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        
R5.0
angle
error
avg. Army
(Hidden texture)
GT   im0   im1
Mequon
(Hidden texture)
GT   im0   im1
Schefflera
(Hidden texture)
GT   im0   im1
Wooden
(Hidden texture)
GT   im0   im1
Grove
(Synthetic)
GT   im0   im1
Urban
(Synthetic)
GT   im0   im1
Yosemite
(Synthetic)
GT   im0   im1
Teddy
(Stereo)
GT   im0   im1
rank all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext
NNF-Local [87]11.6 7.69 2 26.2 5 3.54 2 7.19 14 30.7 27 6.11 22 5.88 5 19.3 8 4.53 16 4.01 10 23.9 17 2.00 13 11.7 1 16.4 3 5.52 3 10.4 16 29.7 9 9.30 11 5.25 21 20.0 25 2.61 11 1.88 8 6.47 28 0.19 1
MDP-Flow2 [68]13.1 10.3 21 30.4 20 6.57 22 5.28 2 23.9 3 4.13 3 5.46 3 17.6 3 3.58 8 4.49 19 25.3 23 2.11 16 15.8 22 21.4 22 10.2 29 10.6 17 29.9 10 9.87 17 4.44 10 19.3 18 2.81 13 1.39 3 4.82 6 1.11 5
OFLAF [77]13.8 8.96 9 27.9 9 4.57 8 7.36 18 26.4 8 6.68 24 4.80 2 14.9 2 3.37 7 4.43 18 21.2 9 2.81 28 13.4 7 19.0 10 7.08 7 11.4 26 28.0 3 9.28 9 5.35 23 19.1 16 3.15 15 2.47 18 5.73 19 5.50 37
NN-field [71]15.3 8.65 5 28.3 10 4.00 4 8.38 28 33.1 43 7.44 30 5.86 4 19.0 7 4.53 16 3.15 2 21.4 11 1.25 3 12.0 4 16.9 5 5.41 2 6.58 2 20.2 1 3.45 1 8.64 55 23.6 58 2.88 14 2.47 18 8.48 42 0.20 2
PMMST [114]21.1 12.9 49 32.6 32 8.45 46 10.2 44 30.5 24 10.7 61 7.39 17 22.2 14 6.31 34 3.87 9 13.5 1 2.73 24 14.0 10 18.7 9 7.52 8 10.9 23 28.9 6 9.95 18 4.99 18 20.8 30 3.18 17 1.52 4 3.87 3 1.12 6
ComponentFusion [96]24.0 8.86 8 28.7 13 5.91 16 6.30 5 24.2 4 5.98 17 6.79 11 21.6 11 4.99 22 4.11 11 24.4 18 2.04 15 16.2 30 22.0 27 11.3 41 13.4 45 40.4 60 12.4 59 7.66 47 21.3 37 5.22 41 2.05 9 5.21 10 3.61 20
ALD-Flow [66]24.4 8.44 4 27.6 8 4.09 5 6.49 7 27.2 12 5.04 9 7.66 22 24.1 24 3.72 10 4.58 21 27.1 36 2.01 14 16.0 25 22.7 35 8.55 12 9.39 9 33.3 21 8.46 8 7.21 43 18.5 10 17.3 98 4.06 51 11.1 56 5.94 46
HAST [109]25.1 7.13 1 21.8 1 3.37 1 7.28 16 26.1 7 6.10 21 3.86 1 12.2 1 0.97 1 3.85 8 21.3 10 1.50 4 11.7 1 16.5 4 4.64 1 15.1 68 35.5 34 14.0 72 19.4 101 36.3 108 39.0 131 1.24 2 3.55 1 1.32 7
nLayers [57]25.6 8.66 6 25.4 3 4.54 6 13.0 85 32.1 36 13.7 93 7.74 24 21.8 12 8.85 64 3.29 4 18.2 2 1.89 10 11.8 3 16.2 2 6.65 6 12.2 32 28.4 4 10.3 21 8.59 54 21.5 42 4.98 37 2.36 16 5.74 20 5.08 33
LME [70]25.7 9.71 15 29.0 15 6.46 21 5.49 4 22.8 2 4.79 7 8.62 38 22.4 15 11.2 75 4.73 23 28.3 51 2.35 19 16.5 33 21.9 25 12.6 54 10.7 18 34.0 27 9.81 16 5.57 24 21.3 37 3.87 27 2.40 17 6.32 25 4.52 28
NNF-EAC [103]25.8 10.9 30 31.8 27 6.97 24 6.64 9 26.4 8 5.65 11 6.61 9 20.7 9 4.44 15 5.48 42 27.1 36 2.97 33 16.5 33 22.3 31 11.1 38 12.1 31 30.7 11 9.97 19 6.42 34 21.4 39 3.94 29 2.95 33 7.51 37 4.63 30
TC/T-Flow [76]26.8 9.15 10 32.1 29 3.69 3 6.89 12 31.2 31 4.32 4 7.32 16 23.1 19 4.08 11 5.14 33 27.2 39 2.80 27 15.6 21 21.9 25 9.71 22 8.63 6 29.2 7 8.40 6 6.72 36 20.2 27 19.7 112 3.86 49 9.43 46 6.28 53
ProFlow_ROB [147]27.2 10.7 25 32.8 38 5.26 13 7.26 15 30.8 28 5.92 14 9.43 46 29.1 50 5.30 25 4.35 17 25.3 23 1.73 9 17.4 42 24.7 47 9.39 17 9.20 7 33.5 22 9.28 9 3.74 6 21.4 39 0.91 3 4.20 53 11.6 58 6.06 48
WLIF-Flow [93]27.8 9.40 14 27.1 6 6.06 18 10.0 41 33.0 41 9.71 45 7.26 15 22.4 15 5.90 33 4.53 20 23.7 15 2.56 23 16.1 26 22.3 31 11.3 41 12.8 35 33.2 20 10.4 24 6.85 38 18.8 13 7.36 56 2.80 29 6.48 29 5.62 40
FC-2Layers-FF [74]29.3 9.97 17 28.7 13 7.96 35 10.4 46 35.3 52 9.95 47 6.11 7 18.1 6 6.82 38 4.12 12 20.9 7 2.48 22 13.3 6 17.7 6 9.47 19 13.5 46 32.6 15 11.3 37 14.0 82 26.0 72 12.5 79 1.84 6 4.18 4 4.53 29
RNLOD-Flow [121]29.7 7.93 3 24.8 2 5.41 14 8.33 27 31.7 33 6.84 26 7.47 18 23.3 20 4.60 18 3.62 6 21.1 8 1.66 7 14.4 12 21.0 16 7.80 9 12.7 34 32.9 16 12.2 58 17.4 95 34.4 103 20.7 114 2.55 21 5.57 17 5.30 35
Layers++ [37]30.3 10.2 19 29.1 16 8.58 49 10.8 52 30.6 25 11.0 67 5.90 6 17.7 4 6.34 35 3.40 5 18.2 2 1.66 7 12.2 5 16.0 1 9.69 21 13.9 52 33.6 23 11.9 52 13.9 81 27.9 78 8.74 62 2.33 15 4.94 7 5.70 43
FESL [72]31.5 8.67 7 25.6 4 4.73 9 13.6 91 39.4 90 12.9 88 8.22 32 24.3 28 7.10 42 3.76 7 20.3 6 2.12 17 14.1 11 20.1 12 9.08 15 11.2 25 31.0 12 9.80 15 11.3 65 30.4 88 7.66 58 2.10 10 5.40 13 2.40 10
