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        
Average
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
PyrWarp [162]4.2 1.99 1 3.00 1 0.99 2 3.02 2 4.11 2 1.39 40 1.81 1 2.54 1 1.13 1 3.95 1 4.73 1 2.77 1 7.51 2 9.25 2 3.06 4 4.46 3 8.27 3 2.05 4 5.65 3 12.5 3 1.51 12 5.84 3 9.02 3 1.60 6
FGME [164]6.9 2.08 2 3.34 3 0.98 1 3.32 9 4.43 4 1.63 93 2.46 2 3.28 2 1.41 10 4.08 2 4.85 2 3.05 9 7.36 1 9.08 1 3.03 2 4.17 2 7.62 2 2.06 5 4.95 2 10.7 2 1.44 2 5.45 2 8.41 2 1.57 3
MPRN [156]15.8 2.53 10 4.43 11 1.21 25 3.78 58 4.97 15 1.57 81 3.39 8 5.49 16 1.28 3 5.03 9 6.58 11 3.19 30 9.53 8 11.9 8 3.31 10 5.25 9 9.92 8 2.22 9 6.87 9 15.5 11 1.49 5 6.72 10 10.4 10 1.60 6
CtxSyn [136]17.1 2.24 3 3.72 5 1.04 3 2.96 1 4.16 3 1.35 32 4.32 76 3.42 4 3.18 119 4.21 3 5.46 4 3.00 3 9.59 10 11.9 8 3.46 13 5.22 7 9.76 7 2.22 9 7.02 12 15.4 10 1.58 46 6.66 9 10.2 8 1.69 16
InterpCNN [158]19.5 2.61 12 4.34 9 1.52 157 3.30 6 4.52 5 1.72 111 3.14 6 3.70 5 1.76 37 4.74 6 5.99 8 3.29 63 8.11 6 10.0 6 2.97 1 4.48 4 8.35 4 2.02 1 5.78 4 12.7 4 1.45 3 6.06 4 9.38 4 1.57 3
DAIN [157]20.7 2.38 6 4.05 6 1.26 112 3.28 4 4.53 6 1.79 123 3.32 7 3.77 6 2.05 58 4.65 5 5.88 5 3.41 100 7.88 3 9.74 3 3.04 3 4.73 6 8.90 6 2.04 3 6.36 5 14.3 5 1.51 12 6.25 5 9.68 6 1.54 2
CyclicGen [153]22.5 2.26 4 3.32 2 1.42 153 3.19 3 4.01 1 2.21 155 2.76 3 4.05 10 1.62 24 4.97 8 5.92 6 3.79 140 8.00 5 9.84 5 3.13 6 3.36 1 5.65 1 2.17 7 4.55 1 9.68 1 1.42 1 4.48 1 6.84 1 1.52 1
MDP-Flow2 [68]24.1 2.89 16 5.38 17 1.19 6 3.47 16 5.07 22 1.26 1 3.66 21 6.10 51 2.48 87 5.20 13 7.48 22 3.14 17 10.2 14 12.8 16 3.61 35 6.13 36 11.8 32 2.31 38 7.36 17 16.8 15 1.49 5 7.75 33 12.1 32 1.69 16
PMMST [114]24.2 2.90 17 5.43 19 1.20 10 3.50 22 5.05 20 1.27 6 3.56 12 5.46 14 1.82 41 5.38 29 7.92 49 3.41 100 10.2 14 12.8 16 3.60 29 5.76 14 11.0 14 2.26 16 7.39 18 16.9 18 1.53 20 7.57 18 11.8 18 1.72 47
TOF-M [154]25.1 2.54 11 4.35 10 1.16 5 3.70 48 5.19 26 1.88 130 3.43 9 3.89 7 1.93 48 5.05 10 6.43 10 3.39 94 9.84 11 12.3 11 3.42 12 5.34 11 10.0 10 2.28 24 6.88 10 15.2 9 1.61 54 7.14 13 11.0 13 1.69 16
SuperSlomo [132]25.8 2.51 8 4.32 8 1.25 99 3.66 42 5.06 21 1.93 143 2.91 4 4.00 8 1.41 10 5.05 10 6.27 9 3.66 130 9.56 9 11.9 8 3.30 9 5.37 12 10.2 12 2.24 11 6.69 7 15.0 8 1.53 20 6.73 11 10.4 10 1.66 9
MEMC-Net+ [155]31.5 2.47 7 4.06 7 1.32 137 3.49 20 4.73 10 1.90 133 4.63 97 4.03 9 3.12 115 4.94 7 5.98 7 3.46 107 8.91 7 11.1 7 3.21 7 4.70 5 8.83 5 2.03 2 6.46 6 14.4 7 1.56 38 6.35 7 9.86 7 1.57 3
OFRI [159]32.2 2.28 5 3.45 4 1.35 146 3.44 13 4.57 7 2.13 153 3.02 5 3.34 3 1.73 34 4.51 4 5.42 3 3.88 141 7.89 4 9.76 4 3.10 5 5.24 8 9.92 8 2.10 6 6.78 8 14.3 5 1.82 108 6.32 6 9.62 5 1.75 89
SepConv-v1 [127]32.9 2.52 9 4.83 12 1.11 4 3.56 31 5.04 18 1.90 133 4.17 62 4.15 11 2.86 105 5.41 38 6.81 12 3.88 141 10.2 14 12.8 16 3.37 11 5.47 13 10.4 13 2.21 8 6.88 10 15.6 12 1.72 91 6.63 8 10.3 9 1.62 8
DeepFlow [86]33.9 2.98 29 5.67 34 1.22 54 3.88 71 5.78 70 1.52 72 3.62 14 5.93 43 1.34 5 5.39 34 7.20 17 3.17 21 11.0 47 13.9 54 3.63 46 5.91 20 11.3 19 2.29 29 7.14 13 16.3 13 1.49 5 7.80 41 12.2 39 1.70 24
CBF [12]38.7 2.83 13 5.20 13 1.23 74 3.97 84 5.79 73 1.56 77 3.62 14 5.47 15 1.60 23 5.21 14 7.12 14 3.29 63 10.1 12 12.6 12 3.62 40 5.97 23 11.5 23 2.31 38 7.76 52 17.8 53 1.61 54 7.60 21 11.9 21 1.76 103
DeepFlow2 [108]39.3 2.99 32 5.65 31 1.22 54 3.88 71 5.79 73 1.48 66 3.62 14 6.03 45 1.34 5 5.38 29 7.44 21 3.22 41 11.0 47 13.8 47 3.67 55 5.83 15 11.2 15 2.25 15 7.60 33 17.4 34 1.50 8 7.82 42 12.2 39 1.77 112
NN-field [71]41.5 2.98 29 5.70 35 1.20 10 3.31 8 4.73 10 1.26 1 4.69 101 5.91 41 2.03 57 5.99 101 9.13 118 3.57 122 10.3 20 12.8 16 3.60 29 6.24 47 12.0 46 2.31 38 7.39 18 16.9 18 1.54 27 7.69 29 12.0 27 1.72 47
SuperFlow [81]41.6 2.94 21 5.56 27 1.24 88 3.99 87 5.78 70 1.67 102 4.06 51 5.55 18 1.83 42 5.52 49 7.07 13 3.20 35 10.2 14 12.7 14 3.68 58 6.13 36 11.8 32 2.24 11 7.68 42 17.5 39 1.77 103 7.44 16 11.6 15 1.69 16
NNF-Local [87]41.8 2.92 20 5.51 25 1.19 6 3.30 6 4.71 9 1.26 1 3.65 19 5.91 41 2.29 77 5.76 79 8.70 100 3.55 120 10.3 20 12.9 22 3.60 29 6.42 67 12.4 66 2.34 51 7.57 29 17.4 34 1.74 93 7.61 22 11.9 21 1.72 47
Aniso. Huber-L1 [22]42.7 2.95 24 5.44 21 1.24 88 4.42 121 6.27 121 1.67 102 3.79 32 5.70 25 1.50 16 5.31 19 7.42 20 3.24 51 11.1 58 14.0 66 3.61 35 5.91 20 11.4 21 2.24 11 7.60 33 17.3 28 1.51 12 7.62 24 11.9 21 1.73 56
IROF-TV [53]43.8 3.07 47 5.91 57 1.23 74 3.71 50 5.47 47 1.40 45 3.70 27 6.27 57 1.58 22 5.25 16 7.60 29 3.17 21 11.0 47 13.9 54 4.47 117 6.37 63 12.4 66 2.30 35 7.79 56 17.9 57 1.50 8 7.63 25 11.9 21 1.66 9
