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 [159]2.7 2.11 1 3.19 1 1.00 1 2.94 1 4.07 2 1.32 22 2.18 1 3.02 1 1.27 2 3.97 1 4.83 1 2.75 1 7.05 1 8.63 1 3.02 2 4.53 3 8.43 3 2.06 4 5.53 2 12.2 2 1.45 2 5.78 2 8.91 2 1.61 6
MPRN [157]15.5 2.53 10 4.43 11 1.21 24 3.78 56 4.97 15 1.57 78 3.39 8 5.49 16 1.28 3 5.03 9 6.58 11 3.19 29 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 5
CFRF [156]16.2 2.31 5 3.98 5 1.10 3 3.56 29 4.85 12 1.77 118 2.59 2 3.68 4 1.66 25 4.52 4 5.41 2 3.50 109 8.35 6 10.3 6 3.22 8 4.78 6 8.90 5 2.18 7 6.15 4 13.6 4 1.50 8 6.31 5 9.78 6 1.62 7
CtxSyn [136]16.7 2.24 2 3.72 4 1.04 2 2.96 2 4.16 3 1.35 31 4.32 74 3.42 3 3.18 116 4.21 2 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 45 6.66 9 10.2 8 1.69 16
InterpCNN [160]18.5 2.61 12 4.34 9 1.52 154 3.30 6 4.52 4 1.72 107 3.14 6 3.70 5 1.76 35 4.74 6 5.99 8 3.29 60 8.11 5 10.0 5 2.97 1 4.48 2 8.35 2 2.02 1 5.78 3 12.7 3 1.45 2 6.06 3 9.38 3 1.57 3
DAIN [158]20.0 2.38 6 4.05 6 1.26 109 3.28 4 4.53 5 1.79 120 3.32 7 3.77 6 2.05 56 4.65 5 5.88 5 3.41 96 7.88 2 9.74 2 3.04 3 4.73 5 8.90 5 2.04 3 6.36 5 14.3 5 1.51 13 6.25 4 9.68 5 1.54 2
CyclicGen [153]21.8 2.26 3 3.32 2 1.42 150 3.19 3 4.01 1 2.21 152 2.76 3 4.05 10 1.62 22 4.97 8 5.92 6 3.79 137 8.00 4 9.84 4 3.13 5 3.36 1 5.65 1 2.17 6 4.55 1 9.68 1 1.42 1 4.48 1 6.84 1 1.52 1
MDP-Flow2 [68]23.8 2.89 16 5.38 17 1.19 6 3.47 15 5.07 22 1.26 1 3.66 21 6.10 49 2.48 85 5.20 13 7.48 22 3.14 16 10.2 14 12.8 16 3.61 35 6.13 35 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]23.9 2.90 17 5.43 19 1.20 10 3.50 21 5.05 20 1.27 6 3.56 12 5.46 14 1.82 39 5.38 29 7.92 49 3.41 96 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]24.6 2.54 11 4.35 10 1.16 5 3.70 46 5.19 26 1.88 127 3.43 9 3.89 7 1.93 46 5.05 10 6.43 10 3.39 90 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 53 7.14 13 11.0 13 1.69 16
SuperSlomo [132]25.3 2.51 8 4.32 8 1.25 96 3.66 41 5.06 21 1.93 140 2.91 4 4.00 8 1.41 9 5.05 10 6.27 9 3.66 127 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]30.7 2.47 7 4.06 7 1.32 134 3.49 19 4.73 9 1.90 130 4.63 95 4.03 9 3.12 112 4.94 7 5.98 7 3.46 103 8.91 7 11.1 7 3.21 6 4.70 4 8.83 4 2.03 2 6.46 6 14.4 7 1.56 37 6.35 7 9.86 7 1.57 3
OFRI [161]31.2 2.28 4 3.45 3 1.35 143 3.44 12 4.57 6 2.13 150 3.02 5 3.34 2 1.73 33 4.51 3 5.42 3 3.88 138 7.89 3 9.76 3 3.10 4 5.24 8 9.92 8 2.10 5 6.78 8 14.3 5 1.82 105 6.32 6 9.62 4 1.75 87
SepConv-v1 [127]32.2 2.52 9 4.83 12 1.11 4 3.56 29 5.04 18 1.90 130 4.17 60 4.15 11 2.86 102 5.41 38 6.81 12 3.88 138 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 88 6.63 8 10.3 9 1.62 7
DeepFlow [86]33.3 2.98 29 5.67 34 1.22 52 3.88 69 5.78 68 1.52 70 3.62 14 5.93 42 1.34 5 5.39 34 7.20 17 3.17 20 11.0 45 13.9 52 3.63 45 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]37.8 2.83 13 5.20 13 1.23 72 3.97 81 5.79 71 1.56 74 3.62 14 5.47 15 1.60 21 5.21 14 7.12 14 3.29 60 10.1 12 12.6 12 3.62 39 5.97 23 11.5 23 2.31 38 7.76 51 17.8 52 1.61 53 7.60 21 11.9 21 1.76 100
DeepFlow2 [108]38.5 2.99 32 5.65 31 1.22 52 3.88 69 5.79 71 1.48 64 3.62 14 6.03 44 1.34 5 5.38 29 7.44 21 3.22 40 11.0 45 13.8 45 3.67 53 5.83 15 11.2 15 2.25 15 7.60 32 17.4 33 1.50 8 7.82 42 12.2 39 1.77 109
SuperFlow [81]40.6 2.94 21 5.56 27 1.24 86 3.99 84 5.78 68 1.67 98 4.06 49 5.55 18 1.83 40 5.52 49 7.07 13 3.20 34 10.2 14 12.7 14 3.68 56 6.13 35 11.8 32 2.24 11 7.68 41 17.5 38 1.77 100 7.44 16 11.6 15 1.69 16
NN-field [71]40.8 2.98 29 5.70 35 1.20 10 3.31 8 4.73 9 1.26 1 4.69 99 5.91 40 2.03 55 5.99 100 9.13 117 3.57 119 10.3 20 12.8 16 3.60 29 6.24 46 12.0 44 2.31 38 7.39 18 16.9 18 1.54 26 7.69 29 12.0 27 1.72 47
NNF-Local [87]41.0 2.92 20 5.51 25 1.19 6 3.30 6 4.71 8 1.26 1 3.65 19 5.91 40 2.29 75 5.76 78 8.70 99 3.55 117 10.3 20 12.9 22 3.60 29 6.42 65 12.4 64 2.34 50 7.57 28 17.4 33 1.74 90 7.61 22 11.9 21 1.72 47
Aniso. Huber-L1 [22]41.8 2.95 24 5.44 21 1.24 86 4.42 118 6.27 118 1.67 98 3.79 32 5.70 25 1.50 14 5.31 19 7.42 20 3.24 49 11.1 56 14.0 64 3.61 35 5.91 20 11.4 21 2.24 11 7.60 32 17.3 27 1.51 13 7.62 24 11.9 21 1.73 56