SVFilterOh [111]32.0 12.7 47 28.4 11 8.58 49 9.41 36 29.1 19 8.31 36 6.39 8 17.7 4 5.05 24 3.23 3 18.8 5 0.95 2 14.9 15 20.9 15 6.51 5 13.2 40 32.1 14 11.6 44 22.0 107 46.5 134 30.5 125 1.61 5 4.97 9 2.45 12
TC-Flow [46]33.0 9.24 11 30.9 23 5.24 12 5.48 3 25.7 6 4.01 2 7.25 13 23.3 20 2.66 4 5.52 43 28.4 52 3.26 40 16.7 37 23.9 43 9.52 20 11.7 27 36.8 39 11.5 43 6.69 35 21.4 39 19.0 109 4.21 54 10.6 53 6.91 65
OAR-Flow [125]34.9 10.8 28 34.0 42 6.23 19 8.94 31 31.9 34 7.53 31 10.4 55 30.3 57 7.58 51 5.60 47 25.9 31 3.04 36 17.0 38 24.0 44 9.35 16 8.62 5 33.0 17 7.87 4 3.37 4 14.6 3 5.54 45 4.80 63 10.4 52 9.44 85
AGIF+OF [85]36.0 10.4 22 29.4 18 7.42 28 12.4 77 37.5 65 12.4 82 7.91 29 24.3 28 7.24 44 4.84 27 23.8 16 2.91 30 14.8 14 20.6 14 9.72 23 13.2 40 36.5 37 10.5 26 7.06 40 20.8 30 7.54 57 3.02 38 6.27 23 6.37 55
Efficient-NL [60]36.0 9.31 12 27.5 7 5.65 15 12.1 75 38.1 75 11.2 69 8.07 31 24.1 24 6.69 37 5.39 39 25.9 31 3.51 51 14.9 15 21.1 18 9.39 17 14.0 55 35.2 32 11.1 34 11.5 67 25.7 70 6.90 53 2.19 13 5.45 15 1.94 9
IROF++ [58]36.1 10.2 19 30.9 23 7.02 25 11.1 59 38.1 75 10.7 61 8.32 36 25.1 33 7.61 52 5.83 50 28.0 47 4.08 61 15.4 20 21.3 20 9.83 24 13.6 47 38.0 48 11.3 37 5.83 27 20.8 30 1.97 9 2.32 14 5.71 18 4.87 32
PMF [73]37.5 11.6 39 29.9 19 4.55 7 7.81 21 30.2 21 6.00 18 7.17 12 23.3 20 3.21 6 4.88 29 23.1 13 2.42 20 13.6 8 18.5 7 6.49 4 16.1 76 42.7 73 15.4 81 27.2 123 43.5 130 28.9 122 2.15 12 4.96 8 4.81 31
PH-Flow [101]37.8 10.9 30 32.6 32 7.94 34 10.9 54 37.4 63 10.5 55 7.56 21 22.8 18 7.74 56 5.75 49 27.2 39 4.04 59 14.4 12 19.8 11 8.81 13 13.0 37 33.6 23 11.1 34 12.7 75 23.1 53 17.6 100 1.84 6 4.19 5 4.50 27
Classic+CPF [83]38.8 10.9 30 31.7 26 7.88 33 11.5 65 37.9 71 10.9 65 8.27 34 25.1 33 7.51 50 5.05 31 25.8 29 3.16 38 15.1 18 21.0 16 10.6 30 13.1 38 34.6 30 10.3 21 9.87 59 22.0 47 13.1 85 2.68 24 5.85 21 5.53 38
COFM [59]39.4 10.1 18 32.0 28 7.63 29 8.06 23 30.4 23 7.17 27 8.93 43 25.9 39 8.04 60 4.17 13 24.9 21 1.63 6 18.8 52 24.0 44 18.6 97 14.4 59 33.0 17 11.7 46 8.15 50 20.4 28 14.7 92 3.16 40 5.36 12 8.09 78
3DFlow [135]40.0 12.6 46 34.9 43 5.05 11 8.12 24 31.5 32 5.95 15 6.67 10 21.9 13 2.51 3 4.59 22 18.4 4 3.30 43 16.6 35 23.0 36 10.9 33 19.7 96 46.8 94 19.8 104 18.3 98 24.2 64 33.3 127 1.20 1 3.86 2 0.68 3
Ramp [62]40.3 10.9 30 32.7 36 7.96 35 10.9 54 37.1 60 10.6 57 7.85 25 24.2 26 7.41 48 5.29 36 27.0 35 3.44 46 16.1 26 22.3 31 10.8 31 13.8 50 35.4 33 11.0 33 11.6 68 21.1 35 18.2 104 2.52 20 5.44 14 5.23 34
Sparse-NonSparse [56]40.9 10.7 25 32.5 31 8.38 44 10.9 54 36.8 58 10.7 61 7.95 30 24.5 32 7.30 46 5.42 41 27.6 42 3.49 50 16.1 26 22.1 28 11.0 36 13.3 42 36.0 36 10.6 28 10.6 63 21.1 35 10.9 70 2.91 30 5.93 22 6.18 51
Correlation Flow [75]41.1 11.9 43 35.3 44 6.03 17 6.85 11 28.0 14 4.77 6 8.29 35 25.8 37 2.17 2 4.84 27 27.2 39 2.77 26 18.5 50 25.9 58 11.7 43 16.9 84 39.5 54 16.7 88 12.1 71 24.6 66 17.8 101 2.59 22 7.33 36 3.08 13
LSM [39]41.7 10.4 22 32.6 32 8.24 39 10.8 52 37.4 63 10.4 54 7.85 25 24.3 28 7.05 40 5.32 37 27.6 42 3.41 45 15.8 22 21.5 23 11.1 38 13.7 48 35.6 35 10.9 32 13.0 76 23.2 54 12.5 79 2.99 37 6.43 27 6.14 50
JOF [141]41.8 9.77 16 29.1 16 7.11 26 12.1 75 37.9 71 12.0 78 7.25 13 21.2 10 7.73 54 4.82 25 25.8 29 3.02 35 14.9 15 20.2 13 10.0 28 13.1 38 33.7 25 10.6 28 17.8 96 29.5 83 28.8 121 2.94 32 6.80 32 5.71 44
ProbFlowFields [128]42.1 16.2 66 47.8 80 11.7 77 8.96 32 31.0 29 8.86 39 9.73 50 28.4 48 10.1 69 6.09 58 25.5 26 4.53 71 18.2 48 25.5 51 10.9 33 9.76 13 34.2 28 11.7 46 4.63 11 18.8 13 3.79 26 2.95 33 8.94 45 3.52 18
Classic+NL [31]44.2 10.5 24 31.4 25 8.38 44 11.1 59 37.9 71 10.6 57 7.87 27 24.0 23 7.48 49 5.57 45 27.6 42 3.62 53 15.8 22 21.5 23 10.8 31 14.1 56 37.4 43 11.4 40 14.8 85 25.9 71 13.4 88 2.61 23 5.29 11 6.10 49
S2D-Matching [84]45.7 10.7 25 32.2 30 8.71 51 10.7 50 36.6 57 10.2 50 8.94 44 27.2 44 6.96 39 5.17 34 26.0 33 3.36 44 16.3 31 22.1 28 10.9 33 14.4 59 37.0 40 11.7 46 16.4 90 26.0 72 16.5 96 2.79 28 5.49 16 6.49 56
FMOF [94]45.8 11.0 37 30.4 20 8.33 43 13.0 85 38.5 81 12.6 84 7.51 19 22.6 17 7.34 47 5.06 32 25.2 22 3.44 46 15.3 19 21.3 20 9.87 26 14.9 67 33.1 19 11.4 40 11.7 70 24.3 65 15.0 94 3.92 50 8.59 43 6.28 53
