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        
Average
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]4.8 2.69 3 7.56 4 1.98 3 1.97 4 7.01 4 1.59 4 2.18 2 5.36 3 1.53 4 1.87 2 9.14 5 1.06 4 2.28 2 2.94 1 1.57 2 2.39 5 6.78 2 2.15 9 2.00 18 3.36 16 1.62 14 0.99 1 2.16 2 0.57 2
NN-field [71]9.5 2.89 8 8.13 16 2.11 5 2.10 6 7.15 9 1.77 14 2.27 4 5.59 5 1.61 8 1.58 1 8.52 4 0.79 1 2.35 4 3.05 5 1.60 3 1.89 1 5.20 1 1.37 1 2.43 44 3.70 47 1.95 35 1.01 2 2.25 3 0.53 1
OFLAF [77]12.2 3.04 15 7.80 10 2.40 13 2.14 7 7.02 5 1.72 9 2.25 3 5.32 2 1.56 5 2.62 17 13.7 22 1.37 19 2.35 4 3.13 6 1.62 4 2.98 21 7.73 7 2.57 19 2.08 23 3.27 11 2.05 38 1.33 12 2.43 6 1.40 15
PMMST [114]13.4 3.42 41 7.60 5 2.65 27 2.32 11 6.39 1 2.20 31 2.63 11 6.08 8 2.03 25 2.06 4 6.07 1 1.44 26 2.60 10 3.27 8 1.91 10 2.56 7 6.78 2 2.09 5 2.06 20 3.53 35 1.63 15 1.27 9 2.29 4 1.02 6
nLayers [57]15.8 2.80 6 7.42 3 2.20 8 2.71 29 7.24 10 2.55 58 2.61 9 6.24 9 2.45 49 2.30 10 12.7 11 1.16 7 2.30 3 3.02 3 1.70 5 2.62 10 6.95 4 2.09 5 2.29 38 3.46 25 1.89 32 1.38 14 3.06 17 1.29 13
MDP-Flow2 [68]17.8 3.23 30 7.93 13 2.60 19 1.92 2 6.64 2 1.52 1 2.46 7 5.91 7 1.56 5 3.05 40 15.8 49 1.51 36 2.77 23 3.50 17 2.16 25 2.86 17 8.58 18 2.70 30 2.00 18 3.50 32 1.59 12 1.28 10 2.67 11 0.89 4
ComponentFusion [96]18.2 2.78 5 8.20 17 2.05 4 2.04 5 7.31 11 1.66 8 2.55 8 6.78 13 1.61 8 2.24 9 13.1 13 1.01 3 2.71 20 3.56 19 2.10 21 3.55 49 12.4 53 3.22 55 2.19 33 3.60 41 1.54 11 1.32 11 2.91 13 1.13 8
TC/T-Flow [76]20.6 2.69 3 7.75 9 1.87 2 2.76 32 10.2 44 1.73 10 3.33 24 9.01 30 1.49 2 2.86 32 16.7 59 1.21 9 2.60 10 3.49 16 1.90 9 2.21 2 7.65 5 2.04 4 1.84 9 3.23 8 3.14 83 2.03 37 4.53 37 1.49 19
FC-2Layers-FF [74]23.6 3.02 14 7.87 12 2.61 20 2.72 30 9.35 35 2.29 39 2.36 5 5.47 4 2.15 32 2.48 11 12.6 10 1.28 11 2.49 7 3.19 7 2.03 16 3.39 38 8.92 20 2.83 40 2.83 67 3.92 60 2.80 62 1.25 7 2.57 10 1.20 10
WLIF-Flow [93]24.8 2.96 10 7.67 6 2.40 13 2.41 16 7.70 15 2.10 25 2.98 17 7.63 18 1.97 24 2.71 24 13.5 18 1.33 14 3.01 40 4.00 46 2.40 42 3.03 24 8.32 12 2.44 15 2.09 25 3.36 16 2.04 37 2.26 44 4.97 44 2.59 49
Layers++ [37]25.1 3.11 17 8.22 20 2.79 39 2.43 19 7.02 5 2.24 34 2.43 6 5.77 6 2.18 35 2.13 6 9.71 7 1.15 6 2.35 4 3.02 3 1.96 11 3.81 55 11.4 41 3.22 55 2.74 62 4.01 65 2.35 48 1.45 15 3.05 16 1.79 28
HAST [109]25.2 2.58 1 7.12 1 1.81 1 2.41 16 7.05 7 2.10 25 1.83 1 4.19 1 1.17 1 2.84 31 15.5 44 1.08 5 2.23 1 2.97 2 1.40 1 3.72 54 10.0 31 3.92 76 3.40 86 4.90 91 5.66 112 1.20 6 2.09 1 1.24 11
FESL [72]26.8 2.96 10 7.70 7 2.54 16 3.26 65 10.4 45 2.56 59 3.25 22 8.39 22 2.17 33 2.56 13 13.2 14 1.31 13 2.57 9 3.40 11 2.12 24 2.60 9 7.65 5 2.30 10 2.64 58 4.22 73 2.47 50 1.75 26 3.49 25 1.71 24
AGIF+OF [85]26.9 3.06 16 8.20 17 2.55 18 3.17 55 10.6 48 2.46 52 3.46 29 8.97 29 2.24 38 2.61 15 13.7 22 1.33 14 2.63 14 3.46 14 2.11 22 2.88 19 8.34 14 2.35 12 2.10 27 3.56 37 2.09 40 1.80 28 3.68 28 2.24 38
Efficient-NL [60]27.0 2.99 13 8.23 21 2.28 9 2.72 30 8.95 31 2.25 37 3.81 38 9.87 36 2.07 29 2.77 28 14.3 29 1.46 31 2.61 12 3.48 15 1.96 11 3.31 34 8.33 13 2.59 21 2.60 53 3.75 48 2.54 53 1.60 21 3.02 14 1.66 21
LME [70]27.1 3.15 22 8.04 15 2.31 11 1.95 3 6.65 3 1.59 4 4.03 44 9.31 31 4.57 88 2.69 22 13.6 20 1.42 23 2.85 30 3.61 22 2.42 43 3.47 45 12.8 58 3.17 51 2.12 29 3.53 35 1.73 17 1.34 13 2.75 12 1.18 9
ALD-Flow [66]27.3 2.82 7 7.86 11 2.16 6 2.84 38 10.1 42 1.86 16 3.73 36 10.4 39 1.67 11 3.10 42 16.8 60 1.28 11 2.69 19 3.60 21 1.85 8 2.79 13 11.3 40 2.32 11 2.07 22 3.25 10 3.10 80 2.03 37 5.11 45 1.94 31
