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]12.2 7.69 2 26.2 5 3.54 2 7.19 15 30.7 28 6.11 23 5.88 5 19.3 8 4.53 18 4.01 10 23.9 18 2.00 13 11.7 1 16.4 3 5.52 3 10.4 17 29.7 9 9.30 11 5.25 24 20.0 27 2.61 13 1.88 8 6.47 28 0.19 1
MDP-Flow2 [68]13.6 10.3 21 30.4 20 6.57 24 5.28 2 23.9 3 4.13 3 5.46 3 17.6 3 3.58 9 4.49 19 25.3 24 2.11 16 15.8 23 21.4 22 10.2 30 10.6 18 29.9 10 9.87 18 4.44 11 19.3 19 2.81 14 1.39 3 4.82 6 1.11 5
OFLAF [77]14.4 8.96 9 27.9 9 4.57 8 7.36 19 26.4 9 6.68 25 4.80 2 14.9 2 3.37 8 4.43 18 21.2 9 2.81 30 13.4 7 19.0 10 7.08 7 11.4 27 28.0 3 9.28 9 5.35 26 19.1 17 3.15 16 2.47 18 5.73 19 5.50 38
NN-field [71]15.9 8.65 5 28.3 10 4.00 4 8.38 29 33.1 44 7.44 31 5.86 4 19.0 7 4.53 18 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 59 23.6 61 2.88 15 2.47 18 8.48 43 0.20 2
PMMST [114]21.9 12.9 50 32.6 32 8.45 48 10.2 45 30.5 25 10.7 62 7.39 18 22.2 14 6.31 36 3.87 9 13.5 1 2.73 26 14.0 10 18.7 9 7.52 8 10.9 24 28.9 6 9.95 19 4.99 20 20.8 32 3.18 18 1.52 4 3.87 3 1.12 6
ComponentFusion [96]25.0 8.86 8 28.7 13 5.91 17 6.30 6 24.2 5 5.98 18 6.79 12 21.6 11 4.99 24 4.11 11 24.4 19 2.04 15 16.2 31 22.0 28 11.3 42 13.4 46 40.4 61 12.4 60 7.66 51 21.3 39 5.22 42 2.05 9 5.21 10 3.61 21
ALD-Flow [66]25.5 8.44 4 27.6 8 4.09 5 6.49 8 27.2 13 5.04 10 7.66 23 24.1 25 3.72 11 4.58 22 27.1 37 2.01 14 16.0 26 22.7 36 8.55 12 9.39 10 33.3 21 8.46 8 7.21 47 18.5 11 17.3 102 4.06 54 11.1 58 5.94 48
HAST [109]25.8 7.13 1 21.8 1 3.37 1 7.28 17 26.1 8 6.10 22 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 70 35.5 34 14.0 74 19.4 104 36.3 111 39.0 135 1.24 2 3.55 1 1.32 7
nLayers [57]26.4 8.66 6 25.4 3 4.54 6 13.0 87 32.1 37 13.7 95 7.74 25 21.8 12 8.85 66 3.29 4 18.2 2 1.89 10 11.8 3 16.2 2 6.65 6 12.2 33 28.4 4 10.3 22 8.59 58 21.5 44 4.98 38 2.36 16 5.74 20 5.08 34
LME [70]26.6 9.71 15 29.0 15 6.46 23 5.49 5 22.8 2 4.79 8 8.62 39 22.4 15 11.2 77 4.73 24 28.3 53 2.35 20 16.5 34 21.9 26 12.6 55 10.7 19 34.0 27 9.81 17 5.57 27 21.3 39 3.87 28 2.40 17 6.32 25 4.52 29
NNF-EAC [103]26.8 10.9 30 31.8 27 6.97 26 6.64 10 26.4 9 5.65 12 6.61 9 20.7 9 4.44 17 5.48 44 27.1 37 2.97 35 16.5 34 22.3 32 11.1 39 12.1 32 30.7 11 9.97 20 6.42 37 21.4 41 3.94 30 2.95 33 7.51 38 4.63 31
TC/T-Flow [76]28.0 9.15 10 32.1 29 3.69 3 6.89 13 31.2 32 4.32 4 7.32 17 23.1 20 4.08 13 5.14 35 27.2 40 2.80 29 15.6 21 21.9 26 9.71 23 8.63 6 29.2 7 8.40 6 6.72 40 20.2 29 19.7 116 3.86 51 9.43 47 6.28 55
ProFlow_ROB [146]28.2 10.7 25 32.8 38 5.26 13 7.26 16 30.8 29 5.92 15 9.43 47 29.1 51 5.30 27 4.35 17 25.3 24 1.73 9 17.4 44 24.7 49 9.39 18 9.20 7 33.5 22 9.28 9 3.74 7 21.4 41 0.91 3 4.20 56 11.6 60 6.06 50
WLIF-Flow [93]28.9 9.40 14 27.1 6 6.06 19 10.0 42 33.0 42 9.71 46 7.26 16 22.4 15 5.90 35 4.53 20 23.7 16 2.56 25 16.1 27 22.3 32 11.3 42 12.8 36 33.2 20 10.4 25 6.85 42 18.8 14 7.36 59 2.80 29 6.48 29 5.62 42
FC-2Layers-FF [74]30.2 9.97 17 28.7 13 7.96 37 10.4 47 35.3 53 9.95 48 6.11 7 18.1 6 6.82 40 4.12 12 20.9 7 2.48 23 13.3 6 17.7 6 9.47 20 13.5 47 32.6 15 11.3 38 14.0 85 26.0 76 12.5 83 1.84 6 4.18 4 4.53 30
RNLOD-Flow [121]30.5 7.93 3 24.8 2 5.41 15 8.33 28 31.7 34 6.84 27 7.47 19 23.3 21 4.60 20 3.62 6 21.1 8 1.66 7 14.4 12 21.0 16 7.80 9 12.7 35 32.9 16 12.2 59 17.4 98 34.4 106 20.7 118 2.55 21 5.57 17 5.30 36
Layers++ [37]31.2 10.2 19 29.1 16 8.58 51 10.8 53 30.6 26 11.0 68 5.90 6 17.7 4 6.34 37 3.40 5 18.2 2 1.66 7 12.2 5 16.0 1 9.69 22 13.9 53 33.6 23 11.9 53 13.9 84 27.9 82 8.74 65 2.33 15 4.94 7 5.70 45
FESL [72]32.4 8.67 7 25.6 4 4.73 9 13.6 93 39.4 92 12.9 90 8.22 33 24.3 29 7.10 44 3.76 7 20.3 6 2.12 17 14.1 11 20.1 12 9.08 15 11.2 26 31.0 12 9.80 16 11.3 68 30.4 92 7.66 61 2.10 10 5.40 13 2.40 11
SVFilterOh [111]33.0 12.7 48 28.4 11 8.58 51 9.41 37 29.1 20 8.31 37 6.39 8 17.7 4 5.05 26 3.23 3 18.8 5 0.95 2 14.9 15 20.9 15 6.51 5 13.2 41 32.1 14 11.6 45 22.0 110 46.5 138 30.5 129 1.61 5 4.97 9 2.45 13
TC-Flow [46]34.5 9.24 11 30.9 23 5.24 12 5.48 4 25.7 7 4.01 2 7.25 14 23.3 21 2.66 5 5.52 45 28.4 54 3.26 42 16.7 38 23.9 45 9.52 21 11.7 28 36.8 39 11.5 44 6.69 39 21.4 41 19.0 113 4.21 57 10.6 55 6.91 69
OAR-Flow [125]36.1 10.8 28 34.0 42 6.23 20 8.94 32 31.9 35 7.53 32 10.4 56 30.3 58 7.58 53 5.60 49 25.9 32 3.04 38 17.0 39 24.0 46 9.35 17 8.62 5 33.0 17 7.87 4 3.37 5 14.6 3 5.54 47 4.80 65 10.4 54 9.44 89
Efficient-NL [60]37.2 9.31 12 27.5 7 5.65 16 12.1 77 38.1 76 11.2 70 8.07 32 24.1 25 6.69 39 5.39 41 25.9 32 3.51 53 14.9 15 21.1 18 9.39 18 14.0 56 35.2 32 11.1 35 11.5 70 25.7 74 6.90 56 2.19 13 5.45 15 1.94 10
AGIF+OF [85]37.2 10.4 22 29.4 18 7.42 30 12.4 79 37.5 66 12.4 84 7.91 30 24.3 29 7.24 46 4.84 28 23.8 17 2.91 32 14.8 14 20.6 14 9.72 24 13.2 41 36.5 37 10.5 27 7.06 44 20.8 32 7.54 60 3.02 38 6.27 23 6.37 57
IROF++ [58]37.2 10.2 19 30.9 23 7.02 27 11.1 60 38.1 76 10.7 62 8.32 37 25.1 34 7.61 54 5.83 52 28.0 49 4.08 63 15.4 20 21.3 20 9.83 25 13.6 48 38.0 49 11.3 38 5.83 30 20.8 32 1.97 11 2.32 14 5.71 18 4.87 33
PMF [73]38.7 11.6 40 29.9 19 4.55 7 7.81 22 30.2 22 6.00 19 7.17 13 23.3 21 3.21 7 4.88 31 23.1 14 2.42 21 13.6 8 18.5 7 6.49 4 16.1 78 42.7 75 15.4 83 27.2 126 43.5 134 28.9 126 2.15 12 4.96 8 4.81 32
PH-Flow [101]38.8 10.9 30 32.6 32 7.94 36 10.9 55 37.4 64 10.5 56 7.56 22 22.8 19 7.74 58 5.75 51 27.2 40 4.04 61 14.4 12 19.8 11 8.81 13 13.0 38 33.6 23 11.1 35 12.7 78 23.1 55 17.6 104 1.84 6 4.19 5 4.50 28
