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
PyrWarp [159]3.2 5.24 2 6.52 2 1.53 1 5.94 1 7.55 2 2.91 16 10.2 2 11.5 5 6.47 6 6.76 1 8.70 1 4.63 1 14.3 1 16.2 1 7.65 1 13.1 5 18.6 6 4.98 7 16.5 2 25.3 2 6.41 2 14.9 2 18.7 2 6.68 6
MPRN [157]14.8 6.90 9 10.7 9 1.78 54 7.67 24 8.95 10 4.37 63 10.2 2 12.1 6 4.23 1 11.0 8 14.1 11 7.77 18 20.8 8 23.5 8 8.13 7 14.1 10 19.9 10 5.38 14 20.8 10 31.7 10 7.28 15 18.1 12 22.7 12 7.62 24
InterpCNN [160]16.6 7.39 11 10.7 9 5.61 157 6.60 3 8.27 5 4.37 63 12.6 6 12.4 9 9.21 27 9.30 4 11.7 5 9.37 46 18.2 4 20.6 4 7.68 2 12.2 2 17.3 2 4.96 6 17.6 3 26.9 3 6.89 12 15.9 3 19.9 3 6.73 9
CtxSyn [136]18.6 5.47 3 7.82 4 2.18 115 5.98 2 7.57 3 3.23 23 19.2 98 10.6 3 17.0 102 7.49 2 9.86 2 5.67 3 20.6 7 23.3 7 8.83 11 12.8 4 18.0 4 4.72 1 19.4 6 29.6 6 6.47 5 16.8 7 21.0 7 7.43 22
CyclicGen [153]18.8 5.21 1 5.40 1 4.82 150 6.70 5 7.19 1 6.53 145 8.79 1 10.2 2 7.42 11 10.2 6 10.7 3 11.3 82 18.5 6 21.0 6 7.91 5 7.38 1 10.4 1 4.92 5 13.6 1 20.8 1 6.46 4 10.5 1 13.2 1 6.74 11
CFRF [156]21.2 6.36 6 9.45 6 3.86 144 7.39 14 8.88 9 5.58 127 11.5 4 13.0 12 8.79 22 9.24 3 10.7 3 10.9 73 18.3 5 20.7 5 8.62 8 13.4 7 19.0 7 4.90 3 19.9 7 30.5 8 6.42 3 17.0 8 21.3 8 7.04 17
SuperSlomo [132]21.5 7.27 10 10.8 11 4.59 148 7.40 15 9.09 12 5.23 104 11.7 5 11.2 4 6.26 4 11.1 10 12.9 8 10.9 73 21.1 10 23.9 10 8.02 6 14.2 12 20.0 12 4.85 2 19.9 7 30.4 7 6.69 10 17.4 10 21.8 10 6.97 15
TOF-M [154]22.2 6.83 8 10.1 8 3.40 142 7.55 19 9.25 14 5.28 105 13.2 11 10.1 1 10.7 43 10.7 7 13.0 10 9.18 41 22.7 11 25.7 11 8.66 10 13.7 8 19.3 8 5.12 9 21.0 11 32.1 11 6.49 6 19.6 13 24.6 13 6.79 13
OFRI [161]27.1 5.75 4 6.90 3 5.06 153 8.11 58 8.48 7 9.61 155 13.4 13 13.5 13 9.12 25 11.0 8 12.3 7 13.7 131 16.5 2 18.7 2 7.90 4 16.3 22 23.2 23 4.90 3 18.9 4 28.9 4 6.34 1 15.9 3 19.9 3 6.50 2
DAIN [158]27.3 6.45 7 9.46 7 4.07 146 6.69 4 8.09 4 6.20 141 16.0 48 12.2 8 13.6 76 9.77 5 11.7 5 10.3 61 16.9 3 19.2 3 8.65 9 13.9 9 19.8 9 5.10 8 19.2 5 29.4 5 8.11 69 16.3 6 20.5 6 6.74 11
MEMC-Net+ [155]31.9 6.33 5 8.74 5 4.91 151 7.33 11 8.39 6 7.57 148 18.2 91 12.4 9 16.0 97 11.1 10 12.9 8 10.2 59 21.0 9 23.8 9 9.64 15 12.4 3 17.5 3 5.12 9 20.2 9 30.9 9 8.35 76 16.1 5 20.2 5 6.83 14
MDP-Flow2 [68]33.1 8.94 42 13.9 40 1.56 2 7.36 13 9.57 20 2.68 3 15.9 46 20.5 94 16.3 98 13.4 27 18.2 42 8.87 37 24.1 18 27.3 18 12.1 28 17.6 41 25.0 46 6.01 35 22.8 22 34.9 23 7.11 13 20.9 29 26.2 29 7.78 28
CBF [12]33.6 8.02 13 12.4 13 1.75 42 8.18 65 10.3 46 4.84 86 13.2 11 15.5 26 9.17 26 11.5 12 15.0 13 7.94 22 22.8 12 25.8 12 12.2 40 16.2 20 22.9 21 6.24 54 23.4 32 35.8 32 8.06 68 21.2 35 26.7 37 8.24 69
PMMST [114]35.4 8.93 38 14.0 47 1.57 3 7.21 8 9.34 15 2.66 1 14.1 26 16.2 37 11.0 47 15.6 92 21.2 104 14.7 141 24.1 18 27.3 18 12.1 28 16.3 22 23.0 22 5.91 25 22.6 20 34.5 20 7.52 29 19.9 16 25.0 16 8.18 57
DeepFlow [86]39.0 8.76 27 13.7 30 1.59 4 8.08 56 10.4 57 4.72 76 13.8 21 18.1 62 7.83 16 12.1 13 15.2 15 8.41 28 28.8 74 32.7 74 12.1 28 17.0 35 24.1 37 5.99 32 21.6 14 33.0 15 7.45 22 23.0 85 28.9 86 7.80 30
SepConv-v1 [127]39.5 8.19 15 12.5 14 5.08 154 7.89 36 9.09 12 8.08 152 20.8 113 12.1 6 18.4 115 12.5 18 14.8 12 11.7 104 23.5 15 26.6 15 9.13 12 14.1 10 19.9 10 5.12 9 21.1 12 32.2 12 8.37 77 17.2 9 21.5 9 6.71 7
DeepFlow2 [108]43.5 8.59 22 13.4 23 1.64 9 8.06 54 10.4 57 4.45 66 13.8 21 18.6 66 8.12 18 12.4 15 16.1 17 10.6 66 28.5 68 32.3 67 12.3 52 16.7 27 23.6 27 5.92 27 23.0 26 35.0 24 7.49 25 22.6 68 28.4 69 8.47 129
SuperFlow [81]44.3 8.83 31 13.8 32 1.68 13 8.19 66 10.3 46 5.04 94 16.0 48 16.6 40 10.9 45 14.9 71 15.1 14 7.67 15 23.0 14 26.0 13 12.5 59 18.0 54 25.5 56 6.55 82 23.6 39 35.8 32 9.80 104 20.7 24 26.0 25 8.12 46
SIOF [67]48.3 8.78 29 13.5 25 1.80 62 8.97 104 11.2 110 4.51 68 16.7 62 23.2 117 11.6 52 13.2 22 17.7 32 9.61 50 23.7 17 26.8 17 11.8 19 17.8 46 25.2 49 5.98 31 23.4 32 35.9 36 7.33 17 22.1 55 27.8 57 8.15 50
CLG-TV [48]48.3 8.34 19 12.9 18 1.98 94 8.74 93 10.8 84 4.75 82 14.0 24 16.0 32 9.23 28 12.4 15 16.1 17 9.95 54 29.7 103 33.7 103 12.0 25 16.8 28 23.9 31 5.46 15 22.2 16 32.9 14 8.02 63 21.8 52 27.4 53 8.33 97
AdaConv-v1 [126]49.5 9.51 78 14.1 54 4.99 152 9.04 108 9.51 19 9.70 156 18.8 97 13.8 15 18.3 114 14.5 58 16.5 22 15.2 146 25.9 30 29.4 30 7.81 3 13.1 5 18.4 5 5.63 18 21.4 13 32.7 13 7.45 22 17.4 10 21.8 10 6.73 9
Aniso. Huber-L1 [22]50.1 8.22 16 12.7 16 1.84 73 9.12 119 11.1 105 5.11 97 13.6 17 16.3 39 7.58 14 12.2 14 16.1 17 9.16 40 29.8 109 33.8 108 12.7 65 16.9 31 23.9 31 5.57 17 23.2 29 35.5 29 7.30 16 21.8 52 27.4 53 8.32 95