IROF-TV [53]42.8 3.07 47 5.91 57 1.23 72 3.71 48 5.47 46 1.40 43 3.70 27 6.27 55 1.58 20 5.25 16 7.60 29 3.17 20 11.0 45 13.9 52 4.47 115 6.37 61 12.4 64 2.30 35 7.79 55 17.9 56 1.50 8 7.63 25 11.9 21 1.66 9
CLG-TV [48]43.2 2.94 21 5.45 22 1.25 96 4.26 105 6.17 105 1.60 83 3.68 25 5.73 27 1.73 33 5.36 25 7.41 19 3.32 78 11.1 56 14.0 64 3.57 18 5.88 19 11.3 19 2.26 16 7.58 29 17.0 22 1.57 42 7.75 33 12.1 32 1.72 47
LME [70]43.4 2.95 24 5.59 29 1.19 6 3.68 44 5.50 49 1.38 36 4.06 49 7.00 93 1.71 32 5.38 29 7.92 49 3.18 24 11.2 69 14.1 72 4.51 143 6.29 51 12.2 51 2.31 38 7.33 15 16.8 15 1.51 13 7.83 43 12.3 43 1.70 24
IROF++ [58]44.1 3.03 38 5.77 43 1.20 10 3.59 33 5.31 34 1.33 25 4.32 74 6.61 72 2.25 70 5.06 12 7.14 15 3.16 19 11.0 45 13.9 52 4.44 111 6.34 56 12.3 58 2.27 21 7.54 27 17.3 27 1.64 68 8.09 66 12.7 67 1.69 16
NNF-EAC [103]45.4 3.01 35 5.60 30 1.25 96 3.63 36 5.36 39 1.29 13 4.17 60 7.03 95 2.99 105 5.50 48 7.96 51 3.28 57 11.2 69 14.1 72 3.60 29 5.86 18 11.2 15 2.26 16 7.43 22 17.0 22 1.54 26 7.79 40 12.2 39 1.73 56
CombBMOF [113]45.6 3.16 77 5.88 52 1.24 86 3.54 25 5.24 29 1.34 29 4.01 45 6.45 66 2.20 67 5.62 68 8.22 67 3.29 60 10.7 30 13.5 31 3.62 39 6.20 43 11.9 40 2.27 21 7.78 54 17.3 27 1.56 37 7.75 33 12.1 32 1.71 37
DF-Auto [115]46.8 2.94 21 5.34 15 1.23 72 3.99 84 5.84 76 1.65 92 3.85 37 6.73 76 1.55 19 5.38 29 7.54 24 3.25 51 10.4 23 13.0 23 3.70 58 6.17 42 11.9 40 2.28 24 7.94 65 18.2 67 1.75 95 7.68 27 12.0 27 1.71 37
ALD-Flow [66]48.2 3.28 105 6.45 107 1.24 86 3.81 60 5.73 66 1.41 47 3.62 14 6.28 56 1.35 7 5.58 58 8.39 80 3.04 7 10.8 33 13.5 31 4.15 91 5.96 22 11.4 21 2.29 29 7.34 16 16.8 15 1.51 13 8.25 88 12.9 81 1.70 24
WLIF-Flow [93]48.5 2.95 24 5.53 26 1.20 10 3.66 41 5.41 42 1.39 39 4.26 69 7.17 103 2.54 88 5.30 18 7.57 27 3.29 60 10.7 30 13.5 31 3.70 58 6.74 112 13.1 108 2.48 113 7.40 20 16.9 18 1.53 20 7.87 49 12.3 43 1.69 16
PH-Flow [101]49.5 3.12 63 6.01 72 1.20 10 3.39 10 4.94 14 1.28 11 3.70 27 6.43 61 2.48 85 5.23 15 7.58 28 3.22 40 10.4 23 13.1 25 3.62 39 6.84 123 13.3 121 2.47 107 7.84 58 18.1 63 1.58 45 7.87 49 12.3 43 1.73 56
Second-order prior [8]49.9 2.91 19 5.39 18 1.24 86 4.26 105 6.21 111 1.56 74 3.82 34 6.34 58 1.62 22 5.39 34 7.68 31 3.04 7 11.1 56 13.9 52 3.59 22 6.14 38 11.9 40 2.31 38 7.61 34 17.4 33 1.63 67 7.90 51 12.4 53 1.78 115
p-harmonic [29]50.8 3.00 33 5.72 37 1.21 24 4.33 110 6.24 116 1.69 103 3.60 13 6.07 48 1.39 8 5.70 70 7.87 44 3.29 60 11.0 45 13.8 45 3.63 45 6.02 26 11.6 26 2.34 50 7.67 39 17.5 38 1.70 83 7.92 55 12.4 53 1.72 47
Brox et al. [5]51.6 3.08 50 5.94 62 1.21 24 3.83 63 5.67 58 1.45 57 3.93 41 5.76 29 1.67 27 5.32 20 7.19 16 3.22 40 10.6 27 13.4 29 3.56 16 6.60 93 12.7 80 2.42 92 8.61 108 19.7 110 3.04 153 7.43 15 11.6 15 1.68 14
FMOF [94]52.5 3.16 77 5.92 60 1.23 72 3.48 16 5.07 22 1.28 11 4.59 93 6.82 80 2.78 98 5.71 72 8.42 81 3.40 93 10.4 23 13.0 23 3.67 53 6.49 72 12.6 73 2.28 24 7.64 36 17.5 38 1.48 4 8.06 65 12.6 63 1.67 12
SIOF [67]53.7 3.06 45 5.74 41 1.24 86 4.40 117 6.40 129 1.63 90 4.17 60 7.43 116 1.93 46 5.40 37 7.75 36 3.44 100 10.1 12 12.6 12 3.58 20 6.10 32 11.8 32 2.29 29 7.52 25 17.2 26 1.53 20 7.96 59 12.5 62 1.73 56
MDP-Flow [26]55.3 2.86 14 5.34 15 1.20 10 3.49 19 5.15 25 1.34 29 4.01 45 5.51 17 2.28 72 5.58 58 7.91 48 3.33 81 11.2 69 14.0 64 4.49 125 6.72 106 13.1 108 2.54 131 7.71 44 17.7 48 1.74 90 7.83 43 12.3 43 1.70 24
Local-TV-L1 [65]55.6 3.00 33 5.47 23 1.30 128 4.43 120 6.23 115 1.75 113 3.50 10 5.35 13 1.45 10 5.39 34 7.56 25 3.29 60 11.2 69 14.1 72 3.91 80 6.16 40 11.8 32 2.47 107 7.67 39 17.6 43 1.55 32 7.57 18 11.8 18 1.76 100
OAR-Flow [125]57.2 3.13 68 5.95 64 1.22 52 3.83 63 5.70 61 1.48 64 3.65 19 6.06 45 1.16 1 5.60 63 8.48 86 3.03 4 11.2 69 14.1 72 4.51 143 6.12 34 11.8 32 2.41 89 7.97 68 17.9 56 1.59 47 8.11 69 12.7 67 1.71 37
JOF [140]57.8 3.08 50 5.89 54 1.24 86 3.48 16 5.04 18 1.37 34 3.85 37 5.98 43 2.07 57 5.43 41 7.81 42 3.28 57 11.3 87 14.2 87 4.51 143 6.72 106 13.1 108 2.37 66 7.48 24 17.1 24 1.54 26 8.01 61 12.6 63 1.73 56