RNLOD-Flow [121]28.2 2.66 2 7.33 2 2.17 7 2.53 25 9.46 36 1.86 16 3.94 42 10.7 44 1.95 22 2.50 12 13.5 18 1.21 9 2.68 17 3.62 24 2.05 18 2.99 22 8.59 19 2.75 34 3.00 75 4.54 80 3.25 88 1.48 17 3.24 20 1.76 27
NNF-EAC [103]28.6 3.31 33 8.21 19 2.68 29 2.19 9 7.49 13 1.76 12 2.73 13 6.62 12 1.70 12 3.18 47 15.8 49 1.64 47 2.87 32 3.66 27 2.24 28 3.02 23 8.07 10 2.59 21 2.19 33 3.48 28 1.74 18 2.85 56 6.52 56 3.12 60
IROF++ [58]28.7 3.17 24 8.69 28 2.61 20 2.79 34 9.61 37 2.33 40 3.43 26 8.86 26 2.38 44 2.87 33 14.8 34 1.52 38 2.74 21 3.57 20 2.19 26 3.20 31 9.70 28 2.71 31 1.96 16 3.45 24 1.22 5 1.80 28 4.06 30 2.50 45
PH-Flow [101]29.1 3.19 27 8.87 33 2.71 30 2.84 38 9.33 34 2.37 42 2.85 14 7.20 15 2.36 41 2.92 35 15.4 41 1.51 36 2.63 14 3.42 12 2.04 17 3.03 24 8.52 17 2.49 17 2.69 60 3.60 41 3.13 82 1.25 7 2.53 8 1.34 14
Classic+CPF [83]29.6 3.14 20 8.60 26 2.63 24 3.03 53 10.6 48 2.33 40 3.66 33 9.58 32 2.20 36 2.61 15 14.1 27 1.34 17 2.68 17 3.53 18 2.21 27 2.85 16 7.95 9 2.38 13 2.44 46 3.49 30 2.90 73 1.67 24 3.40 23 2.43 44
Sparse-NonSparse [56]31.1 3.14 20 8.75 30 2.76 37 3.02 51 10.6 48 2.43 47 3.45 28 8.96 27 2.36 41 2.66 19 13.7 22 1.42 23 2.85 30 3.75 33 2.33 33 3.28 33 9.40 25 2.73 32 2.42 43 3.31 13 2.69 57 1.47 16 3.07 18 1.66 21
TC-Flow [46]32.2 2.91 9 8.00 14 2.34 12 2.18 8 8.77 26 1.52 1 3.84 40 10.7 44 1.49 2 3.13 43 16.6 58 1.46 31 2.78 24 3.73 32 1.96 11 3.08 27 11.4 41 2.66 25 1.94 14 3.43 21 3.20 87 3.06 60 7.04 58 4.08 84
LSM [39]33.4 3.12 18 8.62 27 2.75 36 3.00 49 10.5 47 2.44 49 3.43 26 8.85 25 2.35 40 2.66 19 13.6 20 1.44 26 2.82 26 3.68 28 2.36 35 3.38 37 9.41 26 2.81 38 2.69 60 3.52 33 2.84 66 1.59 20 3.38 22 1.80 29
Correlation Flow [75]33.9 3.38 39 8.40 23 2.64 25 2.23 10 7.54 14 1.56 3 5.14 63 13.1 62 1.60 7 2.09 5 8.15 3 1.35 18 3.12 47 4.09 52 2.34 34 4.01 65 11.5 44 4.00 77 2.59 52 3.61 43 3.00 78 1.49 18 3.04 15 1.42 17
SVFilterOh [111]34.0 3.63 47 8.82 31 2.86 41 2.60 27 8.06 18 2.05 24 2.95 15 7.09 14 2.03 25 2.80 30 13.8 25 1.41 22 2.63 14 3.42 12 1.75 7 3.49 46 10.3 33 3.23 57 3.63 94 5.75 112 4.47 105 1.09 4 2.45 7 0.92 5
Ramp [62]34.5 3.18 26 8.83 32 2.73 33 2.89 43 10.1 42 2.44 49 3.27 23 8.43 23 2.38 44 2.74 26 14.2 28 1.46 31 2.82 26 3.69 30 2.29 31 3.37 36 9.31 23 2.93 44 2.62 56 3.38 19 3.19 86 1.54 19 3.21 19 2.24 38
PMF [73]34.8 3.61 45 9.07 36 2.62 22 2.40 14 8.05 17 1.83 15 2.61 9 6.27 10 1.65 10 3.35 56 15.4 41 1.58 42 2.54 8 3.27 8 1.71 6 3.59 50 11.1 39 3.46 63 4.07 103 6.18 117 4.02 103 1.06 3 2.38 5 1.25 12
ProbFlowFields [128]35.0 4.18 65 12.4 78 3.40 70 2.43 19 8.16 20 2.19 30 3.65 32 9.72 34 2.86 64 2.22 7 9.42 6 1.42 23 3.01 40 3.96 43 2.36 35 2.73 12 10.9 34 2.51 18 1.89 13 3.39 20 1.82 22 2.59 50 6.21 54 2.75 52
COFM [59]35.2 3.17 24 9.90 51 2.46 15 2.41 16 8.34 23 1.92 19 3.77 37 10.5 40 2.54 52 2.71 24 14.9 36 1.19 8 3.08 45 3.92 41 3.25 81 3.83 57 10.9 34 3.15 50 2.20 36 3.35 14 2.91 75 1.62 23 2.56 9 2.09 35
FMOF [94]36.2 3.12 18 8.23 21 2.73 33 3.25 62 10.7 55 2.52 56 3.01 18 7.61 17 2.20 36 2.56 13 13.4 16 1.33 14 2.75 22 3.61 22 2.24 28 3.66 52 8.50 16 2.78 36 2.62 56 3.84 55 3.27 90 2.66 53 5.69 48 1.95 33
OAR-Flow [125]37.3 3.37 37 9.87 50 2.67 28 4.22 83 12.8 78 2.87 75 4.95 59 13.4 65 2.66 56 3.23 49 16.4 57 1.37 19 2.83 28 3.82 36 1.97 14 2.49 6 10.9 34 1.87 3 1.52 2 2.82 1 1.86 27 1.85 31 4.35 35 1.68 23
Classic+NL [31]37.5 3.20 29 8.72 29 2.81 40 3.02 51 10.6 48 2.44 49 3.46 29 8.84 24 2.38 44 2.78 29 14.3 29 1.46 31 2.83 28 3.68 28 2.31 32 3.40 39 9.09 22 2.76 35 2.87 69 3.82 54 2.86 70 1.67 24 3.53 26 2.26 41