CLG-TV [48]44.1 2.94 21 5.45 22 1.25 99 4.26 108 6.17 108 1.60 86 3.68 25 5.73 27 1.73 34 5.36 25 7.41 19 3.32 81 11.1 58 14.0 66 3.57 18 5.88 19 11.3 19 2.26 16 7.58 30 17.0 22 1.57 43 7.75 33 12.1 32 1.72 47
LME [70]44.2 2.95 24 5.59 29 1.19 6 3.68 45 5.50 50 1.38 37 4.06 51 7.00 95 1.71 33 5.38 29 7.92 49 3.18 25 11.2 72 14.1 75 4.51 146 6.29 52 12.2 53 2.31 38 7.33 15 16.8 15 1.51 12 7.83 43 12.3 43 1.70 24
IROF++ [58]45.2 3.03 38 5.77 43 1.20 10 3.59 34 5.31 35 1.33 26 4.32 76 6.61 74 2.25 72 5.06 12 7.14 15 3.16 20 11.0 47 13.9 54 4.44 113 6.34 58 12.3 60 2.27 21 7.54 28 17.3 28 1.64 70 8.09 67 12.7 68 1.69 16
NNF-EAC [103]46.3 3.01 35 5.60 30 1.25 99 3.63 37 5.36 40 1.29 13 4.17 62 7.03 97 2.99 108 5.50 48 7.96 51 3.28 60 11.2 72 14.1 75 3.60 29 5.86 18 11.2 15 2.26 16 7.43 22 17.0 22 1.54 27 7.79 40 12.2 39 1.73 56
CombBMOF [113]46.4 3.16 77 5.88 52 1.24 88 3.54 26 5.24 29 1.34 30 4.01 46 6.45 68 2.20 69 5.62 69 8.22 67 3.29 63 10.7 30 13.5 31 3.62 40 6.20 44 11.9 41 2.27 21 7.78 55 17.3 28 1.56 38 7.75 33 12.1 32 1.71 37
DF-Auto [115]47.9 2.94 21 5.34 15 1.23 74 3.99 87 5.84 78 1.65 96 3.85 37 6.73 78 1.55 21 5.38 29 7.54 24 3.25 53 10.4 23 13.0 23 3.70 60 6.17 43 11.9 41 2.28 24 7.94 66 18.2 68 1.75 98 7.68 27 12.0 27 1.71 37
ALD-Flow [66]49.1 3.28 107 6.45 108 1.24 88 3.81 62 5.73 68 1.41 49 3.62 14 6.28 58 1.35 8 5.58 59 8.39 81 3.04 7 10.8 33 13.5 31 4.15 93 5.96 22 11.4 21 2.29 29 7.34 16 16.8 15 1.51 12 8.25 91 12.9 83 1.70 24
WLIF-Flow [93]49.4 2.95 24 5.53 26 1.20 10 3.66 42 5.41 43 1.39 40 4.26 71 7.17 105 2.54 90 5.30 18 7.57 27 3.29 63 10.7 30 13.5 31 3.70 60 6.74 114 13.1 110 2.48 115 7.40 20 16.9 18 1.53 20 7.87 49 12.3 43 1.69 16
PH-Flow [101]50.2 3.12 63 6.01 72 1.20 10 3.39 11 4.94 14 1.28 11 3.70 27 6.43 63 2.48 87 5.23 15 7.58 28 3.22 41 10.4 23 13.1 25 3.62 40 6.84 125 13.3 123 2.47 109 7.84 59 18.1 64 1.58 46 7.87 49 12.3 43 1.73 56
Second-order prior [8]51.1 2.91 19 5.39 18 1.24 88 4.26 108 6.21 114 1.56 77 3.82 34 6.34 60 1.62 24 5.39 34 7.68 31 3.04 7 11.1 58 13.9 54 3.59 22 6.14 39 11.9 41 2.31 38 7.61 35 17.4 34 1.63 69 7.90 51 12.4 53 1.78 118
p-harmonic [29]51.9 3.00 33 5.72 37 1.21 25 4.33 113 6.24 119 1.69 107 3.60 13 6.07 49 1.39 9 5.70 71 7.87 44 3.29 63 11.0 47 13.8 47 3.63 46 6.02 26 11.6 26 2.34 51 7.67 40 17.5 39 1.70 86 7.92 55 12.4 53 1.72 47
Brox et al. [5]52.7 3.08 50 5.94 62 1.21 25 3.83 65 5.67 60 1.45 59 3.93 41 5.76 30 1.67 28 5.32 20 7.19 16 3.22 41 10.6 27 13.4 29 3.56 16 6.60 95 12.7 82 2.42 94 8.61 111 19.7 113 3.04 156 7.43 15 11.6 15 1.68 14
FMOF [94]53.5 3.16 77 5.92 60 1.23 74 3.48 17 5.07 22 1.28 11 4.59 95 6.82 82 2.78 101 5.71 73 8.42 82 3.40 97 10.4 23 13.0 23 3.67 55 6.49 74 12.6 75 2.28 24 7.64 37 17.5 39 1.48 4 8.06 65 12.6 63 1.67 12
SIOF [67]54.6 3.06 45 5.74 41 1.24 88 4.40 120 6.40 132 1.63 93 4.17 62 7.43 118 1.93 48 5.40 37 7.75 36 3.44 104 10.1 12 12.6 12 3.58 20 6.10 32 11.8 32 2.29 29 7.52 26 17.2 26 1.53 20 7.96 59 12.5 62 1.73 56
MDP-Flow [26]56.5 2.86 14 5.34 15 1.20 10 3.49 20 5.15 25 1.34 30 4.01 46 5.51 17 2.28 74 5.58 59 7.91 48 3.33 84 11.2 72 14.0 66 4.49 127 6.72 108 13.1 110 2.54 133 7.71 45 17.7 49 1.74 93 7.83 43 12.3 43 1.70 24
Local-TV-L1 [65]57.0 3.00 33 5.47 23 1.30 131 4.43 123 6.23 118 1.75 117 3.50 10 5.35 13 1.45 12 5.39 34 7.56 25 3.29 63 11.2 72 14.1 75 3.91 82 6.16 41 11.8 32 2.47 109 7.67 40 17.6 44 1.55 33 7.57 18 11.8 18 1.76 103
HCFN [163]57.3 3.16 77 6.30 92 1.20 10 3.69 47 5.58 54 1.32 23 3.97 44 6.09 50 1.73 34 5.54 52 8.33 74 3.22 41 10.9 41 13.7 42 3.61 35 6.29 52 11.9 41 2.62 147 8.11 80 18.5 79 1.61 54 8.18 75 12.8 76 1.73 56
OAR-Flow [125]58.4 3.13 68 5.95 64 1.22 54 3.83 65 5.70 63 1.48 66 3.65 19 6.06 46 1.16 2 5.60 64 8.48 87 3.03 4 11.2 72 14.1 75 4.51 146 6.12 35 11.8 32 2.41 91 7.97 69 17.9 57 1.59 48 8.11 70 12.7 68 1.71 37
JOF [140]58.8 3.08 50 5.89 54 1.24 88 3.48 17 5.04 18 1.37 35 3.85 37 5.98 44 2.07 59 5.43 41 7.81 42 3.28 60 11.3 90 14.2 90 4.51 146 6.72 108 13.1 110 2.37 67 7.48 24 17.1 24 1.54 27 8.01 61 12.6 63 1.73 56
SegFlow [161]59.8 3.23 95 6.50 111 1.21 25 3.55 29 5.27 33 1.31 19 4.03 49 5.73 27 1.34 5 6.09 108 9.56 134 3.37 90 11.1 58 14.0 66 4.50 132 6.10 32 11.8 32 2.40 79 7.51 25 17.2 26 1.66 77 8.06 65 12.6 63 1.73 56
Ad-TV-NDC [36]63.0 3.23 95 5.70 35 1.44 155 4.78 148 6.46 135 1.92 138 3.67 22 5.86 37 1.50 16 5.97 98 8.14 65 3.51 113 10.8 33 13.5 31 3.63 46 6.24 47 12.0 46 2.40 79 7.70 43 17.3 28 1.51 12 7.48 17 11.7 17 1.73 56
F-TV-L1 [15]63.0 3.30 109 6.36 101 1.29 127 4.39 119 6.32 127 1.62 92 3.80 33 5.90 40 1.76 37 5.61 66 7.97 53 3.31 78 10.9 41 13.6 36 3.59 22 5.84 16 11.2 15 2.33 48 7.70 43 17.6 44 1.79 105 7.61 22 11.9 21 1.78 118