F-TV-L1 [15]61.8 3.30 107 6.36 100 1.29 124 4.39 116 6.32 124 1.62 89 3.80 33 5.90 39 1.76 35 5.61 65 7.97 53 3.31 75 10.9 41 13.6 36 3.59 22 5.84 16 11.2 15 2.33 48 7.70 42 17.6 43 1.79 102 7.61 22 11.9 21 1.78 115
Ad-TV-NDC [36]61.9 3.23 94 5.70 35 1.44 152 4.78 145 6.46 132 1.92 135 3.67 22 5.86 36 1.50 14 5.97 97 8.14 65 3.51 110 10.8 33 13.5 31 3.63 45 6.24 46 12.0 44 2.40 78 7.70 42 17.3 27 1.51 13 7.48 17 11.7 17 1.73 56
Modified CLG [34]62.0 2.87 15 5.32 14 1.24 86 4.51 125 6.21 111 1.96 143 4.15 58 6.45 66 2.67 95 5.56 55 7.69 32 3.64 126 10.8 33 13.5 31 3.63 45 6.36 60 12.3 58 2.39 75 7.46 23 17.1 24 1.56 37 7.86 46 12.3 43 1.75 87
CPM-Flow [116]62.6 3.17 83 6.31 95 1.21 24 3.54 25 5.26 31 1.31 19 4.22 66 5.88 38 1.45 10 6.11 108 9.48 129 3.31 75 11.1 56 13.9 52 4.50 130 6.28 50 12.1 48 2.32 45 7.66 37 17.6 43 1.74 90 8.18 74 12.8 75 1.76 100
2DHMM-SAS [92]63.2 3.10 57 5.91 57 1.21 24 4.10 93 6.05 93 1.46 61 4.38 79 7.10 100 2.07 57 5.38 29 7.78 40 3.22 40 11.3 87 14.3 97 4.42 107 6.33 53 12.2 51 2.26 16 7.95 67 18.2 67 1.64 68 8.19 76 12.8 75 1.70 24
TC/T-Flow [76]64.5 3.21 91 6.24 86 1.22 52 3.90 74 5.86 78 1.43 52 3.69 26 5.83 32 1.50 14 5.88 90 8.93 107 3.15 17 11.1 56 13.9 52 4.50 130 6.23 44 12.0 44 2.26 16 8.61 108 19.0 90 1.93 117 8.16 73 12.8 75 1.70 24
COFM [59]65.1 3.03 38 5.76 42 1.22 52 3.55 28 5.21 28 1.32 22 3.82 34 6.98 91 2.81 99 5.41 38 7.97 53 3.30 70 10.8 33 13.6 36 3.62 39 7.01 137 13.7 134 2.40 78 8.00 73 18.5 78 1.98 120 7.91 52 12.4 53 1.80 135
DMF_ROB [139]65.5 3.15 74 6.13 80 1.22 52 3.96 78 5.87 79 1.56 74 5.24 121 7.74 128 2.62 91 5.73 75 8.32 73 3.19 29 11.0 45 13.8 45 4.50 130 6.07 29 11.7 29 2.37 66 7.66 37 17.5 38 1.50 8 8.10 67 12.7 67 1.73 56
LDOF [28]66.0 3.03 38 5.66 33 1.28 118 4.06 90 5.53 51 2.40 156 4.32 74 6.43 61 2.00 51 5.45 44 7.56 25 3.60 123 10.2 14 12.7 14 3.59 22 6.39 62 12.4 64 2.29 29 8.36 94 19.4 101 2.21 136 7.57 18 11.8 18 1.86 148
FlowFields [110]66.6 3.15 74 6.30 92 1.21 24 3.57 31 5.34 37 1.32 22 4.73 101 6.89 84 3.23 119 5.85 85 8.96 110 3.08 9 10.8 33 13.6 36 4.19 92 6.57 86 12.8 92 2.36 62 7.72 45 17.8 52 1.67 76 8.20 78 12.9 81 1.74 77
Layers++ [37]66.7 2.96 27 5.56 27 1.22 52 3.29 5 4.64 7 1.26 1 4.07 51 7.24 104 3.08 109 5.48 45 8.10 61 3.25 51 12.0 152 15.2 153 4.62 155 7.29 145 14.3 145 2.44 99 7.63 35 17.5 38 1.54 26 7.84 45 12.3 43 1.70 24
nLayers [57]66.9 3.03 38 5.72 37 1.21 24 3.48 16 5.09 24 1.31 19 5.60 126 7.52 119 4.26 141 5.61 65 8.33 74 3.29 60 11.6 130 14.6 129 4.31 98 6.66 99 12.9 101 2.40 78 7.58 29 17.3 27 1.59 47 7.94 56 12.4 53 1.69 16
ComplOF-FED-GPU [35]67.0 3.23 94 6.40 102 1.22 52 3.73 51 5.62 57 1.44 54 5.23 120 6.06 45 3.23 119 5.53 50 8.25 68 3.29 60 11.1 56 13.9 52 4.21 93 6.11 33 11.8 32 2.32 45 8.16 81 18.5 78 1.61 53 8.29 95 12.9 81 1.71 37
TV-L1-MCT [64]67.2 3.17 83 6.05 75 1.22 52 3.87 66 5.82 74 1.40 43 4.48 86 7.75 129 2.24 69 5.37 27 7.76 38 3.24 49 11.6 130 14.7 136 4.31 98 6.08 30 11.7 29 2.31 38 8.07 77 18.6 81 2.15 134 7.68 27 12.0 27 1.68 14
TC-Flow [46]68.5 3.31 109 6.70 119 1.22 52 3.91 76 5.95 81 1.45 57 3.64 18 5.84 33 1.28 3 5.70 70 8.50 88 3.22 40 11.2 69 14.1 72 4.44 111 6.34 56 12.3 58 2.41 89 7.79 55 17.9 56 1.55 32 8.42 110 13.2 112 1.74 77
AdaConv-v1 [126]68.5 3.57 134 6.88 127 1.41 148 4.34 113 5.67 58 2.52 158 5.00 113 5.86 36 2.98 104 6.91 136 8.89 106 4.89 154 10.2 14 12.8 16 3.21 6 5.33 10 10.1 11 2.27 21 7.30 14 16.6 14 1.92 116 6.94 12 10.8 12 1.67 12
CRTflow [80]68.7 3.09 55 5.91 57 1.27 114 4.35 114 6.31 122 1.68 101 4.15 58 7.26 105 1.84 41 5.33 22 7.51 23 3.38 87 11.0 45 13.8 45 4.48 118 6.09 31 11.7 29 2.30 35 8.55 105 19.8 111 1.55 32 8.19 76 12.8 75 1.72 47
DPOF [18]69.0 3.34 115 6.82 123 1.29 124 3.40 11 4.93 13 1.29 13 5.00 113 6.36 59 3.40 122 5.86 86 8.94 108 3.51 110 11.0 45 13.8 45 3.59 22 6.56 83 12.7 80 2.28 24 7.99 70 18.2 67 1.55 32 8.24 85 12.9 81 1.70 24
AGIF+OF [85]69.1 3.12 63 5.95 64 1.20 10 3.64 38 5.39 40 1.40 43 3.96 43 6.44 65 2.28 72 5.48 45 8.03 57 3.25 51 11.4 98 14.3 97 4.49 125 6.91 128 13.5 129 2.37 66 7.85 60 17.9 56 1.54 26 8.44 114 13.2 112 1.73 56