TV-L1-MCT [64]38.5 3.16 23 8.48 25 2.71 30 3.28 66 10.8 59 2.60 65 3.95 43 10.5 40 2.38 44 2.69 22 13.9 26 1.45 30 2.94 36 3.79 34 2.63 60 3.50 47 9.75 29 3.06 48 2.08 23 3.35 14 2.29 46 1.95 34 3.89 29 2.71 51
SimpleFlow [49]42.2 3.35 34 9.20 39 2.98 48 3.18 58 10.7 55 2.71 68 5.06 61 12.6 60 2.70 58 2.95 37 15.1 38 1.58 42 2.91 35 3.79 34 2.47 45 3.59 50 9.49 27 2.99 46 2.39 41 3.46 25 2.24 45 1.60 21 3.56 27 1.57 20
CostFilter [40]42.3 3.84 50 9.64 46 3.06 50 2.55 26 8.09 19 2.03 22 2.69 12 6.47 11 1.88 18 3.66 66 16.8 60 1.88 58 2.62 13 3.34 10 1.99 15 4.05 66 11.0 38 3.65 70 4.16 105 7.18 124 4.66 107 1.16 5 3.36 21 0.87 3
2DHMM-SAS [92]44.3 3.19 27 8.89 34 2.71 30 3.20 60 11.5 66 2.38 43 5.19 64 12.2 56 2.73 60 2.92 35 15.2 39 1.53 39 2.79 25 3.65 26 2.27 30 3.45 43 9.34 24 2.78 36 2.66 59 3.56 37 3.07 79 2.34 47 5.12 46 2.97 58
MLDP_OF [89]45.4 4.13 61 10.3 58 3.60 78 2.34 12 7.70 15 1.88 18 4.23 48 10.9 47 1.87 17 2.74 26 14.6 33 1.37 19 3.10 46 3.91 40 2.48 49 3.40 39 9.00 21 3.79 73 3.46 88 4.20 71 5.55 111 2.31 45 4.64 40 1.98 34
S2D-Matching [84]45.5 3.36 35 9.66 47 2.86 41 3.19 59 11.1 62 2.46 52 4.86 58 12.9 61 2.47 50 2.67 21 13.2 14 1.44 26 2.87 32 3.72 31 2.38 38 3.45 43 9.76 30 2.95 45 3.05 76 3.79 52 3.30 92 1.95 34 4.16 33 3.00 59
MDP-Flow [26]45.6 3.48 43 9.46 43 3.10 52 2.45 21 7.36 12 2.41 44 3.21 21 8.31 21 2.78 62 3.18 47 17.8 65 1.70 52 3.03 42 3.87 37 2.60 56 3.43 41 12.6 56 2.81 38 2.19 33 3.88 58 1.60 13 4.13 76 9.96 81 3.86 80
AggregFlow [97]46.2 4.25 71 11.9 76 3.26 55 4.46 88 13.7 87 3.43 85 4.76 56 12.4 57 3.93 85 3.28 52 15.6 45 1.68 49 2.89 34 3.89 38 2.08 19 2.32 3 7.75 8 2.14 7 2.06 20 3.77 50 1.48 10 2.07 41 4.11 31 2.36 42
CombBMOF [113]46.5 3.94 54 10.6 62 2.74 35 2.80 35 8.55 25 2.16 28 3.10 20 7.99 20 1.76 13 2.99 38 13.4 16 1.95 62 3.04 43 3.89 38 2.49 50 5.64 92 12.3 51 6.74 106 3.54 90 5.16 99 2.81 63 1.85 31 4.60 39 1.10 7
IROF-TV [53]46.7 3.40 40 9.29 41 2.95 47 2.99 48 11.1 62 2.53 57 3.81 38 9.81 35 2.44 48 3.25 51 16.9 62 1.78 56 3.27 64 4.10 53 2.93 73 4.47 72 16.0 84 3.53 65 1.70 4 3.21 6 1.12 3 1.91 33 4.75 42 2.19 37
S2F-IF [123]48.0 4.51 80 13.6 90 3.31 59 2.90 44 10.4 45 2.48 55 4.07 46 10.8 46 3.15 69 3.31 53 15.7 48 1.90 59 3.17 49 4.19 57 2.55 53 2.81 15 11.6 46 2.60 23 1.86 11 3.67 45 1.87 28 2.11 43 4.64 40 2.54 48
FlowFields [110]50.2 4.57 82 13.7 91 3.38 65 3.01 50 10.6 48 2.59 63 4.19 47 11.1 48 3.30 72 3.17 46 15.0 37 1.96 63 3.21 57 4.24 65 2.61 59 2.91 20 12.4 53 2.66 25 1.84 9 3.46 25 1.84 25 2.50 48 6.15 53 2.79 53
NL-TV-NCC [25]50.3 3.89 52 9.16 38 2.98 48 2.87 42 9.69 38 1.99 20 4.44 52 11.6 51 1.76 13 2.64 18 11.8 9 1.48 35 3.49 78 4.60 85 2.47 45 4.67 79 13.5 63 4.26 84 2.83 67 4.57 82 2.84 66 2.62 51 6.00 52 2.25 40
Sparse Occlusion [54]51.0 3.62 46 9.12 37 2.90 43 2.92 46 9.08 32 2.56 59 4.49 53 11.8 54 2.11 31 3.14 44 15.8 49 1.57 41 3.26 62 4.22 61 2.36 35 3.52 48 10.9 34 2.66 25 5.10 120 6.32 118 3.15 84 2.02 36 4.92 43 1.71 24
EPPM w/o HM [88]51.3 4.25 71 11.1 66 3.13 53 2.36 13 8.35 24 1.76 12 3.72 35 10.2 38 1.81 15 3.24 50 14.5 32 1.94 61 3.16 48 3.94 42 2.82 68 4.78 82 12.9 59 4.32 85 3.64 96 4.54 80 5.73 113 1.76 27 4.11 31 1.94 31
OFH [38]51.4 3.90 53 9.77 49 3.62 81 2.84 38 11.0 61 2.04 23 5.52 69 14.4 70 1.89 19 3.52 59 20.5 81 1.60 45 3.18 51 4.06 51 2.82 68 3.86 58 14.1 71 3.59 67 1.77 6 3.62 44 1.81 21 2.64 52 7.08 60 2.15 36