IIOF-NLDP [131]47.6 14.6 54 41.6 63 6.71 23 11.0 58 37.5 65 8.25 35 8.77 41 26.9 42 4.19 12 6.07 57 28.0 47 3.76 55 19.7 65 27.1 72 12.6 54 16.7 81 40.7 63 15.4 81 4.68 15 23.0 51 4.41 33 2.78 27 7.26 35 3.16 14
IROF-TV [53]47.9 11.6 39 35.3 44 9.03 54 11.2 62 38.2 78 10.9 65 8.85 42 26.5 40 7.73 54 6.04 56 33.0 75 3.62 53 17.1 40 23.1 38 13.5 67 16.3 77 44.8 81 13.5 70 3.41 5 16.9 5 1.13 6 2.71 25 6.80 32 5.67 42
TV-L1-MCT [64]49.0 10.9 30 30.5 22 8.56 48 13.8 94 40.9 101 13.2 90 8.68 39 25.8 37 7.98 59 4.83 26 25.7 27 3.26 40 17.4 42 23.5 41 13.7 71 14.8 66 36.7 38 12.7 62 5.84 28 19.4 19 10.1 68 3.53 44 6.42 26 6.63 59
2DHMM-SAS [92]50.3 10.9 30 32.6 32 8.06 37 11.5 65 39.5 91 10.6 57 10.0 53 28.3 47 7.91 58 5.93 52 28.2 50 4.07 60 16.1 26 22.3 31 11.0 36 13.7 48 38.3 50 11.1 34 12.3 73 23.2 54 18.0 103 3.08 39 6.48 29 6.24 52
AggregFlow [97]50.5 13.9 52 33.8 40 11.2 70 13.7 92 39.6 93 12.6 84 12.0 68 31.3 58 13.7 85 5.40 40 23.5 14 3.44 46 17.5 44 25.4 49 7.98 11 8.57 4 25.9 2 8.42 7 7.00 39 24.1 63 4.53 34 5.53 73 9.80 48 11.7 96
SimpleFlow [49]50.5 11.6 39 33.7 39 8.98 53 12.5 81 38.9 84 12.6 84 10.4 55 29.3 53 9.20 65 5.99 53 27.6 42 4.08 61 16.3 31 22.2 30 11.1 38 16.7 81 37.4 43 12.7 62 8.29 51 19.9 23 6.11 50 2.74 26 6.28 24 5.86 45
Aniso-Texture [82]50.9 9.33 13 28.5 12 7.26 27 9.17 34 26.8 11 10.2 50 10.1 54 29.2 52 7.28 45 2.77 1 22.6 12 0.94 1 19.9 68 27.1 72 13.3 65 14.6 63 38.5 51 12.4 59 31.5 129 46.3 133 18.2 104 4.45 58 10.1 49 6.60 58
CostFilter [40]51.0 14.1 53 36.2 50 8.48 47 8.61 30 30.6 25 7.43 29 8.26 33 26.9 42 4.40 14 5.72 48 28.1 49 3.24 39 13.7 9 18.5 7 7.81 10 16.6 80 45.0 86 16.0 85 26.8 121 48.6 137 32.7 126 2.93 31 7.59 38 5.38 36
Adaptive [20]51.5 10.9 30 33.8 40 4.92 10 10.5 47 35.0 51 9.53 44 12.2 69 33.7 62 7.68 53 5.57 45 30.3 61 2.95 32 21.7 93 26.7 67 20.6 104 10.8 20 34.9 31 7.26 3 14.0 82 28.8 82 4.88 35 4.50 60 10.2 51 6.84 63
MDP-Flow [26]51.8 12.2 45 40.6 57 8.88 52 9.32 35 28.3 16 10.5 55 9.09 45 28.1 46 9.37 67 6.03 55 30.6 63 3.99 57 17.2 41 23.1 38 12.4 49 13.9 52 42.7 73 12.5 61 7.10 42 23.6 58 4.09 31 5.35 69 13.2 69 7.09 68
RFlow [90]52.8 14.8 55 43.9 68 11.2 70 6.64 9 26.6 10 5.76 12 11.7 64 35.9 71 5.04 23 4.31 15 27.1 36 1.94 11 19.4 57 26.8 69 13.0 64 14.7 64 42.2 70 11.8 51 13.1 77 22.2 48 13.1 85 5.87 79 14.1 77 8.71 82
Occlusion-TV-L1 [63]53.3 12.9 49 36.1 49 8.26 42 9.51 39 32.7 38 8.99 40 12.3 70 34.4 66 8.27 61 5.53 44 29.8 59 3.04 36 20.5 81 28.5 93 13.8 73 9.95 14 37.9 45 11.6 44 7.64 46 21.8 46 3.47 20 5.69 76 13.9 75 7.59 73
OFH [38]54.5 15.0 57 40.9 59 14.4 90 7.06 13 29.9 20 5.37 10 10.8 58 33.1 61 4.86 21 5.84 51 30.6 63 3.46 49 19.5 60 26.1 60 15.3 80 15.6 72 46.5 93 16.6 87 4.19 8 21.7 44 3.74 25 5.39 71 15.4 88 7.23 69
PWC-Net_ROB [148]57.0 23.5 103 52.0 100 13.4 86 13.0 85 37.8 69 12.4 82 14.0 79 39.3 79 14.4 88 7.08 69 24.7 19 2.76 25 19.9 68 25.7 57 12.7 57 13.8 50 43.4 76 13.4 69 3.79 7 22.4 49 1.03 5 2.14 11 6.78 31 1.08 4
MLDP_OF [89]57.6 18.8 88 51.3 95 16.0 93 8.16 25 32.0 35 6.76 25 10.7 57 31.9 60 5.45 28 4.81 24 26.1 34 2.44 21 18.7 51 24.3 46 13.7 71 15.6 72 37.9 45 18.6 99 19.2 100 28.5 80 38.7 130 3.53 44 7.25 34 4.27 25
DeepFlow2 [108]59.3 15.0 57 43.6 67 11.0 66 10.1 42 34.2 48 9.29 42 12.9 72 36.8 72 11.1 74 7.47 75 32.1 70 4.75 75 17.8 45 25.4 49 9.97 27 10.7 18 40.2 59 10.3 21 6.78 37 18.7 12 13.3 87 9.05 103 17.3 98 15.3 107
DMF_ROB [140]60.5 16.8 72 47.5 79 11.2 70 10.6 49 34.1 47 9.86 46 14.7 82 41.2 91 11.9 78 7.41 74 33.9 81 4.25 64 18.8 52 25.9 58 12.7 57 11.9 29 41.3 68 11.7 46 4.39 9 18.8 13 5.30 43 6.00 81 14.9 84 8.11 79
S2F-IF [123]60.7 18.0 81 51.9 98 10.9 63 11.1 59 38.6 82 10.6 57 13.9 77 40.6 88 13.4 84 7.68 82 32.6 72 5.18 81 19.7 65 27.2 75 13.3 65 10.8 20 39.5 54 11.9 52 4.99 18 19.9 23 6.26 51 3.26 42 10.1 49 3.57 19
PGM-C [120]61.1 17.7 76 50.5 89 11.0 66 11.9 69 39.1 86 11.6 74 13.9 77 40.4 87 13.3 83 7.52 78 35.8 92 4.62 74 19.6 63 27.5 78 12.4 49 9.48 11 37.9 45 9.36 12 4.63 11 16.9 5 5.02 38 4.83 64 14.2 80 6.69 60
Steered-L1 [118]61.2 11.4 38 37.9 52 7.71 32 4.42 1 21.7 1 3.76 1 7.71 23 25.7 35 4.29 13 4.91 30 29.8 59 2.26 18 20.2 75 26.7 67 16.6 87 18.1 90 46.1 92 14.6 74 32.4 130 37.9 115 51.5 140 8.58 100 15.5 90 15.2 106