PGM-C [120]70.4 3.17 83 6.29 90 1.21 24 3.58 32 5.32 35 1.33 25 5.01 115 6.14 52 1.90 44 6.14 111 9.63 134 3.23 46 11.2 69 14.1 72 4.50 130 6.14 38 11.8 32 2.34 50 8.20 83 18.9 87 1.59 47 8.46 117 13.3 118 1.73 56
Classic++ [32]71.0 3.05 43 5.85 48 1.24 86 4.08 92 6.08 96 1.52 70 3.74 30 5.58 21 1.53 18 5.72 74 8.12 63 3.21 36 11.4 98 14.3 97 3.74 69 6.68 101 13.0 103 2.42 92 8.35 93 19.2 94 1.62 63 8.21 80 12.9 81 1.73 56
Sparse-NonSparse [56]71.3 3.07 47 5.88 52 1.21 24 3.61 34 5.33 36 1.33 25 4.29 72 7.47 117 2.19 66 5.37 27 7.74 34 3.21 36 11.5 114 14.5 119 4.36 102 6.66 99 12.9 101 2.41 89 8.69 114 20.1 117 1.67 76 8.27 92 13.0 94 1.70 24
EAI-Flow [151]71.5 3.37 118 6.27 89 1.32 134 3.79 57 5.59 54 1.52 70 4.30 73 7.09 98 2.39 81 5.60 63 8.34 75 2.96 2 11.2 69 14.1 72 4.34 101 6.04 28 11.6 26 2.34 50 7.72 45 17.6 43 3.12 154 7.77 38 12.1 32 1.82 145
ProbFlowFields [128]72.8 3.15 74 6.32 97 1.21 24 3.53 22 5.26 31 1.29 13 5.03 116 7.35 111 3.73 129 5.43 41 7.97 53 3.25 51 11.1 56 14.0 64 4.50 130 6.48 70 12.6 73 2.55 134 7.99 70 18.4 77 2.57 145 7.78 39 12.2 39 1.75 87
ProFlow_ROB [146]73.1 3.16 77 6.30 92 1.21 24 3.77 55 5.71 63 1.39 39 4.12 55 5.27 12 1.62 22 6.15 112 9.68 135 3.11 13 11.5 114 14.5 119 4.50 130 5.85 17 11.2 15 2.24 11 8.50 102 19.4 101 1.56 37 8.70 132 13.6 130 1.85 147
BlockOverlap [61]73.3 2.98 29 5.47 23 1.33 138 4.38 115 6.09 97 1.88 127 4.26 69 5.57 20 3.14 113 5.56 55 7.32 18 4.14 147 11.1 56 13.9 52 3.77 72 6.41 63 12.3 58 2.54 131 7.75 49 17.4 33 3.02 152 7.32 14 11.4 14 1.78 115
S2F-IF [123]73.5 3.26 100 6.66 116 1.20 10 3.53 22 5.25 30 1.29 13 4.11 54 6.64 73 2.34 77 5.89 91 9.06 115 3.08 9 11.4 98 14.3 97 4.51 143 6.41 63 12.4 64 2.40 78 7.84 58 18.1 63 1.76 98 8.33 102 13.1 103 1.75 87
PMF [73]73.6 3.14 70 6.13 80 1.20 10 3.73 51 5.60 55 1.27 6 5.24 121 8.98 144 3.76 130 5.75 76 8.56 94 3.28 57 10.8 33 13.6 36 3.62 39 6.55 80 12.7 80 2.35 59 8.41 99 19.5 107 1.64 68 8.57 124 13.4 123 1.70 24
MLDP_OF [89]73.7 3.08 50 5.98 69 1.21 24 4.01 86 6.01 90 1.49 67 3.67 22 6.14 52 1.47 12 5.78 79 8.13 64 3.95 142 11.3 87 14.2 87 3.87 77 6.71 104 13.0 103 2.51 123 7.73 48 17.7 48 1.71 85 8.18 74 12.8 75 1.76 100
OFLAF [77]74.2 3.10 57 5.98 69 1.20 10 3.44 12 5.03 17 1.26 1 3.73 29 5.82 31 1.66 25 5.33 22 7.74 34 3.10 12 11.6 130 14.7 136 4.50 130 6.58 90 12.8 92 2.48 113 9.33 139 21.6 140 2.06 128 8.45 116 13.2 112 1.80 135
Sparse Occlusion [54]74.2 3.16 77 6.18 84 1.23 72 4.14 100 6.24 116 1.45 57 3.67 22 5.84 33 1.52 17 5.61 65 8.26 69 3.15 17 11.5 114 14.4 108 4.48 118 6.26 48 12.1 48 2.46 104 8.52 103 19.6 109 1.54 26 8.28 94 13.0 94 1.75 87
TF+OM [100]74.6 3.33 114 6.83 124 1.25 96 3.65 39 5.43 44 1.47 63 3.82 34 6.43 61 1.68 29 6.01 102 9.04 114 3.19 29 11.2 69 14.1 72 4.38 104 6.46 69 12.5 69 2.34 50 8.30 92 19.2 94 1.86 109 8.05 64 12.6 63 1.75 87
HAST [109]74.6 3.01 35 5.73 39 1.21 24 3.45 14 5.01 16 1.27 6 6.39 140 8.24 136 4.09 135 5.43 41 7.96 51 3.03 4 11.2 69 14.2 87 3.59 22 7.47 149 14.7 149 2.47 107 8.68 113 20.1 117 1.53 20 8.35 105 13.1 103 1.77 109
FlowFields+ [130]74.8 3.14 70 6.26 88 1.22 52 3.54 25 5.27 33 1.30 18 4.74 104 7.10 100 3.20 117 6.01 102 9.35 125 3.11 13 11.1 56 13.9 52 4.50 130 6.57 86 12.8 92 2.40 78 7.89 64 18.2 67 1.80 103 8.22 82 12.9 81 1.73 56
FlowNetS+ft+v [112]75.0 3.07 47 5.81 45 1.28 118 4.57 134 6.29 120 2.41 157 4.01 45 5.64 23 2.13 63 5.55 53 7.77 39 3.88 138 11.3 87 14.2 87 4.46 114 5.99 25 11.5 23 2.35 59 8.63 111 20.0 114 1.62 63 7.70 30 12.0 27 1.74 77
Filter Flow [19]76.2 3.13 68 5.90 55 1.28 118 4.56 133 6.38 128 1.85 125 4.22 66 6.28 56 2.10 61 5.91 92 7.97 53 3.44 100 10.4 23 13.1 25 3.69 57 6.43 67 12.5 69 2.40 78 8.17 82 18.8 86 1.62 63 7.94 56 12.4 53 1.78 115
EpicFlow [102]78.9 3.17 83 6.34 98 1.21 24 3.79 57 5.70 61 1.44 54 4.28 71 5.73 27 1.67 27 6.37 124 10.1 140 3.39 90 11.2 69 14.1 72 4.50 130 6.23 44 12.0 44 2.38 73 8.11 79 18.5 78 1.76 98 8.76 136 13.8 137 1.74 77
LSM [39]78.9 3.12 63 6.05 75 1.21 24 3.68 44 5.47 46 1.33 25 4.38 79 7.66 126 2.01 52 5.55 53 8.19 66 3.19 29 11.5 114 14.5 119 4.43 108 6.83 120 13.3 121 2.37 66 8.70 115 20.1 117 1.72 88 8.34 104 13.1 103 1.71 37
