Optical flow evaluation results Statistics:     Average   SD   R2.5   R5.0   R10.0   A90   A95   A99  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
SD
interpolation
error
avg. Mequon
(Hidden texture)
im0   GT   im1
Schefflera
(Hidden texture)
im0   GT   im1
Urban
(Synthetic)
im0   GT   im1
Teddy
(Stereo)
im0   GT   im1
Backyard
(High-speed camera)
im0   GT   im1
Basketball
(High-speed camera)
im0   GT   im1
Dumptruck
(High-speed camera)
im0   GT   im1
Evergreen
(High-speed camera)
im0   GT   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
CtxSyn [137]14.9 5.47 1 7.82 1 2.18 114 5.98 1 7.57 1 3.23 22 19.2 89 10.6 1 17.0 93 7.49 1 9.86 1 5.67 1 20.6 2 23.3 2 8.83 3 12.8 1 18.0 1 4.72 1 19.4 2 29.6 2 6.47 1 16.8 1 21.0 1 7.43 15
SuperSlomo [132]15.9 7.27 2 10.8 2 4.59 143 7.40 9 9.09 4 5.23 100 11.7 1 11.2 2 6.26 3 11.1 2 12.9 2 10.9 66 21.1 3 23.9 3 8.02 2 14.2 5 20.0 5 4.85 2 19.9 3 30.4 3 6.69 5 17.4 3 21.8 3 6.97 9
MDP-Flow2 [68]26.0 8.94 34 13.9 32 1.56 1 7.36 8 9.57 12 2.68 3 15.9 39 20.5 85 16.3 89 13.4 19 18.2 34 8.87 34 24.1 10 27.3 10 12.1 20 17.6 32 25.0 37 6.01 26 22.8 14 34.9 15 7.11 7 20.9 21 26.2 21 7.78 20
CBF [12]26.5 8.02 4 12.4 4 1.75 41 8.18 56 10.3 37 4.84 81 13.2 6 15.5 18 9.17 21 11.5 3 15.0 4 7.94 20 22.8 4 25.8 4 12.2 33 16.2 13 22.9 14 6.24 45 23.4 24 35.8 24 8.06 62 21.2 27 26.7 29 8.24 61
PMMST [114]28.2 8.93 30 14.0 39 1.57 2 7.21 4 9.34 7 2.66 1 14.1 19 16.2 29 11.0 40 15.6 83 21.2 95 14.7 131 24.1 10 27.3 10 12.1 20 16.3 15 23.0 15 5.91 17 22.6 12 34.5 12 7.52 22 19.9 8 25.0 8 8.18 49
FGIK [136]29.7 8.10 6 12.4 4 4.36 142 7.78 19 9.20 6 7.01 140 17.9 79 11.5 3 14.4 76 12.9 13 15.5 7 12.6 117 19.9 1 22.6 1 9.56 6 13.5 3 19.0 3 5.15 4 17.7 1 27.1 1 8.23 66 17.9 5 22.4 5 6.70 5
DeepFlow [86]31.8 8.76 19 13.7 22 1.59 3 8.08 48 10.4 48 4.72 72 13.8 14 18.1 54 7.83 13 12.1 4 15.2 6 8.41 26 28.8 67 32.7 67 12.1 20 17.0 26 24.1 28 5.99 24 21.6 6 33.0 7 7.45 15 23.0 76 28.9 77 7.80 22
SepConv-v1 [127]32.2 8.19 7 12.5 6 5.08 146 7.89 29 9.09 4 8.08 144 20.8 104 12.1 4 18.4 106 12.5 9 14.8 3 11.7 95 23.5 7 26.6 7 9.13 4 14.1 4 19.9 4 5.12 3 21.1 4 32.2 4 8.37 70 17.2 2 21.5 2 6.71 6
DeepFlow2 [108]36.1 8.59 14 13.4 15 1.64 8 8.06 46 10.4 48 4.45 63 13.8 14 18.6 59 8.12 15 12.4 6 16.1 9 10.6 59 28.5 60 32.3 59 12.3 45 16.7 18 23.6 18 5.92 19 23.0 18 35.0 16 7.49 18 22.6 60 28.4 61 8.47 119
SuperFlow [81]36.9 8.83 23 13.8 24 1.68 12 8.19 57 10.3 37 5.04 89 16.0 42 16.6 32 10.9 38 14.9 62 15.1 5 7.67 14 23.0 6 26.0 5 12.5 52 18.0 45 25.5 47 6.55 73 23.6 31 35.8 24 9.80 96 20.7 16 26.0 17 8.12 38
CLG-TV [48]40.8 8.34 11 12.9 10 1.98 92 8.74 84 10.8 75 4.75 77 14.0 17 16.0 24 9.23 22 12.4 6 16.1 9 9.95 49 29.7 95 33.7 95 12.0 17 16.8 19 23.9 22 5.46 7 22.2 8 32.9 6 8.02 57 21.8 44 27.4 45 8.33 88
SIOF [67]40.8 8.78 21 13.5 17 1.80 60 8.97 95 11.2 101 4.51 65 16.7 55 23.2 108 11.6 46 13.2 14 17.7 24 9.61 45 23.7 9 26.8 9 11.8 11 17.8 37 25.2 40 5.98 23 23.4 24 35.9 28 7.33 10 22.1 47 27.8 49 8.15 42
AdaConv-v1 [126]42.3 9.51 70 14.1 46 4.99 145 9.04 99 9.51 11 9.70 146 18.8 88 13.8 7 18.3 105 14.5 50 16.5 14 15.2 136 25.9 22 29.4 22 7.81 1 13.1 2 18.4 2 5.63 10 21.4 5 32.7 5 7.45 15 17.4 3 21.8 3 6.73 8
Aniso. Huber-L1 [22]42.8 8.22 8 12.7 8 1.84 71 9.12 110 11.1 96 5.11 92 13.6 10 16.3 31 7.58 11 12.2 5 16.1 9 9.16 37 29.8 101 33.8 100 12.7 58 16.9 22 23.9 22 5.57 9 23.2 21 35.5 21 7.30 9 21.8 44 27.4 45 8.32 86
CombBMOF [113]43.5 9.74 86 14.3 56 3.85 139 7.82 23 10.2 28 3.81 38 16.2 44 19.1 68 12.8 62 13.8 28 18.5 39 10.2 54 26.5 24 30.0 24 12.2 33 17.8 37 25.2 40 6.09 36 23.1 19 35.2 19 7.64 30 21.3 30 26.7 29 8.21 58
LME [70]44.0 8.97 36 14.0 39 1.62 5 8.07 47 10.5 56 3.69 31 16.9 58 17.7 47 9.29 24 14.5 50 19.6 64 9.68 46 29.2 86 33.1 86 15.3 107 18.1 47 25.7 49 6.15 38 22.7 13 34.7 13 7.37 12 21.0 24 26.4 25 8.20 54
NN-field [71]44.4 9.03 42 14.1 46 1.74 36 7.01 3 9.05 3 2.74 8 18.3 83 19.1 68 12.6 60 16.8 110 22.7 115 15.8 138 24.2 12 27.5 12 12.1 20 17.8 37 25.1 38 6.07 32 23.1 19 35.4 20 7.69 35 20.6 13 25.9 14 8.36 102
MDP-Flow [26]44.5 8.27 9 12.8 9 1.74 36 7.26 6 9.42 8 3.90 41 17.2 64 16.1 28 15.0 83 13.6 23 18.0 30 10.9 66 28.8 67 32.7 67 15.3 107 17.9 43 25.2 40 7.36 105 23.6 31 36.1 32 12.2 119 20.6 13 25.9 14 8.07 27
WLIF-Flow [93]45.4 8.64 15 13.4 15 1.69 17 7.89 29 10.2 28 3.94 43 17.0 60 22.0 95 14.5 78 13.7 26 18.4 37 11.5 85 26.7 27 30.3 27 12.3 45 19.8 109 28.0 110 8.12 128 22.4 10 34.2 10 7.58 27 21.1 26 26.4 25 7.62 17
NNF-Local [87]45.5 8.84 25 13.8 24 1.61 4 7.25 5 9.44 9 2.76 9 14.6 25 19.3 74 14.5 78 16.0 97 21.6 102 15.8 138 24.2 12 27.5 12 12.2 33 18.4 55 26.0 58 6.42 65 24.2 40 37.1 44 9.54 89 20.3 11 25.4 11 8.27 73
p-harmonic [29]45.8 8.89 28 13.9 32 1.68 12 8.86 89 10.9 82 5.20 99 13.4 7 17.5 44 6.45 4 13.7 26 17.9 29 10.0 51 28.9 72 32.8 73 12.8 59 17.6 32 24.9 34 6.53 72 22.9 15 35.0 16 8.88 75 22.5 57 28.3 59 8.10 33