Sparse Occlusion [54]61.7 12.7 47 35.8 48 8.24 39 12.4 77 33.4 44 13.4 91 9.67 48 29.1 50 6.55 36 5.99 53 28.5 53 3.56 52 19.4 57 26.4 65 12.4 49 14.7 64 39.4 53 11.7 46 37.7 137 48.6 137 17.8 101 3.66 46 9.43 46 5.64 41
Classic++ [32]62.0 10.8 28 32.7 36 8.25 41 10.5 47 32.9 39 10.7 61 10.8 58 31.6 59 8.46 62 5.25 35 29.7 58 2.99 34 20.0 71 28.0 86 13.9 75 15.2 70 44.1 79 11.9 52 17.3 94 26.2 74 18.3 106 5.82 78 12.7 65 8.14 80
CPM-Flow [116]62.0 17.7 76 50.5 89 11.0 66 11.9 69 39.0 85 11.7 75 13.7 76 39.8 85 13.2 81 7.49 77 35.5 89 4.58 73 19.5 60 27.2 75 12.3 48 9.44 10 37.3 42 9.46 13 5.05 20 19.5 20 5.17 40 5.21 67 14.8 82 7.36 71
FlowFields+ [130]62.2 18.4 83 52.2 102 11.4 74 11.9 69 39.9 95 11.5 71 14.9 85 43.4 97 14.4 88 7.97 85 33.1 76 5.58 85 19.4 57 26.9 71 12.7 57 10.2 15 39.9 57 10.5 26 4.74 16 20.1 26 4.29 32 3.80 47 12.4 63 3.48 17
EpicFlow [102]63.4 17.7 76 50.6 91 10.9 63 12.0 73 39.3 89 11.7 75 14.5 81 42.2 93 13.2 81 7.47 75 35.5 89 4.57 72 19.8 67 27.6 79 12.8 62 9.73 12 38.1 49 10.1 20 4.63 11 17.2 7 4.88 35 5.31 68 14.3 81 7.47 72
NL-TV-NCC [25]64.1 16.5 69 40.4 55 9.10 55 10.7 50 37.0 59 8.07 33 8.59 37 26.8 41 3.17 5 6.24 60 33.4 77 3.26 40 21.4 90 29.7 106 12.7 57 21.2 102 48.2 96 17.3 93 13.4 80 35.6 106 13.0 84 4.73 62 12.8 66 3.24 15
ACK-Prior [27]64.2 19.5 93 41.5 61 14.3 89 6.57 8 27.6 13 4.53 5 7.87 27 25.7 35 3.70 9 4.33 16 25.7 27 1.53 5 20.5 81 25.6 54 18.3 94 23.1 114 44.0 78 18.5 98 29.9 125 33.1 96 45.6 138 7.91 96 14.8 82 11.7 96
BriefMatch [124]64.2 11.8 42 35.7 47 6.41 20 7.52 19 30.3 22 5.97 16 7.54 20 24.2 26 4.62 19 4.28 14 25.4 25 1.98 12 20.6 83 26.2 63 20.9 106 26.8 124 49.2 97 28.2 126 22.8 112 35.9 107 39.6 134 9.81 106 15.1 86 18.3 115
CombBMOF [113]64.9 15.2 59 48.2 82 7.67 30 11.3 63 34.5 49 9.95 47 8.75 40 27.2 44 5.37 27 7.60 81 32.1 70 5.65 88 18.0 47 23.0 36 13.9 75 21.7 107 44.9 83 24.3 117 22.6 109 37.2 110 14.5 91 2.97 36 7.73 40 4.35 26
FlowFields [110]65.2 18.3 82 51.9 98 11.1 69 11.9 69 39.5 91 11.5 71 14.8 83 43.3 96 14.2 86 7.96 84 33.5 80 5.52 84 19.9 68 27.6 79 13.6 69 11.0 24 40.5 61 12.1 56 4.93 17 19.7 21 5.34 44 3.85 48 12.3 62 3.89 22
Complementary OF [21]66.2 20.9 96 51.7 96 21.5 104 6.41 6 28.3 16 4.86 8 9.56 47 30.2 56 5.62 29 8.21 87 31.4 66 6.20 91 19.2 55 25.6 54 15.5 81 21.5 105 49.3 99 17.4 94 6.34 32 19.8 22 11.5 73 6.44 88 16.1 94 10.2 89
TF+OM [100]67.3 14.8 55 35.4 46 7.68 31 9.06 33 28.4 18 9.32 43 11.6 63 28.4 48 16.0 94 6.43 61 29.0 56 4.29 65 20.2 75 25.6 54 18.4 95 17.9 88 38.5 51 16.9 91 16.6 91 33.8 99 14.7 92 6.87 91 15.5 90 9.68 86
ROF-ND [107]67.8 18.4 83 45.8 75 11.5 75 7.31 17 25.4 5 6.02 19 9.70 49 29.4 54 4.66 20 9.09 93 28.7 54 5.98 90 21.6 92 29.5 103 14.5 78 19.9 97 44.8 81 15.3 80 33.3 134 41.0 121 30.1 124 2.95 33 7.63 39 2.41 11
DeepFlow [86]69.2 17.5 75 46.9 77 16.5 94 11.8 67 35.8 53 11.2 69 15.1 86 39.6 83 15.2 92 7.81 83 32.6 72 5.12 80 17.8 45 25.5 51 9.86 25 12.0 30 44.9 83 11.4 40 6.11 31 18.0 8 12.8 82 10.8 112 18.7 106 18.8 117
ComplOF-FED-GPU [35]69.5 17.9 79 52.0 100 15.4 92 7.90 22 33.9 46 5.82 13 10.8 58 34.2 64 5.67 30 6.99 68 31.5 67 4.51 70 19.2 55 26.3 64 12.9 63 18.2 91 50.5 106 18.6 99 15.1 87 23.6 58 22.3 116 5.37 70 15.4 88 6.76 61
TCOF [69]69.7 17.2 74 45.4 74 15.3 91 12.6 82 37.6 67 12.3 80 15.7 88 39.5 81 16.6 96 6.72 64 27.7 46 4.48 69 22.5 100 30.9 117 11.9 44 9.21 8 28.4 4 10.8 31 22.9 113 35.0 105 9.29 64 4.22 55 11.3 57 6.79 62
TV-L1-improved [17]69.8 11.9 43 36.8 51 8.23 38 8.49 29 31.0 29 7.83 32 11.9 66 33.7 62 7.19 43 5.35 38 28.9 55 2.91 30 20.3 79 28.0 86 12.0 46 27.2 126 55.4 117 30.4 129 23.1 115 38.0 116 22.9 117 5.61 75 14.0 76 7.74 76
EPPM w/o HM [88]70.6 19.4 91 53.2 105 11.2 70 8.23 26 34.8 50 6.07 20 11.1 61 35.1 69 5.89 32 7.31 72 33.4 77 4.76 76 18.9 54 23.2 40 17.1 89 21.3 103 50.3 105 20.1 105 20.7 105 30.3 87 40.9 136 3.20 41 8.13 41 5.59 39
HBM-GC [105]71.2 31.9 109 41.2 60 25.6 111 13.2 88 32.9 39 14.2 95 9.93 52 24.4 31 8.75 63 10.1 102 24.7 19 6.95 99 16.6 35 21.1 18 13.6 69 18.5 92 33.7 25 15.5 83 33.9 136 47.5 136 20.1 113 3.38 43 8.62 44 5.97 47
Aniso. Huber-L1 [22]73.3 13.6 51 40.4 55 9.77 56 19.4 101 40.1 97 22.0 102 16.4 92 38.4 74 18.3 99 7.56 79 33.4 77 5.00 79 20.1 74 27.7 84 12.5 52 14.5 61 39.7 56 10.4 24 20.8 106 32.0 91 12.9 83 4.35 56 10.8 54 6.56 57