Black & Anandan [4]79.5 3.22 93 5.87 50 1.30 128 4.82 148 6.55 137 1.78 119 7.16 144 7.10 100 3.93 132 6.25 118 8.49 87 3.35 85 10.9 41 13.7 42 3.56 16 6.33 53 12.2 51 2.37 66 8.23 86 18.6 81 1.64 68 7.67 26 11.9 21 1.69 16
RNLOD-Flow [121]79.9 3.06 45 5.87 50 1.21 24 3.96 78 5.97 87 1.42 49 4.39 81 8.08 133 2.44 83 5.35 24 7.75 36 3.18 24 11.5 114 14.5 119 4.49 125 6.71 104 13.1 108 2.43 96 7.85 60 18.0 61 2.18 135 8.44 114 13.2 112 1.73 56
TCOF [69]80.0 3.12 63 5.94 62 1.21 24 4.60 137 6.64 144 1.76 116 4.13 56 7.30 107 1.81 37 5.42 40 7.88 45 3.25 51 11.3 87 14.2 87 3.63 45 6.42 65 12.4 64 2.36 62 9.08 136 21.0 136 1.59 47 8.37 106 13.1 103 1.76 100
Ramp [62]81.0 3.11 61 5.96 66 1.22 52 3.61 34 5.34 37 1.40 43 4.91 110 8.45 139 3.20 117 5.29 17 7.66 30 3.21 36 11.5 114 14.5 119 4.31 98 6.88 127 13.4 125 2.48 113 8.73 121 20.2 121 1.52 19 8.29 95 13.0 94 1.73 56
Fusion [6]81.5 3.04 42 5.86 49 1.22 52 3.75 54 5.47 46 1.42 49 4.08 52 5.55 18 3.08 109 5.80 81 8.10 61 3.19 29 11.4 98 14.3 97 3.73 66 6.99 134 13.7 134 2.60 140 8.40 98 19.4 101 1.65 73 8.50 119 13.3 118 1.80 135
Classic+NL [31]82.1 3.10 57 5.92 60 1.23 72 3.66 41 5.40 41 1.39 39 4.78 107 8.42 138 3.01 107 5.36 25 7.78 40 3.30 70 11.5 114 14.5 119 4.24 95 6.73 108 13.1 108 2.40 78 8.74 122 20.2 121 1.70 83 8.29 95 13.0 94 1.71 37
AggregFlow [97]82.1 3.80 145 8.08 145 1.23 72 3.87 66 5.83 75 1.43 52 4.21 65 6.79 78 2.85 101 6.11 108 9.36 126 3.31 75 10.6 27 13.3 27 3.67 53 6.13 35 11.8 32 2.34 50 8.70 115 19.8 111 2.30 140 8.27 92 13.0 94 1.75 87
ComponentFusion [96]82.2 3.41 120 7.08 130 1.20 10 3.63 36 5.44 45 1.27 6 4.20 64 6.49 68 2.43 82 5.59 61 8.38 79 3.32 78 11.4 98 14.4 108 4.11 89 6.26 48 12.1 48 2.35 59 9.30 138 21.6 140 2.80 150 8.68 129 13.6 130 1.73 56
Bartels [41]84.3 3.48 127 7.24 134 1.30 128 4.02 87 6.12 102 1.68 101 3.74 30 5.80 30 1.95 49 5.87 88 8.44 83 3.78 136 10.3 20 12.8 16 3.75 71 6.77 115 13.0 103 2.73 157 7.53 26 17.3 27 2.72 148 8.13 70 12.7 67 1.77 109
Occlusion-TV-L1 [63]84.4 3.14 70 6.13 80 1.25 96 4.47 124 6.61 140 1.66 95 3.51 11 5.71 26 1.70 31 6.33 120 9.58 133 3.51 110 11.0 45 13.9 52 3.57 18 6.48 70 12.6 73 2.52 128 8.36 94 18.1 63 2.00 123 8.32 101 13.0 94 1.79 129
LFNet_ROB [149]85.0 3.65 139 7.73 140 1.23 72 3.88 69 5.80 73 1.49 67 4.57 90 8.96 143 2.02 54 5.62 68 8.44 83 3.18 24 11.0 45 13.8 45 4.47 115 7.19 144 14.1 144 2.47 107 7.59 31 17.4 33 1.82 105 8.10 67 12.7 67 1.78 115
Classic+CPF [83]85.1 3.12 63 5.96 66 1.21 24 3.72 50 5.51 50 1.39 39 4.39 81 7.38 114 2.27 71 5.32 20 7.70 33 3.18 24 11.7 140 14.8 142 4.50 130 7.18 143 14.0 143 2.45 101 8.79 123 20.2 121 1.57 42 8.71 134 13.7 133 1.73 56
HBM-GC [105]85.3 3.08 50 5.90 55 1.26 109 3.97 81 6.04 92 1.41 47 3.92 40 5.62 22 2.87 103 5.54 52 8.03 57 3.21 36 11.7 140 14.7 136 4.58 154 7.66 154 15.0 154 2.69 153 8.36 94 19.3 97 1.55 32 7.86 46 12.3 43 1.76 100
CNN-flow-warp+ref [117]85.4 2.90 17 5.43 19 1.25 96 4.10 93 5.95 81 1.83 124 4.92 111 7.63 124 2.45 84 6.13 110 7.85 43 3.72 132 11.3 87 14.2 87 4.51 143 6.03 27 11.6 26 2.46 104 9.00 129 20.8 134 1.65 73 7.91 52 12.4 53 1.76 100
Efficient-NL [60]85.4 3.05 43 5.77 43 1.21 24 3.90 74 5.84 76 1.38 36 5.90 132 6.94 88 4.19 138 5.59 61 8.09 60 3.20 34 11.5 114 14.4 108 4.40 106 6.87 124 13.4 125 2.40 78 8.85 124 20.5 126 1.68 80 8.57 124 13.4 123 1.66 9
FC-2Layers-FF [74]86.1 3.18 87 6.16 83 1.22 52 3.33 9 4.73 9 1.35 31 4.34 78 7.09 98 3.11 111 5.56 55 8.29 70 3.29 60 11.5 114 14.5 119 4.48 118 7.00 135 13.7 134 2.48 113 8.92 128 20.6 129 1.71 85 8.30 98 13.0 94 1.73 56
2D-CLG [1]86.2 3.01 35 5.65 31 1.28 118 4.59 136 6.17 105 1.95 142 5.18 118 6.06 45 3.15 115 6.01 102 7.88 45 3.97 143 11.4 98 14.4 108 4.69 156 5.98 24 11.5 23 2.45 101 8.89 127 20.5 126 1.67 76 7.74 32 12.0 27 1.71 37
Horn & Schunck [3]86.5 3.16 77 5.83 46 1.26 109 4.91 149 6.65 145 1.92 135 6.13 135 6.85 81 3.53 125 6.80 133 9.10 116 3.57 119 10.9 41 13.7 42 3.59 22 6.16 40 11.9 40 2.32 45 8.63 111 19.5 107 1.84 108 7.91 52 12.3 43 1.73 56
FESL [72]86.9 3.16 77 6.02 73 1.21 24 3.65 39 5.42 43 1.35 31 4.39 81 7.61 123 2.18 65 5.71 72 8.35 77 3.30 70 11.6 130 14.7 136 4.51 143 6.73 108 13.1 108 2.47 107 8.70 115 20.1 117 1.56 37 8.42 110 13.2 112 1.75 87