CombBMOF [113]50.7 9.74 94 14.3 64 3.85 143 7.82 30 10.2 36 3.81 39 16.2 51 19.1 75 12.8 68 13.8 36 18.5 47 10.2 59 26.5 32 30.0 32 12.2 40 17.8 46 25.2 49 6.09 44 23.1 27 35.2 27 7.64 37 21.3 38 26.7 37 8.21 66
LME [70]51.3 8.97 44 14.0 47 1.62 6 8.07 55 10.5 65 3.69 32 16.9 65 17.7 55 9.29 30 14.5 58 19.6 72 9.68 51 29.2 93 33.1 93 15.3 116 18.1 56 25.7 58 6.15 47 22.7 21 34.7 21 7.37 19 21.0 32 26.4 33 8.20 62
MDP-Flow [26]51.8 8.27 17 12.8 17 1.74 37 7.26 10 9.42 16 3.90 42 17.2 72 16.1 36 15.0 90 13.6 31 18.0 38 10.9 73 28.8 74 32.7 74 15.3 116 17.9 52 25.2 49 7.36 114 23.6 39 36.1 40 12.2 127 20.6 21 25.9 22 8.07 35
NN-field [71]51.8 9.03 50 14.1 54 1.74 37 7.01 7 9.05 11 2.74 8 18.3 92 19.1 75 12.6 66 16.8 119 22.7 125 15.8 148 24.2 20 27.5 20 12.1 28 17.8 46 25.1 47 6.07 40 23.1 27 35.4 28 7.69 42 20.6 21 25.9 22 8.36 111
IROF-TV [53]52.8 8.93 38 13.9 40 1.82 69 8.15 62 10.6 70 4.01 48 13.9 23 17.6 53 8.70 21 13.3 24 18.0 38 9.04 38 28.5 68 32.3 67 15.3 116 18.5 70 26.2 72 6.57 83 24.7 63 37.8 65 6.81 11 22.2 59 28.0 62 6.71 7
WLIF-Flow [93]52.8 8.64 23 13.4 23 1.69 18 7.89 36 10.2 36 3.94 44 17.0 68 22.0 104 14.5 85 13.7 34 18.4 45 11.5 94 26.7 35 30.3 35 12.3 52 19.8 118 28.0 119 8.12 137 22.4 18 34.2 18 7.58 34 21.1 34 26.4 33 7.62 24
p-harmonic [29]53.0 8.89 36 13.9 40 1.68 13 8.86 98 10.9 91 5.20 103 13.4 13 17.5 52 6.45 5 13.7 34 17.9 37 10.0 56 28.9 79 32.8 80 12.8 66 17.6 41 24.9 43 6.53 81 22.9 23 35.0 24 8.88 83 22.5 65 28.3 67 8.10 41
NNF-Local [87]53.0 8.84 33 13.8 32 1.61 5 7.25 9 9.44 17 2.76 9 14.6 32 19.3 81 14.5 85 16.0 106 21.6 112 15.8 148 24.2 20 27.5 20 12.2 40 18.4 64 26.0 67 6.42 74 24.2 49 37.1 53 9.54 97 20.3 19 25.4 19 8.27 81
Second-order prior [8]53.6 8.06 14 12.5 14 1.93 85 8.80 94 11.0 96 4.80 85 12.8 8 16.2 37 7.51 13 12.6 19 16.7 23 6.25 7 28.9 79 32.8 80 12.2 40 18.1 56 25.7 58 6.10 45 23.3 30 35.5 29 9.35 94 22.7 74 28.6 79 8.45 127
ALD-Flow [66]54.1 10.4 113 16.0 112 1.76 45 7.99 46 10.3 46 3.78 37 14.1 26 19.3 81 6.64 7 16.1 108 21.9 116 5.92 5 26.5 32 30.0 32 14.0 82 16.9 31 23.9 31 6.23 53 22.5 19 34.4 19 7.50 27 23.2 94 29.2 99 8.09 38
OAR-Flow [125]54.4 9.14 59 14.0 47 1.71 25 7.90 38 10.1 30 4.04 51 14.3 29 18.8 69 5.59 2 16.6 116 22.6 122 6.23 6 27.7 54 31.4 54 15.3 116 15.9 16 22.4 16 6.89 95 24.2 49 36.4 44 7.80 50 22.9 83 28.8 84 8.15 50
Ad-TV-NDC [36]55.8 9.09 55 13.8 32 2.24 121 9.50 137 11.1 105 6.94 147 14.2 28 15.4 25 6.85 9 14.5 58 18.6 48 9.51 48 27.4 47 31.1 47 12.3 52 18.2 61 25.8 64 6.40 73 22.9 23 34.7 21 7.43 20 20.6 21 25.8 21 8.26 77
IROF++ [58]57.0 8.58 21 13.3 21 1.68 13 7.99 46 10.4 57 3.84 40 17.3 74 18.5 64 12.5 64 12.4 15 16.7 23 9.15 39 28.4 67 32.3 67 15.3 116 19.5 109 27.6 110 6.06 38 23.3 30 35.6 31 8.55 82 23.4 103 29.4 108 7.79 29
DF-Auto [115]57.5 9.30 70 14.4 73 1.99 95 8.37 76 10.6 70 4.99 90 15.5 43 22.3 106 8.88 23 13.3 24 17.6 31 9.86 53 25.7 27 29.1 27 13.9 81 18.1 56 25.7 58 5.96 30 25.2 71 38.6 76 10.8 117 20.7 24 25.9 22 8.09 38
Brox et al. [5]58.5 9.33 72 14.7 78 1.62 6 7.86 34 10.1 30 4.14 55 15.9 46 16.0 32 10.4 39 13.5 30 17.7 32 8.77 35 26.8 36 30.4 36 11.9 20 19.1 95 27.0 96 9.52 153 28.6 128 43.6 126 23.0 159 19.9 16 25.0 16 8.05 34
Modified CLG [34]59.3 7.87 12 12.2 12 1.68 13 8.96 102 10.7 80 5.94 139 16.8 63 16.7 42 15.9 96 13.3 24 16.4 21 12.6 126 27.6 52 31.3 52 11.9 20 18.8 83 26.6 84 6.50 79 22.3 17 34.0 17 7.67 39 22.2 59 27.9 59 8.64 133
NNF-EAC [103]61.1 9.00 47 14.0 47 1.99 95 7.79 28 10.2 36 2.85 12 17.5 80 25.1 134 19.2 119 15.4 85 20.6 92 11.6 99 29.9 113 33.9 113 12.1 28 16.5 24 23.4 24 5.99 32 22.9 23 35.1 26 7.51 28 20.9 29 26.2 29 8.42 124
Local-TV-L1 [65]64.5 8.65 24 13.3 21 1.90 81 9.07 113 11.0 96 5.04 94 13.1 10 15.3 24 8.62 20 12.8 20 17.0 25 7.89 21 30.8 142 35.0 143 15.5 149 18.4 64 26.0 67 6.98 99 23.9 46 36.5 48 7.66 38 21.4 41 26.9 42 8.40 120
F-TV-L1 [15]64.7 10.4 113 16.2 114 1.94 87 9.02 106 11.2 110 4.72 76 14.6 32 16.7 42 11.0 47 14.2 45 18.9 57 10.3 61 27.5 49 31.2 50 12.3 52 16.0 17 22.6 17 6.38 70 23.9 46 36.6 49 9.23 90 21.3 38 26.7 37 10.2 148
JOF [140]65.1 9.04 51 14.1 54 1.81 66 7.55 19 9.71 25 5.06 96 15.1 37 16.7 42 12.0 54 14.4 54 19.4 67 11.4 88 29.2 93 33.2 95 15.4 140 19.8 118 28.0 119 6.36 69 23.4 32 35.8 32 7.68 41 21.4 41 26.8 41 8.30 89
PH-Flow [101]65.6 9.30 70 14.3 64 1.70 22 7.70 25 10.1 30 2.82 11 14.9 36 20.6 97 14.8 88 14.3 49 19.4 67 11.5 94 25.0 24 28.3 24 12.2 40 21.6 153 30.7 154 9.38 152 25.0 69 38.3 71 7.76 47 22.6 68 28.4 69 8.15 50