Rannacher [23]74.0 15.5 62 43.5 66 10.7 60 11.4 64 35.8 53 11.5 71 14.2 80 39.0 78 10.8 71 6.59 63 30.8 65 4.20 63 21.0 86 29.6 105 12.6 54 19.1 94 50.8 107 15.2 78 14.7 84 26.8 75 16.7 97 4.86 65 12.9 67 7.03 67
SIOF [67]74.0 16.5 69 40.1 54 10.8 62 10.3 45 37.1 60 9.10 41 16.4 92 38.3 73 18.4 100 8.56 88 35.1 87 5.87 89 21.3 89 28.5 93 16.5 86 17.6 86 43.6 77 19.7 103 7.08 41 21.6 43 3.65 23 6.65 89 16.1 94 10.9 93
F-TV-L1 [15]74.4 31.8 108 60.6 110 43.6 126 13.7 92 38.4 80 13.1 89 15.6 87 39.4 80 10.1 69 10.9 105 37.3 98 8.78 106 20.0 71 26.5 66 16.0 85 12.9 36 40.7 63 10.7 30 9.68 58 23.7 61 3.52 22 4.49 59 12.0 60 4.19 24
FF++_ROB [146]74.7 19.0 89 52.4 104 12.2 81 12.4 77 40.0 96 11.9 77 16.2 90 45.2 100 16.3 95 9.16 95 35.6 91 7.36 102 20.2 75 28.0 86 13.8 73 13.3 42 40.5 61 12.8 64 5.68 25 19.2 17 8.50 60 4.50 60 11.8 59 7.66 74
Brox et al. [5]77.2 18.5 85 51.2 93 20.8 103 14.0 95 37.8 69 15.1 97 13.6 75 38.8 76 11.7 76 7.20 71 36.8 95 4.02 58 23.0 104 28.5 93 24.3 116 10.8 20 45.3 88 9.57 14 7.81 48 22.7 50 1.58 7 9.61 105 19.2 109 15.0 105
LocallyOriented [52]77.5 15.8 65 41.5 61 10.9 63 15.0 97 44.5 107 13.7 93 17.6 96 43.4 97 14.2 86 7.16 70 31.5 67 4.82 77 21.0 86 29.0 99 12.5 52 11.7 27 34.5 29 12.9 65 11.6 68 29.6 84 12.0 76 7.94 97 18.4 103 11.1 94
SRR-TVOF-NL [91]77.5 22.3 102 44.7 70 12.5 82 12.0 73 38.1 75 10.2 50 14.8 83 40.6 88 10.9 73 6.13 59 34.1 82 2.81 28 19.6 63 25.5 51 13.5 67 16.4 78 42.4 71 13.0 66 30.5 126 42.5 126 18.3 106 6.41 87 11.0 55 12.0 98
DPOF [18]78.4 20.5 95 50.2 88 10.5 57 12.6 82 41.8 103 11.0 67 11.8 65 34.3 65 10.8 71 8.61 90 38.9 105 5.43 82 19.5 60 26.1 60 15.1 79 16.8 83 41.5 69 15.2 78 23.3 116 23.9 62 50.1 139 5.05 66 14.1 77 4.13 23
CRTflow [80]79.0 16.5 69 49.5 85 10.6 59 9.63 40 33.8 45 8.65 38 13.1 73 38.8 76 7.80 57 6.86 66 34.3 84 4.44 68 20.0 71 27.8 85 12.2 47 31.4 132 59.0 127 36.7 133 10.3 60 30.4 88 12.0 76 8.56 99 20.4 116 12.9 103
Bartels [41]81.2 19.3 90 39.6 53 22.4 107 9.47 38 28.2 15 10.0 49 9.91 51 29.7 55 7.09 41 9.18 96 29.3 57 7.40 103 21.7 93 27.6 79 21.1 108 19.1 94 44.4 80 24.2 116 23.0 114 36.3 108 36.2 128 7.46 95 14.9 84 11.5 95
Dynamic MRF [7]82.1 22.0 100 52.3 103 25.2 109 7.67 20 33.0 41 6.18 23 12.4 71 39.8 85 5.34 26 6.49 62 35.4 88 3.86 56 22.9 102 29.2 101 20.7 105 22.2 109 57.8 124 22.9 113 7.42 44 18.1 9 25.1 118 13.2 119 21.3 121 20.5 121
CBF [12]84.2 15.2 59 44.8 71 12.1 79 23.7 108 37.7 68 30.9 113 13.2 74 34.6 67 14.5 90 6.86 66 32.8 74 4.32 66 22.6 101 28.4 92 20.2 102 15.6 72 41.0 66 12.1 56 32.9 132 39.7 119 29.8 123 5.49 72 13.2 69 8.30 81
DF-Auto [115]84.7 19.4 91 46.0 76 10.5 57 26.6 114 46.1 111 31.1 114 23.7 109 46.1 102 37.0 114 9.05 92 36.8 95 5.59 86 21.7 93 29.1 100 17.4 91 7.80 3 31.8 13 7.93 5 19.5 102 37.4 112 3.25 18 10.9 113 19.6 112 16.4 109
Local-TV-L1 [65]84.7 24.6 104 51.2 93 30.0 112 22.5 107 40.6 99 25.2 106 23.5 108 46.1 102 28.3 109 9.73 99 37.4 99 6.92 98 18.3 49 25.2 48 12.7 57 13.9 52 43.2 75 12.0 55 5.25 21 20.6 29 5.15 39 15.8 124 21.0 119 32.1 129
TriangleFlow [30]85.0 18.7 87 43.9 68 18.0 95 10.1 42 37.2 62 8.18 34 11.9 66 35.5 70 5.81 31 6.72 64 34.6 86 4.37 67 26.7 126 34.7 127 23.4 112 23.1 114 49.6 100 23.5 114 16.7 92 37.2 110 16.3 95 6.85 90 17.3 98 10.3 90
SuperFlow [81]86.1 16.2 66 42.7 65 13.0 84 20.9 102 39.6 93 25.0 105 19.7 101 40.6 88 31.8 111 9.89 101 41.2 108 7.16 100 20.9 85 27.1 72 20.3 103 12.2 32 41.1 67 11.3 37 19.0 99 32.1 93 3.87 27 10.1 108 19.3 110 16.4 109
LDOF [28]86.1 17.1 73 48.0 81 12.9 83 13.3 89 40.6 99 12.2 79 15.8 89 42.4 94 12.7 80 9.70 98 44.0 113 6.27 93 20.7 84 28.0 86 16.8 88 14.3 58 45.9 91 13.8 71 8.36 52 23.3 56 7.98 59 11.2 116 21.2 120 18.3 115
CNN-flow-warp+ref [117]87.3 18.5 85 50.0 86 13.9 88 17.8 99 37.9 71 21.1 101 21.3 105 47.3 106 29.7 110 9.13 94 38.8 102 6.72 96 21.8 96 28.2 90 19.6 99 14.2 57 45.7 90 13.1 67 5.94 29 18.5 10 10.9 70 12.4 118 20.6 118 16.4 109
CLG-TV [48]87.4 15.7 64 42.2 64 11.7 77 20.9 102 39.2 88 24.8 104 16.4 92 39.5 81 18.0 98 9.23 97 37.9 100 6.54 94 22.9 102 30.0 110 17.9 93 16.5 79 47.2 95 14.2 73 19.9 103 30.4 88 11.5 73 5.79 77 14.1 77 6.98 66