SRR-TVOF-NL [91]87.0 3.32 112 6.46 108 1.23 72 3.96 78 5.96 84 1.59 79 4.68 97 7.90 131 3.52 124 5.99 100 8.77 101 3.23 46 11.2 69 14.1 72 4.45 113 6.79 118 13.2 118 2.31 38 7.88 62 18.0 61 1.50 8 8.37 106 13.1 103 1.75 87
RFlow [90]87.4 3.08 50 5.99 71 1.23 72 4.33 110 6.31 122 1.66 95 4.83 108 7.32 108 3.14 113 5.87 88 8.72 100 3.47 104 11.1 56 14.0 64 3.60 29 6.54 79 12.7 80 2.39 75 8.54 104 19.8 111 1.61 53 8.26 90 12.9 81 1.80 135
TriFlow [95]88.8 3.71 142 7.95 144 1.25 96 4.31 109 6.36 127 1.71 106 4.05 48 6.86 83 1.84 41 6.21 116 9.44 128 3.17 20 11.3 87 14.2 87 4.48 118 6.76 114 13.1 108 2.29 29 8.01 75 18.2 67 1.75 95 8.24 85 12.9 81 1.70 24
OFH [38]89.2 3.18 87 6.29 90 1.23 72 4.11 95 5.96 84 1.61 86 4.68 97 8.40 137 1.68 29 5.84 83 8.99 111 3.03 4 11.3 87 14.2 87 4.25 97 6.30 52 12.2 51 2.40 78 8.59 106 19.3 97 1.89 112 8.55 121 13.4 123 1.97 154
3DFlow [135]89.8 3.26 100 6.37 101 1.21 24 3.70 46 5.55 52 1.46 61 4.51 88 6.52 69 2.28 72 5.84 83 8.84 104 3.59 121 11.2 69 14.1 72 3.79 74 7.04 140 13.7 134 2.68 152 8.59 106 19.4 101 1.82 105 8.26 90 12.9 81 1.77 109
PWC-Net_ROB [147]90.3 3.66 141 7.76 141 1.21 24 3.91 76 5.97 87 1.37 34 3.88 39 6.73 76 1.48 13 6.36 122 10.1 140 3.13 15 11.8 145 14.9 146 4.49 125 6.78 117 13.1 108 2.34 50 7.72 45 17.7 48 1.66 75 8.57 124 13.5 128 1.88 149
CostFilter [40]90.6 3.46 126 7.24 134 1.19 6 3.71 48 5.60 55 1.27 6 5.63 128 9.41 150 3.86 131 6.37 124 10.1 140 3.23 46 11.2 69 14.0 64 3.78 73 6.35 58 12.2 51 2.40 78 8.86 126 20.6 129 1.69 81 8.80 138 13.8 137 1.74 77
S2D-Matching [84]90.8 3.21 91 6.22 85 1.22 52 3.97 81 5.95 81 1.48 64 4.57 90 7.70 127 2.84 100 5.48 45 8.06 59 3.48 106 11.4 98 14.3 97 4.14 90 6.97 132 13.6 132 2.56 138 8.09 78 18.6 81 1.74 90 8.21 80 12.9 81 1.76 100
Nguyen [33]90.8 3.26 100 6.11 79 1.33 138 4.94 150 6.51 135 1.91 133 4.09 53 7.32 108 1.96 50 6.19 115 8.53 91 3.60 123 11.1 56 13.9 52 3.58 20 6.55 80 12.7 80 2.36 62 9.44 141 21.8 144 1.80 103 7.86 46 12.3 43 1.74 77
SVFilterOh [111]91.2 3.23 94 6.35 99 1.23 72 3.53 22 5.19 26 1.31 19 5.91 133 8.20 135 4.22 139 5.75 76 8.52 90 3.43 98 11.4 98 14.3 97 4.53 151 6.97 132 13.6 132 2.38 73 7.94 65 18.3 74 1.57 42 8.31 100 13.0 94 1.79 129
Steered-L1 [118]92.2 2.97 28 5.73 39 1.21 24 3.81 60 5.72 65 1.60 83 8.15 147 9.24 147 6.46 155 6.42 126 9.21 123 4.28 150 11.4 98 14.3 97 3.80 75 6.52 76 12.7 80 2.43 96 8.20 83 19.0 90 2.54 143 8.33 102 13.1 103 1.70 24
FlowNet2 [122]92.3 4.84 154 10.1 155 1.29 124 4.11 95 6.13 103 1.61 86 4.73 101 7.06 96 2.36 78 6.36 122 10.0 138 3.38 87 11.2 69 14.1 72 3.71 61 6.44 68 12.5 69 2.33 48 8.45 100 19.4 101 1.61 53 8.03 63 12.6 63 1.77 109
Adaptive [20]92.5 3.24 97 6.44 105 1.25 96 4.57 134 6.61 140 1.72 107 3.94 42 6.12 51 1.81 37 5.86 86 8.66 97 3.47 104 11.6 130 14.6 129 3.59 22 6.55 80 12.7 80 2.51 123 9.03 131 20.6 129 1.59 47 8.13 70 12.7 67 1.78 115
TVL1_ROB [138]92.8 3.32 112 6.25 87 1.36 145 5.03 152 6.77 152 1.94 141 4.50 87 6.70 75 2.55 89 6.22 117 8.66 97 3.63 125 10.8 33 13.6 36 3.63 45 6.52 76 12.7 80 2.43 96 9.03 131 20.7 133 2.13 132 7.72 31 12.1 32 1.70 24
IAOF [50]93.0 3.53 132 6.60 114 1.32 134 5.39 158 7.19 158 1.96 143 5.81 130 7.32 108 3.63 127 6.15 112 8.34 75 3.72 132 11.1 56 14.0 64 3.60 29 6.50 73 12.6 73 2.34 50 8.28 90 19.0 90 1.53 20 7.94 56 12.4 53 1.73 56
Complementary OF [21]94.3 3.48 127 7.32 138 1.20 10 3.89 72 5.96 84 1.45 57 8.94 151 6.94 88 5.45 149 6.33 120 10.0 138 3.09 11 11.3 87 14.2 87 4.24 95 6.33 53 12.3 58 2.42 92 8.62 110 19.3 97 1.75 95 9.07 148 14.3 149 1.72 47
FF++_ROB [145]95.8 3.27 103 6.67 117 1.20 10 3.74 53 5.58 53 1.38 36 4.86 109 7.42 115 2.99 105 6.57 130 10.4 143 3.54 116 11.5 114 14.5 119 4.51 143 6.62 97 12.8 92 2.47 107 7.97 68 18.3 74 1.90 113 8.24 85 12.9 81 1.78 115
TV-L1-improved [17]96.2 3.09 55 6.03 74 1.25 96 4.55 131 6.59 139 1.70 104 5.88 131 5.66 24 4.09 135 5.53 50 7.88 45 3.22 40 11.4 98 14.4 108 3.61 35 6.73 108 13.1 108 2.51 123 9.48 142 22.1 146 1.94 118 8.25 88 12.9 81 1.79 129