Modified CLG [34]63.3 2.87 15 5.32 14 1.24 88 4.51 128 6.21 114 1.96 146 4.15 60 6.45 68 2.67 98 5.56 56 7.69 32 3.64 129 10.8 33 13.5 31 3.63 46 6.36 62 12.3 60 2.39 76 7.46 23 17.1 24 1.56 38 7.86 46 12.3 43 1.75 89
CPM-Flow [116]64.0 3.17 84 6.31 96 1.21 25 3.54 26 5.26 31 1.31 19 4.22 68 5.88 39 1.45 12 6.11 110 9.48 130 3.31 78 11.1 58 13.9 54 4.50 132 6.28 51 12.1 50 2.32 45 7.66 38 17.6 44 1.74 93 8.18 75 12.8 76 1.76 103
2DHMM-SAS [92]64.7 3.10 57 5.91 57 1.21 25 4.10 96 6.05 96 1.46 63 4.38 81 7.10 102 2.07 59 5.38 29 7.78 40 3.22 41 11.3 90 14.3 100 4.42 109 6.33 55 12.2 53 2.26 16 7.95 68 18.2 68 1.64 70 8.19 78 12.8 76 1.70 24
TC/T-Flow [76]65.9 3.21 92 6.24 86 1.22 54 3.90 76 5.86 80 1.43 54 3.69 26 5.83 33 1.50 16 5.88 91 8.93 108 3.15 18 11.1 58 13.9 54 4.50 132 6.23 45 12.0 46 2.26 16 8.61 111 19.0 92 1.93 120 8.16 74 12.8 76 1.70 24
COFM [59]66.3 3.03 38 5.76 42 1.22 54 3.55 29 5.21 28 1.32 23 3.82 34 6.98 93 2.81 102 5.41 38 7.97 53 3.30 73 10.8 33 13.6 36 3.62 40 7.01 140 13.7 137 2.40 79 8.00 74 18.5 79 1.98 123 7.91 52 12.4 53 1.80 138
DMF_ROB [139]66.7 3.15 74 6.13 80 1.22 54 3.96 81 5.87 81 1.56 77 5.24 123 7.74 130 2.62 93 5.73 76 8.32 73 3.19 30 11.0 47 13.8 47 4.50 132 6.07 29 11.7 29 2.37 67 7.66 38 17.5 39 1.50 8 8.10 68 12.7 68 1.73 56
LDOF [28]67.4 3.03 38 5.66 33 1.28 121 4.06 93 5.53 52 2.40 159 4.32 76 6.43 63 2.00 53 5.45 44 7.56 25 3.60 126 10.2 14 12.7 14 3.59 22 6.39 64 12.4 66 2.29 29 8.36 96 19.4 103 2.21 139 7.57 18 11.8 18 1.86 151
FlowFields [110]67.9 3.15 74 6.30 92 1.21 25 3.57 32 5.34 38 1.32 23 4.73 103 6.89 86 3.23 122 5.85 86 8.96 111 3.08 10 10.8 33 13.6 36 4.19 94 6.57 88 12.8 94 2.36 63 7.72 46 17.8 53 1.67 79 8.20 80 12.9 83 1.74 79
Layers++ [37]68.0 2.96 27 5.56 27 1.22 54 3.29 5 4.64 8 1.26 1 4.07 53 7.24 106 3.08 112 5.48 45 8.10 61 3.25 53 12.0 155 15.2 156 4.62 158 7.29 148 14.3 148 2.44 101 7.63 36 17.5 39 1.54 27 7.84 45 12.3 43 1.70 24
nLayers [57]68.2 3.03 38 5.72 37 1.21 25 3.48 17 5.09 24 1.31 19 5.60 129 7.52 121 4.26 144 5.61 66 8.33 74 3.29 63 11.6 133 14.6 132 4.31 100 6.66 101 12.9 103 2.40 79 7.58 30 17.3 28 1.59 48 7.94 56 12.4 53 1.69 16
ComplOF-FED-GPU [35]68.5 3.23 95 6.40 103 1.22 54 3.73 53 5.62 59 1.44 56 5.23 122 6.06 46 3.23 122 5.53 50 8.25 68 3.29 63 11.1 58 13.9 54 4.21 95 6.11 34 11.8 32 2.32 45 8.16 83 18.5 79 1.61 54 8.29 98 12.9 83 1.71 37
TV-L1-MCT [64]68.5 3.17 84 6.05 75 1.22 54 3.87 68 5.82 76 1.40 45 4.48 88 7.75 131 2.24 71 5.37 27 7.76 38 3.24 51 11.6 133 14.7 139 4.31 100 6.08 30 11.7 29 2.31 38 8.07 78 18.6 83 2.15 137 7.68 27 12.0 27 1.68 14
AdaConv-v1 [126]69.8 3.57 136 6.88 129 1.41 151 4.34 116 5.67 60 2.52 161 5.00 115 5.86 37 2.98 107 6.91 138 8.89 107 4.89 157 10.2 14 12.8 16 3.21 7 5.33 10 10.1 11 2.27 21 7.30 14 16.6 14 1.92 119 6.94 12 10.8 12 1.67 12
TC-Flow [46]70.2 3.31 111 6.70 121 1.22 54 3.91 78 5.95 84 1.45 59 3.64 18 5.84 34 1.28 3 5.70 71 8.50 89 3.22 41 11.2 72 14.1 75 4.44 113 6.34 58 12.3 60 2.41 91 7.79 56 17.9 57 1.55 33 8.42 113 13.2 115 1.74 79
CRTflow [80]70.3 3.09 55 5.91 57 1.27 117 4.35 117 6.31 125 1.68 105 4.15 60 7.26 107 1.84 43 5.33 22 7.51 23 3.38 91 11.0 47 13.8 47 4.48 120 6.09 31 11.7 29 2.30 35 8.55 108 19.8 114 1.55 33 8.19 78 12.8 76 1.72 47
DPOF [18]70.5 3.34 117 6.82 125 1.29 127 3.40 12 4.93 13 1.29 13 5.00 115 6.36 61 3.40 125 5.86 87 8.94 109 3.51 113 11.0 47 13.8 47 3.59 22 6.56 85 12.7 82 2.28 24 7.99 71 18.2 68 1.55 33 8.24 88 12.9 83 1.70 24
AGIF+OF [85]70.5 3.12 63 5.95 64 1.20 10 3.64 39 5.39 41 1.40 45 3.96 43 6.44 67 2.28 74 5.48 45 8.03 57 3.25 53 11.4 101 14.3 100 4.49 127 6.91 131 13.5 132 2.37 67 7.85 61 17.9 57 1.54 27 8.44 117 13.2 115 1.73 56
PGM-C [120]72.0 3.17 84 6.29 90 1.21 25 3.58 33 5.32 36 1.33 26 5.01 117 6.14 54 1.90 46 6.14 113 9.63 136 3.23 48 11.2 72 14.1 75 4.50 132 6.14 39 11.8 32 2.34 51 8.20 85 18.9 89 1.59 48 8.46 120 13.3 121 1.73 56
Classic++ [32]72.6 3.05 43 5.85 48 1.24 88 4.08 95 6.08 99 1.52 72 3.74 30 5.58 21 1.53 20 5.72 75 8.12 63 3.21 37 11.4 101 14.3 100 3.74 71 6.68 103 13.0 105 2.42 94 8.35 95 19.2 96 1.62 65 8.21 82 12.9 83 1.73 56
Sparse-NonSparse [56]73.0 3.07 47 5.88 52 1.21 25 3.61 35 5.33 37 1.33 26 4.29 74 7.47 119 2.19 68 5.37 27 7.74 34 3.21 37 11.5 117 14.5 122 4.36 104 6.66 101 12.9 103 2.41 91 8.69 117 20.1 120 1.67 79 8.27 95 13.0 97 1.70 24
EAI-Flow [151]73.0 3.37 120 6.27 89 1.32 137 3.79 59 5.59 56 1.52 72 4.30 75 7.09 100 2.39 83 5.60 64 8.34 76 2.96 2 11.2 72 14.1 75 4.34 103 6.04 28 11.6 26 2.34 51 7.72 46 17.6 44 3.12 157 7.77 38 12.1 32 1.82 148
ProbFlowFields [128]74.0 3.15 74 6.32 98 1.21 25 3.53 23 5.26 31 1.29 13 5.03 118 7.35 113 3.73 132 5.43 41 7.97 53 3.25 53 11.1 58 14.0 66 4.50 132 6.48 72 12.6 75 2.55 136 7.99 71 18.4 78 2.57 148 7.78 39 12.2 39 1.75 89