IROF-TV [53]45.9 8.93 30 13.9 32 1.82 67 8.15 53 10.6 62 4.01 47 13.9 16 17.6 45 8.70 18 13.3 16 18.0 30 9.04 35 28.5 60 32.3 59 15.3 107 18.5 61 26.2 63 6.57 74 24.7 54 37.8 56 6.81 6 22.2 51 28.0 54 6.71 6
Second-order prior [8]46.2 8.06 5 12.5 6 1.93 83 8.80 85 11.0 87 4.80 80 12.8 3 16.2 29 7.51 10 12.6 10 16.7 15 6.25 5 28.9 72 32.8 73 12.2 33 18.1 47 25.7 49 6.10 37 23.3 22 35.5 21 9.35 86 22.7 65 28.6 69 8.45 117
ALD-Flow [66]46.9 10.4 104 16.0 102 1.76 44 7.99 39 10.3 37 3.78 36 14.1 19 19.3 74 6.64 5 16.1 99 21.9 106 5.92 3 26.5 24 30.0 24 14.0 74 16.9 22 23.9 22 6.23 44 22.5 11 34.4 11 7.50 20 23.2 85 29.2 90 8.09 30
OAR-Flow [125]47.4 9.14 51 14.0 39 1.71 24 7.90 31 10.1 22 4.04 50 14.3 22 18.8 62 5.59 1 16.6 107 22.6 112 6.23 4 27.7 46 31.4 46 15.3 107 15.9 9 22.4 9 6.89 86 24.2 40 36.4 36 7.80 43 22.9 73 28.8 75 8.15 42
Ad-TV-NDC [36]48.3 9.09 47 13.8 24 2.24 119 9.50 127 11.1 96 6.94 139 14.2 21 15.4 17 6.85 7 14.5 50 18.6 40 9.51 43 27.4 39 31.1 39 12.3 45 18.2 52 25.8 55 6.40 64 22.9 15 34.7 13 7.43 13 20.6 13 25.8 13 8.26 69
IROF++ [58]49.6 8.58 13 13.3 13 1.68 12 7.99 39 10.4 48 3.84 39 17.3 66 18.5 57 12.5 58 12.4 6 16.7 15 9.15 36 28.4 59 32.3 59 15.3 107 19.5 100 27.6 101 6.06 30 23.3 22 35.6 23 8.55 74 23.4 94 29.4 99 7.79 21
DF-Auto [115]50.1 9.30 62 14.4 65 1.99 93 8.37 68 10.6 62 4.99 85 15.5 36 22.3 97 8.88 19 13.3 16 17.6 23 9.86 48 25.7 19 29.1 19 13.9 73 18.1 47 25.7 49 5.96 22 25.2 63 38.6 68 10.8 109 20.7 16 25.9 14 8.09 30
Brox et al. [5]51.2 9.33 64 14.7 70 1.62 5 7.86 27 10.1 22 4.14 54 15.9 39 16.0 24 10.4 33 13.5 22 17.7 24 8.77 32 26.8 28 30.4 28 11.9 12 19.1 86 27.0 87 9.52 143 28.6 120 43.6 118 23.0 149 19.9 8 25.0 8 8.05 26
Modified CLG [34]51.3 7.87 3 12.2 3 1.68 12 8.96 93 10.7 71 5.94 133 16.8 56 16.7 34 15.9 88 13.3 16 16.4 13 12.6 117 27.6 44 31.3 44 11.9 12 18.8 73 26.6 74 6.50 70 22.3 9 34.0 9 7.67 32 22.2 51 27.9 51 8.64 124
NNF-EAC [103]53.5 9.00 39 14.0 39 1.99 93 7.79 21 10.2 28 2.85 12 17.5 72 25.1 125 19.2 110 15.4 76 20.6 83 11.6 90 29.9 105 33.9 105 12.1 20 16.5 16 23.4 16 5.99 24 22.9 15 35.1 18 7.51 21 20.9 21 26.2 21 8.42 114
Local-TV-L1 [65]57.0 8.65 16 13.3 13 1.90 79 9.07 104 11.0 87 5.04 89 13.1 5 15.3 16 8.62 17 12.8 11 17.0 17 7.89 19 30.8 134 35.0 135 15.5 139 18.4 55 26.0 58 6.98 90 23.9 37 36.5 39 7.66 31 21.4 33 26.9 34 8.40 110
F-TV-L1 [15]57.0 10.4 104 16.2 104 1.94 85 9.02 97 11.2 101 4.72 72 14.6 25 16.7 34 11.0 40 14.2 37 18.9 49 10.3 55 27.5 41 31.2 42 12.3 45 16.0 10 22.6 10 6.38 61 23.9 37 36.6 40 9.23 82 21.3 30 26.7 29 10.2 139
JOF [141]57.5 9.04 43 14.1 46 1.81 64 7.55 13 9.71 17 5.06 91 15.1 30 16.7 34 12.0 48 14.4 46 19.4 59 11.4 79 29.2 86 33.2 87 15.4 130 19.8 109 28.0 110 6.36 60 23.4 24 35.8 24 7.68 34 21.4 33 26.8 33 8.30 81
PH-Flow [101]58.0 9.30 62 14.3 56 1.70 21 7.70 17 10.1 22 2.82 11 14.9 29 20.6 88 14.8 81 14.3 41 19.4 59 11.5 85 25.0 16 28.3 16 12.2 33 21.6 143 30.7 144 9.38 142 25.0 61 38.3 63 7.76 40 22.6 60 28.4 61 8.15 42
FMOF [94]58.9 9.22 58 13.9 32 1.96 89 7.58 14 9.87 18 2.87 13 19.5 93 22.4 98 17.7 100 15.3 72 20.6 83 12.5 116 24.5 14 27.7 14 13.7 69 19.3 94 27.3 95 6.05 28 24.6 52 37.7 54 6.64 4 23.4 94 29.4 99 6.98 10
Filter Flow [19]60.0 9.35 66 14.5 66 1.79 56 9.19 112 11.1 96 5.50 119 17.6 75 16.8 38 12.2 52 14.0 33 18.0 30 11.3 74 24.6 15 27.9 15 12.2 33 18.4 55 26.0 58 7.54 111 24.8 55 37.9 58 7.77 41 21.5 36 27.0 37 8.40 110
DMF_ROB [140]60.5 9.66 78 15.1 82 1.75 41 8.12 51 10.3 37 4.86 82 17.2 64 22.7 103 11.7 47 14.5 50 19.3 55 9.60 44 27.3 36 31.0 36 15.3 107 17.9 43 25.4 45 8.26 131 23.5 28 35.9 28 6.49 2 23.2 85 29.2 90 8.32 86
CRTflow [80]62.6 8.75 18 13.6 19 2.04 98 9.27 117 11.5 123 5.28 101 16.2 44 22.5 100 9.27 23 12.8 11 17.0 17 11.5 85 27.0 31 30.6 31 15.3 107 17.6 32 24.9 34 6.06 30 27.8 105 42.7 108 7.62 29 23.4 94 29.4 99 8.16 47
TC/T-Flow [76]62.8 9.42 68 14.6 69 2.39 123 8.67 82 11.2 101 4.00 45 13.6 10 16.0 24 8.03 14 17.5 122 23.5 125 10.8 63 27.3 36 31.0 36 15.3 107 17.4 30 24.6 30 5.89 16 25.8 78 37.8 56 9.59 91 22.8 68 28.7 72 8.13 40
ComplOF-FED-GPU [35]63.2 9.91 95 15.5 94 1.77 51 7.74 18 10.1 22 4.25 59 19.8 97 17.7 47 17.0 93 15.3 72 20.7 86 11.8 96 28.2 58 32.0 58 14.5 80 16.2 13 22.8 13 5.95 21 26.2 84 39.6 85 9.25 83 22.7 65 28.4 61 8.25 66
CNN-flow-warp+ref [117]63.5 8.33 10 13.0 11 2.06 103 8.26 63 10.3 37 5.85 130 18.3 83 22.7 103 11.1 43 13.6 23 16.0 8 11.1 70 29.1 84 33.0 83 15.3 107 15.7 7 22.1 7 6.96 89 28.2 111 43.1 112 7.67 32 21.8 44 27.3 43 8.49 120
COFM [59]63.6 8.95 35 13.8 24 1.90 79 7.42 10 9.61 13 3.19 21 15.3 33 22.1 96 16.3 89 15.4 76 20.9 89 14.6 127 26.8 28 30.4 28 12.2 33 21.4 140 30.3 140 6.26 50 26.3 85 40.4 88 10.4 105 20.8 18 26.1 18 8.36 102