TriFlow [95]88.0 21.3 98 44.9 72 13.5 87 16.0 98 36.5 56 18.7 99 18.2 98 38.6 75 27.8 107 7.35 73 30.3 61 5.59 86 21.2 88 27.3 77 18.5 96 15.1 68 37.1 41 15.0 77 49.5 142 41.7 123 95.6 145 6.38 86 13.3 71 9.77 87
p-harmonic [29]88.2 21.2 97 63.8 116 20.6 102 12.4 77 35.9 55 12.7 87 17.7 97 47.5 107 14.9 91 10.9 105 42.1 110 8.85 107 20.4 80 26.1 60 17.1 89 17.9 88 52.5 110 18.4 96 15.6 89 28.6 81 5.86 47 5.89 80 13.5 72 7.67 75
FlowNetS+ft+v [112]89.2 15.2 59 44.9 72 10.7 60 13.4 90 38.2 78 13.4 91 18.8 100 42.8 95 24.4 102 9.01 91 38.8 102 6.24 92 23.2 107 31.5 122 15.9 83 13.3 42 42.6 72 13.1 67 18.2 97 32.6 94 21.9 115 8.73 101 19.1 108 12.8 102
OFRF [134]89.4 20.1 94 40.7 58 18.8 97 25.4 112 43.7 105 27.8 111 20.4 103 39.7 84 25.4 103 12.5 107 34.3 84 11.1 110 17.0 38 23.7 42 8.99 14 17.6 86 40.0 58 16.7 88 15.0 86 28.4 79 28.3 120 16.1 125 19.4 111 34.6 130
Second-order prior [8]91.8 15.6 63 48.2 82 12.1 79 12.6 82 39.1 86 12.3 80 16.2 90 44.6 99 12.2 79 7.57 80 31.6 69 5.45 83 22.2 97 30.6 112 14.3 77 20.8 101 56.8 121 17.7 95 28.0 124 33.8 99 27.1 119 7.43 94 17.4 100 10.4 92
Fusion [6]95.5 17.9 79 57.7 107 18.6 96 9.42 37 32.3 37 10.2 50 11.4 62 34.8 68 11.7 76 8.57 89 40.2 106 6.89 97 25.0 119 30.8 116 24.9 122 23.9 117 52.3 109 25.0 120 33.3 134 43.4 128 19.3 111 9.01 102 18.8 107 13.4 104
Learning Flow [11]96.0 16.4 68 47.3 78 11.5 75 14.0 95 40.3 98 14.4 96 16.4 92 41.7 92 15.6 93 8.05 86 40.7 107 4.87 78 27.1 128 35.0 129 22.5 111 17.2 85 50.0 104 16.0 85 15.5 88 34.1 102 13.9 90 10.1 108 20.2 115 12.5 101
LiteFlowNet [143]96.0 32.9 111 71.7 129 19.9 99 18.2 100 45.2 109 17.8 98 21.8 106 55.4 113 17.5 97 10.7 104 34.2 83 7.20 101 24.3 115 30.7 115 20.9 106 21.5 105 52.5 110 18.4 96 11.3 65 33.3 97 3.15 15 6.04 82 13.5 72 7.98 77
StereoFlow [44]96.4 85.4 145 89.0 145 87.9 144 73.1 145 88.5 145 68.8 140 66.8 144 87.5 143 52.4 136 81.5 144 91.1 144 78.5 143 25.9 123 27.6 79 29.7 130 6.38 1 29.4 8 6.60 2 1.39 1 10.9 1 0.20 1 6.34 85 13.8 74 10.3 90
SegOF [10]99.2 28.8 107 51.1 92 13.2 85 37.3 124 51.8 122 44.6 126 30.0 116 53.0 111 43.3 124 27.0 125 49.6 120 22.4 121 24.0 114 27.6 79 28.4 129 24.9 120 58.5 125 24.4 118 2.04 2 16.2 4 0.47 2 10.0 107 16.5 96 16.7 112
AugFNG_ROB [144]101.4 44.1 124 62.1 113 25.2 109 42.2 129 56.7 127 50.8 131 37.7 126 66.7 126 42.9 122 19.0 114 41.2 108 13.4 111 26.5 124 32.3 125 23.4 112 22.6 111 57.7 123 21.1 108 6.07 30 27.3 76 0.91 3 5.54 74 15.1 86 3.80 21
Ad-TV-NDC [36]101.5 44.8 126 63.0 114 69.1 136 40.3 127 48.4 116 48.3 129 34.8 122 58.5 115 39.9 117 26.5 124 47.8 118 27.7 125 20.2 75 28.5 93 11.9 44 15.2 70 40.9 65 14.7 75 8.46 53 21.0 34 5.69 46 23.9 135 28.3 135 41.9 141
Shiralkar [42]101.6 22.0 100 69.5 123 19.6 98 10.9 54 42.6 104 8.48 37 18.4 99 54.0 112 9.43 68 10.1 102 45.4 114 7.72 104 21.5 91 28.9 98 15.9 83 26.8 124 60.7 129 25.4 122 24.3 119 29.9 86 39.4 132 11.0 114 23.8 126 12.2 99
StereoOF-V1MT [119]101.8 21.7 99 68.0 121 20.3 101 11.8 67 50.4 119 7.18 28 20.7 104 62.8 121 9.21 66 9.80 100 50.8 121 6.56 95 27.9 130 35.8 130 23.9 114 25.0 121 67.3 133 24.0 115 8.00 49 27.7 77 12.2 78 13.4 120 23.5 125 15.8 108
WOLF_ROB [149]102.6 26.7 106 70.6 125 21.9 105 21.8 106 51.3 121 19.4 100 28.0 113 61.1 120 26.7 106 12.6 108 42.5 112 10.5 109 22.2 97 28.7 97 19.4 98 21.3 103 55.6 118 19.6 102 7.42 44 23.5 57 8.87 63 11.1 115 20.5 117 20.0 120
FlowNet2 [122]105.7 47.2 128 61.0 111 42.4 123 44.5 131 57.5 128 51.3 132 37.6 125 64.7 123 43.1 123 21.0 118 35.8 92 17.9 117 25.8 120 30.6 112 24.6 118 20.4 98 49.7 102 21.0 106 32.5 131 53.3 141 4.06 30 4.13 52 13.0 68 1.49 8
ContFlow_ROB [150]106.6 49.6 133 71.9 130 36.6 118 34.6 122 54.5 125 38.5 121 39.2 127 66.6 125 44.2 127 20.7 117 42.4 111 15.1 114 31.6 133 37.3 134 30.5 131 29.2 128 59.0 127 29.0 127 10.5 62 33.7 98 2.73 12 4.40 57 12.5 64 3.33 16
HBpMotionGpu [43]107.8 32.0 110 50.0 86 22.9 108 36.1 123 47.0 113 43.9 125 29.2 115 51.9 110 38.6 116 13.0 109 37.1 97 10.2 108 23.5 109 29.5 103 24.2 115 18.9 93 44.9 83 15.9 84 33.2 133 41.2 122 12.6 81 11.8 117 18.5 104 22.7 122
IAOF2 [51]108.5 25.3 105 49.2 84 22.2 106 24.6 109 44.3 106 28.6 112 20.0 102 45.4 101 25.5 104 49.8 134 57.5 129 60.5 137 23.2 107 31.0 118 15.7 82 23.2 116 49.6 100 19.3 101 30.5 126 39.0 118 19.0 109 9.25 104 18.6 105 9.82 88