FMOF [94]66.5 9.22 66 13.9 40 1.96 91 7.58 21 9.87 26 2.87 13 19.5 102 22.4 107 17.7 109 15.3 81 20.6 92 12.5 125 24.5 22 27.7 22 13.7 76 19.3 103 27.3 104 6.05 37 24.6 61 37.7 63 6.64 9 23.4 103 29.4 108 6.98 16
Filter Flow [19]67.9 9.35 74 14.5 74 1.79 58 9.19 121 11.1 105 5.50 124 17.6 84 16.8 46 12.2 58 14.0 41 18.0 38 11.3 82 24.6 23 27.9 23 12.2 40 18.4 64 26.0 67 7.54 120 24.8 64 37.9 67 7.77 48 21.5 44 27.0 45 8.40 120
DMF_ROB [139]68.1 9.66 86 15.1 90 1.75 42 8.12 60 10.3 46 4.86 87 17.2 72 22.7 112 11.7 53 14.5 58 19.3 63 9.60 49 27.3 44 31.0 44 15.3 116 17.9 52 25.4 54 8.26 140 23.5 36 35.9 36 6.49 6 23.2 94 29.2 99 8.32 95
TC/T-Flow [76]70.5 9.42 76 14.6 77 2.39 126 8.67 90 11.2 110 4.00 46 13.6 17 16.0 32 8.03 17 17.5 131 23.5 135 10.8 70 27.3 44 31.0 44 15.3 116 17.4 39 24.6 39 5.89 24 25.8 86 37.8 65 9.59 99 22.8 78 28.7 82 8.13 48
CRTflow [80]70.5 8.75 26 13.6 27 2.04 99 9.27 126 11.5 133 5.28 105 16.2 51 22.5 109 9.27 29 12.8 20 17.0 25 11.5 94 27.0 39 30.6 39 15.3 116 17.6 41 24.9 43 6.06 38 27.8 113 42.7 116 7.62 36 23.4 103 29.4 108 8.16 55
Sparse Occlusion [54]70.8 9.75 95 15.2 93 2.05 102 8.71 91 11.2 110 4.19 57 13.5 15 15.9 31 7.80 15 14.6 64 19.7 77 7.51 14 30.4 125 34.5 126 15.3 116 16.1 18 22.7 18 6.27 60 26.9 104 41.1 106 7.45 22 23.2 94 29.2 99 8.12 46
ComplOF-FED-GPU [35]70.8 9.91 103 15.5 103 1.77 52 7.74 26 10.1 30 4.25 60 19.8 106 17.7 55 17.0 102 15.3 81 20.7 95 11.8 105 28.2 66 32.0 66 14.5 88 16.2 20 22.8 20 5.95 29 26.2 92 39.6 93 9.25 91 22.7 74 28.4 69 8.25 74
CNN-flow-warp+ref [117]71.1 8.33 18 13.0 19 2.06 104 8.26 72 10.3 46 5.85 136 18.3 92 22.7 112 11.1 49 13.6 31 16.0 16 11.1 78 29.1 91 33.0 90 15.3 116 15.7 14 22.1 14 6.96 98 28.2 119 43.1 120 7.67 39 21.8 52 27.3 51 8.49 130
COFM [59]71.3 8.95 43 13.8 32 1.90 81 7.42 16 9.61 21 3.19 22 15.3 40 22.1 105 16.3 98 15.4 85 20.9 98 14.6 137 26.8 36 30.4 36 12.2 40 21.4 149 30.3 149 6.26 59 26.3 93 40.4 96 10.4 113 20.8 26 26.1 26 8.36 111
CPM-Flow [116]72.2 9.82 99 15.4 101 1.69 18 7.60 22 9.90 27 3.04 19 15.6 45 15.7 29 7.43 12 16.9 121 23.0 130 12.0 111 27.6 52 31.3 52 15.3 116 18.5 70 26.2 72 7.13 108 23.4 32 35.8 32 9.99 106 23.8 121 29.9 123 8.37 114
2DHMM-SAS [92]72.4 8.83 31 13.6 27 1.76 45 8.88 100 11.3 118 4.29 61 17.5 80 20.9 98 12.5 64 14.5 58 19.6 72 11.3 82 30.1 118 34.1 117 15.1 104 17.6 41 24.9 43 5.84 20 25.2 71 38.7 78 8.23 73 23.1 89 29.1 92 8.16 55
PMF [73]72.8 9.35 74 14.5 74 1.77 52 7.80 29 10.1 30 2.68 3 24.0 133 28.7 146 22.5 141 15.3 81 20.6 92 11.6 99 25.7 27 29.2 28 12.1 28 19.1 95 27.0 96 5.92 27 27.6 110 42.4 113 9.09 88 23.1 89 29.0 91 6.47 1
Horn & Schunck [3]73.4 8.92 37 13.6 27 1.73 30 9.79 147 11.4 123 6.31 143 24.1 134 18.7 67 18.6 117 15.8 102 19.4 67 11.1 78 28.0 59 31.8 60 10.4 16 17.8 46 25.2 49 5.54 16 25.3 76 38.4 74 9.70 101 22.1 55 27.7 56 8.27 81
TC-Flow [46]73.4 10.9 123 17.1 125 1.71 25 8.86 98 11.6 136 4.00 46 13.0 9 16.0 32 6.24 3 15.6 92 21.1 101 8.58 29 27.9 56 31.7 58 15.1 104 18.7 79 26.4 80 6.72 87 24.6 61 37.6 61 7.95 60 23.4 103 29.4 108 8.28 85
LDOF [28]73.8 8.85 34 13.8 32 2.04 99 10.2 155 9.70 24 10.8 160 17.0 68 20.4 93 12.0 54 13.4 27 17.4 29 12.3 120 22.9 13 26.0 13 11.9 20 18.9 87 26.7 87 6.27 60 30.1 143 46.3 145 16.0 140 19.7 14 24.7 14 8.89 139
2D-CLG [1]74.0 8.51 20 13.2 20 1.76 45 8.84 97 10.4 57 5.71 134 19.4 101 15.6 28 15.0 90 14.2 45 16.3 20 14.0 133 31.1 149 35.3 149 20.9 160 16.1 18 22.7 18 6.34 65 27.7 112 42.3 111 8.19 72 21.4 41 26.9 42 8.13 48
Black & Anandan [4]74.4 9.24 68 14.1 54 1.95 89 9.65 144 11.4 123 5.28 105 28.3 143 24.2 124 20.2 129 14.8 68 18.7 52 10.5 64 27.7 54 31.5 55 9.57 14 19.0 91 27.0 96 6.35 67 24.2 49 36.7 50 8.42 79 21.0 32 26.3 32 6.55 3
FlowNetS+ft+v [112]74.5 9.02 49 14.1 54 2.07 108 10.0 153 11.0 96 9.60 154 16.3 54 14.4 16 13.5 75 13.8 36 17.7 32 13.3 129 29.7 103 33.8 108 15.3 116 16.8 28 23.8 29 6.25 57 27.8 113 42.6 114 7.83 54 20.4 20 25.5 20 8.24 69
PGM-C [120]74.5 9.70 89 15.2 93 1.69 18 7.84 33 10.2 36 3.70 33 21.2 116 17.2 48 12.3 61 17.4 128 23.6 136 8.69 31 28.0 59 31.8 60 15.3 116 16.6 25 23.4 24 6.17 48 26.4 94 40.5 100 8.04 65 24.3 137 30.5 139 8.34 100
OFLAF [77]74.7 9.70 89 15.0 87 1.69 18 7.94 43 10.4 57 2.73 7 14.3 29 15.0 21 10.2 35 13.8 36 18.6 48 8.40 27 30.0 115 34.0 115 15.4 140 17.0 35 23.9 31 6.73 88 30.1 143 46.1 143 13.9 135 23.4 103 29.3 104 9.45 143
ProFlow_ROB [146]74.7 9.82 99 15.5 103 1.71 25 8.15 62 10.6 70 3.63 29 15.4 42 12.7 11 8.98 24 19.8 146 26.9 147 7.99 23 29.0 89 33.0 90 15.3 116 15.6 13 22.0 13 5.16 12 26.4 94 40.3 95 7.90 58 24.4 140 30.5 139 11.5 152