ProFlow_ROB [146]74.6 3.16 77 6.30 92 1.21 25 3.77 57 5.71 65 1.39 40 4.12 57 5.27 12 1.62 24 6.15 114 9.68 137 3.11 14 11.5 117 14.5 122 4.50 132 5.85 17 11.2 15 2.24 11 8.50 104 19.4 103 1.56 38 8.70 135 13.6 133 1.85 150
BlockOverlap [61]75.0 2.98 29 5.47 23 1.33 141 4.38 118 6.09 100 1.88 130 4.26 71 5.57 20 3.14 116 5.56 56 7.32 18 4.14 150 11.1 58 13.9 54 3.77 74 6.41 65 12.3 60 2.54 133 7.75 50 17.4 34 3.02 155 7.32 14 11.4 14 1.78 118
PMF [73]75.0 3.14 70 6.13 80 1.20 10 3.73 53 5.60 57 1.27 6 5.24 123 8.98 147 3.76 133 5.75 77 8.56 95 3.28 60 10.8 33 13.6 36 3.62 40 6.55 82 12.7 82 2.35 60 8.41 101 19.5 109 1.64 70 8.57 127 13.4 126 1.70 24
S2F-IF [123]75.2 3.26 102 6.66 118 1.20 10 3.53 23 5.25 30 1.29 13 4.11 56 6.64 75 2.34 79 5.89 92 9.06 116 3.08 10 11.4 101 14.3 100 4.51 146 6.41 65 12.4 66 2.40 79 7.84 59 18.1 64 1.76 101 8.33 105 13.1 106 1.75 89
MLDP_OF [89]75.4 3.08 50 5.98 69 1.21 25 4.01 89 6.01 93 1.49 69 3.67 22 6.14 54 1.47 14 5.78 80 8.13 64 3.95 145 11.3 90 14.2 90 3.87 79 6.71 106 13.0 105 2.51 125 7.73 49 17.7 49 1.71 88 8.18 75 12.8 76 1.76 103
OFLAF [77]75.7 3.10 57 5.98 69 1.20 10 3.44 13 5.03 17 1.26 1 3.73 29 5.82 32 1.66 27 5.33 22 7.74 34 3.10 13 11.6 133 14.7 139 4.50 132 6.58 92 12.8 94 2.48 115 9.33 142 21.6 143 2.06 131 8.45 119 13.2 115 1.80 138
Sparse Occlusion [54]76.0 3.16 77 6.18 84 1.23 74 4.14 103 6.24 119 1.45 59 3.67 22 5.84 34 1.52 19 5.61 66 8.26 69 3.15 18 11.5 117 14.4 111 4.48 120 6.26 49 12.1 50 2.46 106 8.52 106 19.6 111 1.54 27 8.28 97 13.0 97 1.75 89
FlowFields+ [130]76.1 3.14 70 6.26 88 1.22 54 3.54 26 5.27 33 1.30 18 4.74 106 7.10 102 3.20 120 6.01 103 9.35 126 3.11 14 11.1 58 13.9 54 4.50 132 6.57 88 12.8 94 2.40 79 7.89 65 18.2 68 1.80 106 8.22 84 12.9 83 1.73 56
TF+OM [100]76.2 3.33 116 6.83 126 1.25 99 3.65 40 5.43 45 1.47 65 3.82 34 6.43 63 1.68 30 6.01 103 9.04 115 3.19 30 11.2 72 14.1 75 4.38 106 6.46 71 12.5 71 2.34 51 8.30 94 19.2 96 1.86 112 8.05 64 12.6 63 1.75 89
HAST [109]76.2 3.01 35 5.73 39 1.21 25 3.45 15 5.01 16 1.27 6 6.39 143 8.24 138 4.09 138 5.43 41 7.96 51 3.03 4 11.2 72 14.2 90 3.59 22 7.47 152 14.7 152 2.47 109 8.68 116 20.1 120 1.53 20 8.35 108 13.1 106 1.77 112
FlowNetS+ft+v [112]76.5 3.07 47 5.81 45 1.28 121 4.57 137 6.29 123 2.41 160 4.01 46 5.64 23 2.13 65 5.55 54 7.77 39 3.88 141 11.3 90 14.2 90 4.46 116 5.99 25 11.5 23 2.35 60 8.63 114 20.0 117 1.62 65 7.70 30 12.0 27 1.74 79
Filter Flow [19]77.8 3.13 68 5.90 55 1.28 121 4.56 136 6.38 131 1.85 128 4.22 68 6.28 58 2.10 63 5.91 93 7.97 53 3.44 104 10.4 23 13.1 25 3.69 59 6.43 69 12.5 71 2.40 79 8.17 84 18.8 88 1.62 65 7.94 56 12.4 53 1.78 118
LSM [39]80.6 3.12 63 6.05 75 1.21 25 3.68 45 5.47 47 1.33 26 4.38 81 7.66 128 2.01 54 5.55 54 8.19 66 3.19 30 11.5 117 14.5 122 4.43 110 6.83 122 13.3 123 2.37 67 8.70 118 20.1 120 1.72 91 8.34 107 13.1 106 1.71 37
EpicFlow [102]80.8 3.17 84 6.34 99 1.21 25 3.79 59 5.70 63 1.44 56 4.28 73 5.73 27 1.67 28 6.37 126 10.1 142 3.39 94 11.2 72 14.1 75 4.50 132 6.23 45 12.0 46 2.38 74 8.11 80 18.5 79 1.76 101 8.76 139 13.8 140 1.74 79
Black & Anandan [4]81.1 3.22 94 5.87 50 1.30 131 4.82 151 6.55 140 1.78 122 7.16 147 7.10 102 3.93 135 6.25 120 8.49 88 3.35 88 10.9 41 13.7 42 3.56 16 6.33 55 12.2 53 2.37 67 8.23 88 18.6 83 1.64 70 7.67 26 11.9 21 1.69 16
RNLOD-Flow [121]81.6 3.06 45 5.87 50 1.21 25 3.96 81 5.97 90 1.42 51 4.39 83 8.08 135 2.44 85 5.35 24 7.75 36 3.18 25 11.5 117 14.5 122 4.49 127 6.71 106 13.1 110 2.43 98 7.85 61 18.0 62 2.18 138 8.44 117 13.2 115 1.73 56
TCOF [69]82.0 3.12 63 5.94 62 1.21 25 4.60 140 6.64 147 1.76 120 4.13 58 7.30 109 1.81 39 5.42 40 7.88 45 3.25 53 11.3 90 14.2 90 3.63 46 6.42 67 12.4 66 2.36 63 9.08 139 21.0 139 1.59 48 8.37 109 13.1 106 1.76 103
Ramp [62]82.7 3.11 61 5.96 66 1.22 54 3.61 35 5.34 38 1.40 45 4.91 112 8.45 141 3.20 120 5.29 17 7.66 30 3.21 37 11.5 117 14.5 122 4.31 100 6.88 130 13.4 127 2.48 115 8.73 124 20.2 124 1.52 19 8.29 98 13.0 97 1.73 56
Fusion [6]83.3 3.04 42 5.86 49 1.22 54 3.75 56 5.47 47 1.42 51 4.08 54 5.55 18 3.08 112 5.80 82 8.10 61 3.19 30 11.4 101 14.3 100 3.73 68 6.99 137 13.7 137 2.60 142 8.40 100 19.4 103 1.65 75 8.50 122 13.3 121 1.80 138
Classic+NL [31]83.9 3.10 57 5.92 60 1.23 74 3.66 42 5.40 42 1.39 40 4.78 109 8.42 140 3.01 110 5.36 25 7.78 40 3.30 73 11.5 117 14.5 122 4.24 97 6.73 110 13.1 110 2.40 79 8.74 125 20.2 124 1.70 86 8.29 98 13.0 97 1.71 37
ComponentFusion [96]84.0 3.41 122 7.08 132 1.20 10 3.63 37 5.44 46 1.27 6 4.20 66 6.49 70 2.43 84 5.59 62 8.38 80 3.32 81 11.4 101 14.4 111 4.11 91 6.26 49 12.1 50 2.35 60 9.30 141 21.6 143 2.80 153 8.68 132 13.6 133 1.73 56