Classic+CPF [83]40.0 10.9 30 31.7 26 7.88 35 11.5 66 37.9 72 10.9 66 8.27 35 25.1 34 7.51 52 5.05 33 25.8 30 3.16 40 15.1 18 21.0 16 10.6 31 13.1 39 34.6 30 10.3 22 9.87 63 22.0 49 13.1 89 2.68 24 5.85 21 5.53 39
COFM [59]40.8 10.1 18 32.0 28 7.63 31 8.06 24 30.4 24 7.17 28 8.93 44 25.9 40 8.04 62 4.17 13 24.9 22 1.63 6 18.8 54 24.0 46 18.6 101 14.4 60 33.0 17 11.7 47 8.15 54 20.4 30 14.7 96 3.16 40 5.36 12 8.09 82
3DFlow [135]41.2 12.6 47 34.9 43 5.05 11 8.12 25 31.5 33 5.95 16 6.67 11 21.9 13 2.51 3 4.59 23 18.4 4 3.30 45 16.6 36 23.0 38 10.9 34 19.7 98 46.8 97 19.8 107 18.3 101 24.2 68 33.3 131 1.20 1 3.86 2 0.68 3
Ramp [62]41.5 10.9 30 32.7 36 7.96 37 10.9 55 37.1 61 10.6 58 7.85 26 24.2 27 7.41 50 5.29 38 27.0 36 3.44 48 16.1 27 22.3 32 10.8 32 13.8 51 35.4 33 11.0 34 11.6 71 21.1 37 18.2 108 2.52 20 5.44 14 5.23 35
Sparse-NonSparse [56]42.1 10.7 25 32.5 31 8.38 46 10.9 55 36.8 59 10.7 62 7.95 31 24.5 33 7.30 48 5.42 43 27.6 43 3.49 52 16.1 27 22.1 29 11.0 37 13.3 43 36.0 36 10.6 29 10.6 66 21.1 37 10.9 74 2.91 30 5.93 22 6.18 53
Correlation Flow [75]42.5 11.9 44 35.3 44 6.03 18 6.85 12 28.0 15 4.77 7 8.29 36 25.8 38 2.17 2 4.84 28 27.2 40 2.77 28 18.5 52 25.9 60 11.7 44 16.9 86 39.5 55 16.7 90 12.1 74 24.6 70 17.8 105 2.59 22 7.33 36 3.08 14
LSM [39]42.9 10.4 22 32.6 32 8.24 41 10.8 53 37.4 64 10.4 55 7.85 26 24.3 29 7.05 42 5.32 39 27.6 43 3.41 47 15.8 23 21.5 23 11.1 39 13.7 49 35.6 35 10.9 33 13.0 79 23.2 56 12.5 83 2.99 37 6.43 27 6.14 52
JOF [140]43.0 9.77 16 29.1 16 7.11 28 12.1 77 37.9 72 12.0 80 7.25 14 21.2 10 7.73 56 4.82 26 25.8 30 3.02 37 14.9 15 20.2 13 10.0 29 13.1 39 33.7 25 10.6 29 17.8 99 29.5 87 28.8 125 2.94 32 6.80 32 5.71 46
ProbFlowFields [128]43.4 16.2 68 47.8 82 11.7 80 8.96 33 31.0 30 8.86 40 9.73 51 28.4 49 10.1 71 6.09 60 25.5 27 4.53 73 18.2 50 25.5 53 10.9 34 9.76 14 34.2 28 11.7 47 4.63 12 18.8 14 3.79 27 2.95 33 8.94 46 3.52 19
Classic+NL [31]45.5 10.5 24 31.4 25 8.38 46 11.1 60 37.9 72 10.6 58 7.87 28 24.0 24 7.48 51 5.57 47 27.6 43 3.62 55 15.8 23 21.5 23 10.8 32 14.1 57 37.4 44 11.4 41 14.8 88 25.9 75 13.4 92 2.61 23 5.29 11 6.10 51
S2D-Matching [84]47.0 10.7 25 32.2 30 8.71 53 10.7 51 36.6 58 10.2 51 8.94 45 27.2 45 6.96 41 5.17 36 26.0 34 3.36 46 16.3 32 22.1 29 10.9 34 14.4 60 37.0 40 11.7 47 16.4 93 26.0 76 16.5 100 2.79 28 5.49 16 6.49 59
FMOF [94]47.2 11.0 38 30.4 20 8.33 45 13.0 87 38.5 82 12.6 86 7.51 20 22.6 17 7.34 49 5.06 34 25.2 23 3.44 48 15.3 19 21.3 20 9.87 27 14.9 68 33.1 19 11.4 41 11.7 73 24.3 69 15.0 98 3.92 52 8.59 44 6.28 55
HCFN [162]49.0 10.9 30 36.7 51 6.43 22 5.32 3 24.0 4 4.44 5 6.63 10 22.6 17 2.60 4 4.85 30 27.9 48 2.54 24 15.6 21 21.5 23 9.30 16 15.0 69 40.7 64 13.9 73 35.1 141 46.6 139 40.3 139 5.63 79 12.3 65 11.0 98
IIOF-NLDP [131]49.0 14.6 55 41.6 65 6.71 25 11.0 59 37.5 66 8.25 36 8.77 42 26.9 43 4.19 14 6.07 59 28.0 49 3.76 57 19.7 67 27.1 74 12.6 55 16.7 83 40.7 64 15.4 83 4.68 16 23.0 53 4.41 34 2.78 27 7.26 35 3.16 15
IROF-TV [53]49.2 11.6 40 35.3 44 9.03 56 11.2 63 38.2 79 10.9 66 8.85 43 26.5 41 7.73 56 6.04 58 33.0 77 3.62 55 17.1 42 23.1 40 13.5 70 16.3 79 44.8 83 13.5 71 3.41 6 16.9 5 1.13 7 2.71 25 6.80 32 5.67 44
TV-L1-MCT [64]50.6 10.9 30 30.5 22 8.56 50 13.8 96 40.9 104 13.2 92 8.68 40 25.8 38 7.98 61 4.83 27 25.7 28 3.26 42 17.4 44 23.5 43 13.7 74 14.8 67 36.7 38 12.7 63 5.84 31 19.4 20 10.1 71 3.53 46 6.42 26 6.63 62
2DHMM-SAS [92]51.7 10.9 30 32.6 32 8.06 39 11.5 66 39.5 93 10.6 58 10.0 54 28.3 48 7.91 60 5.93 54 28.2 52 4.07 62 16.1 27 22.3 32 11.0 37 13.7 49 38.3 51 11.1 35 12.3 76 23.2 56 18.0 107 3.08 39 6.48 29 6.24 54
SimpleFlow [49]52.0 11.6 40 33.7 39 8.98 55 12.5 83 38.9 85 12.6 86 10.4 56 29.3 54 9.20 67 5.99 55 27.6 43 4.08 63 16.3 32 22.2 31 11.1 39 16.7 83 37.4 44 12.7 63 8.29 55 19.9 25 6.11 52 2.74 26 6.28 24 5.86 47
AggregFlow [97]52.2 13.9 53 33.8 40 11.2 73 13.7 94 39.6 95 12.6 86 12.0 69 31.3 59 13.7 88 5.40 42 23.5 15 3.44 48 17.5 46 25.4 51 7.98 11 8.57 4 25.9 2 8.42 7 7.00 43 24.1 67 4.53 35 5.53 76 9.80 49 11.7 101
Aniso-Texture [82]52.5 9.33 13 28.5 12 7.26 29 9.17 35 26.8 12 10.2 51 10.1 55 29.2 53 7.28 47 2.77 1 22.6 12 0.94 1 19.9 71 27.1 74 13.3 68 14.6 64 38.5 52 12.4 60 31.5 133 46.3 137 18.2 108 4.45 60 10.1 51 6.60 61
CostFilter [40]52.5 14.1 54 36.2 50 8.48 49 8.61 31 30.6 26 7.43 30 8.26 34 26.9 43 4.40 16 5.72 50 28.1 51 3.24 41 13.7 9 18.5 7 7.81 10 16.6 82 45.0 88 16.0 87 26.8 124 48.6 142 32.7 130 2.93 31 7.59 39 5.38 37
Adaptive [20]53.1 10.9 30 33.8 40 4.92 10 10.5 48 35.0 52 9.53 45 12.2 70 33.7 63 7.68 55 5.57 47 30.3 63 2.95 34 21.7 96 26.7 69 20.6 108 10.8 21 34.9 31 7.26 3 14.0 85 28.8 86 4.88 36 4.50 62 10.2 53 6.84 67
MDP-Flow [26]53.7 12.2 46 40.6 59 8.88 54 9.32 36 28.3 17 10.5 56 9.09 46 28.1 47 9.37 69 6.03 57 30.6 65 3.99 59 17.2 43 23.1 40 12.4 50 13.9 53 42.7 75 12.5 62 7.10 46 23.6 61 4.09 32 5.35 72 13.2 72 7.09 72
RFlow [90]54.7 14.8 56 43.9 70 11.2 73 6.64 10 26.6 11 5.76 13 11.7 65 35.9 73 5.04 25 4.31 15 27.1 37 1.94 11 19.4 59 26.8 71 13.0 65 14.7 65 42.2 72 11.8 52 13.1 80 22.2 50 13.1 89 5.87 83 14.1 81 8.71 86
Occlusion-TV-L1 [63]55.3 12.9 50 36.1 49 8.26 44 9.51 40 32.7 39 8.99 41 12.3 71 34.4 68 8.27 63 5.53 46 29.8 61 3.04 38 20.5 84 28.5 96 13.8 76 9.95 15 37.9 46 11.6 45 7.64 50 21.8 48 3.47 21 5.69 80 13.9 79 7.59 77
WRT [150]55.4 15.4 63 39.7 55 5.30 14 15.2 100 40.5 101 13.7 95 12.4 72 33.7 63 4.05 12 4.55 21 22.8 13 2.34 19 17.0 39 22.7 36 13.0 65 24.7 123 45.1 89 18.9 103 6.51 38 23.5 59 6.55 54 3.24 42 7.37 37 3.24 16