EpicFlow [102]74.9 9.69 88 15.2 93 1.67 12 7.90 38 10.2 36 4.37 63 16.0 48 14.5 17 9.75 32 19.1 142 25.8 145 12.3 120 27.9 56 31.6 56 15.3 116 16.9 31 23.9 31 6.21 52 24.9 66 38.0 68 10.3 111 24.6 143 30.9 144 8.30 89
MLDP_OF [89]75.0 9.06 52 14.1 54 1.83 72 8.81 95 11.3 118 4.78 84 14.0 24 17.6 53 8.56 19 15.5 89 20.3 87 15.8 148 29.7 103 33.7 103 13.6 72 19.1 95 27.0 96 5.86 22 23.8 42 36.3 42 8.15 71 23.2 94 29.1 92 8.25 74
Fusion [6]75.1 8.82 30 13.8 32 2.62 130 7.96 44 10.1 30 4.47 67 16.5 57 13.6 14 17.3 108 14.0 41 18.1 41 9.97 55 29.8 109 33.8 108 12.8 66 19.4 105 27.4 105 10.1 156 26.4 94 40.4 96 8.14 70 21.7 48 27.2 49 10.1 147
EAI-Flow [151]76.4 11.1 126 15.4 101 6.27 159 8.02 50 10.2 36 4.70 75 16.9 65 20.1 91 15.0 90 14.8 68 19.8 79 4.86 2 29.2 93 33.1 93 14.8 95 16.6 25 23.5 26 5.99 32 23.8 42 36.4 44 20.9 155 22.6 68 28.4 69 11.1 150
LFNet_ROB [149]76.5 11.6 133 18.2 136 2.58 129 8.05 52 10.4 57 4.02 50 17.8 87 26.6 138 11.5 51 13.2 22 17.8 35 7.21 12 26.9 38 30.5 38 14.8 95 21.1 143 29.9 144 7.31 112 23.5 36 35.9 36 11.3 120 22.4 63 28.2 65 8.11 44
TV-L1-MCT [64]76.6 9.18 62 14.2 62 1.78 54 8.53 83 11.1 105 3.70 33 17.7 86 23.3 120 13.6 76 14.4 54 19.5 71 11.6 99 30.5 131 34.6 129 13.8 78 18.1 56 25.7 58 6.02 36 25.8 86 39.5 90 15.0 138 21.7 48 27.3 51 7.99 32
AGIF+OF [85]76.6 9.07 53 14.0 47 1.78 54 7.93 42 10.3 46 3.78 37 14.4 31 17.8 57 12.4 62 14.9 71 20.2 84 11.4 88 28.9 79 32.8 80 15.3 116 20.0 121 28.3 121 6.98 99 25.5 79 39.0 81 7.74 45 23.9 128 30.1 132 8.28 85
Bartels [41]77.9 12.7 145 20.1 146 2.13 114 8.52 82 11.0 96 4.96 89 13.5 15 14.5 17 10.2 35 14.4 54 18.9 57 10.8 70 23.5 15 26.6 15 12.9 69 19.0 91 26.9 93 6.94 97 24.5 56 37.5 59 19.7 152 23.4 103 29.4 108 8.31 92
S2F-IF [123]78.1 10.3 110 16.3 116 1.79 58 7.83 32 10.2 36 2.90 15 17.0 68 20.0 89 13.9 81 16.1 108 21.6 112 6.69 8 29.2 93 33.2 95 15.3 116 16.8 28 23.7 28 6.34 65 24.9 66 38.2 69 10.7 115 23.9 128 30.0 130 8.35 108
OFH [38]79.6 9.54 80 15.0 87 1.74 37 8.49 81 10.6 70 5.13 98 18.1 89 24.9 132 10.4 39 17.4 128 23.7 138 5.72 4 28.7 72 32.5 70 14.6 91 17.6 41 24.8 41 5.85 21 26.0 90 39.2 85 10.2 109 22.7 74 28.5 77 14.1 157
BlockOverlap [61]80.1 9.09 55 14.3 64 2.04 99 8.96 102 10.9 91 5.37 117 18.1 89 15.5 26 18.0 112 14.2 45 17.2 27 14.0 133 28.9 79 32.8 80 13.8 78 18.8 83 26.7 87 7.92 131 24.8 64 37.2 54 21.0 156 20.0 18 25.1 18 8.38 115
nLayers [57]80.2 9.15 60 14.3 64 1.76 45 7.42 16 9.62 22 3.57 27 27.8 141 29.9 149 25.8 151 15.9 104 21.5 110 11.9 106 30.2 119 34.3 120 14.7 94 20.3 128 28.8 129 6.45 76 23.5 36 36.0 39 7.87 56 21.6 45 27.1 46 8.10 41
TCOF [69]80.5 9.34 73 14.3 64 1.89 77 9.50 137 11.7 143 5.42 118 16.2 51 21.7 102 10.3 37 13.8 36 18.6 48 9.45 47 30.4 125 34.6 129 13.6 72 18.2 61 25.7 58 6.20 51 28.5 125 43.5 125 7.54 30 22.9 83 28.8 84 8.18 57
HAST [109]80.6 8.87 35 13.8 32 1.76 45 7.34 12 9.50 18 2.70 5 28.8 145 28.6 145 24.0 146 14.9 71 20.2 84 7.68 16 28.9 79 32.8 80 12.1 28 21.3 148 30.2 148 7.57 122 28.6 128 43.9 129 7.55 32 22.8 78 28.7 82 8.43 126
DPOF [18]81.9 11.0 124 17.4 129 3.88 145 7.78 27 10.2 36 3.01 17 18.7 95 18.1 62 18.4 115 16.5 113 22.4 119 14.6 137 28.8 74 32.7 74 12.1 28 18.9 87 26.7 87 6.18 50 25.2 71 38.4 74 7.59 35 23.6 116 29.6 116 8.07 35
Layers++ [37]82.2 8.93 38 14.0 47 1.76 45 6.74 6 8.61 8 2.71 6 18.3 92 25.8 136 19.3 120 15.3 81 20.8 96 11.3 82 33.1 157 37.6 157 19.8 157 21.6 153 30.6 153 8.73 146 24.4 54 37.4 57 7.81 52 21.6 45 27.1 46 8.09 38
FlowFields [110]82.4 9.98 104 15.7 106 2.08 110 7.96 44 10.4 57 3.62 28 23.1 126 23.2 117 20.3 131 16.0 106 21.5 110 7.08 11 27.0 39 30.6 39 14.2 84 19.2 101 27.1 101 6.08 43 24.4 54 37.4 57 10.2 109 23.2 94 29.2 99 8.35 108
Classic++ [32]83.2 9.48 77 14.9 82 1.80 62 8.59 84 11.0 96 4.61 71 13.7 20 15.0 21 9.57 31 14.4 54 19.0 59 8.76 34 29.9 113 33.9 113 13.6 72 20.2 126 28.7 127 6.87 94 27.4 108 42.0 108 9.63 100 23.8 121 29.9 123 8.34 100
SRR-TVOF-NL [91]84.1 9.65 84 14.8 79 1.82 69 8.21 70 10.6 70 4.76 83 22.7 124 28.1 143 21.9 136 15.6 92 20.9 98 9.18 41 28.9 79 32.8 80 15.3 116 20.7 137 29.3 137 5.91 25 24.5 56 37.6 61 6.56 8 22.5 65 28.2 65 8.34 100
NL-TV-NCC [25]84.4 9.19 64 14.3 64 2.18 115 9.02 106 11.6 136 4.13 54 14.8 34 16.7 42 10.9 45 20.8 147 28.1 149 8.19 25 26.5 32 30.0 32 13.1 70 18.9 87 26.7 87 6.43 75 26.6 99 40.4 96 15.1 139 23.7 120 29.7 120 8.29 88