Sparse Occlusion [54]63.8 9.75 87 15.2 85 2.05 101 8.71 83 11.2 101 4.19 56 13.5 8 15.9 23 7.80 12 14.6 56 19.7 69 7.51 13 30.4 117 34.5 118 15.3 107 16.1 11 22.7 11 6.27 51 26.9 96 41.1 98 7.45 15 23.2 85 29.2 90 8.12 38
CPM-Flow [116]64.6 9.82 91 15.4 93 1.69 17 7.60 15 9.90 19 3.04 18 15.6 38 15.7 21 7.43 9 16.9 112 23.0 120 12.0 102 27.6 44 31.3 44 15.3 107 18.5 61 26.2 63 7.13 99 23.4 24 35.8 24 9.99 98 23.8 112 29.9 114 8.37 105
2DHMM-SAS [92]64.8 8.83 23 13.6 19 1.76 44 8.88 91 11.3 109 4.29 60 17.5 72 20.9 89 12.5 58 14.5 50 19.6 64 11.3 74 30.1 110 34.1 109 15.1 95 17.6 32 24.9 34 5.84 12 25.2 63 38.7 70 8.23 66 23.1 80 29.1 83 8.16 47
PMF [73]65.3 9.35 66 14.5 66 1.77 51 7.80 22 10.1 22 2.68 3 24.0 124 28.7 136 22.5 132 15.3 72 20.6 83 11.6 90 25.7 19 29.2 20 12.1 20 19.1 86 27.0 87 5.92 19 27.6 102 42.4 105 9.09 80 23.1 80 29.0 82 6.47 1
Horn & Schunck [3]65.4 8.92 29 13.6 19 1.73 29 9.79 137 11.4 113 6.31 136 24.1 125 18.7 60 18.6 108 15.8 93 19.4 59 11.1 70 28.0 51 31.8 52 10.4 8 17.8 37 25.2 40 5.54 8 25.3 68 38.4 66 9.70 93 22.1 47 27.7 48 8.27 73
LDOF [28]65.5 8.85 26 13.8 24 2.04 98 10.2 145 9.70 16 10.8 150 17.0 60 20.4 84 12.0 48 13.4 19 17.4 21 12.3 111 22.9 5 26.0 5 11.9 12 18.9 77 26.7 77 6.27 51 30.1 134 46.3 136 16.0 132 19.7 6 24.7 6 8.89 130
TC-Flow [46]66.0 10.9 114 17.1 115 1.71 24 8.86 89 11.6 126 4.00 45 13.0 4 16.0 24 6.24 2 15.6 83 21.1 92 8.58 27 27.9 48 31.7 50 15.1 95 18.7 69 26.4 70 6.72 78 24.6 52 37.6 52 7.95 54 23.4 94 29.4 99 8.28 77
2D-CLG [1]66.2 8.51 12 13.2 12 1.76 44 8.84 88 10.4 48 5.71 128 19.4 92 15.6 20 15.0 83 14.2 37 16.3 12 14.0 123 31.1 141 35.3 141 20.9 150 16.1 11 22.7 11 6.34 56 27.7 104 42.3 103 8.19 65 21.4 33 26.9 34 8.13 40
FlowNetS+ft+v [112]66.5 9.02 41 14.1 46 2.07 107 10.0 143 11.0 87 9.60 145 16.3 47 14.4 8 13.5 68 13.8 28 17.7 24 13.3 121 29.7 95 33.8 100 15.3 107 16.8 19 23.8 20 6.25 48 27.8 105 42.6 106 7.83 47 20.4 12 25.5 12 8.24 61
Black & Anandan [4]66.7 9.24 60 14.1 46 1.95 87 9.65 134 11.4 113 5.28 101 28.3 134 24.2 115 20.2 120 14.8 60 18.7 44 10.5 57 27.7 46 31.5 47 9.57 7 19.0 82 27.0 87 6.35 58 24.2 40 36.7 41 8.42 72 21.0 24 26.3 24 6.55 2
EpicFlow [102]67.2 9.69 80 15.2 85 1.67 11 7.90 31 10.2 28 4.37 62 16.0 42 14.5 9 9.75 26 19.1 133 25.8 135 12.3 111 27.9 48 31.6 48 15.3 107 16.9 22 23.9 22 6.21 43 24.9 57 38.0 59 10.3 103 24.6 134 30.9 135 8.30 81
PGM-C [120]67.2 9.70 81 15.2 85 1.69 17 7.84 26 10.2 28 3.70 32 21.2 107 17.2 40 12.3 55 17.4 119 23.6 126 8.69 28 28.0 51 31.8 52 15.3 107 16.6 17 23.4 16 6.17 39 26.4 86 40.5 92 8.04 59 24.3 128 30.5 130 8.34 91
OFLAF [77]67.2 9.70 81 15.0 79 1.69 17 7.94 36 10.4 48 2.73 7 14.3 22 15.0 13 10.2 29 13.8 28 18.6 40 8.40 25 30.0 107 34.0 107 15.4 130 17.0 26 23.9 22 6.73 79 30.1 134 46.1 134 13.9 127 23.4 94 29.3 95 9.45 134
MLDP_OF [89]67.3 9.06 44 14.1 46 1.83 70 8.81 86 11.3 109 4.78 79 14.0 17 17.6 45 8.56 16 15.5 80 20.3 78 15.8 138 29.7 95 33.7 95 13.6 65 19.1 86 27.0 87 5.86 14 23.8 34 36.3 34 8.15 64 23.2 85 29.1 83 8.25 66
Fusion [6]67.5 8.82 22 13.8 24 2.62 127 7.96 37 10.1 22 4.47 64 16.5 50 13.6 6 17.3 99 14.0 33 18.1 33 9.97 50 29.8 101 33.8 100 12.8 59 19.4 96 27.4 96 10.1 146 26.4 86 40.4 88 8.14 63 21.7 40 27.2 41 10.1 138
ProFlow_ROB [147]67.7 9.82 91 15.5 94 1.71 24 8.15 53 10.6 62 3.63 28 15.4 35 12.7 5 8.98 20 19.8 137 26.9 137 7.99 21 29.0 82 33.0 83 15.3 107 15.6 6 22.0 6 5.16 5 26.4 86 40.3 87 7.90 52 24.4 131 30.5 130 11.5 142
TV-L1-MCT [64]68.9 9.18 54 14.2 54 1.78 53 8.53 75 11.1 96 3.70 32 17.7 77 23.3 111 13.6 69 14.4 46 19.5 63 11.6 90 30.5 123 34.6 121 13.8 70 18.1 47 25.7 49 6.02 27 25.8 78 39.5 82 15.0 130 21.7 40 27.3 43 7.99 24
LFNet_ROB [151]69.0 11.6 123 18.2 126 2.58 126 8.05 44 10.4 48 4.02 49 17.8 78 26.6 129 11.5 45 13.2 14 17.8 27 7.21 11 26.9 30 30.5 30 14.8 87 21.1 134 29.9 135 7.31 103 23.5 28 35.9 28 11.3 112 22.4 55 28.2 57 8.11 36
AGIF+OF [85]69.0 9.07 45 14.0 39 1.78 53 7.93 35 10.3 37 3.78 36 14.4 24 17.8 49 12.4 56 14.9 62 20.2 75 11.4 79 28.9 72 32.8 73 15.3 107 20.0 112 28.3 112 6.98 90 25.5 71 39.0 73 7.74 38 23.9 119 30.1 123 8.28 77
Bartels [41]70.0 12.7 135 20.1 136 2.13 113 8.52 74 11.0 87 4.96 84 13.5 8 14.5 9 10.2 29 14.4 46 18.9 49 10.8 63 23.5 7 26.6 7 12.9 62 19.0 82 26.9 84 6.94 88 24.5 47 37.5 50 19.7 143 23.4 94 29.4 99 8.31 84
S2F-IF [123]70.5 10.3 102 16.3 106 1.79 56 7.83 25 10.2 28 2.90 15 17.0 60 20.0 81 13.9 73 16.1 99 21.6 102 6.69 6 29.2 86 33.2 87 15.3 107 16.8 19 23.7 19 6.34 56 24.9 57 38.2 61 10.7 107 23.9 119 30.0 121 8.35 99
OFH [38]72.0 9.54 72 15.0 79 1.74 36 8.49 73 10.6 62 5.13 93 18.1 81 24.9 123 10.4 33 17.4 119 23.7 128 5.72 2 28.7 65 32.5 63 14.6 83 17.6 32 24.8 32 5.85 13 26.0 82 39.2 77 10.2 101 22.7 65 28.5 67 14.1 147
BlockOverlap [61]72.0 9.09 47 14.3 56 2.04 98 8.96 93 10.9 82 5.37 112 18.1 81 15.5 18 18.0 103 14.2 37 17.2 19 14.0 123 28.9 72 32.8 73 13.8 70 18.8 73 26.7 77 7.92 122 24.8 55 37.2 45 21.0 146 20.0 10 25.1 10 8.38 106
