.36 114 4.79 111 5.55 85 5.34 124 4.99 121 13.6 99 5.09 122 4.72 112 6.59 114 2.89 66 2.38 119 3.59 108 2.92 107
IAOF2 [51]109.0 5.05 105 13.6 83 4.64 105 4.90 109 14.5 109 5.78 112 3.68 102 18.6 106 5.15 104 12.3 136 34.1 128 13.8 136 4.65 106 6.21 116 3.78 91 4.47 112 13.5 96 3.70 101 5.73 127 7.13 126 3.98 98 1.96 103 3.53 106 2.35 98
FlowNet2 [122]110.0 8.99 126 25.8 123 7.01 120 9.84 129 19.0 119 10.7 128 7.98 121 20.1 110 13.5 124 4.47 120 9.41 63 4.21 119 5.17 122 6.08 112 4.92 118 4.10 103 11.2 75 4.43 110 5.98 132 7.71 135 2.90 68 1.78 95 2.92 84 1.89 85
TVL1_ROB [139]110.2 13.5 135 26.7 126 16.1 139 14.6 135 23.8 129 16.6 136 16.9 134 36.5 135 25.4 137 11.9 135 33.8 125 12.8 134 4.66 107 6.23 117 3.96 96 2.38 58 16.0 109 2.89 80 2.32 17 4.57 40 1.49 8 5.63 139 6.44 136 12.6 138
EPMNet [133]110.3 8.88 125 26.2 125 7.20 123 9.32 127 18.2 115 10.0 126 7.14 115 18.8 108 12.3 120 4.79 122 12.3 86 4.62 123 5.17 122 6.08 112 4.92 118 4.10 103 11.2 75 4.43 110 4.88 118 7.05 123 2.56 51 1.93 102 3.57 107 2.07 91
BlockOverlap [61]110.5 6.80 116 12.1 74 5.94 115 5.51 115 13.6 103 6.58 115 5.32 111 22.2 115 7.30 111 4.20 116 16.7 104 4.06 118 4.45 97 5.39 72 5.11 123 4.91 118 12.5 87 4.34 108 6.77 139 7.13 126 9.52 138 2.02 104 3.24 94 9.49 134
HBpMotionGpu [43]111.4 5.92 110 15.0 95 4.79 108 7.78 122 22.4 126 9.04 123 7.17 116 39.2 139 17.3 130 3.31 110 13.4 91 3.14 112 4.71 109 5.88 102 4.84 115 3.74 97 13.5 96 3.54 95 5.96 131 7.17 128 3.68 84 2.24 113 3.43 100 4.65 122
SPSA-learn [13]112.2 6.87 117 21.3 117 7.92 126 6.02 117 21.1 122 6.96 117 7.55 118 27.5 121 12.7 122 4.44 118 29.2 121 4.59 122 4.80 112 5.92 105 4.93 120 4.94 119 17.3 116 5.02 121 3.37 68 5.01 68 2.29 37 4.14 133 4.97 130 6.49 127
2D-CLG [1]112.4 9.69 130 37.7 138 7.18 122 11.1 132 21.9 124 13.9 134 19.0 139 34.8 130 28.7 138 13.0 137 46.7 134 12.8 134 4.97 117 5.79 98 5.47 128 4.08 101 21.2 129 4.32 107 2.29 13 4.00 6 1.64 11 4.47 134 5.51 134 6.55 128
GroupFlow [9]113.0 9.15 128 25.8 123 10.5 132 11.6 134 30.0 137 12.3 131 10.2 127 35.4 132 11.9 118 3.50 113 15.8 100 3.39 115 5.48 129 6.56 126 4.42 108 9.25 136 24.8 132 10.8 138 2.35 19 4.58 41 1.67 12 2.93 126 5.22 132 4.99 123
GraphCuts [14]113.0 6.34 111 17.1 100 5.55 113 5.30 113 20.9 120 5.26 109 6.05 114 20.4 111 12.4 121 2.85 107 20.9 110 2.15 99 4.74 110 5.95 106 4.90 117 8.69 135 12.6 88 5.19 124 5.79 128 6.40 108 6.80 128 2.45 122 3.48 102 3.59 117
Black & Anandan [4]114.2 7.19 118 18.9 108 8.40 127 5.96 116 22.6 127 6.69 116 8.73 123 28.7 123 12.1 119 4.46 119 29.4 122 4.52 121 4.91 116 6.59 127 4.09 99 4.18 108 19.4 125 4.44 112 4.69 109 6.36 106 2.01 22 3.13 129 4.46 124 5.06 124