PGM-C [120]52.0 4.62 86 14.0 95 3.39 67 3.29 68 12.3 71 2.70 67 4.39 51 11.7 52 3.43 75 4.00 74 19.8 72 2.15 68 3.19 52 4.23 62 2.54 51 2.79 13 11.9 48 2.45 16 1.83 7 3.21 6 1.83 23 2.31 45 5.87 49 1.82 30
Occlusion-TV-L1 [63]53.1 3.59 44 9.61 44 2.64 25 2.93 47 10.6 48 2.41 44 6.16 75 15.2 73 2.70 58 3.32 54 17.0 63 1.68 49 3.38 68 4.44 75 2.82 68 3.10 29 13.2 62 2.68 28 2.17 30 3.52 33 1.46 8 4.63 86 11.1 95 3.53 69
Complementary OF [21]54.0 4.44 76 11.2 69 4.04 88 2.51 24 9.77 40 1.74 11 3.93 41 10.6 42 2.04 27 3.87 70 18.8 67 2.19 71 3.17 49 4.00 46 2.92 72 4.64 77 13.8 68 3.64 69 2.17 30 3.36 16 2.51 51 3.08 61 7.04 58 3.65 73
Adaptive [20]55.0 3.29 31 9.43 42 2.28 9 3.10 54 11.4 65 2.46 52 6.58 79 15.7 79 2.52 51 3.14 44 15.6 45 1.56 40 3.67 87 4.46 77 3.48 90 3.32 35 13.0 61 2.38 13 2.76 65 4.39 77 1.93 34 3.58 68 8.18 67 2.88 55
Aniso-Texture [82]55.1 2.96 10 7.72 8 2.54 16 2.48 23 8.26 22 2.24 34 6.48 77 15.9 83 2.63 54 1.96 3 10.1 8 0.98 2 3.26 62 4.21 59 2.60 56 5.74 94 16.9 92 5.61 97 4.47 112 5.88 115 3.33 93 3.51 67 7.12 61 3.68 75
ACK-Prior [27]55.8 4.19 67 9.27 40 3.60 78 2.40 14 8.21 21 1.65 7 3.40 25 8.96 27 1.84 16 2.87 33 14.4 31 1.44 26 3.36 67 4.15 54 3.07 76 6.35 102 16.1 86 4.90 91 4.21 107 4.80 86 6.03 115 3.29 64 5.99 51 2.82 54
CPM-Flow [116]57.4 4.63 87 14.1 98 3.39 67 3.33 69 12.5 75 2.73 69 4.37 49 11.7 52 3.43 75 4.00 74 19.9 74 2.14 67 3.19 52 4.23 62 2.54 51 3.08 27 12.0 49 2.88 42 1.87 12 3.44 22 1.84 25 2.91 58 7.48 65 2.91 57
EpicFlow [102]57.7 4.61 85 14.0 95 3.39 67 3.33 69 12.5 75 2.74 70 5.37 66 14.8 72 3.46 78 3.94 73 19.2 69 2.13 66 3.20 54 4.23 62 2.58 55 2.87 18 12.2 50 2.64 24 1.83 7 3.28 12 1.83 23 3.21 63 7.12 61 3.61 70
DPOF [18]57.9 4.67 90 12.6 83 3.30 57 3.57 74 10.6 48 3.12 82 3.09 19 7.50 16 2.32 39 3.06 41 14.8 34 1.82 57 3.21 57 4.18 56 2.79 67 4.47 72 12.5 55 3.33 58 4.09 104 3.92 60 6.96 117 2.09 42 4.39 36 1.74 26
DeepFlow2 [108]58.6 4.04 58 11.2 69 3.38 65 3.80 76 12.4 74 2.86 74 5.12 62 13.4 65 3.00 65 4.17 79 20.1 76 2.18 70 2.96 37 3.97 44 2.08 19 3.06 26 12.6 56 2.69 29 2.17 30 3.24 9 2.71 58 4.74 88 10.4 88 4.38 89
ROF-ND [107]59.3 4.12 59 10.0 52 3.37 64 2.78 33 8.82 28 2.12 27 4.61 55 11.9 55 2.09 30 2.23 8 6.56 2 1.69 51 3.60 84 4.75 95 2.85 71 4.92 85 13.6 66 3.75 71 4.59 114 5.18 100 4.10 104 2.67 54 5.19 47 3.46 68
TCOF [69]59.4 4.17 64 10.4 60 3.71 83 3.17 55 10.7 55 2.59 63 6.58 79 15.7 79 3.82 83 3.69 68 16.1 54 2.37 78 3.78 90 4.95 104 2.47 45 2.59 8 8.47 15 2.58 20 3.66 97 4.83 87 2.67 56 1.83 30 4.20 34 1.46 18
RFlow [90]60.3 3.82 49 10.0 52 3.44 73 2.61 28 9.73 39 2.02 21 5.66 71 14.5 71 2.05 28 3.93 72 23.1 95 1.90 59 3.24 59 4.19 57 2.66 63 4.12 69 15.2 80 3.34 60 2.61 54 3.56 37 2.65 55 4.48 82 10.5 91 3.93 83
Steered-L1 [118]61.0 3.30 32 8.44 24 2.91 44 1.89 1 7.14 8 1.60 6 3.61 31 9.91 37 1.89 19 3.45 57 19.4 71 1.64 47 3.42 71 4.30 67 3.39 84 5.18 87 14.5 73 4.37 87 5.09 119 5.05 95 10.1 121 5.56 95 10.2 86 6.24 102
HBM-GC [105]61.2 5.25 95 10.5 61 4.34 95 3.17 55 8.78 27 2.94 78 4.38 50 10.6 42 2.68 57 3.59 62 12.8 12 2.47 81 2.96 37 3.64 25 2.64 61 3.96 64 8.26 11 3.56 66 4.40 110 5.92 116 3.62 97 2.55 49 6.34 55 3.29 63
ComplOF-FED-GPU [35]63.0 4.28 73 11.3 71 3.70 82 3.25 62 13.0 80 2.16 28 4.06 45 11.2 49 1.95 22 3.91 71 19.2 69 2.01 64 3.20 54 4.15 54 2.64 61 4.61 76 16.1 86 3.90 75 2.98 74 3.77 50 3.69 98 2.85 56 7.44 64 2.53 47
SRR-TVOF-NL [91]63.3 4.47 78 10.9 64 3.32 61 4.04 80 13.2 83 2.90 76 4.81 57 12.5 58 3.15 69 3.33 55 15.3 40 1.61 46 3.24 59 4.03 50 2.70 65 3.94 62 11.8 47 3.33 58 4.16 105 5.21 103 3.44 96 2.06 40 3.48 24 2.42 43