nLayers [57]72.5 9.15 52 14.3 56 1.76 44 7.42 10 9.62 14 3.57 26 27.8 132 29.9 139 25.8 142 15.9 95 21.5 100 11.9 97 30.2 111 34.3 112 14.7 86 20.3 119 28.8 120 6.45 67 23.5 28 36.0 31 7.87 50 21.6 37 27.1 38 8.10 33
TCOF [69]72.8 9.34 65 14.3 56 1.89 75 9.50 127 11.7 133 5.42 113 16.2 44 21.7 93 10.3 31 13.8 28 18.6 40 9.45 42 30.4 117 34.6 121 13.6 65 18.2 52 25.7 49 6.20 42 28.5 117 43.5 117 7.54 23 22.9 73 28.8 75 8.18 49
HAST [109]73.1 8.87 27 13.8 24 1.76 44 7.34 7 9.50 10 2.70 5 28.8 136 28.6 135 24.0 137 14.9 62 20.2 75 7.68 15 28.9 72 32.8 73 12.1 20 21.3 139 30.2 139 7.57 113 28.6 120 43.9 121 7.55 25 22.8 68 28.7 72 8.43 116
ContFlow_ROB [150]73.4 12.0 130 18.8 130 2.02 96 8.35 66 10.5 56 5.15 95 15.9 39 18.2 56 11.0 40 23.1 142 31.4 145 7.06 9 28.5 60 32.3 59 12.1 20 18.9 77 26.8 81 6.05 28 24.9 57 38.1 60 7.86 49 22.9 73 28.7 72 8.63 122
DPOF [18]73.8 11.0 115 17.4 119 3.88 140 7.78 19 10.2 28 3.01 16 18.7 86 18.1 54 18.4 106 16.5 104 22.4 109 14.6 127 28.8 67 32.7 67 12.1 20 18.9 77 26.7 77 6.18 41 25.2 63 38.4 66 7.59 28 23.6 107 29.6 107 8.07 27
Layers++ [37]74.3 8.93 30 14.0 39 1.76 44 6.74 2 8.61 2 2.71 6 18.3 83 25.8 127 19.3 111 15.3 72 20.8 87 11.3 74 33.1 147 37.6 147 19.8 147 21.6 143 30.6 143 8.73 136 24.4 45 37.4 48 7.81 45 21.6 37 27.1 38 8.09 30
FlowFields [110]74.7 9.98 96 15.7 97 2.08 109 7.96 37 10.4 48 3.62 27 23.1 117 23.2 108 20.3 122 16.0 97 21.5 100 7.08 10 27.0 31 30.6 31 14.2 76 19.2 92 27.1 92 6.08 35 24.4 45 37.4 48 10.2 101 23.2 85 29.2 90 8.35 99
Classic++ [32]75.7 9.48 69 14.9 74 1.80 60 8.59 76 11.0 87 4.61 68 13.7 13 15.0 13 9.57 25 14.4 46 19.0 51 8.76 31 29.9 105 33.9 105 13.6 65 20.2 117 28.7 118 6.87 85 27.4 100 42.0 100 9.63 92 23.8 112 29.9 114 8.34 91
SRR-TVOF-NL [91]76.3 9.65 76 14.8 71 1.82 67 8.21 61 10.6 62 4.76 78 22.7 115 28.1 133 21.9 127 15.6 83 20.9 89 9.18 38 28.9 72 32.8 73 15.3 107 20.7 128 29.3 128 5.91 17 24.5 47 37.6 52 6.56 3 22.5 57 28.2 57 8.34 91
NL-TV-NCC [25]76.8 9.19 56 14.3 56 2.18 114 9.02 97 11.6 126 4.13 53 14.8 27 16.7 34 10.9 38 20.8 138 28.1 139 8.19 23 26.5 24 30.0 24 13.1 63 18.9 77 26.7 77 6.43 66 26.6 91 40.4 88 15.1 131 23.7 111 29.7 111 8.29 80
HBM-GC [105]77.2 9.25 61 14.5 66 1.81 64 9.08 106 11.9 142 3.75 35 17.3 66 18.7 60 17.9 101 14.3 41 19.2 53 8.85 33 30.0 107 34.0 107 15.5 139 21.5 141 30.4 141 8.27 132 27.4 100 42.1 102 7.15 8 20.8 18 26.1 18 7.05 12
Complementary OF [21]77.7 11.4 122 18.1 125 1.70 21 9.23 115 12.1 143 4.19 56 31.6 141 19.0 66 23.6 134 19.5 136 26.5 136 6.72 7 28.1 56 31.8 52 14.6 83 17.3 29 24.4 29 6.38 61 26.1 83 39.0 73 8.92 77 22.3 53 27.9 51 7.57 16
Nguyen [33]77.7 9.83 93 15.2 85 1.73 29 9.59 132 11.0 87 5.65 127 15.3 33 20.5 85 10.3 31 14.6 56 18.8 45 12.1 104 28.8 67 32.7 67 12.2 33 19.4 96 27.4 96 8.01 126 29.7 129 45.5 129 8.29 69 21.2 27 26.6 28 8.34 91
Efficient-NL [60]78.8 8.71 17 13.5 17 1.68 12 8.66 80 11.2 101 3.65 29 22.5 111 20.0 81 19.9 116 14.3 41 19.3 55 11.0 68 30.5 123 34.7 128 15.0 90 20.1 113 28.4 114 6.27 51 28.5 117 43.7 119 8.92 77 23.8 112 29.9 114 6.66 4
FESL [72]79.1 9.09 47 13.9 32 1.74 36 7.90 31 10.3 37 3.35 24 16.5 50 21.9 94 12.0 48 15.1 69 20.3 78 11.4 79 30.8 134 35.0 135 15.4 130 19.6 103 27.8 106 6.48 68 27.8 105 42.6 106 7.75 39 23.9 119 30.0 121 8.39 107
ProbFlowFields [128]79.2 10.1 97 16.0 102 1.78 53 8.04 43 10.5 56 3.08 20 25.8 131 28.8 137 24.3 138 14.5 50 19.6 64 11.4 79 27.2 34 30.9 35 15.3 107 17.4 30 24.6 30 8.78 137 27.3 99 42.0 100 18.8 141 22.4 55 28.1 55 8.39 107
AggregFlow [97]79.4 12.9 137 20.3 137 1.75 41 8.34 65 10.8 75 4.14 54 20.0 98 24.4 118 19.5 115 16.5 104 22.3 108 12.2 108 25.2 17 28.6 17 12.2 33 16.9 22 23.9 22 6.60 75 29.0 126 43.9 121 16.7 134 23.0 76 28.9 77 8.03 25
FlowFields+ [130]80.7 9.67 79 15.2 85 3.33 138 7.86 27 10.3 37 3.02 17 23.3 119 24.6 120 20.8 123 17.0 114 23.0 120 6.91 8 27.3 36 31.0 36 15.4 130 19.0 82 26.9 84 6.24 45 25.3 68 38.8 71 13.1 123 23.2 85 29.1 83 8.39 107
StereoOF-V1MT [119]81.1 11.1 117 17.3 117 1.73 29 8.61 77 10.6 62 5.28 101 23.4 121 17.3 41 17.1 97 16.6 107 19.9 72 12.3 111 27.4 39 31.1 39 15.0 90 17.0 26 23.8 20 6.80 83 30.2 136 46.2 135 12.3 120 21.6 37 26.9 34 9.58 135
RNLOD-Flow [121]81.2 8.93 30 13.8 24 1.65 9 8.48 72 11.0 87 4.06 51 16.3 47 23.2 108 12.8 62 14.1 35 19.1 52 11.1 70 29.7 95 33.7 95 15.6 141 20.3 119 28.7 118 8.92 140 25.7 74 39.4 80 16.4 133 24.2 125 30.4 127 8.20 54
PWC-Net_ROB [148]81.2 11.7 125 18.2 126 2.05 101 8.35 66 10.9 82 3.91 42 13.6 10 17.4 43 6.79 6 18.8 129 25.6 134 8.72 30 30.5 123 34.6 121 15.1 95 19.4 96 27.4 96 5.68 11 23.6 31 36.2 33 7.95 54 24.2 125 30.4 127 11.5 142
FlowNet2 [122]81.4 15.6 146 23.6 147 1.96 89 9.34 119 12.1 143 4.72 72 17.3 66 19.2 72 13.0 65 17.1 117 23.1 122 10.1 52 28.0 51 31.8 52 12.3 45 18.6 63 26.3 66 6.35 58 26.7 92 40.8 95 8.04 59 21.7 40 27.2 41 8.30 81