OFH [38]56.6 15.0 58 40.9 61 14.4 93 7.06 14 29.9 21 5.37 11 10.8 59 33.1 62 4.86 23 5.84 53 30.6 65 3.46 51 19.5 62 26.1 62 15.3 84 15.6 74 46.5 96 16.6 89 4.19 9 21.7 46 3.74 26 5.39 74 15.4 92 7.23 73
PWC-Net_ROB [147]58.7 23.5 106 52.0 103 13.4 89 13.0 87 37.8 70 12.4 84 14.0 82 39.3 81 14.4 91 7.08 71 24.7 20 2.76 27 19.9 71 25.7 59 12.7 58 13.8 51 43.4 78 13.4 70 3.79 8 22.4 51 1.03 6 2.14 11 6.78 31 1.08 4
MLDP_OF [89]59.5 18.8 91 51.3 98 16.0 96 8.16 26 32.0 36 6.76 26 10.7 58 31.9 61 5.45 30 4.81 25 26.1 35 2.44 22 18.7 53 24.3 48 13.7 74 15.6 74 37.9 46 18.6 101 19.2 103 28.5 84 38.7 134 3.53 46 7.25 34 4.27 26
DeepFlow2 [108]61.5 15.0 58 43.6 69 11.0 69 10.1 43 34.2 49 9.29 43 12.9 74 36.8 74 11.1 76 7.47 77 32.1 72 4.75 78 17.8 47 25.4 51 9.97 28 10.7 19 40.2 60 10.3 22 6.78 41 18.7 13 13.3 91 9.05 108 17.3 103 15.3 112
SegFlow [160]62.0 17.6 78 50.4 91 10.9 65 11.9 70 39.1 87 11.7 76 13.7 78 39.9 89 13.3 85 7.50 80 35.7 94 4.56 74 19.7 67 27.4 80 13.0 65 9.37 9 37.2 42 9.48 14 5.08 23 19.8 23 5.25 43 4.01 53 11.9 62 5.55 40
DMF_ROB [139]62.5 16.8 74 47.5 81 11.2 73 10.6 50 34.1 48 9.86 47 14.7 85 41.2 94 11.9 80 7.41 76 33.9 83 4.25 66 18.8 54 25.9 60 12.7 58 11.9 30 41.3 70 11.7 47 4.39 10 18.8 14 5.30 45 6.00 85 14.9 88 8.11 83
S2F-IF [123]62.7 18.0 84 51.9 101 10.9 65 11.1 60 38.6 83 10.6 58 13.9 80 40.6 91 13.4 87 7.68 85 32.6 74 5.18 84 19.7 67 27.2 77 13.3 68 10.8 21 39.5 55 11.9 53 4.99 20 19.9 25 6.26 53 3.26 43 10.1 51 3.57 20
PGM-C [120]63.1 17.7 79 50.5 92 11.0 69 11.9 70 39.1 87 11.6 75 13.9 80 40.4 90 13.3 85 7.52 81 35.8 95 4.62 77 19.6 65 27.5 81 12.4 50 9.48 12 37.9 46 9.36 12 4.63 12 16.9 5 5.02 39 4.83 66 14.2 84 6.69 63
Steered-L1 [118]63.5 11.4 39 37.9 53 7.71 34 4.42 1 21.7 1 3.76 1 7.71 24 25.7 36 4.29 15 4.91 32 29.8 61 2.26 18 20.2 78 26.7 69 16.6 91 18.1 92 46.1 95 14.6 76 32.4 134 37.9 119 51.5 145 8.58 105 15.5 94 15.2 111
Sparse Occlusion [54]63.5 12.7 48 35.8 48 8.24 41 12.4 79 33.4 45 13.4 93 9.67 49 29.1 51 6.55 38 5.99 55 28.5 55 3.56 54 19.4 59 26.4 67 12.4 50 14.7 65 39.4 54 11.7 47 37.7 142 48.6 142 17.8 105 3.66 48 9.43 47 5.64 43
CPM-Flow [116]64.0 17.7 79 50.5 92 11.0 69 11.9 70 39.0 86 11.7 76 13.7 78 39.8 87 13.2 83 7.49 79 35.5 91 4.58 76 19.5 62 27.2 77 12.3 49 9.44 11 37.3 43 9.46 13 5.05 22 19.5 21 5.17 41 5.21 70 14.8 86 7.36 75
Classic++ [32]64.1 10.8 28 32.7 36 8.25 43 10.5 48 32.9 40 10.7 62 10.8 59 31.6 60 8.46 64 5.25 37 29.7 60 2.99 36 20.0 74 28.0 89 13.9 78 15.2 72 44.1 81 11.9 53 17.3 97 26.2 78 18.3 110 5.82 82 12.7 68 8.14 84
FlowFields+ [130]64.3 18.4 86 52.2 105 11.4 77 11.9 70 39.9 97 11.5 72 14.9 88 43.4 100 14.4 91 7.97 88 33.1 78 5.58 88 19.4 59 26.9 73 12.7 58 10.2 16 39.9 58 10.5 27 4.74 17 20.1 28 4.29 33 3.80 49 12.4 67 3.48 18
EpicFlow [102]65.5 17.7 79 50.6 94 10.9 65 12.0 75 39.3 91 11.7 76 14.5 84 42.2 96 13.2 83 7.47 77 35.5 91 4.57 75 19.8 70 27.6 82 12.8 63 9.73 13 38.1 50 10.1 21 4.63 12 17.2 7 4.88 36 5.31 71 14.3 85 7.47 76
NL-TV-NCC [25]66.1 16.5 71 40.4 57 9.10 57 10.7 51 37.0 60 8.07 34 8.59 38 26.8 42 3.17 6 6.24 62 33.4 79 3.26 42 21.4 93 29.7 110 12.7 58 21.2 104 48.2 99 17.3 95 13.4 83 35.6 109 13.0 88 4.73 64 12.8 69 3.24 16
BriefMatch [124]66.5 11.8 43 35.7 47 6.41 21 7.52 20 30.3 23 5.97 17 7.54 21 24.2 27 4.62 21 4.28 14 25.4 26 1.98 12 20.6 86 26.2 65 20.9 110 26.8 129 49.2 100 28.2 131 22.8 115 35.9 110 39.6 138 9.81 111 15.1 90 18.3 120
ACK-Prior [27]66.6 19.5 96 41.5 63 14.3 92 6.57 9 27.6 14 4.53 6 7.87 28 25.7 36 3.70 10 4.33 16 25.7 28 1.53 5 20.5 84 25.6 56 18.3 98 23.1 118 44.0 80 18.5 100 29.9 129 33.1 100 45.6 143 7.91 101 14.8 86 11.7 101
CombBMOF [113]66.9 15.2 60 48.2 84 7.67 32 11.3 64 34.5 50 9.95 48 8.75 41 27.2 45 5.37 29 7.60 84 32.1 72 5.65 91 18.0 49 23.0 38 13.9 78 21.7 109 44.9 85 24.3 122 22.6 112 37.2 114 14.5 95 2.97 36 7.73 41 4.35 27
FlowFields [110]67.4 18.3 85 51.9 101 11.1 72 11.9 70 39.5 93 11.5 72 14.8 86 43.3 99 14.2 89 7.96 87 33.5 82 5.52 87 19.9 71 27.6 82 13.6 72 11.0 25 40.5 62 12.1 57 4.93 19 19.7 22 5.34 46 3.85 50 12.3 65 3.89 23
Complementary OF [21]68.7 20.9 99 51.7 99 21.5 107 6.41 7 28.3 17 4.86 9 9.56 48 30.2 57 5.62 31 8.21 90 31.4 68 6.20 94 19.2 57 25.6 56 15.5 85 21.5 107 49.3 102 17.4 96 6.34 35 19.8 23 11.5 77 6.44 93 16.1 99 10.2 93
TF+OM [100]69.6 14.8 56 35.4 46 7.68 33 9.06 34 28.4 19 9.32 44 11.6 64 28.4 49 16.0 97 6.43 63 29.0 58 4.29 67 20.2 78 25.6 56 18.4 99 17.9 90 38.5 52 16.9 93 16.6 94 33.8 102 14.7 96 6.87 96 15.5 94 9.68 90
ROF-ND [107]70.0 18.4 86 45.8 77 11.5 78 7.31 18 25.4 6 6.02 20 9.70 50 29.4 55 4.66 22 9.09 96 28.7 56 5.98 93 21.6 95 29.5 107 14.5 81 19.9 99 44.8 83 15.3 82 33.3 138 41.0 125 30.1 128 2.95 33 7.63 40 2.41 12
DeepFlow [86]71.6 17.5 77 46.9 79 16.5 97 11.8 68 35.8 54 11.2 70 15.1 89 39.6 85 15.2 95 7.81 86 32.6 74 5.12 83 17.8 47 25.5 53 9.86 26 12.0 31 44.9 85 11.4 41 6.11 34 18.0 9 12.8 86 10.8 117 18.7 111 18.8 122
ComplOF-FED-GPU [35]71.8 17.9 82 52.0 103 15.4 95 7.90 23 33.9 47 5.82 14 10.8 59 34.2 66 5.67 32 6.99 70 31.5 69 4.51 72 19.2 57 26.3 66 12.9 64 18.2 93 50.5 109 18.6 101 15.1 90 23.6 61 22.3 120 5.37 73 15.4 92 6.76 64
TCOF [69]71.8 17.2 76 45.4 76 15.3 94 12.6 84 37.6 68 12.3 82 15.7 91 39.5 83 16.6 99 6.72 66 27.7 47 4.48 71 22.5 104 30.9 121 11.9 45 9.21 8 28.4 4 10.8 32 22.9 116 35.0 108 9.29 67 4.22 58 11.3 59 6.79 65