TF+OM [100]65.2 3.97 55 10.2 55 2.94 46 2.91 45 9.12 33 2.57 62 5.22 65 11.5 50 6.92 93 3.59 62 16.1 54 2.28 75 3.20 54 3.97 44 3.11 77 4.70 80 14.5 73 4.32 85 3.06 78 4.84 88 2.71 58 3.93 72 8.79 72 4.32 88
Aniso. Huber-L1 [22]65.8 3.71 48 10.1 54 3.08 51 4.36 87 13.0 80 3.77 89 6.92 83 15.3 75 3.60 81 3.54 60 15.9 52 2.04 65 3.38 68 4.45 76 2.47 45 3.88 59 12.9 59 2.74 33 3.37 85 4.36 76 2.85 69 3.16 62 7.52 66 2.90 56
DeepFlow [86]67.1 4.49 79 11.7 73 4.14 90 4.26 84 12.8 78 3.36 83 5.96 72 14.2 69 5.10 89 4.89 90 23.1 95 2.67 84 2.98 39 4.00 46 2.11 22 3.26 32 13.5 63 2.84 41 2.09 25 3.10 3 2.77 60 5.83 97 11.4 97 5.45 99
Classic++ [32]67.7 3.37 37 9.67 48 2.91 44 3.28 66 12.1 69 2.61 66 5.46 68 14.1 68 3.00 65 3.63 64 20.2 79 1.70 52 3.24 59 4.34 69 2.60 56 4.65 78 16.0 84 3.60 68 3.09 79 3.94 63 3.28 91 4.64 87 10.4 88 3.71 76
TV-L1-improved [17]67.8 3.36 35 9.63 45 2.62 22 2.82 36 10.7 55 2.23 32 6.50 78 15.8 81 2.73 60 3.80 69 21.3 86 1.76 55 3.34 66 4.38 73 2.39 39 5.97 96 18.1 98 5.67 98 3.57 92 4.92 93 3.43 95 4.01 75 9.84 80 3.44 67
LocallyOriented [52]70.3 4.54 81 12.8 85 3.27 56 4.73 92 14.8 94 3.73 88 7.77 89 18.3 96 3.44 77 3.56 61 15.6 45 2.22 72 3.46 75 4.47 78 2.69 64 3.15 30 10.2 32 3.19 53 2.61 54 4.20 71 2.52 52 4.39 79 8.52 69 5.23 95
SIOF [67]70.5 4.23 69 10.2 55 3.31 59 3.97 78 14.5 92 2.97 79 7.81 91 16.4 86 7.48 94 4.82 86 20.1 76 2.96 87 3.54 81 4.49 79 3.12 78 4.31 70 13.5 63 4.13 80 2.36 40 3.59 40 1.68 16 3.46 66 7.39 63 3.37 65
TriangleFlow [30]72.4 4.12 59 10.6 62 3.47 74 3.47 73 13.1 82 2.41 44 6.00 73 15.2 73 2.17 33 2.99 38 16.0 53 1.58 42 4.46 111 5.79 116 4.15 103 5.42 90 13.9 70 5.24 92 3.10 81 5.47 108 2.90 73 3.02 59 6.82 57 3.64 72
CRTflow [80]73.1 4.18 65 11.8 75 3.20 54 3.22 61 10.8 59 2.43 47 6.20 76 15.5 77 2.63 54 4.21 80 22.0 89 2.24 73 3.32 65 4.34 69 2.44 44 7.43 109 19.3 104 8.15 112 2.55 50 4.09 67 2.59 54 4.60 84 11.2 96 4.45 90
Brox et al. [5]73.2 4.44 76 12.4 78 4.22 93 3.72 75 13.5 86 3.06 80 4.97 60 13.3 64 3.11 67 4.58 84 22.0 89 2.37 78 3.79 92 4.60 85 4.33 107 3.91 61 17.0 93 3.45 62 2.22 37 3.79 52 1.19 4 4.62 85 10.0 82 3.38 66
BriefMatch [124]74.8 3.44 42 9.01 35 2.77 38 2.85 41 9.93 41 2.23 32 2.97 16 7.65 19 1.94 21 3.64 65 20.1 76 1.75 54 4.10 105 4.90 102 5.82 117 7.95 111 17.8 96 8.08 111 4.73 116 5.20 101 12.2 123 7.88 113 12.0 100 13.7 119
Rannacher [23]75.0 4.13 61 11.0 65 3.61 80 3.39 71 12.3 71 2.80 73 7.26 85 17.4 92 3.59 80 4.40 82 23.1 95 2.24 73 3.43 73 4.54 82 2.56 54 5.41 89 18.5 99 4.23 82 2.92 71 3.91 59 2.82 64 3.45 65 9.14 73 3.27 62
F-TV-L1 [15]76.2 5.44 98 12.5 82 5.69 102 5.46 96 15.0 97 4.03 91 7.48 86 16.3 85 3.42 74 5.08 92 23.3 98 2.81 86 3.42 71 4.34 69 3.03 74 4.05 66 15.1 79 3.18 52 2.43 44 3.92 60 1.87 28 3.90 71 9.35 77 2.61 50
Local-TV-L1 [65]77.0 5.33 96 12.6 83 5.19 100 6.90 102 15.7 100 6.22 100 10.0 102 18.2 95 8.89 95 5.81 98 24.7 103 3.70 97 3.05 44 4.00 46 2.39 39 4.05 66 14.6 75 3.09 49 1.95 15 3.11 4 2.15 42 5.85 98 10.8 93 7.34 105
SuperFlow [81]77.0 4.16 63 11.1 66 3.32 61 4.80 93 12.2 70 4.68 95 7.80 90 16.0 84 10.6 103 5.16 94 22.4 93 3.24 94 3.39 70 4.24 65 3.71 94 3.44 42 13.7 67 2.91 43 3.19 82 4.62 84 1.87 28 4.74 88 10.6 92 4.24 86
DF-Auto [115]77.2 5.04 94 13.7 91 3.30 57 6.51 99 14.1 91 6.09 99 8.14 95 16.5 87 10.2 101 5.06 91 21.3 86 3.10 93 3.74 88 4.91 103 3.25 81 2.67 11 11.4 41 2.14 7 3.36 84 5.23 104 1.45 7 4.45 81 9.18 74 4.28 87
TriFlow [95]77.6 4.73 92 12.4 78 3.49 76 4.03 79 12.5 75 3.70 87 8.18 97 17.2 90 10.4 102 3.50 58 15.4 41 2.32 77 3.43 73 4.21 59 3.42 85 3.90 60 12.3 51 3.76 72 7.86 125 5.72 111 16.2 125 2.80 55 5.89 50 2.50 45