TI-DOFE [24]82.2 9.80 89 15.2 85 2.80 131 9.94 141 11.4 113 5.62 124 15.5 36 15.7 21 10.5 36 17.0 114 21.7 104 10.6 59 27.1 33 30.8 33 12.1 20 20.9 132 29.6 133 6.99 92 24.0 39 36.3 34 8.92 77 24.3 128 28.1 55 12.5 145
Sparse-NonSparse [56]82.3 9.18 54 14.3 56 1.73 29 8.14 52 10.6 62 3.31 23 16.6 53 22.9 106 13.8 72 14.8 60 19.8 71 11.3 74 30.5 123 34.6 121 15.0 90 20.1 113 28.5 116 7.48 109 28.5 117 43.7 119 9.49 87 23.5 104 29.5 104 8.24 61
TVL1_ROB [139]82.3 10.5 107 16.3 106 1.88 74 9.86 139 11.6 126 5.57 120 20.0 98 19.0 66 14.6 80 15.6 83 20.3 78 11.9 97 26.4 23 29.9 23 12.1 20 19.0 82 26.8 81 7.12 98 28.2 111 42.9 109 12.9 122 20.9 21 26.2 21 8.34 91
Occlusion-TV-L1 [63]83.0 10.1 97 15.9 100 2.43 124 9.36 120 11.8 139 5.01 88 12.7 2 14.7 11 7.22 8 17.0 114 22.7 115 11.4 79 28.6 63 32.5 63 12.0 17 18.7 69 26.5 73 7.48 109 25.2 63 37.7 54 10.0 99 24.3 128 30.3 126 9.33 132
ACK-Prior [27]83.1 9.81 90 15.1 82 2.07 107 8.01 42 10.4 48 3.86 40 25.1 128 19.1 68 22.0 129 15.1 69 20.1 74 10.1 52 30.4 117 34.4 115 15.4 130 19.1 86 26.9 84 7.57 113 25.8 78 39.3 78 19.5 142 22.3 53 27.9 51 7.73 18
3DFlow [135]83.3 9.65 76 14.9 74 1.89 75 7.82 23 10.0 21 4.94 83 16.9 58 19.9 79 13.7 70 16.5 104 22.4 109 15.8 138 29.3 90 33.2 87 12.5 52 18.4 55 25.9 57 8.56 135 27.2 97 41.4 99 10.1 100 23.4 94 29.3 95 8.87 128
LSM [39]83.4 9.10 50 14.2 54 1.73 29 8.33 64 10.9 82 3.40 25 16.6 53 22.7 103 12.2 52 15.0 68 20.3 78 11.0 68 30.5 123 34.7 128 15.1 95 20.7 128 29.4 129 6.17 39 28.1 110 43.0 111 11.5 114 23.8 112 29.9 114 8.27 73
Classic+CPF [83]83.6 9.07 45 14.0 39 1.80 60 8.09 49 10.5 56 3.71 34 17.0 60 21.5 91 12.9 64 13.9 32 18.8 45 11.4 79 30.7 132 34.9 133 15.4 130 21.2 136 30.0 137 7.73 120 28.2 111 43.2 114 7.80 43 24.7 137 31.0 137 7.89 23
ResPWCR_ROB [145]84.2 11.2 121 17.7 121 1.95 87 8.98 96 11.7 133 4.11 52 15.2 32 17.3 41 10.0 27 23.1 142 31.2 144 10.5 57 30.5 123 34.6 121 14.2 76 20.3 119 28.8 120 5.27 6 23.8 34 36.4 36 7.54 23 25.4 143 31.9 147 7.76 19
TriFlow [95]84.6 13.1 138 20.8 138 2.06 103 9.53 130 12.2 145 5.29 107 16.5 50 18.5 57 10.1 28 17.2 118 22.8 117 7.74 16 27.9 48 31.6 48 15.1 95 19.4 96 27.4 96 6.07 32 24.5 47 37.2 45 10.9 110 23.8 112 29.8 113 8.15 42
CostFilter [40]84.7 10.8 113 17.0 114 1.80 60 7.90 31 10.3 37 2.66 1 24.6 127 27.7 132 21.9 127 18.7 128 25.4 132 13.7 122 27.5 41 31.1 39 12.6 55 18.2 52 25.8 55 5.87 15 28.9 124 44.2 125 9.34 85 24.4 131 30.7 133 8.20 54
FFV1MT [106]84.8 11.6 123 17.7 121 2.19 116 9.20 113 10.9 82 5.96 134 22.6 112 30.3 140 16.3 89 15.5 80 18.8 45 12.4 114 27.5 41 31.2 42 11.6 10 18.6 63 25.7 49 7.42 108 27.2 97 40.7 93 8.88 75 21.2 27 26.4 25 9.73 136
TF+OM [100]85.0 11.8 127 18.7 129 3.19 135 8.23 62 10.8 75 4.54 66 15.1 30 19.7 77 10.4 33 16.3 102 21.9 106 7.87 18 28.9 72 32.8 73 19.1 146 18.6 63 26.3 66 6.68 77 26.5 90 40.7 93 11.5 114 23.8 112 29.9 114 8.23 60
H+S_ROB [138]85.8 9.20 57 14.1 46 1.72 27 8.66 80 10.2 28 5.63 125 39.8 150 41.0 150 32.8 151 14.3 41 17.4 21 9.30 40 29.6 94 33.6 94 12.2 33 19.5 100 27.6 101 7.00 93 31.4 140 48.0 140 10.3 103 23.0 76 28.9 77 8.34 91
Ramp [62]85.8 9.22 58 14.3 56 1.73 29 8.19 57 10.7 71 4.24 58 21.9 110 28.8 137 21.1 126 14.2 37 19.2 53 11.6 90 30.6 130 34.8 131 14.8 87 20.4 123 29.0 126 7.40 106 28.0 109 42.9 109 7.57 26 23.0 76 28.9 77 8.28 77
AugFNG_ROB [144]86.3 12.1 132 19.0 132 1.94 85 8.44 71 10.6 62 5.42 113 17.3 66 23.9 114 10.8 37 26.2 148 34.7 147 11.5 85 31.6 143 35.9 143 15.3 107 18.7 69 26.4 70 6.38 61 24.9 57 38.2 61 7.91 53 19.8 7 24.8 7 8.36 102
EPMNet [133]87.3 16.1 148 24.7 148 2.22 117 9.04 99 11.7 133 4.55 67 17.3 66 19.2 72 13.0 65 26.7 150 36.3 151 12.1 104 28.0 51 31.8 52 12.3 45 18.4 55 26.0 58 6.25 48 26.7 92 40.8 95 8.04 59 22.6 60 28.4 61 8.35 99
IAOF2 [51]87.3 10.7 112 16.6 110 2.36 121 9.40 121 11.6 126 5.33 108 17.4 71 18.0 51 12.4 56 14.1 35 18.2 34 9.32 41 30.3 115 34.4 115 14.0 74 20.5 127 29.1 127 8.20 129 25.2 63 38.3 63 8.49 73 23.1 80 29.1 83 8.24 61
SVFilterOh [111]87.5 10.5 107 16.4 108 1.97 91 7.65 16 9.98 20 3.05 19 28.0 133 30.4 141 25.4 140 15.6 83 21.2 95 14.7 131 28.9 72 32.7 67 15.4 130 20.1 113 28.4 114 6.61 76 25.8 78 39.5 82 7.84 48 22.5 57 28.3 59 8.49 120
Heeger++ [104]88.0 14.5 143 21.7 142 4.63 144 9.50 127 11.0 87 5.73 129 25.4 130 23.5 113 14.4 76 15.5 80 18.8 45 12.4 114 28.7 65 32.5 63 15.2 103 15.8 8 22.2 8 6.73 79 27.6 102 39.8 86 9.28 84 22.1 47 27.6 47 8.34 91
Dynamic MRF [7]88.5 10.1 97 15.9 100 1.81 64 8.42 70 10.8 75 4.73 76 19.5 93 19.1 68 12.2 52 15.6 83 19.3 55 12.8 120 27.2 34 30.8 33 15.2 103 18.6 63 26.3 66 7.28 102 28.8 123 44.1 124 12.4 121 24.6 134 30.7 133 9.73 136