Modified CLG [34]109.0 34.8 115 61.1 112 35.3 115 33.3 120 46.5 112 41.7 124 36.8 124 63.0 122 45.1 129 22.1 119 55.4 125 18.7 119 23.9 112 31.2 119 21.7 110 15.8 75 51.5 108 14.8 76 9.01 56 24.6 66 11.1 72 17.6 129 25.7 131 29.6 127
LFNet_ROB [151]109.7 42.0 119 80.9 139 30.7 113 25.2 111 54.8 126 25.3 107 33.7 120 74.4 132 26.0 105 17.2 112 48.0 119 14.4 113 26.5 124 32.5 126 24.8 121 23.0 113 56.4 119 22.7 111 12.5 74 38.3 117 6.87 52 6.05 83 15.7 92 9.05 84
EPMNet [133]110.5 47.1 127 71.6 128 41.3 121 41.8 128 61.0 132 47.5 128 34.2 121 60.0 118 40.1 118 22.9 122 38.8 102 20.2 120 25.8 120 30.6 112 24.6 118 20.4 98 49.7 102 21.0 106 23.9 118 44.7 131 3.33 19 7.39 93 18.0 101 7.28 70
Filter Flow [19]110.7 33.3 112 51.7 96 20.1 100 25.0 110 47.2 115 27.7 110 27.7 112 50.0 108 37.9 115 31.7 127 54.1 124 29.9 126 25.8 120 31.2 119 28.3 128 26.4 123 52.9 113 24.7 119 42.3 139 61.5 143 13.6 89 6.09 84 12.1 61 6.88 64
ResPWCR_ROB [145]110.8 47.7 129 78.6 133 41.4 122 20.9 102 45.6 110 22.0 102 26.3 111 59.1 117 28.2 108 16.7 111 47.4 116 13.7 112 23.7 110 28.3 91 27.2 125 25.0 121 57.6 122 25.4 122 22.7 111 42.0 124 10.0 66 8.31 98 16.9 97 12.2 99
2D-CLG [1]110.9 44.0 123 63.3 115 36.1 116 44.3 130 52.3 123 55.1 134 49.1 135 75.4 133 50.5 133 64.3 140 76.4 139 67.8 140 24.8 117 29.7 106 27.4 126 20.5 100 53.6 114 22.4 110 2.52 3 13.0 2 3.50 21 22.8 134 27.9 134 36.9 133
SPSA-learn [13]111.4 35.8 116 71.2 126 43.1 125 28.4 116 47.0 113 32.8 117 31.4 118 57.7 114 42.2 121 22.2 120 51.0 122 22.9 123 23.9 112 29.4 102 24.6 118 24.8 119 56.5 120 25.1 121 10.7 64 25.1 68 3.72 24 21.7 132 24.9 130 35.5 132
TVL1_ROB [139]111.6 66.6 139 79.1 136 86.0 141 52.8 137 52.6 124 65.8 138 51.6 136 78.2 138 53.6 139 55.5 138 76.0 138 58.3 136 23.0 104 31.4 121 17.6 92 14.5 61 49.2 97 17.1 92 4.65 14 20.9 33 2.19 10 26.8 139 31.5 136 41.0 140
BlockOverlap [61]111.8 41.4 118 54.1 106 36.2 117 27.3 115 41.4 102 32.6 116 26.2 110 46.5 104 31.8 111 20.0 115 36.6 94 18.1 118 22.4 99 26.8 69 25.7 123 24.5 118 45.6 89 21.1 108 39.3 138 47.0 135 43.5 137 13.8 121 16.0 93 28.7 126
IAOF [50]113.1 33.8 113 58.3 108 40.6 119 33.0 119 44.5 107 39.5 122 30.6 117 58.7 116 33.8 113 34.1 130 52.4 123 40.8 130 23.1 106 29.9 108 19.7 101 22.5 110 53.7 115 16.8 90 22.3 108 34.0 101 10.0 66 19.5 130 23.9 127 37.1 135
GraphCuts [14]114.2 34.5 114 59.0 109 32.1 114 26.2 113 51.1 120 26.4 109 28.1 114 51.7 109 40.4 120 13.0 109 47.5 117 7.98 105 23.7 110 30.0 110 24.3 116 33.4 133 45.2 87 25.7 124 31.2 128 37.7 114 36.8 129 10.7 111 19.7 113 17.7 114
Black & Anandan [4]115.2 38.5 117 69.5 123 53.4 128 28.5 117 49.6 118 32.0 115 33.4 119 60.5 119 40.2 119 22.6 121 55.9 126 22.8 122 24.5 116 32.2 124 19.6 99 21.7 107 58.9 126 22.7 111 22.6 109 37.6 113 5.27 42 16.7 127 22.6 124 25.4 124
GroupFlow [9]115.4 42.7 120 67.1 120 53.4 128 44.8 132 63.8 137 50.2 130 36.7 123 69.4 129 43.9 125 17.2 112 46.0 115 16.7 115 27.8 129 34.9 128 21.2 109 36.7 136 67.0 132 43.6 137 6.40 33 21.7 44 7.17 54 16.6 126 25.9 132 25.0 123
2bit-BM-tele [98]117.9 55.1 134 64.1 118 69.1 136 21.4 105 38.7 83 25.3 107 23.3 107 46.7 105 21.2 101 26.2 123 38.7 101 25.2 124 24.9 118 29.9 108 27.7 127 31.3 131 52.6 112 34.6 131 43.3 140 51.7 140 54.5 141 10.3 110 20.1 114 16.8 113
Nguyen [33]120.4 43.9 122 66.0 119 42.8 124 54.0 138 49.4 117 70.1 141 42.9 130 67.4 127 47.3 131 55.4 137 65.7 133 64.4 138 27.0 127 31.8 123 31.0 132 22.8 112 54.8 116 27.3 125 13.1 77 25.2 69 6.08 49 22.2 133 26.9 133 38.9 137
SILK [79]123.0 49.5 132 69.2 122 69.3 138 39.9 126 60.6 131 47.0 127 40.4 129 70.7 130 45.6 130 32.0 128 56.5 127 31.2 128 31.4 132 36.9 133 33.3 134 31.1 130 63.2 130 32.3 130 10.3 60 23.0 51 17.3 98 25.0 136 31.9 137 36.9 133
UnFlow [129]123.9 70.9 141 78.9 134 58.5 131 51.3 136 67.4 140 56.9 135 54.4 138 83.6 141 52.8 137 33.4 129 60.2 130 30.1 127 36.7 141 38.4 137 46.2 142 38.2 137 69.6 136 42.8 136 26.2 120 40.3 120 1.60 8 7.20 92 18.3 102 8.75 83
Periodicity [78]125.4 48.9 131 63.9 117 41.0 120 34.5 121 60.0 130 37.5 120 55.4 139 67.4 127 56.6 140 20.4 116 56.9 128 17.5 116 53.2 144 66.7 145 46.5 143 48.3 142 76.0 143 46.4 139 9.14 57 34.4 103 9.98 65 28.3 140 48.2 144 40.6 139