CLG-TV [48]77.8 4.00 56 10.3 58 3.40 70 4.33 86 12.3 71 4.08 92 6.78 81 15.5 77 3.64 82 4.07 76 17.7 64 2.39 80 3.79 92 4.86 98 3.23 80 4.48 74 16.5 90 3.80 74 3.55 91 4.65 85 2.89 72 4.00 74 10.1 84 3.18 61
CBF [12]79.2 3.88 51 10.2 55 3.50 77 4.60 90 11.3 64 5.06 96 5.43 67 13.1 62 3.39 73 4.09 77 21.2 85 2.16 69 3.80 95 4.72 94 3.52 91 4.33 71 14.4 72 3.01 47 4.97 117 5.51 109 4.93 109 3.99 73 9.27 76 3.91 82
Bartels [41]80.7 4.43 74 11.1 66 4.17 92 2.83 37 8.84 29 2.56 59 4.54 54 12.5 58 2.80 63 4.87 87 22.1 91 3.05 91 3.58 83 4.35 72 4.15 103 5.55 91 17.5 94 5.78 99 3.74 98 5.02 94 5.98 114 5.21 94 11.9 99 5.20 94
Fusion [6]81.0 4.43 74 13.7 91 4.08 89 2.47 22 8.91 30 2.24 34 3.70 34 9.68 33 3.12 68 3.68 67 19.8 72 2.54 83 4.26 108 5.16 109 4.31 106 6.32 99 16.8 91 6.15 103 4.55 113 5.78 113 3.10 80 7.12 108 13.6 109 7.86 109
p-harmonic [29]81.4 4.64 88 13.0 86 4.43 96 3.41 72 11.9 67 2.93 77 7.60 87 18.1 94 3.96 86 4.65 85 21.0 83 2.97 89 3.46 75 4.33 68 3.34 83 4.75 81 17.5 94 4.60 90 3.05 76 4.17 69 2.15 42 5.09 93 10.9 94 3.77 78
CNN-flow-warp+ref [117]82.4 4.93 93 14.5 102 4.29 94 4.18 82 11.9 67 4.24 93 8.23 98 19.7 103 6.35 92 5.13 93 24.4 102 2.96 87 3.55 82 4.40 74 3.85 96 3.82 56 15.0 77 3.39 61 1.96 16 3.44 22 2.14 41 10.0 117 14.8 114 10.8 115
Dynamic MRF [7]83.0 4.58 83 12.4 78 4.14 90 3.25 62 13.9 88 2.27 38 6.02 74 16.8 88 2.36 41 4.39 81 22.6 94 2.51 82 3.61 85 4.55 83 3.46 87 6.81 104 22.2 114 6.78 108 2.41 42 3.48 28 3.69 98 9.26 115 17.8 118 10.2 112
SegOF [10]83.5 5.85 99 13.5 89 3.98 87 7.40 103 14.9 95 8.13 108 8.55 100 17.3 91 9.01 96 6.50 102 18.1 66 5.14 104 3.90 99 4.53 81 4.81 111 6.57 103 21.7 112 6.81 109 1.65 3 3.49 30 1.08 2 3.71 69 9.23 75 3.63 71
FlowNetS+ft+v [112]84.3 4.22 68 12.1 77 3.48 75 4.50 89 13.4 84 3.85 90 8.29 99 18.4 97 6.20 91 4.87 87 21.6 88 3.01 90 3.93 100 5.04 106 3.47 89 3.71 53 15.3 81 3.21 54 3.32 83 5.12 97 3.87 100 3.76 70 9.44 78 3.74 77
LDOF [28]84.9 4.60 84 13.0 86 3.77 84 4.67 91 15.5 99 3.67 86 5.63 70 14.0 67 4.21 87 5.80 97 27.1 112 3.43 95 3.52 80 4.50 80 3.46 87 4.84 84 17.8 96 4.04 78 2.46 48 4.14 68 3.25 88 4.85 91 12.0 100 3.78 79
Second-order prior [8]85.0 4.03 57 11.6 72 3.35 63 3.88 77 14.0 90 3.08 81 7.21 84 17.6 93 3.57 79 4.14 78 19.9 74 2.31 76 3.66 86 4.86 98 2.73 66 7.32 107 21.2 110 6.76 107 4.02 101 4.58 83 4.01 102 4.27 77 10.4 88 5.12 91
FlowNet2 [122]88.5 8.58 113 18.6 111 6.31 104 9.39 110 17.6 105 9.09 111 8.06 94 15.8 81 9.81 99 5.61 96 16.2 56 4.12 99 4.04 103 4.88 100 3.79 95 4.92 85 16.2 88 4.50 88 4.28 108 6.73 120 2.84 66 2.05 39 4.54 38 1.41 16
StereoFlow [44]88.8 17.1 127 28.1 127 17.9 126 18.7 124 29.7 125 16.5 119 20.1 124 30.9 124 17.5 121 21.2 125 38.3 126 17.9 123 4.60 112 5.05 107 5.52 113 2.38 4 11.5 44 1.77 2 1.25 1 2.92 2 0.71 1 4.49 83 10.3 87 4.23 85
Ad-TV-NDC [36]90.2 8.36 112 14.0 95 11.1 120 12.9 117 19.9 111 12.8 117 14.4 113 23.1 106 12.1 107 7.40 105 20.6 82 6.33 105 3.47 77 4.66 90 2.39 39 3.95 63 13.8 68 3.51 64 2.48 49 3.75 48 2.05 38 9.75 116 12.1 102 16.7 122
Learning Flow [11]93.1 4.23 69 11.7 73 3.41 72 4.16 81 15.3 98 3.42 84 6.78 81 16.9 89 3.83 84 6.41 101 25.3 106 4.25 100 4.66 114 6.01 121 4.00 99 6.33 101 20.7 109 5.30 93 3.09 79 4.84 88 2.91 75 7.08 107 15.0 115 5.27 96
Shiralkar [42]93.3 4.64 88 14.1 98 3.94 85 4.29 85 16.9 103 2.77 71 7.75 88 18.8 99 3.19 71 5.54 95 25.0 105 3.56 96 3.51 79 4.55 83 3.04 75 7.41 108 20.1 108 6.41 104 3.76 99 4.35 75 5.28 110 6.56 104 14.4 113 5.30 97