AggregFlow [97]84.0 3.80 147 8.08 147 1.23 74 3.87 68 5.83 77 1.43 54 4.21 67 6.79 80 2.85 104 6.11 110 9.36 127 3.31 78 10.6 27 13.3 27 3.67 55 6.13 36 11.8 32 2.34 51 8.70 118 19.8 114 2.30 143 8.27 95 13.0 97 1.75 89
Bartels [41]86.2 3.48 129 7.24 136 1.30 131 4.02 90 6.12 105 1.68 105 3.74 30 5.80 31 1.95 51 5.87 89 8.44 84 3.78 139 10.3 20 12.8 16 3.75 73 6.77 117 13.0 105 2.73 160 7.53 27 17.3 28 2.72 151 8.13 71 12.7 68 1.77 112
Occlusion-TV-L1 [63]86.3 3.14 70 6.13 80 1.25 99 4.47 127 6.61 143 1.66 99 3.51 11 5.71 26 1.70 32 6.33 122 9.58 135 3.51 113 11.0 47 13.9 54 3.57 18 6.48 72 12.6 75 2.52 130 8.36 96 18.1 64 2.00 126 8.32 104 13.0 97 1.79 132
Classic+CPF [83]86.8 3.12 63 5.96 66 1.21 25 3.72 52 5.51 51 1.39 40 4.39 83 7.38 116 2.27 73 5.32 20 7.70 33 3.18 25 11.7 143 14.8 145 4.50 132 7.18 146 14.0 146 2.45 103 8.79 126 20.2 124 1.57 43 8.71 137 13.7 136 1.73 56
LFNet_ROB [149]86.9 3.65 141 7.73 142 1.23 74 3.88 71 5.80 75 1.49 69 4.57 92 8.96 146 2.02 56 5.62 69 8.44 84 3.18 25 11.0 47 13.8 47 4.47 117 7.19 147 14.1 147 2.47 109 7.59 32 17.4 34 1.82 108 8.10 68 12.7 68 1.78 118
HBM-GC [105]87.0 3.08 50 5.90 55 1.26 112 3.97 84 6.04 95 1.41 49 3.92 40 5.62 22 2.87 106 5.54 52 8.03 57 3.21 37 11.7 143 14.7 139 4.58 157 7.66 157 15.0 157 2.69 156 8.36 96 19.3 99 1.55 33 7.86 46 12.3 43 1.76 103
Efficient-NL [60]87.2 3.05 43 5.77 43 1.21 25 3.90 76 5.84 78 1.38 37 5.90 135 6.94 90 4.19 141 5.59 62 8.09 60 3.20 35 11.5 117 14.4 111 4.40 108 6.87 126 13.4 127 2.40 79 8.85 127 20.5 129 1.68 83 8.57 127 13.4 126 1.66 9
CNN-flow-warp+ref [117]87.2 2.90 17 5.43 19 1.25 99 4.10 96 5.95 84 1.83 127 4.92 113 7.63 126 2.45 86 6.13 112 7.85 43 3.72 135 11.3 90 14.2 90 4.51 146 6.03 27 11.6 26 2.46 106 9.00 132 20.8 137 1.65 75 7.91 52 12.4 53 1.76 103
2D-CLG [1]88.0 3.01 35 5.65 31 1.28 121 4.59 139 6.17 108 1.95 145 5.18 120 6.06 46 3.15 118 6.01 103 7.88 45 3.97 146 11.4 101 14.4 111 4.69 159 5.98 24 11.5 23 2.45 103 8.89 130 20.5 129 1.67 79 7.74 32 12.0 27 1.71 37
Horn & Schunck [3]88.0 3.16 77 5.83 46 1.26 112 4.91 152 6.65 148 1.92 138 6.13 138 6.85 83 3.53 128 6.80 135 9.10 117 3.57 122 10.9 41 13.7 42 3.59 22 6.16 41 11.9 41 2.32 45 8.63 114 19.5 109 1.84 111 7.91 52 12.3 43 1.73 56
FC-2Layers-FF [74]88.1 3.18 88 6.16 83 1.22 54 3.33 10 4.73 10 1.35 32 4.34 80 7.09 100 3.11 114 5.56 56 8.29 70 3.29 63 11.5 117 14.5 122 4.48 120 7.00 138 13.7 137 2.48 115 8.92 131 20.6 132 1.71 88 8.30 101 13.0 97 1.73 56
FESL [72]88.8 3.16 77 6.02 73 1.21 25 3.65 40 5.42 44 1.35 32 4.39 83 7.61 125 2.18 67 5.71 73 8.35 78 3.30 73 11.6 133 14.7 139 4.51 146 6.73 110 13.1 110 2.47 109 8.70 118 20.1 120 1.56 38 8.42 113 13.2 115 1.75 89
SRR-TVOF-NL [91]88.9 3.32 114 6.46 109 1.23 74 3.96 81 5.96 87 1.59 82 4.68 99 7.90 133 3.52 127 5.99 101 8.77 102 3.23 48 11.2 72 14.1 75 4.45 115 6.79 120 13.2 120 2.31 38 7.88 63 18.0 62 1.50 8 8.37 109 13.1 106 1.75 89
RFlow [90]89.5 3.08 50 5.99 71 1.23 74 4.33 113 6.31 125 1.66 99 4.83 110 7.32 110 3.14 116 5.87 89 8.72 101 3.47 108 11.1 58 14.0 66 3.60 29 6.54 81 12.7 82 2.39 76 8.54 107 19.8 114 1.61 54 8.26 93 12.9 83 1.80 138
TriFlow [95]90.8 3.71 144 7.95 146 1.25 99 4.31 112 6.36 130 1.71 110 4.05 50 6.86 85 1.84 43 6.21 118 9.44 129 3.17 21 11.3 90 14.2 90 4.48 120 6.76 116 13.1 110 2.29 29 8.01 76 18.2 68 1.75 98 8.24 88 12.9 83 1.70 24
OFH [38]91.2 3.18 88 6.29 90 1.23 74 4.11 98 5.96 87 1.61 89 4.68 99 8.40 139 1.68 30 5.84 84 8.99 112 3.03 4 11.3 90 14.2 90 4.25 99 6.30 54 12.2 53 2.40 79 8.59 109 19.3 99 1.89 115 8.55 124 13.4 126 1.97 157
3DFlow [135]92.0 3.26 102 6.37 102 1.21 25 3.70 48 5.55 53 1.46 63 4.51 90 6.52 71 2.28 74 5.84 84 8.84 105 3.59 124 11.2 72 14.1 75 3.79 76 7.04 143 13.7 137 2.68 155 8.59 109 19.4 103 1.82 108 8.26 93 12.9 83 1.77 112
PWC-Net_ROB [147]92.2 3.66 143 7.76 143 1.21 25 3.91 78 5.97 90 1.37 35 3.88 39 6.73 78 1.48 15 6.36 124 10.1 142 3.13 16 11.8 148 14.9 149 4.49 127 6.78 119 13.1 110 2.34 51 7.72 46 17.7 49 1.66 77 8.57 127 13.5 131 1.88 152
Nguyen [33]92.7 3.26 102 6.11 79 1.33 141 4.94 153 6.51 138 1.91 136 4.09 55 7.32 110 1.96 52 6.19 117 8.53 92 3.60 126 11.1 58 13.9 54 3.58 20 6.55 82 12.7 82 2.36 63 9.44 144 21.8 147 1.80 106 7.86 46 12.3 43 1.74 79
CostFilter [40]92.8 3.46 128 7.24 136 1.19 6 3.71 50 5.60 57 1.27 6 5.63 131 9.41 153 3.86 134 6.37 126 10.1 142 3.23 48 11.2 72 14.0 66 3.78 75 6.35 60 12.2 53 2.40 79 8.86 129 20.6 132 1.69 84 8.80 141 13.8 140 1.74 79
S2D-Matching [84]92.9 3.21 92 6.22 85 1.22 54 3.97 84 5.95 84 1.48 66 4.57 92 7.70 129 2.84 103 5.48 45 8.06 59 3.48 110 11.4 101 14.3 100 4.14 92 6.97 135 13.6 135 2.56 140 8.09 79 18.6 83 1.74 93 8.21 82 12.9 83 1.76 103