Adaptive [20]88.6 11.0 115 17.3 117 1.89 75 9.41 123 11.6 126 5.19 98 14.8 27 17.1 39 11.1 43 15.7 90 21.1 92 12.1 104 31.1 141 35.3 141 12.0 17 18.8 73 26.6 74 8.00 125 27.8 105 42.3 103 8.01 56 22.6 60 28.4 61 8.63 122
Classic+NL [31]88.6 8.97 36 13.9 32 1.79 56 8.11 50 10.5 56 4.01 47 20.8 104 28.3 134 19.9 116 14.3 41 19.3 55 11.5 85 30.7 132 34.8 131 14.6 83 20.3 119 28.8 120 7.40 106 28.3 114 43.4 115 11.9 118 23.5 104 29.6 107 8.25 66
IAOF [50]88.7 11.1 117 16.6 110 5.32 147 10.6 147 12.3 146 5.87 131 23.3 119 24.2 115 19.4 112 15.4 76 19.7 69 12.0 102 28.9 72 32.8 73 12.1 20 18.8 73 26.6 74 7.26 101 25.6 73 39.1 76 7.35 11 22.1 47 27.8 49 8.26 69
TV-L1-improved [17]88.8 9.53 71 14.9 74 1.99 93 9.46 124 11.7 133 5.17 96 22.6 112 14.8 12 20.1 119 13.4 19 17.8 27 8.05 22 30.2 111 34.3 112 11.9 12 19.6 103 27.7 103 8.09 127 29.9 132 45.8 132 9.73 94 23.4 94 29.3 95 8.42 114
Steered-L1 [118]89.0 8.76 19 13.7 22 1.82 67 8.00 41 10.3 37 4.72 72 31.9 142 33.2 147 29.2 146 17.4 119 22.8 117 14.1 125 29.5 93 33.5 93 14.2 76 19.7 107 27.9 108 6.28 55 26.4 86 40.4 88 18.7 140 23.8 112 29.9 114 7.04 11
ROF-ND [107]89.1 9.00 39 13.9 32 1.62 5 9.53 130 10.8 75 10.7 149 16.4 49 22.9 106 12.7 61 18.3 126 24.1 129 11.9 97 29.4 92 33.3 92 15.2 103 18.6 63 26.2 63 7.60 116 24.5 47 37.3 47 13.2 125 24.4 131 30.5 130 9.33 132
TriangleFlow [30]89.8 9.59 74 14.8 71 2.06 103 9.07 104 11.4 113 5.47 117 19.2 89 20.2 83 13.9 73 13.6 23 18.2 34 8.31 24 30.0 107 34.1 109 9.31 5 17.8 37 25.2 40 7.56 112 30.8 138 47.2 138 13.9 127 25.5 146 31.9 147 11.3 141
FOLKI [16]89.8 10.6 109 16.5 109 2.43 124 9.94 141 11.2 101 6.70 138 19.6 95 21.6 92 19.9 116 18.3 126 19.4 59 17.3 143 28.0 51 31.7 50 13.6 65 19.1 86 27.1 92 10.9 148 24.2 40 36.9 42 17.3 137 21.3 30 26.7 29 8.10 33
FF++_ROB [146]89.9 10.6 109 16.7 112 1.70 21 8.19 57 10.6 62 3.67 30 21.6 109 22.6 101 17.0 93 19.0 131 25.5 133 14.9 135 28.9 72 32.8 73 15.4 130 19.3 94 27.4 96 6.24 45 25.7 74 39.5 82 11.8 117 23.5 104 29.5 104 8.27 73
LocallyOriented [52]91.2 10.1 97 15.7 97 1.79 56 9.46 124 11.6 126 5.28 101 23.1 117 24.2 115 20.9 125 19.3 135 23.2 123 7.35 12 30.4 117 34.6 121 12.6 55 18.9 77 26.8 81 6.27 51 25.7 74 38.6 68 7.89 51 23.6 107 29.6 107 8.19 52
SILK [79]92.1 9.72 85 15.1 82 2.69 128 10.2 145 11.4 113 7.82 143 39.2 149 32.9 146 28.5 145 14.6 56 18.4 37 9.73 47 29.0 82 32.9 82 10.4 8 21.2 136 30.0 137 7.00 93 24.5 47 37.5 50 8.03 58 23.1 80 28.9 77 8.31 84
S2D-Matching [84]93.8 9.57 73 14.9 74 1.76 44 8.37 68 10.8 75 4.36 61 20.1 101 24.9 123 18.2 104 15.7 90 21.3 99 15.7 137 28.8 67 32.7 67 14.5 80 21.5 141 30.4 141 11.0 149 25.7 74 39.3 78 11.5 114 23.1 80 29.1 83 8.75 127
BriefMatch [124]94.1 9.89 94 15.5 94 2.11 111 8.05 44 10.2 28 5.90 132 23.5 122 18.0 51 22.7 133 18.2 125 18.6 40 18.7 146 28.1 56 31.9 57 13.8 70 19.5 100 27.7 103 7.05 96 26.7 92 39.4 80 21.6 147 23.4 94 29.3 95 14.3 149
GraphCuts [14]94.5 11.7 125 17.8 123 2.02 96 8.15 53 10.5 56 4.65 70 25.3 129 15.2 15 19.4 112 14.9 62 19.6 64 11.9 97 29.8 101 33.8 100 17.8 144 19.6 103 27.8 106 6.50 70 28.6 120 43.9 121 11.1 111 24.0 123 30.2 124 8.15 42
RFlow [90]95.1 9.71 83 15.2 85 1.91 82 9.06 102 11.2 101 5.42 113 22.8 116 22.6 101 17.9 101 15.8 93 21.2 95 12.7 119 29.2 86 33.2 87 11.9 12 19.2 92 27.2 94 7.63 117 28.9 124 44.4 126 7.73 37 23.4 94 29.5 104 8.46 118
ComponentFusion [96]95.4 12.3 133 19.5 133 1.66 10 8.65 79 11.4 113 2.88 14 19.7 96 21.0 90 15.1 85 15.4 76 20.9 89 14.4 126 29.7 95 33.7 95 14.5 80 18.6 63 26.3 66 7.67 118 31.9 141 49.0 143 20.5 144 24.2 125 30.4 127 8.18 49
Learning Flow [11]96.1 8.99 38 14.1 46 1.85 73 9.10 108 11.3 109 4.99 85 40.2 151 42.5 151 31.6 150 14.9 62 17.2 19 12.2 108 30.8 134 35.0 135 15.1 95 18.7 69 26.4 70 7.58 115 25.1 62 38.3 63 11.4 113 25.5 146 31.7 143 8.24 61
SLK [47]97.0 9.63 75 15.0 79 1.90 79 9.14 111 10.3 37 5.63 125 34.7 144 19.7 77 22.4 131 18.9 130 24.2 130 20.4 149 29.8 101 33.8 100 12.2 33 18.1 47 25.5 47 6.93 87 31.9 141 48.8 141 9.12 81 22.8 68 28.5 67 14.2 148
FC-2Layers-FF [74]97.1 9.71 83 14.9 74 2.11 111 7.51 12 9.66 15 4.67 71 20.5 102 25.1 125 20.2 120 15.6 83 21.1 92 11.9 97 30.5 123 34.6 121 15.3 107 20.8 130 29.4 129 7.31 103 29.7 129 45.6 131 9.76 95 23.6 107 29.7 111 8.22 59
Adaptive flow [45]97.1 10.3 102 14.8 71 2.37 122 9.87 140 11.5 123 5.57 120 18.0 80 17.9 50 17.1 97 16.4 103 20.0 73 14.8 133 32.3 145 36.7 145 16.6 142 21.1 134 29.8 134 8.41 133 23.8 34 36.4 36 13.1 123 21.7 40 27.1 38 7.17 13
Shiralkar [42]97.2 12.0 130 18.8 130 1.72 27 9.11 109 11.1 96 5.14 94 21.2 107 16.6 32 13.7 70 19.2 134 24.3 131 10.6 59 29.7 95 33.7 95 12.8 59 18.0 45 25.4 45 7.19 100 29.4 127 44.9 127 10.4 105 25.1 142 31.5 142 9.03 131
EPPM w/o HM [88]98.2 10.4 104 16.2 104 2.97 133 8.62 78 11.3 109 2.76 9 29.0 137 27.4 131 22.2 130 16.8 110 22.6 112 10.8 63 25.8 21 29.2 20 12.1 20 20.2 117 28.6 117 6.49 69 29.8 131 45.8 132 18.0 138 24.0 123 30.2 124 8.72 126