TV-L1-improved [17]72.3 11.9 44 36.8 52 8.23 40 8.49 30 31.0 30 7.83 33 11.9 67 33.7 63 7.19 45 5.35 40 28.9 57 2.91 32 20.3 82 28.0 89 12.0 47 27.2 131 55.4 123 30.4 133 23.1 118 38.0 120 22.9 121 5.61 78 14.0 80 7.74 80
EPPM w/o HM [88]72.9 19.4 94 53.2 108 11.2 73 8.23 27 34.8 51 6.07 21 11.1 62 35.1 71 5.89 34 7.31 74 33.4 79 4.76 79 18.9 56 23.2 42 17.1 93 21.3 105 50.3 108 20.1 108 20.7 108 30.3 91 40.9 141 3.20 41 8.13 42 5.59 41
HBM-GC [105]73.3 31.9 112 41.2 62 25.6 114 13.2 90 32.9 40 14.2 98 9.93 53 24.4 32 8.75 65 10.1 105 24.7 20 6.95 102 16.6 36 21.1 18 13.6 72 18.5 94 33.7 25 15.5 85 33.9 140 47.5 141 20.1 117 3.38 44 8.62 45 5.97 49
Aniso. Huber-L1 [22]75.8 13.6 52 40.4 57 9.77 58 19.4 104 40.1 99 22.0 106 16.4 95 38.4 76 18.3 102 7.56 82 33.4 79 5.00 82 20.1 77 27.7 87 12.5 53 14.5 62 39.7 57 10.4 25 20.8 109 32.0 95 12.9 87 4.35 59 10.8 56 6.56 60
Rannacher [23]76.3 15.5 64 43.5 68 10.7 62 11.4 65 35.8 54 11.5 72 14.2 83 39.0 80 10.8 73 6.59 65 30.8 67 4.20 65 21.0 89 29.6 109 12.6 55 19.1 96 50.8 110 15.2 80 14.7 87 26.8 79 16.7 101 4.86 67 12.9 70 7.03 71
SIOF [67]76.7 16.5 71 40.1 56 10.8 64 10.3 46 37.1 61 9.10 42 16.4 95 38.3 75 18.4 103 8.56 91 35.1 89 5.87 92 21.3 92 28.5 96 16.5 90 17.6 88 43.6 79 19.7 106 7.08 45 21.6 45 3.65 24 6.65 94 16.1 99 10.9 97
F-TV-L1 [15]76.8 31.8 111 60.6 113 43.6 131 13.7 94 38.4 81 13.1 91 15.6 90 39.4 82 10.1 71 10.9 108 37.3 101 8.78 109 20.0 74 26.5 68 16.0 89 12.9 37 40.7 64 10.7 31 9.68 62 23.7 64 3.52 23 4.49 61 12.0 63 4.19 25
FF++_ROB [145]77.2 19.0 92 52.4 107 12.2 84 12.4 79 40.0 98 11.9 79 16.2 93 45.2 103 16.3 98 9.16 98 35.6 93 7.36 105 20.2 78 28.0 89 13.8 76 13.3 43 40.5 62 12.8 65 5.68 28 19.2 18 8.50 63 4.50 62 11.8 61 7.66 78
Brox et al. [5]80.0 18.5 88 51.2 96 20.8 106 14.0 97 37.8 70 15.1 100 13.6 77 38.8 78 11.7 78 7.20 73 36.8 98 4.02 60 23.0 108 28.5 96 24.3 122 10.8 21 45.3 91 9.57 15 7.81 52 22.7 52 1.58 9 9.61 110 19.2 114 15.0 110
SRR-TVOF-NL [91]80.0 22.3 105 44.7 72 12.5 85 12.0 75 38.1 76 10.2 51 14.8 86 40.6 91 10.9 75 6.13 61 34.1 84 2.81 30 19.6 65 25.5 53 13.5 70 16.4 80 42.4 73 13.0 67 30.5 130 42.5 130 18.3 110 6.41 92 11.0 57 12.0 103
LocallyOriented [52]80.2 15.8 67 41.5 63 10.9 65 15.0 99 44.5 111 13.7 95 17.6 99 43.4 100 14.2 89 7.16 72 31.5 69 4.82 80 21.0 89 29.0 102 12.5 53 11.7 28 34.5 29 12.9 66 11.6 71 29.6 88 12.0 80 7.94 102 18.4 108 11.1 99
DPOF [18]80.9 20.5 98 50.2 90 10.5 59 12.6 84 41.8 106 11.0 68 11.8 66 34.3 67 10.8 73 8.61 93 38.9 109 5.43 85 19.5 62 26.1 62 15.1 82 16.8 85 41.5 71 15.2 80 23.3 119 23.9 66 50.1 144 5.05 68 14.1 81 4.13 24
CRTflow [80]82.0 16.5 71 49.5 87 10.6 61 9.63 41 33.8 46 8.65 39 13.1 75 38.8 78 7.80 59 6.86 68 34.3 86 4.44 70 20.0 74 27.8 88 12.2 48 31.4 137 59.0 133 36.7 137 10.3 64 30.4 92 12.0 80 8.56 104 20.4 121 12.9 108
Bartels [41]83.9 19.3 93 39.6 54 22.4 110 9.47 39 28.2 16 10.0 50 9.91 52 29.7 56 7.09 43 9.18 99 29.3 59 7.40 106 21.7 96 27.6 82 21.1 112 19.1 96 44.4 82 24.2 121 23.0 117 36.3 111 36.2 132 7.46 100 14.9 88 11.5 100
Dynamic MRF [7]85.1 22.0 103 52.3 106 25.2 112 7.67 21 33.0 42 6.18 24 12.4 72 39.8 87 5.34 28 6.49 64 35.4 90 3.86 58 22.9 106 29.2 105 20.7 109 22.2 112 57.8 130 22.9 117 7.42 48 18.1 10 25.1 122 13.2 124 21.3 126 20.5 126
CBF [12]86.9 15.2 60 44.8 73 12.1 82 23.7 112 37.7 69 30.9 117 13.2 76 34.6 69 14.5 93 6.86 68 32.8 76 4.32 68 22.6 105 28.4 95 20.2 106 15.6 74 41.0 68 12.1 57 32.9 136 39.7 123 29.8 127 5.49 75 13.2 72 8.30 85
Local-TV-L1 [65]87.6 24.6 107 51.2 96 30.0 116 22.5 111 40.6 102 25.2 110 23.5 111 46.1 105 28.3 113 9.73 102 37.4 102 6.92 101 18.3 51 25.2 50 12.7 58 13.9 53 43.2 77 12.0 56 5.25 24 20.6 31 5.15 40 15.8 129 21.0 124 32.1 134
DF-Auto [115]87.7 19.4 94 46.0 78 10.5 59 26.6 118 46.1 115 31.1 118 23.7 112 46.1 105 37.0 118 9.05 95 36.8 98 5.59 89 21.7 96 29.1 104 17.4 95 7.80 3 31.8 13 7.93 5 19.5 105 37.4 116 3.25 19 10.9 118 19.6 117 16.4 114
TriangleFlow [30]88.1 18.7 90 43.9 70 18.0 98 10.1 43 37.2 63 8.18 35 11.9 67 35.5 72 5.81 33 6.72 66 34.6 88 4.37 69 26.7 131 34.7 133 23.4 117 23.1 118 49.6 103 23.5 118 16.7 95 37.2 114 16.3 99 6.85 95 17.3 103 10.3 94
LDOF [28]89.1 17.1 75 48.0 83 12.9 86 13.3 91 40.6 102 12.2 81 15.8 92 42.4 97 12.7 82 9.70 101 44.0 118 6.27 96 20.7 87 28.0 89 16.8 92 14.3 59 45.9 94 13.8 72 8.36 56 23.3 58 7.98 62 11.2 121 21.2 125 18.3 120
SuperFlow [81]89.1 16.2 68 42.7 67 13.0 87 20.9 105 39.6 95 25.0 109 19.7 104 40.6 91 31.8 115 9.89 104 41.2 113 7.16 103 20.9 88 27.1 74 20.3 107 12.2 33 41.1 69 11.3 38 19.0 102 32.1 97 3.87 28 10.1 113 19.3 115 16.4 114
CNN-flow-warp+ref [117]90.4 18.5 88 50.0 88 13.9 91 17.8 102 37.9 72 21.1 104 21.3 108 47.3 109 29.7 114 9.13 97 38.8 106 6.72 99 21.8 99 28.2 93 19.6 103 14.2 58 45.7 93 13.1 68 5.94 32 18.5 11 10.9 74 12.4 123 20.6 123 16.4 114
CLG-TV [48]90.5 15.7 66 42.2 66 11.7 80 20.9 105 39.2 90 24.8 108 16.4 95 39.5 83 18.0 101 9.23 100 37.9 103 6.54 97 22.9 106 30.0 114 17.9 97 16.5 81 47.2 98 14.2 75 19.9 106 30.4 92 11.5 77 5.79 81 14.1 81 6.98 70
TriFlow [95]90.8 21.3 101 44.9 74 13.5 90 16.0 101 36.5 57 18.7 102 18.2 101 38.6 77 27.8 110 7.35 75 30.3 63 5.59 89 21.2 91 27.3 79 18.5 100 15.1 70 37.1 41 15.0 79 49.5 147 41.7 127 95.6 150 6.38 91 13.3 74 9.77 91
p-harmonic [29]91.3 21.2 100 63.8 121 20.6 105 12.4 79 35.9 56 12.7 89 17.7 100 47.5 110 14.9 94 10.9 108 42.1 115 8.85 110 20.4 83 26.1 62 17.1 93 17.9 90 52.5 114 18.4 98 15.6 92 28.6 85 5.86 49 5.89 84 13.5 76 7.67 79