StereoOF-V1MT [119]93.9 4.71 91 14.1 98 3.95 86 5.10 95 20.3 113 2.78 72 7.98 93 20.7 104 2.57 53 4.48 83 21.1 84 2.79 85 4.20 107 5.29 111 4.10 101 6.85 106 22.3 115 6.42 105 2.45 47 4.17 69 3.15 84 10.5 118 18.4 121 10.5 113
IAOF2 [51]94.6 5.38 97 13.7 91 4.50 97 5.95 98 14.6 93 5.61 98 8.80 101 18.8 99 9.40 97 12.2 115 23.8 101 13.1 118 3.86 96 4.89 101 3.12 78 5.21 88 14.9 76 4.54 89 4.33 109 5.15 98 3.93 101 4.39 79 8.57 70 3.87 81
Modified CLG [34]96.0 7.17 107 17.1 110 6.47 106 6.85 101 14.9 95 7.48 104 14.0 109 24.8 110 15.7 117 8.35 108 27.3 113 6.36 106 3.96 101 4.99 105 4.08 100 4.54 75 19.3 104 4.15 81 2.33 39 3.86 57 2.40 49 6.00 99 13.8 111 5.40 98
2D-CLG [1]96.5 10.1 115 22.6 119 7.59 111 9.84 112 16.9 103 11.1 116 16.9 119 28.2 119 18.8 123 14.1 118 31.1 117 13.1 118 3.86 96 4.62 88 4.53 108 5.98 97 21.2 110 5.97 101 1.76 5 3.14 5 1.46 8 6.29 101 12.9 108 5.81 100
GraphCuts [14]97.0 6.25 100 14.3 101 5.53 101 8.60 106 20.1 112 6.61 102 7.91 92 15.4 76 10.9 104 4.88 89 19.0 68 3.05 91 3.78 90 4.71 92 3.94 97 8.74 116 16.4 89 5.39 95 4.04 102 4.87 90 4.85 108 6.35 102 12.2 103 6.05 101
Filter Flow [19]97.0 6.48 101 14.6 103 4.96 98 5.73 97 15.7 100 5.07 97 10.1 103 18.6 98 14.3 113 9.04 110 23.3 98 7.80 110 3.98 102 4.71 92 4.21 105 5.86 95 15.0 77 5.41 96 4.98 118 6.87 121 2.78 61 4.82 90 8.66 71 3.65 73
SPSA-learn [13]97.2 6.84 106 16.7 108 6.74 107 8.47 105 19.4 109 7.49 105 12.5 105 23.1 106 13.1 111 8.40 109 25.8 109 7.08 108 3.87 98 4.66 90 4.10 101 6.32 99 18.8 100 6.89 110 2.56 51 3.85 56 1.79 19 7.29 109 12.5 105 7.47 107
HBpMotionGpu [43]98.8 6.57 103 15.0 105 5.17 99 8.29 104 18.0 106 8.29 109 14.1 110 26.5 113 13.2 112 6.12 100 25.3 106 3.94 98 3.79 92 4.62 88 3.97 98 4.80 83 15.7 82 4.11 79 4.40 110 5.20 101 2.87 71 6.28 100 11.7 98 7.31 104
GroupFlow [9]99.3 8.00 109 18.6 111 8.09 113 11.1 115 23.7 118 10.3 114 12.6 106 25.6 111 12.8 109 5.84 99 20.3 80 4.39 101 4.69 115 5.81 117 3.67 92 9.29 117 22.4 116 10.1 119 2.11 28 3.99 64 2.29 46 5.75 96 10.0 82 7.39 106
IAOF [50]99.5 6.49 102 14.6 103 6.42 105 9.22 109 18.5 107 7.94 107 16.4 118 27.4 117 13.0 110 8.22 106 22.2 92 7.73 109 3.77 89 4.76 96 3.42 85 6.84 105 18.8 100 4.23 82 3.59 93 4.46 78 2.83 65 7.51 111 10.1 84 10.6 114
Black & Anandan [4]100.0 6.81 105 15.4 106 7.43 109 8.77 107 19.5 110 7.35 103 13.0 107 22.9 105 12.5 108 8.29 107 26.1 110 6.77 107 4.18 106 5.28 110 3.69 93 6.19 98 20.0 107 5.34 94 3.63 94 5.05 95 1.79 19 6.45 103 12.2 103 5.17 93
Nguyen [33]103.2 7.88 108 16.8 109 7.02 108 13.4 118 19.0 108 15.3 118 17.6 120 28.9 120 17.2 120 12.0 114 26.9 111 11.6 116 4.38 109 5.07 108 5.58 116 5.69 93 19.7 106 5.93 100 2.75 63 4.02 66 1.91 33 6.59 105 12.5 105 6.52 103
BlockOverlap [61]103.2 6.67 104 13.1 88 5.87 103 6.62 100 13.9 88 6.53 101 10.6 104 19.5 102 10.1 100 6.97 104 24.9 104 5.13 103 4.38 109 4.61 87 6.37 120 7.47 110 15.7 82 6.05 102 6.23 121 6.41 119 13.0 124 6.92 106 9.60 79 12.2 117
UnFlow [129]104.0 14.6 125 25.8 124 9.09 117 9.40 111 16.8 102 9.89 113 14.2 111 26.9 114 11.2 105 10.0 111 25.4 108 8.67 112 5.43 121 5.90 118 6.72 121 8.64 114 24.0 118 9.41 117 3.51 89 4.90 91 1.37 6 4.37 78 12.6 107 3.33 64
2bit-BM-tele [98]105.5 8.00 109 15.8 107 8.40 115 4.91 94 13.4 84 4.67 94 8.14 95 19.0 101 5.12 90 6.62 103 23.5 100 5.04 102 4.08 104 4.78 97 4.61 110 8.68 115 18.8 100 8.31 113 6.46 123 7.08 123 9.47 120 7.36 110 14.1 112 9.62 111