SVFilterOh [111]93.2 3.23 95 6.35 100 1.23 74 3.53 23 5.19 26 1.31 19 5.91 136 8.20 137 4.22 142 5.75 77 8.52 91 3.43 102 11.4 101 14.3 100 4.53 154 6.97 135 13.6 135 2.38 74 7.94 66 18.3 75 1.57 43 8.31 103 13.0 97 1.79 132
Steered-L1 [118]94.3 2.97 28 5.73 39 1.21 25 3.81 62 5.72 67 1.60 86 8.15 150 9.24 150 6.46 158 6.42 128 9.21 124 4.28 153 11.4 101 14.3 100 3.80 77 6.52 78 12.7 82 2.43 98 8.20 85 19.0 92 2.54 146 8.33 105 13.1 106 1.70 24
FlowNet2 [122]94.5 4.84 157 10.1 158 1.29 127 4.11 98 6.13 106 1.61 89 4.73 103 7.06 98 2.36 80 6.36 124 10.0 140 3.38 91 11.2 72 14.1 75 3.71 63 6.44 70 12.5 71 2.33 48 8.45 102 19.4 103 1.61 54 8.03 63 12.6 63 1.77 112
Adaptive [20]94.5 3.24 99 6.44 106 1.25 99 4.57 137 6.61 143 1.72 111 3.94 42 6.12 53 1.81 39 5.86 87 8.66 98 3.47 108 11.6 133 14.6 132 3.59 22 6.55 82 12.7 82 2.51 125 9.03 134 20.6 132 1.59 48 8.13 71 12.7 68 1.78 118
TVL1_ROB [138]94.6 3.32 114 6.25 87 1.36 148 5.03 155 6.77 155 1.94 144 4.50 89 6.70 77 2.55 91 6.22 119 8.66 98 3.63 128 10.8 33 13.6 36 3.63 46 6.52 78 12.7 82 2.43 98 9.03 134 20.7 136 2.13 135 7.72 31 12.1 32 1.70 24
IAOF [50]94.8 3.53 134 6.60 116 1.32 137 5.39 161 7.19 161 1.96 146 5.81 133 7.32 110 3.63 130 6.15 114 8.34 76 3.72 135 11.1 58 14.0 66 3.60 29 6.50 75 12.6 75 2.34 51 8.28 92 19.0 92 1.53 20 7.94 56 12.4 53 1.73 56
CompactFlow_ROB [160]95.7 3.91 150 8.50 154 1.24 88 3.94 80 5.94 83 1.54 76 5.28 125 8.58 143 2.62 93 8.69 158 14.5 160 3.26 58 10.9 41 13.7 42 3.64 53 6.87 126 13.4 127 2.33 48 8.50 104 19.6 111 1.53 20 8.22 84 12.9 83 1.75 89
Complementary OF [21]96.5 3.48 129 7.32 140 1.20 10 3.89 74 5.96 87 1.45 59 8.94 154 6.94 90 5.45 152 6.33 122 10.0 140 3.09 12 11.3 90 14.2 90 4.24 97 6.33 55 12.3 60 2.42 94 8.62 113 19.3 99 1.75 98 9.07 151 14.3 152 1.72 47
FF++_ROB [145]97.8 3.27 105 6.67 119 1.20 10 3.74 55 5.58 54 1.38 37 4.86 111 7.42 117 2.99 108 6.57 132 10.4 145 3.54 119 11.5 117 14.5 122 4.51 146 6.62 99 12.8 94 2.47 109 7.97 69 18.3 75 1.90 116 8.24 88 12.9 83 1.78 118
TV-L1-improved [17]98.2 3.09 55 6.03 74 1.25 99 4.55 134 6.59 142 1.70 108 5.88 134 5.66 24 4.09 138 5.53 50 7.88 45 3.22 41 11.4 101 14.4 111 3.61 35 6.73 110 13.1 110 2.51 125 9.48 145 22.1 149 1.94 121 8.25 91 12.9 83 1.79 132
AugFNG_ROB [143]98.2 3.73 145 7.90 145 1.25 99 4.12 101 6.02 94 1.74 114 4.70 102 8.79 145 1.94 50 8.14 156 13.4 157 3.29 63 12.0 155 15.1 154 4.50 132 6.50 75 12.6 75 2.28 24 8.03 77 18.3 75 1.62 65 7.75 33 12.1 32 1.75 89
TI-DOFE [24]98.7 3.41 122 6.44 106 1.44 155 5.20 159 6.82 158 2.01 150 4.19 65 6.41 62 1.88 45 6.98 139 9.50 131 3.70 133 10.8 33 13.6 36 3.61 35 6.59 93 12.8 94 2.36 63 8.13 82 18.2 68 1.77 103 8.53 123 12.4 53 2.33 161
EPPM w/o HM [88]99.2 3.35 118 6.86 128 1.21 25 3.85 67 5.88 82 1.29 13 7.03 145 9.47 156 3.97 137 6.15 114 9.51 132 3.38 91 10.6 27 13.3 27 3.62 40 7.00 138 13.7 137 2.37 67 8.85 127 20.5 129 2.62 150 8.42 113 13.2 115 1.76 103
GraphCuts [14]101.0 3.65 141 7.01 131 1.27 117 3.89 74 5.71 65 1.59 82 7.54 148 5.84 34 4.31 145 5.98 100 8.42 82 3.45 106 11.4 101 14.4 111 4.09 89 6.56 85 12.8 94 2.30 35 8.70 118 20.2 124 1.98 123 8.59 131 13.5 131 1.73 56
BriefMatch [124]101.5 3.25 101 6.49 110 1.25 99 3.87 68 5.67 60 1.97 148 6.16 139 6.17 56 4.79 148 6.83 137 8.37 79 5.73 160 11.0 47 13.8 47 3.73 68 6.75 115 13.0 105 2.61 144 7.99 71 17.9 57 3.29 158 8.22 84 12.8 76 2.32 160
NL-TV-NCC [25]102.8 3.37 120 6.58 115 1.24 88 4.23 107 6.41 133 1.49 69 4.39 83 6.68 76 2.07 59 7.19 147 11.2 151 3.35 88 10.7 30 13.4 29 4.00 86 6.95 132 13.4 127 2.44 101 9.06 136 20.0 117 2.13 135 8.42 113 13.1 106 1.78 118
EPMNet [133]103.7 4.90 158 10.5 162 1.28 121 4.04 92 5.98 92 1.60 86 4.73 103 7.06 98 2.36 80 8.74 160 15.0 161 3.48 110 11.2 72 14.1 75 3.71 63 6.70 105 13.0 105 2.34 51 8.45 102 19.4 103 1.61 54 8.38 111 13.1 106 1.78 118
IAOF2 [51]104.3 3.43 125 6.70 121 1.28 121 4.62 142 6.77 155 1.74 114 4.41 87 6.89 86 2.12 64 5.97 98 8.53 92 3.33 84 11.6 133 14.7 139 4.06 88 6.87 126 13.4 127 2.51 125 8.26 89 18.7 87 1.61 54 8.22 84 12.9 83 1.74 79
TriangleFlow [30]105.6 3.24 99 6.31 96 1.26 112 4.29 111 6.29 123 1.66 99 4.67 98 6.85 83 2.48 87 5.78 80 8.47 86 3.30 73 11.4 101 14.4 111 3.47 14 6.63 100 12.8 94 2.37 67 9.67 149 22.5 150 2.08 132 9.69 158 15.2 158 1.90 154
ResPWCR_ROB [144]106.3 3.52 133 7.36 141 1.23 74 4.06 93 6.18 111 1.53 75 4.57 92 6.90 88 1.91 47 7.44 150 12.2 155 3.40 97 11.5 117 14.6 132 4.39 107 7.10 144 13.7 137 2.54 133 7.81 58 17.8 53 1.67 79 9.04 150 14.2 149 1.71 37
LocallyOriented [52]106.6 3.29 108 6.53 113 1.26 112 4.64 143 6.69 150 1.74 114 5.61 130 7.56 122 3.67 131 6.73 133 9.84 139 3.18 25 11.5 117 14.4 111 3.71 63 6.57 88 12.7 82 2.45 103 8.71 122 19.3 99 1.71 88 8.40 112 13.1 106 1.72 47