IAOF [50]115.2 6.54 113 18.3 105 7.13 121 6.99 118 18.4 116 7.90 121 7.71 119 32.3 127 8.44 113 8.21 130 31.8 124 9.78 132 4.61 103 6.01 109 4.14 101 4.35 110 18.9 124 3.43 92 4.69 109 6.08 102 3.31 76 3.23 131 4.69 127 15.9 141
2bit-BM-tele [98]118.2 8.99 126 18.6 107 10.2 130 4.45 107 11.3 93 5.04 106 4.66 109 17.3 100 4.41 101 5.23 123 21.7 113 5.04 124 4.99 118 5.96 107 5.46 127 6.47 130 18.3 120 7.49 131 7.77 141 8.57 139 12.5 141 2.29 116 3.89 117 2.99 110
Nguyen [33]120.4 8.16 120 23.0 120 7.57 125 16.5 138 22.7 128 19.3 138 16.8 133 36.0 133 20.7 135 13.8 138 39.5 130 14.7 138 5.40 127 6.44 125 6.70 133 4.54 115 18.5 122 5.42 125 3.50 75 5.02 69 2.08 26 4.00 132 5.50 133 8.53 132
UnFlow [129]120.5 19.4 143 44.0 143 10.2 130 11.3 133 21.2 123 12.4 133 18.1 136 36.0 133 15.5 126 7.47 129 34.0 127 6.40 127 7.10 138 7.11 131 8.76 138 8.31 134 24.8 132 9.26 134 5.13 120 6.50 111 1.52 9 1.57 82 3.14 90 2.01 89
Heeger++ [104]123.0 18.3 142 32.1 135 10.5 132 9.98 130 34.3 143 7.90 121 16.0 131 32.7 128 11.0 115 9.23 131 47.6 135 7.86 130 5.95 132 6.74 128 5.71 129 23.4 143 49.5 144 24.5 143 3.61 80 6.53 112 2.58 52 1.78 95 3.68 112 2.96 108
SILK [79]123.7 10.7 131 31.4 134 13.1 137 8.77 125 26.6 132 9.80 125 13.6 129 34.9 131 16.7 129 6.53 126 45.4 132 6.08 126 6.11 133 7.36 136 6.71 134 6.96 132 29.4 138 7.39 130 2.97 49 4.77 54 3.96 97 5.00 136 6.99 137 10.7 136
Horn & Schunck [3]124.5 8.40 122 27.2 127 9.62 128 7.28 121 28.3 134 7.55 119 13.3 128 31.9 126 15.8 127 7.35 128 48.5 137 7.69 129 5.84 131 7.34 135 5.45 126 5.80 127 25.8 135 6.79 129 5.25 122 7.11 125 2.11 28 5.21 137 8.30 139 6.66 129
Periodicity [78]128.5 12.3 133 51.4 150 7.39 124 9.23 126 38.3 145 11.1 129 34.7 145 48.1 145 36.0 144 4.27 117 57.7 144 3.99 117 24.4 145 73.2 145 16.2 144 29.6 145 74.3 145 29.4 145 3.29 62 5.67 89 1.90 18 6.64 140 44.8 145 21.5 142
FFV1MT [106]128.9 17.0 141 35.1 137 10.1 129 8.30 123 33.0 141 7.40 118 17.2 135 40.0 141 15.3 125 9.57 132 55.8 143 8.75 131 7.99 143 8.46 143 10.1 141 21.8 142 36.1 141 23.3 142 4.43 105 7.02 121 4.09 104 1.78 95 3.68 112 2.96 108
TI-DOFE [24]129.5 16.4 139 34.0 136 21.2 143 21.5 141 31.9 138 25.3 142 24.4 143 41.0 143 33.0 143 22.8 141 46.3 133 25.2 142 6.25 135 7.67 138 6.82 135 6.37 129 25.6 134 7.87 132 3.94 90 5.78 94 1.78 16 8.49 143 9.86 142 12.5 137
H+S_ROB [138]129.7 14.9 137 45.1 144 10.5 132 15.0 137 29.6 136 16.1 135 24.2 142 40.2 142 29.9 142 33.2 144 52.4 141 34.9 143 7.74 142 8.16 140 11.7 143 13.6 141 42.2 143 17.3 141 2.88 43 5.51 81 2.54 50 8.22 142 8.90 140 8.03 131
SLK [47]130.2 12.3 133 43.0 142 16.5 140 19.8 140 32.9 140 22.4 140 21.4 140 38.4 137 29.3 141 41.6 145 51.6 139 44.5 145 6.87 137 7.63 137 8.94 139 8.09 133 31.2 140 9.56 135 3.34 66 5.41 79 2.60 55 8.13 141 9.23 141 13.9 140