HBM-GC [105]84.7 9.25 69 14.5 74 1.81 66 9.08 115 11.9 152 3.75 36 17.3 74 18.7 67 17.9 110 14.3 49 19.2 61 8.85 36 30.0 115 34.0 115 15.5 149 21.5 150 30.4 150 8.27 141 27.4 108 42.1 110 7.15 14 20.8 26 26.1 26 7.05 19
Complementary OF [21]85.4 11.4 132 18.1 135 1.70 22 9.23 124 12.1 153 4.19 57 31.6 150 19.0 73 23.6 143 19.5 145 26.5 146 6.72 9 28.1 64 31.8 60 14.6 91 17.3 38 24.4 38 6.38 70 26.1 91 39.0 81 8.92 85 22.3 61 27.9 59 7.57 23
Nguyen [33]85.5 9.83 101 15.2 93 1.73 30 9.59 142 11.0 96 5.65 133 15.3 40 20.5 94 10.3 37 14.6 64 18.8 53 12.1 113 28.8 74 32.7 74 12.2 40 19.4 105 27.4 105 8.01 135 29.7 138 45.5 138 8.29 75 21.2 35 26.6 36 8.34 100
Efficient-NL [60]86.2 8.71 25 13.5 25 1.68 13 8.66 88 11.2 110 3.65 30 22.5 120 20.0 89 19.9 125 14.3 49 19.3 63 11.0 76 30.5 131 34.7 136 15.0 99 20.1 122 28.4 123 6.27 60 28.5 125 43.7 127 8.92 85 23.8 121 29.9 123 6.66 5
FESL [72]86.8 9.09 55 13.9 40 1.74 37 7.90 38 10.3 46 3.35 25 16.5 57 21.9 103 12.0 54 15.1 78 20.3 87 11.4 88 30.8 142 35.0 143 15.4 140 19.6 112 27.8 115 6.48 77 27.8 113 42.6 114 7.75 46 23.9 128 30.0 130 8.39 116
ProbFlowFields [128]87.2 10.1 105 16.0 112 1.78 54 8.04 51 10.5 65 3.08 21 25.8 140 28.8 147 24.3 147 14.5 58 19.6 72 11.4 88 27.2 42 30.9 43 15.3 116 17.4 39 24.6 39 8.78 147 27.3 107 42.0 108 18.8 150 22.4 63 28.1 63 8.39 116
AggregFlow [97]87.6 12.9 147 20.3 147 1.75 42 8.34 74 10.8 84 4.14 55 20.0 107 24.4 127 19.5 124 16.5 113 22.3 118 12.2 117 25.2 25 28.6 25 12.2 40 16.9 31 23.9 31 6.60 84 29.0 135 43.9 129 16.7 143 23.0 85 28.9 86 8.03 33
FlowFields+ [130]88.5 9.67 87 15.2 93 3.33 141 7.86 34 10.3 46 3.02 18 23.3 128 24.6 129 20.8 132 17.0 123 23.0 130 6.91 10 27.3 44 31.0 44 15.4 140 19.0 91 26.9 93 6.24 54 25.3 76 38.8 79 13.1 131 23.2 94 29.1 92 8.39 116
PWC-Net_ROB [147]88.7 11.7 135 18.2 136 2.05 102 8.35 75 10.9 91 3.91 43 13.6 17 17.4 51 6.79 8 18.8 138 25.6 144 8.72 33 30.5 131 34.6 129 15.1 104 19.4 105 27.4 105 5.68 19 23.6 39 36.2 41 7.95 60 24.2 134 30.4 136 11.5 152
RNLOD-Flow [121]88.9 8.93 38 13.8 32 1.65 10 8.48 80 11.0 96 4.06 52 16.3 54 23.2 117 12.8 68 14.1 43 19.1 60 11.1 78 29.7 103 33.7 103 15.6 151 20.3 128 28.7 127 8.92 150 25.7 82 39.4 88 16.4 142 24.2 134 30.4 136 8.20 62
FlowNet2 [122]89.2 15.6 156 23.6 157 1.96 91 9.34 128 12.1 153 4.72 76 17.3 74 19.2 79 13.0 71 17.1 126 23.1 132 10.1 57 28.0 59 31.8 60 12.3 52 18.6 73 26.3 76 6.35 67 26.7 100 40.8 103 8.04 65 21.7 48 27.2 49 8.30 89
StereoOF-V1MT [119]89.2 11.1 126 17.3 127 1.73 30 8.61 85 10.6 70 5.28 105 23.4 130 17.3 49 17.1 106 16.6 116 19.9 81 12.3 120 27.4 47 31.1 47 15.0 99 17.0 35 23.8 29 6.80 92 30.2 145 46.2 144 12.3 128 21.6 45 26.9 42 9.58 144
Sparse-NonSparse [56]90.0 9.18 62 14.3 64 1.73 30 8.14 61 10.6 70 3.31 24 16.6 60 22.9 115 13.8 80 14.8 68 19.8 79 11.3 82 30.5 131 34.6 129 15.0 99 20.1 122 28.5 125 7.48 118 28.5 125 43.7 127 9.49 95 23.5 113 29.5 113 8.24 69
TI-DOFE [24]90.4 9.80 97 15.2 93 2.80 134 9.94 151 11.4 123 5.62 130 15.5 43 15.7 29 10.5 42 17.0 123 21.7 114 10.6 66 27.1 41 30.8 41 12.1 28 20.9 141 29.6 142 6.99 101 24.0 48 36.3 42 8.92 85 24.3 137 28.1 63 12.5 155
TVL1_ROB [138]90.5 10.5 116 16.3 116 1.88 76 9.86 149 11.6 136 5.57 125 20.0 107 19.0 73 14.6 87 15.6 92 20.3 87 11.9 106 26.4 31 29.9 31 12.1 28 19.0 91 26.8 91 7.12 107 28.2 119 42.9 117 12.9 130 20.9 29 26.2 29 8.34 100
ACK-Prior [27]90.8 9.81 98 15.1 90 2.07 108 8.01 49 10.4 57 3.86 41 25.1 137 19.1 75 22.0 138 15.1 78 20.1 83 10.1 57 30.4 125 34.4 123 15.4 140 19.1 95 26.9 93 7.57 122 25.8 86 39.3 86 19.5 151 22.3 61 27.9 59 7.73 26
Occlusion-TV-L1 [63]91.0 10.1 105 15.9 110 2.43 127 9.36 129 11.8 149 5.01 93 12.7 7 14.7 19 7.22 10 17.0 123 22.7 125 11.4 88 28.6 70 32.5 70 12.0 25 18.7 79 26.5 83 7.48 118 25.2 71 37.7 63 10.0 107 24.3 137 30.3 135 9.33 141
LSM [39]91.2 9.10 58 14.2 62 1.73 30 8.33 73 10.9 91 3.40 26 16.6 60 22.7 112 12.2 58 15.0 77 20.3 87 11.0 76 30.5 131 34.7 136 15.1 104 20.7 137 29.4 138 6.17 48 28.1 118 43.0 119 11.5 122 23.8 121 29.9 123 8.27 81
3DFlow [135]91.2 9.65 84 14.9 82 1.89 77 7.82 30 10.0 29 4.94 88 16.9 65 19.9 86 13.7 78 16.5 113 22.4 119 15.8 148 29.3 98 33.2 95 12.5 59 18.4 64 25.9 66 8.56 144 27.2 105 41.4 107 10.1 108 23.4 103 29.3 104 8.87 137
Classic+CPF [83]91.4 9.07 53 14.0 47 1.80 62 8.09 57 10.5 65 3.71 35 17.0 68 21.5 100 12.9 70 13.9 40 18.8 53 11.4 88 30.7 140 34.9 141 15.4 140 21.2 145 30.0 146 7.73 129 28.2 119 43.2 122 7.80 50 24.7 146 31.0 146 7.89 31
ResPWCR_ROB [144]92.1 11.2 131 17.7 131 1.95 89 8.98 105 11.7 143 4.11 53 15.2 39 17.3 49 10.0 33 23.1 153 31.2 155 10.5 64 30.5 131 34.6 129 14.2 84 20.3 128 28.8 129 5.27 13 23.8 42 36.4 44 7.54 30 25.4 152 31.9 156 7.76 27