UnFlow [129]100.3 13.4 139 21.2 141 2.71 130 8.81 86 10.7 71 6.35 137 18.7 86 18.9 63 14.8 81 14.6 56 19.6 64 7.77 17 31.8 144 36.1 144 15.0 90 22.2 146 31.4 146 7.79 121 24.2 40 37.0 43 7.49 18 28.1 150 33.7 151 11.6 144
Correlation Flow [75]101.0 9.75 87 15.3 92 1.84 71 9.28 118 11.6 126 5.17 96 17.5 72 18.9 63 15.2 86 16.1 99 21.7 104 11.3 74 30.2 111 34.3 112 12.5 52 21.2 136 29.9 135 8.24 130 31.3 139 47.8 139 9.82 97 24.9 140 31.3 141 6.61 3
LiteFlowNet [143]103.5 12.6 134 19.7 135 2.06 103 8.19 57 10.7 71 3.96 44 20.8 104 26.3 128 15.4 87 26.2 148 35.0 149 12.2 108 30.9 140 35.0 135 14.9 89 20.4 123 28.8 120 6.74 82 28.3 114 43.1 112 7.70 36 22.8 68 28.6 69 8.87 128
HBpMotionGpu [43]103.6 12.7 135 19.5 133 2.69 128 9.65 134 11.7 133 5.48 118 20.0 98 23.3 111 17.0 93 17.6 123 23.4 124 10.6 59 30.8 134 35.0 135 25.1 151 20.4 123 28.9 125 7.95 123 22.0 7 33.7 8 7.44 14 23.2 85 29.1 83 8.40 110
PGAM+LK [55]104.5 11.9 129 18.0 124 7.26 150 9.48 126 10.8 75 7.62 141 31.5 140 39.9 149 31.4 149 19.0 131 23.6 126 16.3 142 29.1 84 33.0 83 12.6 55 18.4 55 26.0 58 6.80 83 25.5 71 39.0 73 14.8 129 22.6 60 28.4 61 8.41 113
2bit-BM-tele [98]105.8 11.1 117 17.2 116 2.34 120 9.40 121 11.7 133 5.36 110 28.5 135 37.1 148 31.0 148 15.7 90 20.8 87 9.18 38 28.6 63 32.5 63 15.0 90 22.0 145 31.1 145 9.53 144 39.1 151 59.9 151 26.9 151 20.8 18 26.1 18 8.11 36
Rannacher [23]106.5 11.1 117 17.5 120 1.89 75 9.59 132 11.8 139 5.28 101 24.3 126 18.0 51 20.8 123 15.9 95 21.2 95 11.6 90 30.4 117 34.5 118 12.3 45 19.7 107 27.9 108 7.98 124 29.6 128 45.3 128 9.57 90 24.7 137 31.0 137 8.19 52
OFRF [134]107.0 13.6 140 21.1 140 2.23 118 9.25 116 11.4 113 5.60 122 19.2 89 19.5 76 14.1 75 16.9 112 22.8 117 14.6 127 30.8 134 34.9 133 14.4 79 19.6 103 27.7 103 6.07 32 28.3 114 43.4 115 7.78 42 24.7 137 31.1 139 8.34 91
StereoFlow [44]107.3 14.9 144 22.2 144 3.28 136 10.0 143 12.7 149 4.99 85 16.8 56 18.9 63 12.1 51 15.2 71 20.4 82 10.4 56 33.4 148 37.9 148 20.8 148 23.8 148 33.5 148 8.41 133 25.3 68 38.8 71 7.81 45 23.6 107 29.6 107 8.67 125
SimpleFlow [49]109.9 9.15 52 14.3 56 1.73 29 9.05 101 11.4 113 5.35 109 36.0 147 32.6 145 29.4 147 14.9 62 20.2 75 11.2 73 30.6 130 34.7 128 15.1 95 22.6 147 32.0 147 9.11 141 34.7 146 53.2 147 13.8 126 23.9 119 29.9 114 8.33 88
Aniso-Texture [82]110.8 10.6 109 16.7 112 1.74 36 9.83 138 12.4 147 5.36 110 17.6 75 19.9 79 13.1 67 22.9 141 27.8 138 19.7 148 30.3 115 34.4 115 15.4 130 20.8 130 29.4 129 8.86 139 26.8 95 41.0 97 8.38 71 24.6 134 30.9 135 8.26 69
SegOF [10]110.8 11.8 127 18.2 126 5.53 148 8.88 91 11.4 113 4.62 69 31.1 139 20.5 85 23.7 135 25.8 146 34.8 148 18.2 145 30.2 111 34.2 111 15.3 107 19.1 86 27.0 87 7.08 97 32.5 144 49.7 144 16.8 135 22.8 68 28.6 69 8.08 29
SPSA-learn [13]111.0 15.1 145 22.9 145 1.93 83 9.08 106 11.0 87 5.42 113 33.0 143 24.8 121 23.8 136 17.6 123 22.4 109 12.1 104 29.3 90 33.2 87 15.1 95 17.8 37 25.1 38 6.73 79 37.7 148 57.7 149 25.5 150 25.4 143 31.8 144 8.33 88
HCIC-L [99]116.4 14.3 142 20.9 139 2.86 132 11.2 148 13.3 150 7.62 141 23.9 123 31.6 143 25.6 141 21.0 139 28.2 140 14.8 133 25.6 18 29.0 18 12.2 33 24.0 149 33.9 149 10.5 147 30.5 137 46.8 137 18.5 139 23.3 92 29.2 90 7.37 14
IIOF-NLDP [131]118.5 10.2 101 15.8 99 2.10 110 9.06 102 11.2 101 5.60 122 20.6 103 24.8 121 16.9 92 16.7 109 22.6 112 14.6 127 30.4 117 34.5 118 20.8 148 20.4 123 28.8 120 8.81 138 37.7 148 57.6 148 16.8 135 24.9 140 31.2 140 8.26 69
WOLF_ROB [149]118.5 16.7 149 24.7 148 3.17 134 9.76 136 11.8 139 5.28 101 22.6 112 24.5 119 19.4 112 21.5 140 28.4 141 8.71 29 30.8 134 35.0 135 15.2 103 20.1 113 28.3 112 7.04 95 32.0 143 48.8 141 8.28 68 25.4 143 31.8 144 8.20 54
GroupFlow [9]125.6 15.6 146 23.3 146 3.31 137 9.20 113 11.4 113 6.26 135 30.9 138 22.4 98 18.9 109 25.4 145 30.0 143 21.2 150 32.4 146 36.7 145 15.3 107 20.9 132 29.4 129 7.71 119 29.9 132 45.5 129 9.50 88 23.3 92 29.1 83 10.6 140
Pyramid LK [2]132.7 14.0 141 21.7 142 4.34 141 13.7 149 11.5 123 9.94 147 37.6 148 26.8 130 24.6 139 25.9 147 29.3 142 18.7 146 35.0 149 39.7 149 13.3 64 19.9 111 24.8 32 9.57 145 33.3 145 51.1 145 10.7 107 26.0 148 32.4 149 13.0 146
Periodicity [78]148.0 18.1 150 27.0 150 6.22 149 17.4 150 12.4 147 10.2 148 35.2 146 30.7 142 27.8 143 24.1 144 31.6 146 17.5 144 37.6 151 42.6 151 18.8 145 27.7 150 39.3 150 11.2 150 38.6 150 58.9 150 22.9 148 27.3 149 33.2 150 14.3 149
AVG_FLOW_ROB [142]148.8 31.2 151 31.0 151 11.6 151 19.8 151 21.4 151 12.0 151 34.9 145 32.0 144 28.1 144 31.2 151 36.2 150 23.9 151 36.4 150 41.0 150 16.9 143 39.5 151 55.0 151 16.9 151 36.8 147 52.3 146 20.8 145 30.2 151 31.8 144 15.5 151
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

Methodtime*framescolor Reference and notes
[1] 2D-CLG 844 2 gray The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences.