FlowNetS+ft+v [112]92.2 15.2 60 44.9 74 10.7 62 13.4 92 38.2 79 13.4 93 18.8 103 42.8 98 24.4 105 9.01 94 38.8 106 6.24 95 23.2 111 31.5 126 15.9 87 13.3 43 42.6 74 13.1 68 18.2 100 32.6 98 21.9 119 8.73 106 19.1 113 12.8 107
OFRF [134]92.4 20.1 97 40.7 60 18.8 100 25.4 116 43.7 108 27.8 115 20.4 106 39.7 86 25.4 106 12.5 111 34.3 86 11.1 115 17.0 39 23.7 44 8.99 14 17.6 88 40.0 59 16.7 90 15.0 89 28.4 83 28.3 124 16.1 130 19.4 116 34.6 135
Second-order prior [8]94.8 15.6 65 48.2 84 12.1 82 12.6 84 39.1 87 12.3 82 16.2 93 44.6 102 12.2 81 7.57 83 31.6 71 5.45 86 22.2 101 30.6 116 14.3 80 20.8 103 56.8 127 17.7 97 28.0 127 33.8 102 27.1 123 7.43 99 17.4 105 10.4 96
ContinualFlow_ROB [152]97.7 38.4 120 64.1 123 31.4 118 31.9 123 52.5 128 35.2 123 32.8 123 61.5 125 38.0 120 15.4 115 42.4 116 9.42 112 27.2 134 32.9 132 23.6 119 30.9 134 52.8 117 37.9 138 3.27 4 17.7 8 1.31 8 3.48 45 10.0 50 1.76 9
Fusion [6]98.9 17.9 82 57.7 110 18.6 99 9.42 38 32.3 38 10.2 51 11.4 63 34.8 70 11.7 78 8.57 92 40.2 110 6.89 100 25.0 123 30.8 120 24.9 128 23.9 121 52.3 113 25.0 125 33.3 138 43.4 132 19.3 115 9.01 107 18.8 112 13.4 109
LiteFlowNet [142]99.3 32.9 114 71.7 135 19.9 102 18.2 103 45.2 113 17.8 101 21.8 109 55.4 116 17.5 100 10.7 107 34.2 85 7.20 104 24.3 119 30.7 119 20.9 110 21.5 107 52.5 114 18.4 98 11.3 68 33.3 101 3.15 16 6.04 86 13.5 76 7.98 81
Learning Flow [11]99.4 16.4 70 47.3 80 11.5 78 14.0 97 40.3 100 14.4 99 16.4 95 41.7 95 15.6 96 8.05 89 40.7 112 4.87 81 27.1 133 35.0 135 22.5 115 17.2 87 50.0 107 16.0 87 15.5 91 34.1 105 13.9 94 10.1 113 20.2 120 12.5 106
StereoFlow [44]100.0 85.4 150 89.0 150 87.9 149 73.1 150 88.5 150 68.8 145 66.8 149 87.5 148 52.4 141 81.5 149 91.1 149 78.5 148 25.9 127 27.6 82 29.7 136 6.38 1 29.4 8 6.60 2 1.39 1 10.9 1 0.20 1 6.34 90 13.8 78 10.3 94
SegOF [10]103.1 28.8 110 51.1 95 13.2 88 37.3 129 51.8 126 44.6 131 30.0 120 53.0 114 43.3 129 27.0 130 49.6 125 22.4 126 24.0 118 27.6 82 28.4 135 24.9 125 58.5 131 24.4 123 2.04 2 16.2 4 0.47 2 10.0 112 16.5 101 16.7 117
EAI-Flow [151]103.7 40.7 122 62.9 118 39.5 123 21.2 108 43.8 109 21.4 105 25.8 113 57.4 117 28.2 111 11.7 110 38.0 104 9.37 111 21.9 100 29.0 102 15.1 82 22.2 112 50.8 110 20.5 109 29.0 128 36.6 113 10.6 73 5.07 69 13.3 74 6.83 66
Shiralkar [42]105.2 22.0 103 69.5 129 19.6 101 10.9 55 42.6 107 8.48 38 18.4 102 54.0 115 9.43 70 10.1 105 45.4 119 7.72 107 21.5 94 28.9 101 15.9 87 26.8 129 60.7 134 25.4 127 24.3 122 29.9 90 39.4 136 11.0 119 23.8 131 12.2 104
Ad-TV-NDC [36]105.4 44.8 131 63.0 119 69.1 141 40.3 132 48.4 120 48.3 134 34.8 127 58.5 119 39.9 122 26.5 129 47.8 123 27.7 130 20.2 78 28.5 96 11.9 45 15.2 72 40.9 67 14.7 77 8.46 57 21.0 36 5.69 48 23.9 140 28.3 140 41.9 146
AugFNG_ROB [143]105.6 44.1 129 62.1 116 25.2 112 42.2 134 56.7 132 50.8 136 37.7 131 66.7 130 42.9 127 19.0 120 41.2 113 13.4 117 26.5 129 32.3 130 23.4 117 22.6 115 57.7 129 21.1 112 6.07 33 27.3 80 0.91 3 5.54 77 15.1 90 3.80 22
StereoOF-V1MT [119]105.8 21.7 102 68.0 127 20.3 104 11.8 68 50.4 123 7.18 29 20.7 107 62.8 126 9.21 68 9.80 103 50.8 126 6.56 98 27.9 136 35.8 136 23.9 120 25.0 126 67.3 138 24.0 119 8.00 53 27.7 81 12.2 82 13.4 125 23.5 130 15.8 113
CompactFlow_ROB [159]106.0 53.0 138 62.6 117 27.7 115 31.6 122 53.2 130 35.5 124 39.0 132 69.8 134 49.1 137 16.7 116 40.3 111 12.3 116 26.3 128 32.1 128 23.1 116 22.1 111 53.3 119 24.0 119 4.89 18 23.7 64 0.94 5 6.25 89 15.9 97 6.48 58
WOLF_ROB [148]106.5 26.7 109 70.6 131 21.9 108 21.8 110 51.3 125 19.4 103 28.0 117 61.1 124 26.7 109 12.6 112 42.5 117 10.5 114 22.2 101 28.7 100 19.4 102 21.3 105 55.6 124 19.6 105 7.42 48 23.5 59 8.87 66 11.1 120 20.5 122 20.0 125
FlowNet2 [122]109.7 47.2 133 61.0 114 42.4 128 44.5 136 57.5 133 51.3 137 37.6 130 64.7 128 43.1 128 21.0 123 35.8 95 17.9 122 25.8 124 30.6 116 24.6 124 20.4 100 49.7 105 21.0 110 32.5 135 53.3 146 4.06 31 4.13 55 13.0 71 1.49 8
HBpMotionGpu [43]111.6 32.0 113 50.0 88 22.9 111 36.1 128 47.0 117 43.9 130 29.2 119 51.9 113 38.6 121 13.0 113 37.1 100 10.2 113 23.5 113 29.5 107 24.2 121 18.9 95 44.9 85 15.9 86 33.2 137 41.2 126 12.6 85 11.8 122 18.5 109 22.7 127
IAOF2 [51]112.3 25.3 108 49.2 86 22.2 109 24.6 113 44.3 110 28.6 116 20.0 105 45.4 104 25.5 107 49.8 139 57.5 134 60.5 142 23.2 111 31.0 122 15.7 86 23.2 120 49.6 103 19.3 104 30.5 130 39.0 122 19.0 113 9.25 109 18.6 110 9.82 92
Modified CLG [34]113.3 34.8 118 61.1 115 35.3 120 33.3 126 46.5 116 41.7 129 36.8 129 63.0 127 45.1 133 22.1 124 55.4 130 18.7 124 23.9 116 31.2 123 21.7 114 15.8 77 51.5 112 14.8 78 9.01 60 24.6 70 11.1 76 17.6 134 25.7 136 29.6 132
LFNet_ROB [149]114.2 42.0 124 80.9 144 30.7 117 25.2 115 54.8 131 25.3 111 33.7 125 74.4 137 26.0 108 17.2 118 48.0 124 14.4 119 26.5 129 32.5 131 24.8 127 23.0 117 56.4 125 22.7 115 12.5 77 38.3 121 6.87 55 6.05 87 15.7 96 9.05 88
EPMNet [133]114.9 47.1 132 71.6 134 41.3 126 41.8 133 61.0 137 47.5 133 34.2 126 60.0 122 40.1 123 22.9 127 38.8 106 20.2 125 25.8 124 30.6 116 24.6 124 20.4 100 49.7 105 21.0 110 23.9 121 44.7 135 3.33 20 7.39 98 18.0 106 7.28 74
Filter Flow [19]114.9 33.3 115 51.7 99 20.1 103 25.0 114 47.2 119 27.7 114 27.7 116 50.0 111 37.9 119 31.7 132 54.1 129 29.9 131 25.8 124 31.2 123 28.3 134 26.4 128 52.9 118 24.7 124 42.3 144 61.5 148 13.6 93 6.09 88 12.1 64 6.88 68