TriFlow [95]92.5 13.1 148 20.8 148 2.06 104 9.53 140 12.2 155 5.29 112 16.5 57 18.5 64 10.1 34 17.2 127 22.8 127 7.74 17 27.9 56 31.6 56 15.1 104 19.4 105 27.4 105 6.07 40 24.5 56 37.2 54 10.9 118 23.8 121 29.8 122 8.15 50
CostFilter [40]92.8 10.8 122 17.0 124 1.80 62 7.90 38 10.3 46 2.66 1 24.6 136 27.7 142 21.9 136 18.7 137 25.4 142 13.7 131 27.5 49 31.1 47 12.6 62 18.2 61 25.8 64 5.87 23 28.9 133 44.2 134 9.34 93 24.4 140 30.7 142 8.20 62
TF+OM [100]92.8 11.8 137 18.7 139 3.19 138 8.23 71 10.8 84 4.54 69 15.1 37 19.7 84 10.4 39 16.3 111 21.9 116 7.87 20 28.9 79 32.8 80 19.1 156 18.6 73 26.3 76 6.68 86 26.5 98 40.7 101 11.5 122 23.8 121 29.9 123 8.23 68
FFV1MT [106]93.1 11.6 133 17.7 131 2.19 117 9.20 122 10.9 91 5.96 140 22.6 121 30.3 150 16.3 98 15.5 89 18.8 53 12.4 123 27.5 49 31.2 50 11.6 18 18.6 73 25.7 58 7.42 117 27.2 105 40.7 101 8.88 83 21.2 35 26.4 33 9.73 145
Ramp [62]93.7 9.22 66 14.3 64 1.73 30 8.19 66 10.7 80 4.24 59 21.9 119 28.8 147 21.1 135 14.2 45 19.2 61 11.6 99 30.6 138 34.8 139 14.8 95 20.4 132 29.0 135 7.40 115 28.0 117 42.9 117 7.57 33 23.0 85 28.9 86 8.28 85
H+S_ROB [137]93.8 9.20 65 14.1 54 1.72 28 8.66 88 10.2 36 5.63 131 39.8 160 41.0 160 32.8 161 14.3 49 17.4 29 9.30 44 29.6 102 33.6 102 12.2 40 19.5 109 27.6 110 7.00 102 31.4 149 48.0 149 10.3 111 23.0 85 28.9 86 8.34 100
AugFNG_ROB [143]94.6 12.1 141 19.0 141 1.94 87 8.44 79 10.6 70 5.42 118 17.3 74 23.9 123 10.8 44 26.2 158 34.7 157 11.5 94 31.6 152 35.9 152 15.3 116 18.7 79 26.4 80 6.38 70 24.9 66 38.2 69 7.91 59 19.8 15 24.8 15 8.36 111
IAOF2 [51]95.2 10.7 121 16.6 120 2.36 124 9.40 130 11.6 136 5.33 113 17.4 79 18.0 59 12.4 62 14.1 43 18.2 42 9.32 45 30.3 123 34.4 123 14.0 82 20.5 136 29.1 136 8.20 138 25.2 71 38.3 71 8.49 80 23.1 89 29.1 92 8.24 69
EPMNet [133]95.2 16.1 158 24.7 158 2.22 118 9.04 108 11.7 143 4.55 70 17.3 74 19.2 79 13.0 71 26.7 160 36.3 161 12.1 113 28.0 59 31.8 60 12.3 52 18.4 64 26.0 67 6.25 57 26.7 100 40.8 103 8.04 65 22.6 68 28.4 69 8.35 108
SVFilterOh [111]95.5 10.5 116 16.4 118 1.97 93 7.65 23 9.98 28 3.05 20 28.0 142 30.4 151 25.4 149 15.6 92 21.2 104 14.7 141 28.9 79 32.7 74 15.4 140 20.1 122 28.4 123 6.61 85 25.8 86 39.5 90 7.84 55 22.5 65 28.3 67 8.49 130
Heeger++ [104]96.2 14.5 153 21.7 152 4.63 149 9.50 137 11.0 96 5.73 135 25.4 139 23.5 122 14.4 84 15.5 89 18.8 53 12.4 123 28.7 72 32.5 70 15.2 112 15.8 15 22.2 15 6.73 88 27.6 110 39.8 94 9.28 92 22.1 55 27.6 55 8.34 100
Classic+NL [31]96.5 8.97 44 13.9 40 1.79 58 8.11 58 10.5 65 4.01 48 20.8 113 28.3 144 19.9 125 14.3 49 19.3 63 11.5 94 30.7 140 34.8 139 14.6 91 20.3 128 28.8 129 7.40 115 28.3 122 43.4 123 11.9 126 23.5 113 29.6 116 8.25 74
Dynamic MRF [7]96.7 10.1 105 15.9 110 1.81 66 8.42 78 10.8 84 4.73 80 19.5 102 19.1 75 12.2 58 15.6 92 19.3 63 12.8 128 27.2 42 30.8 41 15.2 112 18.6 73 26.3 76 7.28 111 28.8 132 44.1 133 12.4 129 24.6 143 30.7 142 9.73 145
Adaptive [20]96.7 11.0 124 17.3 127 1.89 77 9.41 132 11.6 136 5.19 102 14.8 34 17.1 47 11.1 49 15.7 99 21.1 101 12.1 113 31.1 149 35.3 149 12.0 25 18.8 83 26.6 84 8.00 134 27.8 113 42.3 111 8.01 62 22.6 68 28.4 69 8.63 132
TV-L1-improved [17]96.8 9.53 79 14.9 82 1.99 95 9.46 134 11.7 143 5.17 100 22.6 121 14.8 20 20.1 128 13.4 27 17.8 35 8.05 24 30.2 119 34.3 120 11.9 20 19.6 112 27.7 112 8.09 136 29.9 141 45.8 141 9.73 102 23.4 103 29.3 104 8.42 124
IAOF [50]97.2 11.1 126 16.6 120 5.32 155 10.6 157 12.3 156 5.87 137 23.3 128 24.2 124 19.4 121 15.4 85 19.7 77 12.0 111 28.9 79 32.8 80 12.1 28 18.8 83 26.6 84 7.26 110 25.6 81 39.1 84 7.35 18 22.1 55 27.8 57 8.26 77
Steered-L1 [118]97.2 8.76 27 13.7 30 1.82 69 8.00 48 10.3 46 4.72 76 31.9 151 33.2 157 29.2 156 17.4 128 22.8 127 14.1 135 29.5 101 33.5 101 14.2 84 19.7 116 27.9 117 6.28 64 26.4 94 40.4 96 18.7 149 23.8 121 29.9 123 7.04 17
ROF-ND [107]97.5 9.00 47 13.9 40 1.62 6 9.53 140 10.8 84 10.7 159 16.4 56 22.9 115 12.7 67 18.3 135 24.1 139 11.9 106 29.4 100 33.3 100 15.2 112 18.6 73 26.2 72 7.60 125 24.5 56 37.3 56 13.2 133 24.4 140 30.5 139 9.33 141
TriangleFlow [30]97.7 9.59 82 14.8 79 2.06 104 9.07 113 11.4 123 5.47 122 19.2 98 20.2 92 13.9 81 13.6 31 18.2 42 8.31 26 30.0 115 34.1 117 9.31 13 17.8 46 25.2 49 7.56 121 30.8 147 47.2 147 13.9 135 25.5 155 31.9 156 11.3 151
FF++_ROB [145]98.0 10.6 118 16.7 122 1.70 22 8.19 66 10.6 70 3.67 31 21.6 118 22.6 110 17.0 102 19.0 140 25.5 143 14.9 145 28.9 79 32.8 80 15.4 140 19.3 103 27.4 105 6.24 54 25.7 82 39.5 90 11.8 125 23.5 113 29.5 113 8.27 81