AugFNG_ROB [143]96.2 3.73 143 7.90 143 1.25 96 4.12 98 6.02 91 1.74 110 4.70 100 8.79 142 1.94 48 8.14 154 13.4 155 3.29 60 12.0 152 15.1 151 4.50 130 6.50 73 12.6 73 2.28 24 8.03 76 18.3 74 1.62 63 7.75 33 12.1 32 1.75 87
TI-DOFE [24]96.9 3.41 120 6.44 105 1.44 152 5.20 156 6.82 155 2.01 147 4.19 63 6.41 60 1.88 43 6.98 137 9.50 130 3.70 130 10.8 33 13.6 36 3.61 35 6.59 91 12.8 92 2.36 62 8.13 80 18.2 67 1.77 100 8.53 120 12.4 53 2.33 158
EPPM w/o HM [88]97.1 3.35 116 6.86 126 1.21 24 3.85 65 5.88 80 1.29 13 7.03 142 9.47 153 3.97 134 6.15 112 9.51 131 3.38 87 10.6 27 13.3 27 3.62 39 7.00 135 13.7 134 2.37 66 8.85 124 20.5 126 2.62 147 8.42 110 13.2 112 1.76 100
GraphCuts [14]98.7 3.65 139 7.01 129 1.27 114 3.89 72 5.71 63 1.59 79 7.54 145 5.84 33 4.31 142 5.98 99 8.42 81 3.45 102 11.4 98 14.4 108 4.09 87 6.56 83 12.8 92 2.30 35 8.70 115 20.2 121 1.98 120 8.59 128 13.5 128 1.73 56
BriefMatch [124]99.5 3.25 99 6.49 109 1.25 96 3.87 66 5.67 58 1.97 145 6.16 136 6.17 54 4.79 145 6.83 135 8.37 78 5.73 157 11.0 45 13.8 45 3.73 66 6.75 113 13.0 103 2.61 142 7.99 70 17.9 56 3.29 155 8.22 82 12.8 75 2.32 157
NL-TV-NCC [25]100.5 3.37 118 6.58 113 1.24 86 4.23 104 6.41 130 1.49 67 4.39 81 6.68 74 2.07 57 7.19 145 11.2 149 3.35 85 10.7 30 13.4 29 4.00 84 6.95 129 13.4 125 2.44 99 9.06 133 20.0 114 2.13 132 8.42 110 13.1 103 1.78 115
EPMNet [133]101.1 4.90 155 10.5 159 1.28 118 4.04 89 5.98 89 1.60 83 4.73 101 7.06 96 2.36 78 8.74 157 15.0 158 3.48 106 11.2 69 14.1 72 3.71 61 6.70 103 13.0 103 2.34 50 8.45 100 19.4 101 1.61 53 8.38 108 13.1 103 1.78 115
IAOF2 [51]102.1 3.43 123 6.70 119 1.28 118 4.62 139 6.77 152 1.74 110 4.41 85 6.89 84 2.12 62 5.97 97 8.53 91 3.33 81 11.6 130 14.7 136 4.06 86 6.87 124 13.4 125 2.51 123 8.26 87 18.7 85 1.61 53 8.22 82 12.9 81 1.74 77
TriangleFlow [30]103.3 3.24 97 6.31 95 1.26 109 4.29 108 6.29 120 1.66 95 4.67 96 6.85 81 2.48 85 5.78 79 8.47 85 3.30 70 11.4 98 14.4 108 3.47 14 6.63 98 12.8 92 2.37 66 9.67 146 22.5 147 2.08 129 9.69 155 15.2 155 1.90 151
ResPWCR_ROB [144]104.0 3.52 131 7.36 139 1.23 72 4.06 90 6.18 108 1.53 73 4.57 90 6.90 86 1.91 45 7.44 148 12.2 153 3.40 93 11.5 114 14.6 129 4.39 105 7.10 141 13.7 134 2.54 131 7.81 57 17.8 52 1.67 76 9.04 147 14.2 146 1.71 37
LocallyOriented [52]104.2 3.29 106 6.53 111 1.26 109 4.64 140 6.69 147 1.74 110 5.61 127 7.56 120 3.67 128 6.73 131 9.84 137 3.18 24 11.5 114 14.4 108 3.71 61 6.57 86 12.7 80 2.45 101 8.71 119 19.3 97 1.71 85 8.40 109 13.1 103 1.72 47
Correlation Flow [75]105.9 3.27 103 6.50 110 1.20 10 4.42 118 6.56 138 1.65 92 3.98 44 6.10 49 2.30 76 5.93 94 8.94 108 3.32 78 11.6 130 14.6 129 3.84 76 7.63 153 14.8 151 2.65 150 9.95 151 23.0 151 2.01 125 8.73 135 13.7 133 1.71 37
ContinualFlow_ROB [152]106.2 3.79 144 8.09 146 1.25 96 4.03 88 6.11 100 1.61 86 4.76 105 7.58 121 2.38 80 7.09 140 11.7 150 3.17 20 12.2 156 15.4 156 4.49 125 6.35 58 12.3 58 2.29 29 8.71 119 20.0 114 1.61 53 9.02 145 14.2 146 1.78 115
ROF-ND [107]106.8 3.18 87 5.83 46 1.21 24 4.13 99 6.13 103 1.92 135 4.22 66 7.51 118 2.22 68 7.10 141 10.8 144 3.53 114 11.4 98 14.3 97 4.48 118 6.95 129 13.5 129 2.53 129 8.21 85 18.6 81 1.90 113 9.08 149 14.2 146 1.81 143
ACK-Prior [27]107.1 3.30 107 6.56 112 1.21 24 3.81 60 5.78 68 1.42 49 7.13 143 6.90 86 5.04 146 6.02 105 8.78 102 3.70 130 11.7 140 14.7 136 4.57 153 6.95 129 13.5 129 2.50 119 8.36 94 19.2 94 2.53 142 8.56 123 13.4 123 1.73 56
StereoOF-V1MT [119]107.8 3.56 133 7.20 133 1.22 52 4.27 107 6.18 108 1.70 104 6.10 134 6.80 79 3.43 123 7.17 144 9.52 132 4.01 146 11.2 69 14.1 72 4.43 108 6.61 96 12.5 69 2.60 140 9.49 143 21.6 140 2.05 126 8.01 61 12.4 53 1.78 115
HBpMotionGpu [43]107.9 3.63 137 7.28 136 1.35 143 4.78 145 6.69 147 1.92 135 4.33 77 7.01 94 2.56 90 6.46 127 9.81 136 3.40 93 11.5 114 14.4 108 5.69 161 6.83 120 13.3 121 2.55 134 7.40 20 16.9 18 1.51 13 8.30 98 13.0 94 1.79 129
Aniso-Texture [82]110.1 3.11 61 6.09 77 1.21 24 4.51 125 6.62 142 1.75 113 4.77 106 6.43 61 2.08 60 7.44 148 10.9 145 4.80 152 11.6 130 14.6 129 4.51 143 7.49 150 14.7 149 2.71 155 8.28 90 19.1 93 1.61 53 8.68 129 13.6 130 1.74 77