2D-CLG [1]115.1 44.0 128 63.3 120 36.1 121 44.3 135 52.3 127 55.1 139 49.1 140 75.4 138 50.5 138 64.3 145 76.4 144 67.8 145 24.8 121 29.7 110 27.4 132 20.5 102 53.6 120 22.4 114 2.52 3 13.0 2 3.50 22 22.8 139 27.9 139 36.9 138
ResPWCR_ROB [144]115.2 47.7 134 78.6 138 41.4 127 20.9 105 45.6 114 22.0 106 26.3 115 59.1 121 28.2 111 16.7 116 47.4 121 13.7 118 23.7 114 28.3 94 27.2 131 25.0 126 57.6 128 25.4 127 22.7 114 42.0 128 10.0 69 8.31 103 16.9 102 12.2 104
TVL1_ROB [138]115.7 66.6 144 79.1 141 86.0 146 52.8 142 52.6 129 65.8 143 51.6 141 78.2 143 53.6 144 55.5 143 76.0 143 58.3 141 23.0 108 31.4 125 17.6 96 14.5 62 49.2 100 17.1 94 4.65 15 20.9 35 2.19 12 26.8 144 31.5 141 41.0 145
SPSA-learn [13]115.8 35.8 119 71.2 132 43.1 130 28.4 120 47.0 117 32.8 121 31.4 122 57.7 118 42.2 126 22.2 125 51.0 127 22.9 128 23.9 116 29.4 106 24.6 124 24.8 124 56.5 126 25.1 126 10.7 67 25.1 72 3.72 25 21.7 137 24.9 135 35.5 137
BlockOverlap [61]116.0 41.4 123 54.1 109 36.2 122 27.3 119 41.4 105 32.6 120 26.2 114 46.5 107 31.8 115 20.0 121 36.6 97 18.1 123 22.4 103 26.8 71 25.7 129 24.5 122 45.6 92 21.1 112 39.3 143 47.0 140 43.5 142 13.8 126 16.0 98 28.7 131
IAOF [50]117.3 33.8 116 58.3 111 40.6 124 33.0 125 44.5 111 39.5 127 30.6 121 58.7 120 33.8 117 34.1 135 52.4 128 40.8 135 23.1 110 29.9 112 19.7 105 22.5 114 53.7 121 16.8 92 22.3 111 34.0 104 10.0 69 19.5 135 23.9 132 37.1 140
GraphCuts [14]118.5 34.5 117 59.0 112 32.1 119 26.2 117 51.1 124 26.4 113 28.1 118 51.7 112 40.4 125 13.0 113 47.5 122 7.98 108 23.7 114 30.0 114 24.3 122 33.4 138 45.2 90 25.7 129 31.2 132 37.7 118 36.8 133 10.7 116 19.7 118 17.7 119
Black & Anandan [4]119.6 38.5 121 69.5 129 53.4 133 28.5 121 49.6 122 32.0 119 33.4 124 60.5 123 40.2 124 22.6 126 55.9 131 22.8 127 24.5 120 32.2 129 19.6 103 21.7 109 58.9 132 22.7 115 22.6 112 37.6 117 5.27 44 16.7 132 22.6 129 25.4 129
GroupFlow [9]120.2 42.7 125 67.1 126 53.4 133 44.8 137 63.8 142 50.2 135 36.7 128 69.4 133 43.9 130 17.2 118 46.0 120 16.7 120 27.8 135 34.9 134 21.2 113 36.7 141 67.0 137 43.6 142 6.40 36 21.7 46 7.17 57 16.6 131 25.9 137 25.0 128
2bit-BM-tele [98]122.2 55.1 139 64.1 123 69.1 141 21.4 109 38.7 84 25.3 111 23.3 110 46.7 108 21.2 104 26.2 128 38.7 105 25.2 129 24.9 122 29.9 112 27.7 133 31.3 136 52.6 116 34.6 135 43.3 145 51.7 145 54.5 146 10.3 115 20.1 119 16.8 118
Nguyen [33]125.0 43.9 127 66.0 125 42.8 129 54.0 143 49.4 121 70.1 146 42.9 135 67.4 131 47.3 135 55.4 142 65.7 138 64.4 143 27.0 132 31.8 127 31.0 137 22.8 116 54.8 122 27.3 130 13.1 80 25.2 73 6.08 51 22.2 138 26.9 138 38.9 142
SILK [79]127.8 49.5 137 69.2 128 69.3 143 39.9 131 60.6 136 47.0 132 40.4 134 70.7 135 45.6 134 32.0 133 56.5 132 31.2 133 31.4 138 36.9 139 33.3 139 31.1 135 63.2 135 32.3 134 10.3 64 23.0 53 17.3 102 25.0 141 31.9 142 36.9 138
UnFlow [129]128.6 70.9 146 78.9 139 58.5 136 51.3 141 67.4 145 56.9 140 54.4 143 83.6 146 52.8 142 33.4 134 60.2 135 30.1 132 36.7 146 38.4 142 46.2 147 38.2 142 69.6 141 42.8 141 26.2 123 40.3 124 1.60 10 7.20 97 18.3 107 8.75 87
Periodicity [78]130.2 48.9 136 63.9 122 41.0 125 34.5 127 60.0 135 37.5 126 55.4 144 67.4 131 56.6 145 20.4 122 56.9 133 17.5 121 53.2 149 66.7 150 46.5 148 48.3 147 76.0 148 46.4 144 9.14 61 34.4 106 9.98 68 28.3 145 48.2 149 40.6 144
Horn & Schunck [3]130.7 43.3 126 80.7 143 58.6 137 32.5 124 59.7 134 35.1 122 40.2 133 76.3 141 44.7 132 31.5 131 64.8 136 32.6 134 29.3 137 36.4 138 27.0 130 27.5 132 68.7 139 29.7 132 27.0 125 43.3 131 7.32 58 25.9 142 36.5 145 34.6 135
H+S_ROB [137]133.9 60.1 142 76.9 136 59.9 139 57.3 144 76.3 148 63.5 142 60.9 146 89.5 150 51.6 140 79.9 148 79.2 146 83.1 149 36.5 145 39.6 145 45.4 146 45.4 144 73.7 147 49.8 146 5.73 29 32.8 99 5.96 50 34.5 147 35.1 144 37.9 141
Heeger++ [104]134.0 61.9 143 80.2 142 47.4 132 44.8 137 77.8 149 40.9 128 68.0 150 84.7 147 62.1 148 43.6 138 69.1 139 41.9 136 32.6 140 37.9 140 32.0 138 51.1 148 78.4 149 54.2 148 13.3 82 43.4 132 10.4 72 15.0 127 21.4 127 19.6 123
SLK [47]134.7 44.7 130 78.9 139 59.1 138 58.2 146 71.2 146 70.9 147 47.5 138 83.5 145 50.6 139 65.0 146 69.5 140 73.4 146 34.7 142 38.9 144 42.9 145 34.8 139 70.9 144 39.4 139 12.1 74 29.8 89 11.5 77 34.4 146 40.1 146 48.8 147
FFV1MT [106]137.0 59.9 141 77.8 137 53.6 135 37.7 130 72.5 147 37.0 125 63.6 148 82.1 144 62.4 149 42.8 137 73.9 142 42.6 137 41.9 148 45.8 148 52.3 149 52.5 149 81.8 150 56.1 149 20.2 107 42.4 129 18.3 110 15.0 127 21.4 127 19.6 123
TI-DOFE [24]137.2 73.1 147 84.6 148 89.6 150 61.2 148 64.7 144 74.8 149 58.6 145 88.7 149 58.0 146 70.9 147 81.6 147 76.1 147 31.7 139 38.0 141 35.4 140 29.7 133 68.7 139 36.3 136 17.1 96 32.0 95 8.67 64 35.5 148 42.8 147 49.8 148
FOLKI [16]139.5 48.0 135 71.5 133 68.8 140 48.6 140 63.2 139 59.5 141 43.0 136 75.6 139 44.0 131 40.4 136 65.6 137 45.8 138 35.3 143 40.6 146 41.6 143 36.3 140 71.6 146 44.4 143 23.6 120 44.7 135 40.4 140 36.9 149 43.4 148 54.5 149
PGAM+LK [55]141.8 58.6 140 80.9 144 69.8 144 45.1 139 63.7 141 51.9 138 43.2 137 76.2 140 47.5 136 50.3 140 82.2 148 51.4 139 32.7 141 36.0 137 42.3 144 41.4 143 70.1 142 41.2 140 56.3 148 58.0 147 55.0 147 25.9 142 32.4 143 40.3 143
Adaptive flow [45]142.3 76.7 149 83.7 147 86.4 147 57.9 145 63.6 140 67.3 144 48.7 139 73.2 136 52.9 143 52.7 141 69.9 141 56.0 140 35.4 144 38.4 142 39.4 142 46.1 145 70.6 143 47.6 145 73.1 149 75.2 149 88.1 148 17.2 133 24.6 134 25.6 130