Correlation Flow [75]108.2 3.27 105 6.50 111 1.20 10 4.42 121 6.56 141 1.65 96 3.98 45 6.10 51 2.30 78 5.93 95 8.94 109 3.32 81 11.6 133 14.6 132 3.84 78 7.63 156 14.8 154 2.65 153 9.95 154 23.0 154 2.01 128 8.73 138 13.7 136 1.71 37
ContinualFlow_ROB [152]108.5 3.79 146 8.09 148 1.25 99 4.03 91 6.11 103 1.61 89 4.76 107 7.58 123 2.38 82 7.09 142 11.7 152 3.17 21 12.2 159 15.4 159 4.49 127 6.35 60 12.3 60 2.29 29 8.71 122 20.0 117 1.61 54 9.02 148 14.2 149 1.78 118
ROF-ND [107]109.1 3.18 88 5.83 46 1.21 25 4.13 102 6.13 106 1.92 138 4.22 68 7.51 120 2.22 70 7.10 143 10.8 146 3.53 117 11.4 101 14.3 100 4.48 120 6.95 132 13.5 132 2.53 131 8.21 87 18.6 83 1.90 116 9.08 152 14.2 149 1.81 146
ACK-Prior [27]109.3 3.30 109 6.56 114 1.21 25 3.81 62 5.78 70 1.42 51 7.13 146 6.90 88 5.04 149 6.02 106 8.78 103 3.70 133 11.7 143 14.7 139 4.57 156 6.95 132 13.5 132 2.50 121 8.36 96 19.2 96 2.53 145 8.56 126 13.4 126 1.73 56
HBpMotionGpu [43]110.1 3.63 139 7.28 138 1.35 146 4.78 148 6.69 150 1.92 138 4.33 79 7.01 96 2.56 92 6.46 129 9.81 138 3.40 97 11.5 117 14.4 111 5.69 164 6.83 122 13.3 123 2.55 136 7.40 20 16.9 18 1.51 12 8.30 101 13.0 97 1.79 132
StereoOF-V1MT [119]110.1 3.56 135 7.20 135 1.22 54 4.27 110 6.18 111 1.70 108 6.10 137 6.80 81 3.43 126 7.17 146 9.52 133 4.01 149 11.2 72 14.1 75 4.43 110 6.61 98 12.5 71 2.60 142 9.49 146 21.6 143 2.05 129 8.01 61 12.4 53 1.78 118
Aniso-Texture [82]112.4 3.11 61 6.09 77 1.21 25 4.51 128 6.62 145 1.75 117 4.77 108 6.43 63 2.08 62 7.44 150 10.9 147 4.80 155 11.6 133 14.6 132 4.51 146 7.49 153 14.7 152 2.71 158 8.28 92 19.1 95 1.61 54 8.68 132 13.6 133 1.74 79
Dynamic MRF [7]114.5 3.19 91 6.41 104 1.22 54 4.11 98 6.21 114 1.56 77 5.37 127 7.35 113 2.70 99 6.74 134 9.18 122 4.19 151 11.1 58 13.9 54 4.48 120 7.02 141 13.7 137 2.62 147 9.26 140 21.4 142 2.23 140 8.57 127 13.3 121 1.80 138
LiteFlowNet [142]115.2 3.86 148 8.34 150 1.22 54 3.80 61 5.75 69 1.44 56 5.33 126 9.45 155 2.66 97 8.72 159 14.4 159 3.88 141 11.8 148 14.8 145 4.50 132 7.03 142 13.7 137 2.40 79 9.07 138 20.4 128 1.69 84 8.13 71 12.7 68 1.78 118
FOLKI [16]115.3 3.64 140 7.12 133 1.65 159 5.22 160 6.72 153 2.36 158 5.20 121 8.08 135 3.96 136 7.93 153 9.33 125 5.52 159 11.2 72 14.0 66 3.70 60 6.56 85 12.6 75 2.74 161 8.00 74 18.2 68 2.88 154 7.96 59 12.3 43 1.78 118
Shiralkar [42]116.0 3.57 136 7.31 139 1.22 54 4.46 126 6.33 129 1.65 96 5.49 128 6.98 93 2.73 100 7.42 149 10.9 147 3.43 102 11.5 117 14.4 111 3.73 68 6.57 88 12.7 82 2.48 115 9.58 147 21.9 148 1.88 114 9.18 154 14.4 153 1.75 89
SimpleFlow [49]116.7 3.10 57 5.97 68 1.22 54 4.19 105 6.11 103 1.64 95 9.91 157 9.43 154 6.53 159 5.58 59 8.29 70 3.30 73 11.6 133 14.6 132 4.43 110 7.42 150 14.6 151 2.56 140 10.7 158 25.2 158 2.73 152 9.16 153 14.4 153 1.73 56
Rannacher [23]117.1 3.31 111 6.72 124 1.25 99 4.60 140 6.66 149 1.72 111 6.36 142 6.54 72 4.25 143 5.91 93 8.87 106 3.49 112 11.5 117 14.5 122 3.63 46 6.73 110 13.1 110 2.53 131 9.35 143 21.7 146 1.98 123 8.70 135 13.7 136 1.75 89
SILK [79]117.1 3.45 127 6.85 127 1.36 148 5.11 157 6.70 152 2.21 155 11.1 159 9.96 157 6.24 157 6.49 130 8.82 104 3.59 124 11.4 101 14.3 100 3.54 15 6.87 126 13.3 123 2.63 149 7.76 52 17.7 49 1.87 113 8.20 80 12.7 68 1.80 138
Learning Flow [11]117.2 3.14 70 6.09 77 1.27 117 4.51 128 6.53 139 1.67 102 11.5 163 12.9 163 7.17 162 6.31 121 8.30 72 3.66 130 11.7 143 14.8 145 3.89 80 6.59 93 12.8 94 2.48 115 8.27 91 18.9 89 1.96 122 8.68 132 13.4 126 1.80 138
OFRF [134]120.5 4.02 151 8.26 149 1.33 141 4.53 132 6.49 136 1.81 125 4.60 96 7.27 108 2.13 65 6.02 106 9.15 119 3.39 94 11.8 148 14.9 149 4.23 96 7.13 145 13.9 145 2.39 76 9.02 133 20.8 137 1.59 48 8.79 140 13.8 140 1.77 112
Adaptive flow [45]120.8 3.60 138 6.30 92 1.54 158 5.14 158 6.79 157 2.14 154 4.52 91 6.60 73 3.01 110 6.54 131 8.64 97 4.23 152 12.1 158 15.2 156 4.09 89 7.57 154 14.9 156 2.64 151 7.75 50 17.8 53 2.28 142 8.47 121 13.3 121 1.71 37
H+S_ROB [137]121.2 3.43 125 6.69 120 1.29 127 4.55 134 6.05 96 1.91 136 11.3 160 12.3 162 7.31 163 6.98 139 8.51 90 3.51 113 11.4 101 14.4 111 3.65 54 6.60 95 12.8 94 2.42 94 9.86 152 22.7 152 2.08 132 8.84 144 13.7 136 1.74 79
UnFlow [129]121.8 4.05 152 8.73 155 1.31 135 4.44 125 6.28 122 1.87 129 4.92 113 7.36 115 2.62 93 5.95 97 9.00 113 3.27 59 12.0 155 15.2 156 4.37 105 7.59 155 14.8 154 2.61 144 7.77 54 17.6 44 1.64 70 10.4 159 15.4 159 2.33 161
StereoFlow [44]122.5 5.35 163 10.3 160 1.42 153 5.03 155 7.21 162 1.76 120 4.14 59 6.94 90 2.01 54 5.83 83 8.55 94 3.33 84 13.7 161 17.3 161 4.70 160 8.71 162 17.2 162 2.70 157 7.88 63 18.1 64 1.61 54 8.82 143 13.9 145 1.79 132