FOLKI [16]98.4 10.6 118 16.5 119 2.43 127 9.94 151 11.2 110 6.70 146 19.6 104 21.6 101 19.9 125 18.3 135 19.4 67 17.3 153 28.0 59 31.7 58 13.6 72 19.1 95 27.1 101 10.9 158 24.2 49 36.9 51 17.3 146 21.3 38 26.7 37 8.10 41
LocallyOriented [52]99.1 10.1 105 15.7 106 1.79 58 9.46 134 11.6 136 5.28 105 23.1 126 24.2 124 20.9 134 19.3 144 23.2 133 7.35 13 30.4 125 34.6 129 12.6 62 18.9 87 26.8 91 6.27 60 25.7 82 38.6 76 7.89 57 23.6 116 29.6 116 8.19 60
SILK [79]100.3 9.72 93 15.1 90 2.69 131 10.2 155 11.4 123 7.82 151 39.2 159 32.9 156 28.5 155 14.6 64 18.4 45 9.73 52 29.0 89 32.9 89 10.4 16 21.2 145 30.0 146 7.00 102 24.5 56 37.5 59 8.03 64 23.1 89 28.9 86 8.31 92
S2D-Matching [84]101.7 9.57 81 14.9 82 1.76 45 8.37 76 10.8 84 4.36 62 20.1 110 24.9 132 18.2 113 15.7 99 21.3 108 15.7 147 28.8 74 32.7 74 14.5 88 21.5 150 30.4 150 11.0 159 25.7 82 39.3 86 11.5 122 23.1 89 29.1 92 8.75 136
BriefMatch [124]102.4 9.89 102 15.5 103 2.11 112 8.05 52 10.2 36 5.90 138 23.5 131 18.0 59 22.7 142 18.2 134 18.6 48 18.7 156 28.1 64 31.9 65 13.8 78 19.5 109 27.7 112 7.05 105 26.7 100 39.4 88 21.6 157 23.4 103 29.3 104 14.3 159
GraphCuts [14]102.7 11.7 135 17.8 133 2.02 98 8.15 62 10.5 65 4.65 73 25.3 138 15.2 23 19.4 121 14.9 71 19.6 72 11.9 106 29.8 109 33.8 108 17.8 154 19.6 112 27.8 115 6.50 79 28.6 128 43.9 129 11.1 119 24.0 132 30.2 133 8.15 50
RFlow [90]103.3 9.71 91 15.2 93 1.91 84 9.06 111 11.2 110 5.42 118 22.8 125 22.6 110 17.9 110 15.8 102 21.2 104 12.7 127 29.2 93 33.2 95 11.9 20 19.2 101 27.2 103 7.63 126 28.9 133 44.4 135 7.73 44 23.4 103 29.5 113 8.46 128
ContinualFlow_ROB [152]103.3 12.2 142 19.3 142 2.23 119 8.71 91 11.3 118 4.73 80 17.5 80 19.9 86 13.3 74 22.6 151 30.7 154 8.65 30 32.4 155 36.8 156 15.3 116 18.5 70 26.2 72 6.12 46 28.6 128 43.9 129 8.50 81 22.7 74 28.4 69 8.39 116
ComponentFusion [96]103.7 12.3 143 19.5 143 1.66 11 8.65 87 11.4 123 2.88 14 19.7 105 21.0 99 15.1 93 15.4 85 20.9 98 14.4 136 29.7 103 33.7 103 14.5 88 18.6 73 26.3 76 7.67 127 31.9 150 49.0 152 20.5 153 24.2 134 30.4 136 8.18 57
Learning Flow [11]104.5 8.99 46 14.1 54 1.85 75 9.10 117 11.3 118 4.99 90 40.2 161 42.5 161 31.6 160 14.9 71 17.2 27 12.2 117 30.8 142 35.0 143 15.1 104 18.7 79 26.4 80 7.58 124 25.1 70 38.3 71 11.4 121 25.5 155 31.7 152 8.24 69
FC-2Layers-FF [74]105.1 9.71 91 14.9 82 2.11 112 7.51 18 9.66 23 4.67 74 20.5 111 25.1 134 20.2 129 15.6 92 21.1 101 11.9 106 30.5 131 34.6 129 15.3 116 20.8 139 29.4 138 7.31 112 29.7 138 45.6 140 9.76 103 23.6 116 29.7 120 8.22 67
Shiralkar [42]105.4 12.0 140 18.8 140 1.72 28 9.11 118 11.1 105 5.14 99 21.2 116 16.6 40 13.7 78 19.2 143 24.3 141 10.6 66 29.7 103 33.7 103 12.8 66 18.0 54 25.4 54 7.19 109 29.4 136 44.9 136 10.4 113 25.1 151 31.5 151 9.03 140
Adaptive flow [45]105.4 10.3 110 14.8 79 2.37 125 9.87 150 11.5 133 5.57 125 18.0 88 17.9 58 17.1 106 16.4 112 20.0 82 14.8 143 32.3 154 36.7 154 16.6 152 21.1 143 29.8 143 8.41 142 23.8 42 36.4 44 13.1 131 21.7 48 27.1 46 7.17 20
SLK [47]105.4 9.63 83 15.0 87 1.90 81 9.14 120 10.3 46 5.63 131 34.7 153 19.7 84 22.4 140 18.9 139 24.2 140 20.4 159 29.8 109 33.8 108 12.2 40 18.1 56 25.5 56 6.93 96 31.9 150 48.8 150 9.12 89 22.8 78 28.5 77 14.2 158
EPPM w/o HM [88]106.5 10.4 113 16.2 114 2.97 136 8.62 86 11.3 118 2.76 9 29.0 146 27.4 140 22.2 139 16.8 119 22.6 122 10.8 70 25.8 29 29.2 28 12.1 28 20.2 126 28.6 126 6.49 78 29.8 140 45.8 141 18.0 147 24.0 132 30.2 133 8.72 135
UnFlow [129]108.6 13.4 149 21.2 151 2.71 133 8.81 95 10.7 80 6.35 144 18.7 95 18.9 70 14.8 88 14.6 64 19.6 72 7.77 18 31.8 153 36.1 153 15.0 99 22.2 156 31.4 156 7.79 130 24.2 49 37.0 52 7.49 25 28.1 160 33.7 161 11.6 154
Correlation Flow [75]108.7 9.75 95 15.3 100 1.84 73 9.28 127 11.6 136 5.17 100 17.5 80 18.9 70 15.2 94 16.1 108 21.7 114 11.3 82 30.2 119 34.3 120 12.5 59 21.2 145 29.9 144 8.24 139 31.3 148 47.8 148 9.82 105 24.9 149 31.3 150 6.61 4
LiteFlowNet [142]111.8 12.6 144 19.7 145 2.06 104 8.19 66 10.7 80 3.96 45 20.8 113 26.3 137 15.4 95 26.2 158 35.0 159 12.2 117 30.9 148 35.0 143 14.9 98 20.4 132 28.8 129 6.74 91 28.3 122 43.1 120 7.70 43 22.8 78 28.6 79 8.87 137
HBpMotionGpu [43]112.2 12.7 145 19.5 143 2.69 131 9.65 144 11.7 143 5.48 123 20.0 107 23.3 120 17.0 102 17.6 132 23.4 134 10.6 66 30.8 142 35.0 143 25.1 161 20.4 132 28.9 134 7.95 132 22.0 15 33.7 16 7.44 21 23.2 94 29.1 92 8.40 120
PGAM+LK [55]113.3 11.9 139 18.0 134 7.26 160 9.48 136 10.8 84 7.62 149 31.5 149 39.9 159 31.4 159 19.0 140 23.6 136 16.3 152 29.1 91 33.0 90 12.6 62 18.4 64 26.0 67 6.80 92 25.5 79 39.0 81 14.8 137 22.6 68 28.4 69 8.41 123