Horn & Schunck [3]108.9 8.01 111 19.9 113 8.38 114 9.13 108 23.2 117 7.71 106 14.2 111 25.9 112 14.6 115 12.4 116 30.6 115 11.3 115 4.64 113 5.64 113 4.60 109 8.21 113 24.4 119 8.45 114 4.01 100 5.41 105 1.95 35 9.16 114 17.5 116 8.86 110
SILK [79]110.2 9.34 114 20.4 114 10.5 119 10.4 113 21.9 114 10.3 114 16.0 117 27.5 118 14.5 114 10.3 112 29.0 114 8.54 111 4.81 116 5.65 114 5.56 115 9.41 118 25.4 121 8.74 115 2.79 66 3.68 46 4.62 106 10.9 119 17.8 118 12.3 118
Heeger++ [104]111.5 11.9 120 21.8 117 8.08 112 12.5 116 29.7 125 9.42 112 14.8 114 27.1 115 9.68 98 14.3 119 31.0 116 12.7 117 4.98 118 5.74 115 4.97 112 17.5 125 34.1 126 18.4 125 2.75 63 5.44 106 2.15 42 12.3 121 18.8 122 14.8 120
TI-DOFE [24]112.4 13.4 123 23.2 120 16.5 125 16.5 121 24.1 119 18.2 123 20.2 125 31.1 125 20.6 124 19.9 124 32.9 120 20.8 125 4.89 117 5.90 118 5.54 114 8.04 112 23.9 117 8.81 116 2.97 73 4.34 74 1.88 31 10.9 119 17.7 117 11.9 116
HCIC-L [99]116.1 15.7 126 22.0 118 10.1 118 31.5 127 26.6 123 41.0 127 14.8 114 23.1 106 16.8 119 18.4 123 34.4 122 18.2 124 5.94 122 6.35 122 6.35 119 10.6 121 19.2 103 11.4 121 18.7 127 17.8 127 19.2 126 4.93 92 8.34 68 5.16 92
SLK [47]116.2 11.6 118 26.0 125 14.6 124 15.3 120 25.0 121 17.5 121 17.8 122 30.1 123 18.1 122 25.4 127 33.6 121 28.0 127 5.25 119 5.90 118 7.03 122 10.3 120 27.4 123 10.6 120 2.89 70 4.47 79 2.94 77 14.9 124 20.7 124 18.8 123
FFV1MT [106]117.2 12.0 121 23.3 121 8.83 116 10.7 114 26.6 123 8.71 110 15.6 116 29.0 121 12.0 106 16.6 122 36.3 125 15.5 121 6.51 125 6.40 123 10.4 125 16.2 124 30.7 125 17.7 124 3.41 87 5.44 106 3.35 94 12.3 121 18.8 122 14.8 120
Adaptive flow [45]118.8 13.2 122 20.8 115 14.0 123 17.1 123 22.0 115 17.9 122 18.1 123 27.1 115 22.8 126 11.8 113 31.1 117 10.5 113 6.35 124 7.13 125 6.25 118 9.87 119 21.8 113 9.44 118 12.6 126 11.4 126 20.0 127 7.75 112 13.6 109 7.73 108
PGAM+LK [55]120.0 11.8 119 25.6 122 13.9 122 14.8 119 24.4 120 16.7 120 13.2 108 24.0 109 15.0 116 16.2 121 41.2 127 15.3 120 5.40 120 5.45 112 8.10 123 12.3 123 26.5 122 12.1 122 7.42 124 8.24 125 7.87 118 13.2 123 18.3 120 19.4 124
Periodicity [78]120.8 11.2 117 27.0 126 7.46 110 16.6 122 29.8 127 18.2 123 25.3 127 31.2 127 24.9 127 12.7 117 35.7 124 11.1 114 31.7 127 41.4 127 25.1 127 23.8 127 41.5 127 23.8 127 2.92 71 5.62 110 6.90 116 18.6 126 33.1 127 22.3 125
FOLKI [16]121.6 10.5 116 25.6 122 11.9 121 20.9 125 26.2 122 26.1 125 17.6 120 31.1 125 16.5 118 15.4 120 32.6 119 16.0 122 6.16 123 6.53 124 9.07 124 12.2 122 29.7 124 13.0 123 4.67 115 5.83 114 9.41 119 18.2 125 22.8 125 25.1 126
Pyramid LK [2]124.1 13.9 124 20.9 116 21.4 127 24.1 126 23.1 116 30.2 126 20.9 126 29.5 122 21.9 125 22.2 126 34.6 123 25.0 126 18.7 126 23.1 126 20.2 126 21.2 126 24.5 120 21.0 126 6.41 122 7.02 122 10.8 122 25.6 127 31.5 126 34.5 127
AdaConv-v1 [126]128.0 39.2 128 39.9 128 41.8 128 73.0 128 74.5 128 71.1 128 70.1 128 67.3 128 71.8 128 64.4 128 66.2 128 65.9 128 76.5 128 78.1 128 72.0 128 68.2 128 64.9 128 66.5 128 52.3 128 45.1 128 70.9 128 81.8 128 81.6 128 82.3 128
SepConv-v1 [127]128.0 39.2 128 39.9 128 41.8 128 73.0 128 74.5 128 71.1 128 70.1 128 67.3 128 71.8 128 64.4 128 66.2 128 65.9 128 76.5 128 78.1 128 72.0 128 68.2 128 64.9 128 66.5 128 52.3 128 45.1 128 70.9 128 81.8 128 81.6 128 82.3 128
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 Anonymous. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015 submission 744.
[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. Submitted to TIP 2016.
[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.
* 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.