2bit-BM-tele [98]123.8 3.31 111 6.41 104 1.34 145 4.53 132 6.62 145 1.80 124 6.23 140 9.24 150 6.19 156 5.94 96 8.59 96 3.55 120 11.3 90 14.2 90 4.03 87 7.72 158 15.1 158 3.02 162 12.2 162 28.7 163 4.77 164 7.76 37 12.1 32 1.82 148
IIOF-NLDP [131]125.1 3.36 119 6.62 117 1.21 25 4.22 106 6.32 127 1.59 82 5.16 119 7.63 126 2.63 96 6.10 109 9.20 123 3.53 117 11.6 133 14.6 132 4.79 162 7.42 150 14.5 150 2.71 158 12.0 161 28.2 161 3.38 159 8.93 146 13.9 145 1.74 79
SPSA-learn [13]128.5 3.89 149 7.79 144 1.27 117 4.43 123 6.17 108 1.81 125 9.03 155 8.47 142 5.47 153 6.80 135 9.40 128 3.72 135 11.5 117 14.5 122 3.91 82 6.51 77 12.6 75 2.46 106 11.9 159 27.9 160 4.54 162 10.5 161 16.5 161 1.75 89
FFV1MT [106]129.0 4.09 154 8.38 151 1.31 135 4.68 145 6.18 111 2.02 151 6.95 144 11.5 159 3.35 124 7.12 144 9.16 120 3.98 147 11.3 90 14.1 75 3.74 71 6.77 117 12.7 82 2.50 121 9.59 148 21.0 139 2.05 129 8.87 145 13.8 140 1.90 154
SegOF [10]131.5 3.51 131 7.12 133 1.32 137 4.17 104 6.10 101 1.59 82 8.69 152 7.75 131 5.15 150 8.58 157 14.3 158 4.29 154 11.7 143 14.8 145 4.50 132 6.79 120 13.2 120 2.50 121 10.1 155 23.5 155 2.55 147 8.80 141 13.8 140 1.72 47
PGAM+LK [55]133.8 4.08 153 8.41 152 1.65 159 4.74 147 6.45 134 2.27 157 8.87 153 12.2 160 6.88 160 8.06 155 10.9 147 4.83 156 11.4 101 14.3 100 3.90 81 6.83 122 13.2 120 2.55 136 8.26 89 18.9 89 2.27 141 8.55 124 13.3 121 1.90 154
Heeger++ [104]134.2 4.76 156 9.63 157 1.33 141 4.65 144 6.22 117 1.90 133 7.84 149 9.26 152 3.57 129 7.12 144 9.16 120 3.98 147 11.9 152 15.0 152 4.47 117 6.52 78 12.2 53 2.61 144 9.82 150 20.6 132 2.00 126 9.02 148 14.0 147 1.79 132
SLK [47]135.5 3.51 131 6.96 130 1.41 151 4.72 146 6.10 101 1.98 149 9.84 156 7.59 124 5.20 151 7.98 154 11.0 150 6.14 161 11.8 148 14.9 149 3.71 63 6.60 95 12.7 82 2.50 121 9.87 153 22.8 153 2.08 132 8.94 147 14.0 147 2.03 158
HCIC-L [99]137.9 4.98 160 9.28 156 1.77 162 4.97 154 6.87 160 2.11 152 5.70 132 10.0 158 4.41 147 7.85 152 11.8 153 3.68 132 10.9 41 13.7 42 3.72 67 8.18 161 16.1 161 2.55 136 9.06 136 21.0 139 2.58 149 9.57 157 15.0 157 1.81 146
WRT [150]137.9 3.42 124 6.71 123 1.23 74 4.33 113 6.06 98 1.89 132 9.93 158 8.00 134 5.95 155 6.98 139 9.01 114 3.77 138 11.9 152 15.1 154 3.97 85 7.82 159 15.4 159 2.64 151 12.5 163 29.5 164 3.47 160 10.5 161 16.6 162 1.80 138
WOLF_ROB [148]140.2 5.06 161 10.3 160 1.30 131 4.79 150 6.72 153 1.75 117 6.29 141 9.03 148 4.14 140 7.37 148 11.8 153 3.33 84 11.9 152 15.0 152 4.48 120 7.40 149 14.3 148 2.51 125 10.5 157 23.9 156 1.74 93 9.44 155 14.8 155 1.78 118
Pyramid LK [2]148.2 4.16 155 8.44 153 1.74 161 5.83 162 6.82 158 2.76 162 11.4 161 8.60 144 5.89 154 12.4 163 16.7 162 7.03 163 14.3 162 18.1 162 3.92 84 6.69 104 12.2 53 2.63 149 10.3 156 24.0 157 2.45 144 11.1 163 17.4 163 2.55 163
GroupFlow [9]150.9 4.94 159 10.2 159 1.36 148 4.51 128 6.50 137 1.92 138 8.67 151 9.13 149 4.38 146 8.83 161 13.0 156 5.40 158 12.9 160 16.3 160 4.53 154 7.89 160 15.5 160 2.65 153 9.85 151 22.6 151 1.91 118 9.52 156 14.9 156 1.88 152
Periodicity [78]161.6 5.27 162 11.1 163 1.83 163 7.09 163 7.33 163 2.86 163 11.4 161 12.2 160 7.13 161 10.5 162 17.1 163 6.14 161 14.9 163 19.0 163 4.71 161 9.13 163 17.9 163 3.16 163 11.9 159 27.8 159 3.76 161 10.4 159 15.8 160 2.29 159
AVG_FLOW_ROB [141]163.8 14.6 164 20.0 164 3.66 164 11.3 164 12.1 164 4.33 164 13.4 164 14.1 164 7.93 164 19.0 164 25.3 164 10.2 164 18.3 164 23.1 164 5.58 163 16.7 164 32.2 164 4.90 164 16.6 164 28.6 162 4.56 163 15.9 164 19.8 164 4.61 164
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] MEMC-Net+ 0.16 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.
[156] MPRN 0.32 4 color Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[157] DAIN 0.13 2 color Anonymous. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019 submission 1769.
[158] InterpCNN 0.65 2 color Anonymous. (Interpolation results only.) Video frame interpolation with a stack of synthesis networks and intermediate optical flows. CVPR 2019 submission 6533.
[159] OFRI 0.31 2 color Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
[160] CompactFlow_ROB 0.05 2 color Anonymous. CompactFlow: spatially shiftable window revisited. CVPR 2019 submission 1387.
[161] 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.
[162] PyrWarp 0.14 2 color Anonymous. (Interpolation results only.) Video frame interpolation using differentiable forward-warping of feature pyramids. ICCV 2019 submission 741.
[163] HCFN 0.18 2 color Anonymous. Practical coarse-to-fine optical flow with deep networks. ICCV 2019 submission 116.
[164] FGME 0.23 2 color Anonymous. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. ICCV 2019 submission 4327.
* 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.