2bit-BM-tele [98]114.2 11.1 126 17.2 126 2.34 122 9.40 130 11.7 143 5.36 115 28.5 144 37.1 158 31.0 158 15.7 99 20.8 96 9.18 41 28.6 70 32.5 70 15.0 99 22.0 155 31.1 155 9.53 154 39.1 161 59.9 161 26.9 161 20.8 26 26.1 26 8.11 44
Rannacher [23]114.8 11.1 126 17.5 130 1.89 77 9.59 142 11.8 149 5.28 105 24.3 135 18.0 59 20.8 132 15.9 104 21.2 104 11.6 99 30.4 125 34.5 126 12.3 52 19.7 116 27.9 117 7.98 133 29.6 137 45.3 137 9.57 98 24.7 146 31.0 146 8.19 60
OFRF [134]115.2 13.6 150 21.1 150 2.23 119 9.25 125 11.4 123 5.60 128 19.2 98 19.5 83 14.1 83 16.9 121 22.8 127 14.6 137 30.8 142 34.9 141 14.4 87 19.6 112 27.7 112 6.07 40 28.3 122 43.4 123 7.78 49 24.7 146 31.1 148 8.34 100
StereoFlow [44]115.8 14.9 154 22.2 154 3.28 139 10.0 153 12.7 159 4.99 90 16.8 63 18.9 70 12.1 57 15.2 80 20.4 91 10.4 63 33.4 158 37.9 158 20.8 158 23.8 158 33.5 158 8.41 142 25.3 76 38.8 79 7.81 52 23.6 116 29.6 116 8.67 134
SimpleFlow [49]118.4 9.15 60 14.3 64 1.73 30 9.05 110 11.4 123 5.35 114 36.0 157 32.6 155 29.4 157 14.9 71 20.2 84 11.2 81 30.6 138 34.7 136 15.1 104 22.6 157 32.0 157 9.11 151 34.7 155 53.2 156 13.8 134 23.9 128 29.9 123 8.33 97
Aniso-Texture [82]119.2 10.6 118 16.7 122 1.74 37 9.83 148 12.4 157 5.36 115 17.6 84 19.9 86 13.1 73 22.9 152 27.8 148 19.7 158 30.3 123 34.4 123 15.4 140 20.8 139 29.4 138 8.86 149 26.8 103 41.0 105 8.38 78 24.6 143 30.9 144 8.26 77
SPSA-learn [13]119.6 15.1 155 22.9 155 1.93 85 9.08 115 11.0 96 5.42 118 33.0 152 24.8 130 23.8 145 17.6 132 22.4 119 12.1 113 29.3 98 33.2 95 15.1 104 17.8 46 25.1 47 6.73 88 37.7 157 57.7 158 25.5 160 25.4 152 31.8 153 8.33 97
SegOF [10]119.8 11.8 137 18.2 136 5.53 156 8.88 100 11.4 123 4.62 72 31.1 148 20.5 94 23.7 144 25.8 156 34.8 158 18.2 155 30.2 119 34.2 119 15.3 116 19.1 95 27.0 96 7.08 106 32.5 153 49.7 153 16.8 144 22.8 78 28.6 79 8.08 37
HCIC-L [99]125.3 14.3 152 20.9 149 2.86 135 11.2 158 13.3 160 7.62 149 23.9 132 31.6 153 25.6 150 21.0 148 28.2 150 14.8 143 25.6 26 29.0 26 12.2 40 24.0 159 33.9 159 10.5 157 30.5 146 46.8 146 18.5 148 23.3 101 29.2 99 7.37 21
WOLF_ROB [148]126.8 16.7 159 24.7 158 3.17 137 9.76 146 11.8 149 5.28 105 22.6 121 24.5 128 19.4 121 21.5 150 28.4 151 8.71 32 30.8 142 35.0 143 15.2 112 20.1 122 28.3 121 7.04 104 32.0 152 48.8 150 8.28 74 25.4 152 31.8 153 8.20 62
IIOF-NLDP [131]127.0 10.2 109 15.8 108 2.10 111 9.06 111 11.2 110 5.60 128 20.6 112 24.8 130 16.9 101 16.7 118 22.6 122 14.6 137 30.4 125 34.5 126 20.8 158 20.4 132 28.8 129 8.81 148 37.7 157 57.6 157 16.8 144 24.9 149 31.2 149 8.26 77
WRT [150]134.3 10.3 110 15.8 108 2.35 123 9.41 132 10.6 70 9.35 153 35.2 155 27.6 141 26.8 152 21.2 149 21.4 109 13.6 130 31.3 151 35.6 151 13.7 76 21.5 150 30.4 150 8.56 144 39.0 160 59.6 160 16.0 140 26.1 158 32.6 159 8.31 92
GroupFlow [9]134.5 15.6 156 23.3 156 3.31 140 9.20 122 11.4 123 6.26 142 30.9 147 22.4 107 18.9 118 25.4 155 30.0 153 21.2 160 32.4 155 36.7 154 15.3 116 20.9 141 29.4 138 7.71 128 29.9 141 45.5 138 9.50 96 23.3 101 29.1 92 10.6 149
Pyramid LK [2]142.0 14.0 151 21.7 152 4.34 147 13.7 159 11.5 133 9.94 157 37.6 158 26.8 139 24.6 148 25.9 157 29.3 152 18.7 156 35.0 159 39.7 159 13.3 71 19.9 120 24.8 41 9.57 155 33.3 154 51.1 154 10.7 115 26.0 157 32.4 158 13.0 156
Periodicity [78]157.8 18.1 160 27.0 160 6.22 158 17.4 160 12.4 157 10.2 158 35.2 155 30.7 152 27.8 153 24.1 154 31.6 156 17.5 154 37.6 161 42.6 161 18.8 155 27.7 160 39.3 160 11.2 160 38.6 159 58.9 159 22.9 158 27.3 159 33.2 160 14.3 159
AVG_FLOW_ROB [141]158.6 31.2 161 31.0 161 11.6 161 19.8 161 21.4 161 12.0 161 34.9 154 32.0 154 28.1 154 31.2 161 36.2 160 23.9 161 36.4 160 41.0 160 16.9 153 39.5 161 55.0 161 16.9 161 36.8 156 52.3 155 20.8 154 30.2 161 31.8 153 15.5 161
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] CFRF 0.128 2 color Anonymous. (Interpolation results only.) Coarse-to-fine refinement framework for video frame interpolation. CVPR 2019 submission 1992.
[157] MPRN 0.32 4 color Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[158] DAIN 0.13 2 color Anonymous. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019 submission 1769.
[159] PyrWarp 0.14 2 color Anonymous. (Interpolation results only.) Feature pyramid warping for video frame interpolation. CVPR 2019 submission 868.
[160] 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.
[161] OFRI 0.31 2 color Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
* 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.