HCIC-L [99]144.5 76.5 148 86.4 149 73.3 145 70.1 149 62.5 138 85.3 150 63.5 147 66.1 129 79.5 150 83.3 150 91.8 150 86.5 150 39.0 147 42.8 147 38.7 141 46.4 146 66.6 136 52.3 147 89.6 150 85.9 150 94.0 149 19.8 136 24.2 133 29.6 132
Pyramid LK [2]146.3 68.1 145 83.5 146 86.8 148 59.4 147 64.5 143 73.1 148 52.8 142 76.3 141 61.4 147 60.2 144 79.0 145 65.9 144 53.8 150 61.8 149 64.5 150 59.4 150 71.1 145 63.0 150 43.9 146 49.4 144 39.5 137 50.2 150 60.2 150 70.8 150
AdaConv-v1 [126]151.6 100.0 152 99.9 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 152 100.0 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.8 152 100.0 152 99.7 152 97.0 152 99.9 152 99.9 151 99.9 151 99.9 151
SepConv-v1 [127]151.6 100.0 152 99.9 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 152 100.0 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.8 152 100.0 152 99.7 152 97.0 152 99.9 152 99.9 151 99.9 151 99.9 151
SuperSlomo [132]151.6 100.0 152 99.9 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 152 100.0 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.8 152 100.0 152 99.7 152 97.0 152 99.9 152 99.9 151 99.9 151 99.9 151
CtxSyn [136]151.6 100.0 152 99.9 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 152 100.0 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.8 152 100.0 152 99.7 152 97.0 152 99.9 152 99.9 151 99.9 151 99.9 151
CyclicGen [153]151.6 100.0 152 99.9 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 152 100.0 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.8 152 100.0 152 99.7 152 97.0 152 99.9 152 99.9 151 99.9 151 99.9 151
TOF-M [154]151.6 100.0 152 99.9 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 152 100.0 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.8 152 100.0 152 99.7 152 97.0 152 99.9 152 99.9 151 99.9 151 99.9 151
MPRN [155]151.6 100.0 152 99.9 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 152 100.0 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.8 152 100.0 152 99.7 152 97.0 152 99.9 152 99.9 151 99.9 151 99.9 151
DAIN [156]151.6 100.0 152 99.9 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 152 100.0 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.8 152 100.0 152 99.7 152 97.0 152 99.9 152 99.9 151 99.9 151 99.9 151
FRUCnet [157]151.6 100.0 152 99.9 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 152 100.0 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.8 152 100.0 152 99.7 152 97.0 152 99.9 152 99.9 151 99.9 151 99.9 151
OFRI [158]151.6 100.0 152 99.9 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 152 100.0 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.8 152 100.0 152 99.7 152 97.0 152 99.9 152 99.9 151 99.9 151 99.9 151
PyrWarp [161]151.6 100.0 152 99.9 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 152 100.0 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.8 152 100.0 152 99.7 152 97.0 152 99.9 152 99.9 151 99.9 151 99.9 151
FGME [163]151.6 100.0 152 99.9 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 152 100.0 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.8 152 100.0 152 99.7 152 97.0 152 99.9 152 99.9 151 99.9 151 99.9 151
MS-PFT [164]151.6 100.0 152 99.9 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 152 100.0 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.8 152 100.0 152 99.7 152 97.0 152 99.9 152 99.9 151 99.9 151 99.9 151
MEMC-Net+ [165]151.6 100.0 152 99.9 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 152 100.0 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.8 152 100.0 152 99.7 152 97.0 152 99.9 152 99.9 151 99.9 151 99.9 151
ADC [166]151.6 100.0 152 99.9 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 152 100.0 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.8 152 100.0 152 99.7 152 97.0 152 99.9 152 99.9 151 99.9 151 99.9 151
DSepConv [167]151.6 100.0 152 99.9 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 152 100.0 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.8 152 100.0 152 99.7 152 97.0 152 99.9 152 99.9 151 99.9 151 99.9 151
MAF-net [168]151.6 100.0 152 99.9 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 152 100.0 152 99.9 152 99.9 152 99.9 152 99.9 152 99.9 152 99.8 152 100.0 152 99.7 152 97.0 152 99.9 152 99.9 151 99.9 151 99.9 151
AVG_FLOW_ROB [141]151.7 99.9 151 99.7 151 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 99.6 151 98.8 151 99.5 151 99.6 151 99.7 151 99.0 151 97.0 151 96.3 151 95.6 151 99.1 151 92.9 151 99.6 151 100.0 168 99.9 151 99.9 151
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

Methodtime*framescolor Reference and notes
[1] 2D-CLG 844 2 gray The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences.
[2] Pyramid LK 12 2 color A modification of Bouguet's pyramidal implementation of Lucas-Kanade.
[3] Horn & Schunck 49 2 gray A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data.
[4] Black & Anandan 328 2 gray A modern Matlab implementation of the Black & Anandan method by Deqing Sun.
[5] Brox et al. 18 2 color T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.)
[6] Fusion 2,666 2 color V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008.
[7] Dynamic MRF 366 2 gray B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.)
[8] Second-order prior 14 2 gray W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[9] GroupFlow 600 2 gray X. Ren. Local Grouping for Optical Flow. CVPR 2008.
[10] SegOF 60 2 color L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available.