[2] Pyramid LK 12 2 color A modification of Bouguet's pyramidal implementation of Lucas-Kanade.
[3] Horn & Schunck 49 2 gray A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data.
[4] Black & Anandan 328 2 gray A modern Matlab implementation of the Black & Anandan method by Deqing Sun.
[5] Brox et al. 18 2 color T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.)
[6] Fusion 2,666 2 color V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008.
[7] Dynamic MRF 366 2 gray B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.)
[8] Second-order prior 14 2 gray W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[9] GroupFlow 600 2 gray X. Ren. Local Grouping for Optical Flow. CVPR 2008.
[10] SegOF 60 2 color L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available.
[11] Learning Flow 825 2 gray D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008.
[12] CBF 69 2 color W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[13] SPSA-learn 200 2 color Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008.
[14] GraphCuts 1,200 2 color T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008.
[15] F-TV-L1 8 2 gray A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008.
[16] FOLKI 1.4 2 gray G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005.
[17] TV-L1-improved 2.9 2 gray A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision.
[18] DPOF 287 2 color C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.)
[19] Filter Flow 34,000 2 color S. Seitz and S. Baker. Filter flow. ICCV 2009.
[20] Adaptive 9.2 2 gray A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009.
[21] Complementary OF 44 2 color H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[22] Aniso. Huber-L1 2 2 gray M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision.
[23] Rannacher 0.12 2 gray J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009.
[24] TI-DOFE 260 2 gray C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009.
[25] NL-TV-NCC 20 2 color M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010.
[26] MDP-Flow 188 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010.
[27] ACK-Prior 5872 2 color K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010.
[28] LDOF 122 2 color T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011.
[29] p-harmonic 565 2 gray J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010.
[30] TriangleFlow 4200 2 gray B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010.
[31] Classic+NL 972 2 color D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code.
[32] Classic++ 486 2 gray A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010.
[33] Nguyen 33 2 gray D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011.
[34] Modified CLG 133 2 gray R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010.
[35] ComplOF-FED-GPU 0.97 2 color P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010.
[36] Ad-TV-NDC 35 2 gray M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010.
[37] Layers++ 18206 2 color D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010.
[38] OFH 620 3 color H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011.
[39] LSM 1615 2 color K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011.
[40] CostFilter 55 2 color C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011.
[41] Bartels 0.15 2 gray C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU.
[42] Shiralkar 600 2 gray M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242.
[43] HBpMotionGpu 1000 5 gray S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.)
[44] StereoFlow 7200 2 color G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772.
[45] Adaptive flow 121 2 gray T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011.
[46] TC-Flow 2500 5 color S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011.
[47] SLK 300 2 gray T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011.
[48] CLG-TV 29 2 gray M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code.
[49] SimpleFlow 1.7 2 color M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012.
[50] IAOF 57 2 gray D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011.
[51] IAOF2 56 2 gray D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011.
[52] LocallyOriented 9541 2 gray Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012.
[53] IROF-TV 261 2 color H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop.
[54] Sparse Occlusion 2312 2 color A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011.
[55] PGAM+LK 0.37 2 gray A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010.
[56] Sparse-NonSparse 713 2 color L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013.
[57] nLayers 36150 4 color D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012.
[58] IROF++ 187 2 color H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013.
[59] COFM 600 3 color M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013.
[60] Efficient-NL 400 2 color P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012.
[61] BlockOverlap 2 2 gray M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to MMSP 2012.
[62] Ramp 1200 2 color A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012.
[63] Occlusion-TV-L1 538 3 gray C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012.
[64] TV-L1-MCT 90 2 color M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012.
[65] Local-TV-L1 500 2 gray L. Raket. Local smoothness for global optical flow. ICIP 2012.
[66] ALD-Flow 61 2 color M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012.
[67] SIOF 234 2 color L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012.
[68] MDP-Flow2 342 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available.
[69] TCOF 1421 all gray J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013.
[70] LME 476 2 color W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013.
[71] NN-field 362 2 color L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[72] FESL 3310 2 color W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013.
[73] PMF 35 2 color J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013.
[74] FC-2Layers-FF 2662 4 color D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013.
[75] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[76] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[77] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[78] Periodicity 8000 4 color G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013.
[79] SILK 572 2 gray P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP.
[80] CRTflow 13 3 color O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013.
[81] SuperFlow 178 2 color Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507.
[82] Aniso-Texture 300 2 color Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267.
[83] Classic+CPF 640 2 gray Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013.
[84] S2D-Matching 1200 2 color Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479.
[85] AGIF+OF 438 2 gray Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015.
[86] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[87] NNF-Local 673 2 color Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014.
[88] EPPM w/o HM 2.5 2 color L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014.
[89] MLDP_OF 165 2 gray M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014.
[90] RFlow 20 2 gray S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014.
[91] SRR-TVOF-NL 32 all color P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014.
[92] 2DHMM-SAS 157 2 color M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission.
[93] WLIF-Flow 700 2 color Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014.
[94] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[95] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[96] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[97] AggregFlow 1642 2 color D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759.
[98] 2bit-BM-tele 124 2 gray R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013.
[99] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[100] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[101] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[102] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[103] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[104] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[105] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[106] FFV1MT 358 5 gray F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015.
[107] ROF-ND 4 2 color S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015.
[108] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[109] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[110] FlowFields 15 2 color C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015.
[111] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[112] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[113] CombBMOF 51 2 color M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.)
[114] PMMST 182 2 color F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015.
[115] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[116] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[117] CNN-flow-warp+ref 1.4 3 color D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016.
[118] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[119] StereoOF-V1MT 343 2 gray Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132.
[120] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[121] RNLOD-Flow 1040 2 gray C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. IEEE TIP 26(8):4055-4067, 2017.
[122] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[123] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[124] BriefMatch 0.068 2 gray G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62.
[125] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[126] AdaConv-v1 2.8 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[127] SepConv-v1 0.2 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[128] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[129] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[130] FlowFields+ 10.5 2 color C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017.
[131] IIOF-NLDP 150 2 color D.-H. Trinh, W. Blondel, and C. Daul. A general form of illumination-invariant descriptors in variational optical flow estimation. ICIP 2017.
[132] SuperSlomo 0.5 2 color Anonymous. (Interpolation results only.) Super SloMo: High quality estimation of multiple intermediate frames for video interpolation. CVPR 2018 submission 325.
[133] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[134] OFRF 90 2 color T. Mai, M. Gouiffes, and S. Bouchafa. Optical Flow refinement using iterative propagation under color, proximity and flow reliability constraints. Submitted to Signal, Image and Video Processing 2017.
[135] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
[136] FGIK 0.18 2 color Anonymous. (Interpolation results only.) Learning flow-guided interpolation kernels for video frame synthesis. ECCV 2018 submission 433.
[137] CtxSyn 0.07 2 color S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[138] H+S_ROB 5 2 color ROB 2018 baseline submission, based on: E. Meinhardt-Llopis, J. Sanchez, and D. Kondermann. Horn-Schunck optical flow with a multi-scale strategy. Image Processing On Line 3:151–172, 2013.
[139] TVL1_ROB 1 2 color ROB 2018 baseline submission, based on: J. Sanchez, E. Meinhardt-Llopis, and G. Facciolo. TV-L1 optical flow estimation. Image Processing On Line 3:137-150, 2013.
[140] DMF_ROB 10 2 color ROB 2018 baseline submission, based on: P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[141] JOF 657 2 gray C. Zhang, L. Ge, Z. Chen, M. Li, W. Liu, and H. Chen. Refined TV-L1 optical flow estimation using joint filtering. Submitted to IEEE TMM, 2018.
[142] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[143] LiteFlowNet 0.06 2 color T.-W. Hui, X. Tang, and C. C. Loy. LiteFlowNet: A lightweight convolutional neural network for optical flow estimation. CVPR 2018.
[144] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[145] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[146] FF++_ROB 17.43 2 color R. Schuster, C. Bailer, O. Wasenmueller, D. Stricker. FlowFields++: Accurate optical flow correspondences meet robust interpolation. ICIP 2018. Submitted to ROB 2018.
[147] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[148] PWC-Net_ROB 0.069 2 color D. Sun, X. Yang, M.-Y. Liu, and J. Kautz. PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. CVPR 2018.
[149] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[150] ContFlow_ROB 0.45 all color Anonymous. Continual Flow. ROB 2018 submission.
[151] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
* The "time" column lists the reported runtime in seconds on the "Urban" sequence. Note that these runtimes are not normalized by processor speed or type.