Adaptive flow [45]136.2 16.4 139 28.7 130 16.7 141 17.2 139 25.5 131 19.6 139 18.8 138 37.6 136 36.5 145 11.2 134 43.6 131 11.9 133 7.11 139 7.79 139 7.88 136 10.1 139 24.1 131 10.1 137 16.1 144 14.2 144 22.1 144 2.92 125 4.89 129 5.22 125
HCIC-L [99]137.0 24.1 145 31.3 133 12.9 136 27.6 144 28.7 135 69.9 145 16.0 131 30.6 125 23.1 136 18.1 140 55.4 142 17.8 140 7.39 140 8.35 142 8.32 137 12.6 140 18.3 120 14.4 140 25.6 145 23.8 145 23.6 145 2.62 123 4.51 125 9.36 133
PGAM+LK [55]137.7 14.0 136 40.6 140 18.8 142 14.9 136 33.1 142 17.8 137 14.4 130 32.9 129 19.3 133 15.7 139 63.6 145 14.9 139 6.36 136 6.81 129 9.14 140 9.83 138 30.7 139 9.83 136 10.4 142 12.2 143 10.3 139 5.30 138 7.26 138 13.0 139
FOLKI [16]138.2 11.0 132 41.0 141 14.5 138 24.9 143 32.3 139 36.7 143 18.7 137 43.8 144 20.5 134 10.9 133 50.5 138 13.8 136 7.42 141 8.28 141 10.6 142 9.75 137 36.9 142 12.1 139 4.77 117 7.29 130 11.0 140 12.2 144 11.4 143 36.4 144
Pyramid LK [2]141.1 15.8 138 28.2 128 30.4 145 35.8 145 28.0 133 49.6 144 22.3 141 38.6 138 29.1 140 31.8 143 51.7 140 39.0 144 18.3 144 24.8 144 24.1 145 26.7 144 28.6 137 26.7 144 7.19 140 8.98 141 7.70 134 32.7 145 40.6 144 57.0 145
AdaConv-v1 [126]146.1 45.2 146 50.1 145 46.0 146 78.3 146 79.6 146 76.9 146 78.3 146 73.0 146 77.6 146 79.2 146 80.8 146 79.6 146 83.7 146 84.3 146 83.6 146 82.1 146 80.6 146 81.5 146 69.6 147 58.5 147 75.3 147 84.4 146 84.7 146 83.9 146
SepConv-v1 [127]146.1 45.2 146 50.1 145 46.0 146 78.3 146 79.6 146 76.9 146 78.3 146 73.0 146 77.6 146 79.2 146 80.8 146 79.6 146 83.7 146 84.3 146 83.6 146 82.1 146 80.6 146 81.5 146 69.6 147 58.5 147 75.3 147 84.4 146 84.7 146 83.9 146
SuperSlomo [132]146.1 45.2 146 50.1 145 46.0 146 78.3 146 79.6 146 76.9 146 78.3 146 73.0 146 77.6 146 79.2 146 80.8 146 79.6 146 83.7 146 84.3 146 83.6 146 82.1 146 80.6 146 81.5 146 69.6 147 58.5 147 75.3 147 84.4 146 84.7 146 83.9 146
FGIK [136]146.1 45.2 146 50.1 145 46.0 146 78.3 146 79.6 146 76.9 146 78.3 146 73.0 146 77.6 146 79.2 146 80.8 146 79.6 146 83.7 146 84.3 146 83.6 146 82.1 146 80.6 146 81.5 146 69.6 147 58.5 147 75.3 147 84.4 146 84.7 146 83.9 146
CtxSyn [137]146.1 45.2 146 50.1 145 46.0 146 78.3 146 79.6 146 76.9 146 78.3 146 73.0 146 77.6 146 79.2 146 80.8 146 79.6 146 83.7 146 84.3 146 83.6 146 82.1 146 80.6 146 81.5 146 69.6 147 58.5 147 75.3 147 84.4 146 84.7 146 83.9 146
AVG_FLOW_ROB [142]150.4 85.5 151 80.5 151 99.9 151 99.9 151 99.9 151 99.9 151 96.1 151 99.9 151 95.9 151 89.9 151 87.4 151 95.1 151 99.9 151 99.9 151 99.9 151 95.8 151 81.5 151 91.9 151 39.9 146 40.1 146 34.2 146 99.9 151 99.9 151 99.9 151
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

Methodtime*framescolor Reference and notes
[1] 2D-CLG 844 2 gray The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences.