[11] Learning Flow 825 2 gray D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008.
[12] CBF 69 2 color W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[13] SPSA-learn 200 2 color Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008.
[14] GraphCuts 1,200 2 color T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008.
[15] F-TV-L1 8 2 gray A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008.
[16] FOLKI 1.4 2 gray G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005.
[17] TV-L1-improved 2.9 2 gray A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision.
[18] DPOF 287 2 color C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.)
[19] Filter Flow 34,000 2 color S. Seitz and S. Baker. Filter flow. ICCV 2009.
[20] Adaptive 9.2 2 gray A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009.
[21] Complementary OF 44 2 color H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[22] Aniso. Huber-L1 2 2 gray M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision.
[23] Rannacher 0.12 2 gray J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009.
[24] TI-DOFE 260 2 gray C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009.
[25] NL-TV-NCC 20 2 color M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010.
[26] MDP-Flow 188 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010.
[27] ACK-Prior 5872 2 color K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010.
[28] LDOF 122 2 color T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011.
[29] p-harmonic 565 2 gray J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010.
[30] TriangleFlow 4200 2 gray B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010.
[31] Classic+NL 972 2 color D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code.
[32] Classic++ 486 2 gray A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010.
[33] Nguyen 33 2 gray D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011.
[34] Modified CLG 133 2 gray R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010.
[35] ComplOF-FED-GPU 0.97 2 color P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010.
[36] Ad-TV-NDC 35 2 gray M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010.
[37] Layers++ 18206 2 color D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010.
[38] OFH 620 3 color H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011.
[39] LSM 1615 2 color K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011.
[40] CostFilter 55 2 color C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011.
[41] Bartels 0.15 2 gray C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU.
[42] Shiralkar 600 2 gray M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242.
[43] HBpMotionGpu 1000 5 gray S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.)
[44] StereoFlow 7200 2 color G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772.
[45] Adaptive flow 121 2 gray T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011.
[46] TC-Flow 2500 5 color S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011.
[47] SLK 300 2 gray T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011.
[48] CLG-TV 29 2 gray M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code.
[49] SimpleFlow 1.7 2 color M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012.
[50] IAOF 57 2 gray D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011.
[51] IAOF2 56 2 gray D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011.
[52] LocallyOriented 9541 2 gray Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012.
[53] IROF-TV 261 2 color H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop.
[54] Sparse Occlusion 2312 2 color A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011.
[55] PGAM+LK 0.37 2 gray A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010.
[56] Sparse-NonSparse 713 2 color L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013.
[57] nLayers 36150 4 color D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012.
[58] IROF++ 187 2 color H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013.
[59] COFM 600 3 color M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013.
[60] Efficient-NL 400 2 color P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012.
[61] BlockOverlap 2 2 gray M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to MMSP 2012.
[62] Ramp 1200 2 color A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012.
[63] Occlusion-TV-L1 538 3 gray C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012.
[64] TV-L1-MCT 90 2 color M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012.
[65] Local-TV-L1 500 2 gray L. Raket. Local smoothness for global optical flow. ICIP 2012.
[66] ALD-Flow 61 2 color M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012.
[67] SIOF 234 2 color L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012.
[68] MDP-Flow2 342 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available.
[69] TCOF 1421 all gray J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013.
[70] LME 476 2 color W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013.
[71] NN-field 362 2 color L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[72] FESL 3310 2 color W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013.
[73] PMF 35 2 color J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013.
[74] FC-2Layers-FF 2662 4 color D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013.
[75] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[76] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[77] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[78] Periodicity 8000 4 color G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013.
[79] SILK 572 2 gray P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP.
[80] CRTflow 13 3 color O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013.
[81] SuperFlow 178 2 color Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507.
[82] Aniso-Texture 300 2 color Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267.
[83] Classic+CPF 640 2 gray Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013.
[84] S2D-Matching 1200 2 color Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479.
[85] AGIF+OF 438 2 gray Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015.
[86] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[87] NNF-Local 673 2 color Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014.
[88] EPPM w/o HM 2.5 2 color L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014.
[89] MLDP_OF 165 2 gray M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014.
[90] RFlow 20 2 gray S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014.
[91] SRR-TVOF-NL 32 all color P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014.
[92] 2DHMM-SAS 157 2 color M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission.
[93] WLIF-Flow 700 2 color Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014.
[94] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[95] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[96] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[97] AggregFlow 1642 2 color D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759.
[98] 2bit-BM-tele 124 2 gray R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013.
[99] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[100] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[101] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[102] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[103] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[104] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[105] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[106] FFV1MT 358 5 gray F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015.
[107] ROF-ND 4 2 color S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015.
[108] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[109] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[110] FlowFields 15 2 color C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015.
[111] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[112] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[113] CombBMOF 51 2 color M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.)
[114] PMMST 182 2 color F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015.
[115] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[116] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[117] CNN-flow-warp+ref 1.4 3 color D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016.
[118] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[119] StereoOF-V1MT 343 2 gray Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132.
[120] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[121] RNLOD-Flow 1040 2 gray C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. IEEE TIP 26(8):4055-4067, 2017.
[122] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[123] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[124] BriefMatch 0.068 2 gray G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62.
[125] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[126] AdaConv-v1 2.8 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[127] SepConv-v1 0.2 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[128] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[129] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[130] FlowFields+ 10.5 2 color C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017.
[131] IIOF-NLDP 150 2 color D.-H. Trinh, W. Blondel, and C. Daul. A general form of illumination-invariant descriptors in variational optical flow estimation. ICIP 2017.
[132] SuperSlomo 0.5 2 color Anonymous. (Interpolation results only.) Super SloMo: High quality estimation of multiple intermediate frames for video interpolation. CVPR 2018 submission 325.
[133] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[134] OFRF 90 2 color T. Mai, M. Gouiffes, and S. Bouchafa. Optical Flow refinement using iterative propagation under color, proximity and flow reliability constraints. Submitted to Signal, Image and Video Processing 2017.
[135] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
[136] CtxSyn 0.07 2 color S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[137] 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.
[138] 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.
[139] 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.
[140] 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.
[141] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[142] 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.
[143] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[144] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[145] 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.
[146] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[147] 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.
[148] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[149] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
[150] WRT 9 2 color L. Mei, J. Lai, X. Xie, J. Zhu, and J. Chen. Illumination-invariance optical flow estimation using weighted regularization transform. Submitted to IEEE TCSVT 2018.
[151] EAI-Flow 2.1 2 color Anonymous. Hierarchical coherency sensitive hashing and interpolation with RANSAC for large displacement optical flow. CVIU 2018 submission 17-678.
[152] ContinualFlow_ROB 0.5 all color M Neoral, J. Sochman, and J. Matas. Continual occlusions and optical flow estimation. ACCV 2018.
[153] CyclicGen 0.088 2 color Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
[154] TOF-M 0.393 2 color T. Xue, B. Chen, J. Wu, D. Wei, and W. Freeman. Video enhancement with task-oriented flow. arXiv 1711.09078, 2017.
[155] MPRN 0.32 4 color Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[156] DAIN 0.13 2 color Anonymous. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019 submission 1769.
[157] FRUCnet 0.65 2 color V. T. Nguyen, K. Lee, and H.-J. Lee. (Interpolation results only.) A stacked deep MEMC network for frame rate up conversion and its application to HEVC. Submitted to IEEE TCSVT 2019.
[158] OFRI 0.31 2 color Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
[159] CompactFlow_ROB 0.05 2 color Anonymous. CompactFlow: spatially shiftable window revisited. CVPR 2019 submission 1387.
[160] SegFlow 3.2 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. Efficient segmentation-based PatchMatch for large displacement optical flow estimation. IEEE TCSVT 2018.
[161] PyrWarp 0.14 2 color Anonymous. (Interpolation results only.) Video frame interpolation using differentiable forward-warping of feature pyramids. ICCV 2019 submission 741.
[162] HCFN 0.18 2 color Anonymous. Practical coarse-to-fine optical flow with deep networks. ICCV 2019 submission 116.
[163] FGME 0.23 2 color Anonymous. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. ICCV 2019 submission 4327.
[164] MS-PFT 0.44 2 color X. Cheng and Z. Chen. (Interpolation results only.) A multi-scale position feature transform network for video frame interpolation. Submitted to TCSVT 2019.
[165] MEMC-Net+ 0.12 2 color W. Bao, W.-S. Lai, X. Zhang, Z. Gao, and M.-H. Yang. (Interpolation results only.) MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement. Submitted to TPAMI 2018.
[166] ADC 0.01 2 color Anonymous. (Interpolation results only.) Learning spatial transform for video frame interpolation. ICCV 2019 submission 5424.
[167] DSepConv 0.3 2 color Anonymous. (Interpolation results only.) Video frame interpolation via deformable separable convolution. AAAI 2020 submission 2271.
[168] MAF-net 0.3 2 color Anonymous. (Interpolation results only.) MAF-net: Motion attention feedback network for video frame interpolation. AAAI 2020 submission 9862.
* 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.