Horn & Schunck [3]125.9 43.3 121 80.7 138 58.6 132 32.5 118 59.7 129 35.1 118 40.2 128 76.3 136 44.7 128 31.5 126 64.8 131 32.6 129 29.3 131 36.4 132 27.0 124 27.5 127 68.7 134 29.7 128 27.0 122 43.3 127 7.32 55 25.9 137 36.5 140 34.6 130
H+S_ROB [138]129.1 60.1 137 76.9 131 59.9 134 57.3 139 76.3 143 63.5 137 60.9 141 89.5 145 51.6 135 79.9 143 79.2 141 83.1 144 36.5 140 39.6 140 45.4 141 45.4 139 73.7 142 49.8 141 5.73 26 32.8 95 5.96 48 34.5 142 35.1 139 37.9 136
Heeger++ [104]129.2 61.9 138 80.2 137 47.4 127 44.8 132 77.8 144 40.9 123 68.0 145 84.7 142 62.1 143 43.6 133 69.1 134 41.9 131 32.6 135 37.9 135 32.0 133 51.1 143 78.4 144 54.2 143 13.3 79 43.4 128 10.4 69 15.0 122 21.4 122 19.6 118
SLK [47]129.8 44.7 125 78.9 134 59.1 133 58.2 141 71.2 141 70.9 142 47.5 133 83.5 140 50.6 134 65.0 141 69.5 135 73.4 141 34.7 137 38.9 139 42.9 140 34.8 134 70.9 139 39.4 134 12.1 71 29.8 85 11.5 73 34.4 141 40.1 141 48.8 142
FFV1MT [106]132.1 59.9 136 77.8 132 53.6 130 37.7 125 72.5 142 37.0 119 63.6 143 82.1 139 62.4 144 42.8 132 73.9 137 42.6 132 41.9 143 45.8 143 52.3 144 52.5 144 81.8 145 56.1 144 20.2 104 42.4 125 18.3 106 15.0 122 21.4 122 19.6 118
TI-DOFE [24]132.5 73.1 142 84.6 143 89.6 145 61.2 143 64.7 139 74.8 144 58.6 140 88.7 144 58.0 141 70.9 142 81.6 142 76.1 142 31.7 134 38.0 136 35.4 135 29.7 129 68.7 134 36.3 132 17.1 93 32.0 91 8.67 61 35.5 143 42.8 142 49.8 143
FOLKI [16]134.5 48.0 130 71.5 127 68.8 135 48.6 135 63.2 134 59.5 136 43.0 131 75.6 134 44.0 126 40.4 131 65.6 132 45.8 133 35.3 138 40.6 141 41.6 138 36.3 135 71.6 141 44.4 138 23.6 117 44.7 131 40.4 135 36.9 144 43.4 143 54.5 144
PGAM+LK [55]136.8 58.6 135 80.9 139 69.8 139 45.1 134 63.7 136 51.9 133 43.2 132 76.2 135 47.5 132 50.3 135 82.2 143 51.4 134 32.7 136 36.0 131 42.3 139 41.4 138 70.1 137 41.2 135 56.3 143 58.0 142 55.0 142 25.9 137 32.4 138 40.3 138
Adaptive flow [45]137.3 76.7 144 83.7 142 86.4 142 57.9 140 63.6 135 67.3 139 48.7 134 73.2 131 52.9 138 52.7 136 69.9 136 56.0 135 35.4 139 38.4 137 39.4 137 46.1 140 70.6 138 47.6 140 73.1 144 75.2 144 88.1 143 17.2 128 24.6 129 25.6 125
HCIC-L [99]139.5 76.5 143 86.4 144 73.3 140 70.1 144 62.5 133 85.3 145 63.5 142 66.1 124 79.5 145 83.3 145 91.8 145 86.5 145 39.0 142 42.8 142 38.7 136 46.4 141 66.6 131 52.3 142 89.6 145 85.9 145 94.0 144 19.8 131 24.2 128 29.6 127
Pyramid LK [2]141.3 68.1 140 83.5 141 86.8 143 59.4 142 64.5 138 73.1 143 52.8 137 76.3 136 61.4 142 60.2 139 79.0 140 65.9 139 53.8 145 61.8 144 64.5 145 59.4 145 71.1 140 63.0 145 43.9 141 49.4 139 39.5 133 50.2 145 60.2 145 70.8 145
AVG_FLOW_ROB [142]146.2 99.9 146 99.7 146 100.0 146 100.0 146 100.0 146 100.0 146 99.9 146 99.9 146 99.9 146 99.6 146 98.8 146 99.5 146 99.6 146 99.7 146 99.0 146 97.0 146 96.3 146 95.6 146 99.1 146 92.9 146 99.6 146 100.0 151 99.9 146 99.9 146
AdaConv-v1 [126]146.6 100.0 147 99.9 147 100.0 146 100.0 146 100.0 146 100.0 146 99.9 146 99.9 146 99.9 146 100.0 147 100.0 147 99.9 147 99.9 147 99.9 147 99.9 147 99.9 147 99.8 147 100.0 147 99.7 147 97.0 147 99.9 147 99.9 146 99.9 146 99.9 146
SepConv-v1 [127]146.6 100.0 147 99.9 147 100.0 146 100.0 146 100.0 146 100.0 146 99.9 146 99.9 146 99.9 146 100.0 147 100.0 147 99.9 147 99.9 147 99.9 147 99.9 147 99.9 147 99.8 147 100.0 147 99.7 147 97.0 147 99.9 147 99.9 146 99.9 146 99.9 146
SuperSlomo [132]146.6 100.0 147 99.9 147 100.0 146 100.0 146 100.0 146 100.0 146 99.9 146 99.9 146 99.9 146 100.0 147 100.0 147 99.9 147 99.9 147 99.9 147 99.9 147 99.9 147 99.8 147 100.0 147 99.7 147 97.0 147 99.9 147 99.9 146 99.9 146 99.9 146
FGIK [136]146.6 100.0 147 99.9 147 100.0 146 100.0 146 100.0 146 100.0 146 99.9 146 99.9 146 99.9 146 100.0 147 100.0 147 99.9 147 99.9 147 99.9 147 99.9 147 99.9 147 99.8 147 100.0 147 99.7 147 97.0 147 99.9 147 99.9 146 99.9 146 99.9 146
CtxSyn [137]146.6 100.0 147 99.9 147 100.0 146 100.0 146 100.0 146 100.0 146 99.9 146 99.9 146 99.9 146 100.0 147 100.0 147 99.9 147 99.9 147 99.9 147 99.9 147 99.9 147 99.8 147 100.0 147 99.7 147 97.0 147 99.9 147 99.9 146 99.9 146 99.9 146
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.