[2] Pyramid LK 12 2 color A modification of Bouguet's pyramidal implementation of Lucas-Kanade.
[3] Horn & Schunck 49 2 gray A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data.
[4] Black & Anandan 328 2 gray A modern Matlab implementation of the Black & Anandan method by Deqing Sun.
[5] Brox et al. 18 2 color T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.)
[6] Fusion 2,666 2 color V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008.
[7] Dynamic MRF 366 2 gray B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.)
[8] Second-order prior 14 2 gray W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[9] GroupFlow 600 2 gray X. Ren. Local Grouping for Optical Flow. CVPR 2008.
[10] SegOF 60 2 color L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available.
[11] Learning Flow 825 2 gray D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008.
[12] CBF 69 2 color W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[13] SPSA-learn 200 2 color Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008.
[14] GraphCuts 1,200 2 color T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008.
[15] F-TV-L1 8 2 gray A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008.
[16] FOLKI 1.4 2 gray G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005.
[17] TV-L1-improved 2.9 2 gray A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision.
[18] DPOF 287 2 color C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.)
[19] Filter Flow 34,000 2 color S. Seitz and S. Baker. Filter flow. ICCV 2009.
[20] Adaptive 9.2 2 gray A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009.
[21] Complementary OF 44 2 color H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[22] Aniso. Huber-L1 2 2 gray M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision.
[23] Rannacher 0.12 2 gray J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009.
[24] TI-DOFE 260 2 gray C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009.
[25] NL-TV-NCC 20 2 color M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010.
[26] MDP-Flow 188 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010.
[27] ACK-Prior 5872 2 color K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010.
[28] LDOF 122 2 color T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011.
[29] p-harmonic 565 2 gray J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010.
[30] TriangleFlow 4200 2 gray B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010.
[31] Classic+NL 972 2 color D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code.
[32] Classic++ 486 2 gray A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010.
[33] Nguyen 33 2 gray D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011.
[34] Modified CLG 133 2 gray R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010.
[35] ComplOF-FED-GPU 0.97 2 color P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010.
[36] Ad-TV-NDC 35 2 gray M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010.
[37] Layers++ 18206 2 color D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010.
[38] OFH 620 3 color H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011.
[39] LSM 1615 2 color K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011.
[40] CostFilter 55 2 color C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011.
[41] Bartels 0.15 2 gray C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU.
[42] Shiralkar 600 2 gray M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242.
[43] HBpMotionGpu 1000 5 gray S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.)
[44] StereoFlow 7200 2 color G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772.
[45] Adaptive flow 121 2 gray T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011.
[46] TC-Flow 2500 5 color S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011.
[47] SLK 300 2 gray T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011.
[48] CLG-TV 29 2 gray M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code.
[49] SimpleFlow 1.7 2 color M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012.
[50] IAOF 57 2 gray D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011.
[51] IAOF2 56 2 gray D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011.
[52] LocallyOriented 9541 2 gray Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012.
[53] IROF-TV 261 2 color H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop.
[54] Sparse Occlusion 2312 2 color A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011.
[55] PGAM+LK 0.37 2 gray A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010.
[56] Sparse-NonSparse 713 2 color L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013.
[57] nLayers 36150 4 color D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012.
[58] IROF++ 187 2 color H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013.
[59] COFM 600 3 color M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013.
[60] Efficient-NL 400 2 color P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012.
[61] BlockOverlap 2 2 gray M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to MMSP 2012.
[62] Ramp 1200 2 color A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012.
[63] Occlusion-TV-L1 538 3 gray C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012.
[64] TV-L1-MCT 90 2 color M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012.
[65] Local-TV-L1 500 2 gray L. Raket. Local smoothness for global optical flow. ICIP 2012.
[66] ALD-Flow 61 2 color M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012.
[67] SIOF 234 2 color L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012.
[68] MDP-Flow2 342 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available.
[69] TCOF 1421 all gray J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013.
[70] LME 476 2 color W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013.
[71] NN-field 362 2 color L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[72] FESL 3310 2 color W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013.
[73] PMF 35 2 color J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013.
[74] FC-2Layers-FF 2662 4 color D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013.
[75] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[76] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[77] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[78] Periodicity 8000 4 color G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013.
[79] SILK 572 2 gray P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP.
[80] CRTflow 13 3 color O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013.
[81] SuperFlow 178 2 color Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507.
[82] Aniso-Texture 300 2 color Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267.
[83] Classic+CPF 640 2 gray Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013.
[84] S2D-Matching 1200 2 color Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479.
[85] AGIF+OF 438 2 gray Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015.
[86] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[87] NNF-Local 673 2 color Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014.
[88] EPPM w/o HM 2.5 2 color L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014.
[89] MLDP_OF 165 2 gray M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014.
[90] RFlow 20 2 gray S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014.
[91] SRR-TVOF-NL 32 all color P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014.
[92] 2DHMM-SAS 157 2 color M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission.
[93] WLIF-Flow 700 2 color Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014.
[94] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[95] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[96] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[97] AggregFlow 1642 2 color D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759.
[98] 2bit-BM-tele 124 2 gray R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013.
[99] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[100] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[101] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[102] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[103] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[104] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[105] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[106] FFV1MT 358 5 gray F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015.
[107] ROF-ND 4 2 color S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015.
[108] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[109] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[110] FlowFields 15 2 color C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015.
[111] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[112] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[113] CombBMOF 51 2 color M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.)
[114] PMMST 182 2 color F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015.
[115] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[116] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[117] CNN-flow-warp+ref 1.4 3 color D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016.
[118] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[119] StereoOF-V1MT 343 2 gray Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132.
[120] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[121] RNLOD-Flow 1040 2 gray C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. IEEE TIP 26(8):4055-4067, 2017.
[122] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[123] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[124] BriefMatch 0.068 2 gray G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62.
[125] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[126] AdaConv-v1 2.8 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[127] SepConv-v1 0.2 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[128] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[129] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[130] FlowFields+ 10.5 2 color C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017.
[131] IIOF-NLDP 150 2 color D.-H. Trinh, W. Blondel, and C. Daul. A general form of illumination-invariant descriptors in variational optical flow estimation. ICIP 2017.
[132] SuperSlomo 0.5 2 color Anonymous. (Interpolation results only.) Super SloMo: High quality estimation of multiple intermediate frames for video interpolation. CVPR 2018 submission 325.
[133] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[134] OFRF 90 2 color T. Mai, M. Gouiffes, and S. Bouchafa. Optical Flow refinement using iterative propagation under color, proximity and flow reliability constraints. Submitted to Signal, Image and Video Processing 2017.
[135] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
[136] FGIK 0.18 2 color Anonymous. (Interpolation results only.) Learning flow-guided interpolation kernels for video frame synthesis. ECCV 2018 submission 433.
[137] CtxSyn 0.07 2 color S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[138] H+S_ROB 5 2 color ROB 2018 baseline submission, based on: E. Meinhardt-Llopis, J. Sanchez, and D. Kondermann. Horn-Schunck optical flow with a multi-scale strategy. Image Processing On Line 3:151–172, 2013.
[139] TVL1_ROB 1 2 color ROB 2018 baseline submission, based on: J. Sanchez, E. Meinhardt-Llopis, and G. Facciolo. TV-L1 optical flow estimation. Image Processing On Line 3:137-150, 2013.
[140] DMF_ROB 10 2 color ROB 2018 baseline submission, based on: P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[141] JOF 657 2 gray C. Zhang, L. Ge, Z. Chen, M. Li, W. Liu, and H. Chen. Refined TV-L1 optical flow estimation using joint filtering. Submitted to IEEE TMM, 2018.
[142] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[143] LiteFlowNet 0.06 2 color T.-W. Hui, X. Tang, and C. C. Loy. LiteFlowNet: A lightweight convolutional neural network for optical flow estimation. CVPR 2018.
[144] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[145] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[146] FF++_ROB 17.43 2 color R. Schuster, C. Bailer, O. Wasenmueller, D. Stricker. FlowFields++: Accurate optical flow correspondences meet robust interpolation. ICIP 2018. Submitted to ROB 2018.
[147] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[148] PWC-Net_ROB 0.069 2 color D. Sun, X. Yang, M.-Y. Liu, and J. Kautz. PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. CVPR 2018.
[149] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[150] 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.