Dynamic MRF [7]112.1 3.19 90 6.41 103 1.22 52 4.11 95 6.21 111 1.56 74 5.37 124 7.35 111 2.70 96 6.74 132 9.18 121 4.19 148 11.1 56 13.9 52 4.48 118 7.02 138 13.7 134 2.62 145 9.26 137 21.4 139 2.23 137 8.57 124 13.3 118 1.80 135
LiteFlowNet [142]112.8 3.86 146 8.34 148 1.22 52 3.80 59 5.75 67 1.44 54 5.33 123 9.45 152 2.66 94 8.72 156 14.4 157 3.88 138 11.8 145 14.8 142 4.50 130 7.03 139 13.7 134 2.40 78 9.07 135 20.4 125 1.69 81 8.13 70 12.7 67 1.78 115
FOLKI [16]113.2 3.64 138 7.12 131 1.65 156 5.22 157 6.72 150 2.36 155 5.20 119 8.08 133 3.96 133 7.93 151 9.33 124 5.52 156 11.2 69 14.0 64 3.70 58 6.56 83 12.6 73 2.74 158 8.00 73 18.2 67 2.88 151 7.96 59 12.3 43 1.78 115
Shiralkar [42]113.4 3.57 134 7.31 137 1.22 52 4.46 123 6.33 126 1.65 92 5.49 125 6.98 91 2.73 97 7.42 147 10.9 145 3.43 98 11.5 114 14.4 108 3.73 66 6.57 86 12.7 80 2.48 113 9.58 144 21.9 145 1.88 111 9.18 151 14.4 150 1.75 87
SimpleFlow [49]114.3 3.10 57 5.97 68 1.22 52 4.19 102 6.11 100 1.64 91 9.91 154 9.43 151 6.53 156 5.58 58 8.29 70 3.30 70 11.6 130 14.6 129 4.43 108 7.42 147 14.6 148 2.56 138 10.7 155 25.2 155 2.73 149 9.16 150 14.4 150 1.73 56
Rannacher [23]114.5 3.31 109 6.72 122 1.25 96 4.60 137 6.66 146 1.72 107 6.36 139 6.54 70 4.25 140 5.91 92 8.87 105 3.49 108 11.5 114 14.5 119 3.63 45 6.73 108 13.1 108 2.53 129 9.35 140 21.7 143 1.98 120 8.70 132 13.7 133 1.75 87
Learning Flow [11]114.8 3.14 70 6.09 77 1.27 114 4.51 125 6.53 136 1.67 98 11.5 160 12.9 160 7.17 159 6.31 119 8.30 72 3.66 127 11.7 140 14.8 142 3.89 78 6.59 91 12.8 92 2.48 113 8.27 89 18.9 87 1.96 119 8.68 129 13.4 123 1.80 135
SILK [79]114.8 3.45 125 6.85 125 1.36 145 5.11 154 6.70 149 2.21 152 11.1 156 9.96 154 6.24 154 6.49 128 8.82 103 3.59 121 11.4 98 14.3 97 3.54 15 6.87 124 13.3 121 2.63 146 7.76 51 17.7 48 1.87 110 8.20 78 12.7 67 1.80 135
OFRF [134]118.0 4.02 148 8.26 147 1.33 138 4.53 129 6.49 133 1.81 122 4.60 94 7.27 106 2.13 63 6.02 105 9.15 118 3.39 90 11.8 145 14.9 146 4.23 94 7.13 142 13.9 142 2.39 75 9.02 130 20.8 134 1.59 47 8.79 137 13.8 137 1.77 109
Adaptive flow [45]118.5 3.60 136 6.30 92 1.54 155 5.14 155 6.79 154 2.14 151 4.52 89 6.60 71 3.01 107 6.54 129 8.64 96 4.23 149 12.1 155 15.2 153 4.09 87 7.57 151 14.9 153 2.64 148 7.75 49 17.8 52 2.28 139 8.47 118 13.3 118 1.71 37
H+S_ROB [137]118.6 3.43 123 6.69 118 1.29 124 4.55 131 6.05 93 1.91 133 11.3 157 12.3 159 7.31 160 6.98 137 8.51 89 3.51 110 11.4 98 14.4 108 3.65 52 6.60 93 12.8 92 2.42 92 9.86 149 22.7 149 2.08 129 8.84 141 13.7 133 1.74 77
UnFlow [129]119.4 4.05 149 8.73 152 1.31 132 4.44 122 6.28 119 1.87 126 4.92 111 7.36 113 2.62 91 5.95 96 9.00 112 3.27 56 12.0 152 15.2 153 4.37 103 7.59 152 14.8 151 2.61 142 7.77 53 17.6 43 1.64 68 10.4 156 15.4 156 2.33 158
StereoFlow [44]120.0 5.35 160 10.3 157 1.42 150 5.03 152 7.21 159 1.76 116 4.14 57 6.94 88 2.01 52 5.83 82 8.55 93 3.33 81 13.7 158 17.3 158 4.70 157 8.71 159 17.2 159 2.70 154 7.88 62 18.1 63 1.61 53 8.82 140 13.9 142 1.79 129
2bit-BM-tele [98]121.3 3.31 109 6.41 103 1.34 142 4.53 129 6.62 142 1.80 121 6.23 137 9.24 147 6.19 153 5.94 95 8.59 95 3.55 117 11.3 87 14.2 87 4.03 85 7.72 155 15.1 155 3.02 159 12.2 159 28.7 160 4.77 161 7.76 37 12.1 32 1.82 145
IIOF-NLDP [131]122.5 3.36 117 6.62 115 1.21 24 4.22 103 6.32 124 1.59 79 5.16 117 7.63 124 2.63 93 6.10 107 9.20 122 3.53 114 11.6 130 14.6 129 4.79 159 7.42 147 14.5 147 2.71 155 12.0 158 28.2 158 3.38 156 8.93 143 13.9 142 1.74 77
SPSA-learn [13]126.0 3.89 147 7.79 142 1.27 114 4.43 120 6.17 105 1.81 122 9.03 152 8.47 140 5.47 150 6.80 133 9.40 127 3.72 132 11.5 114 14.5 119 3.91 80 6.51 75 12.6 73 2.46 104 11.9 156 27.9 157 4.54 159 10.5 158 16.5 158 1.75 87
FFV1MT [106]126.3 4.09 151 8.38 149 1.31 132 4.68 142 6.18 108 2.02 148 6.95 141 11.5 156 3.35 121 7.12 142 9.16 119 3.98 144 11.3 87 14.1 72 3.74 69 6.77 115 12.7 80 2.50 119 9.59 145 21.0 136 2.05 126 8.87 142 13.8 137 1.90 151
SegOF [10]129.0 3.51 129 7.12 131 1.32 134 4.17 101 6.10 98 1.59 79 8.69 149 7.75 129 5.15 147 8.58 155 14.3 156 4.29 151 11.7 140 14.8 142 4.50 130 6.79 118 13.2 118 2.50 119 10.1 152 23.5 152 2.55 144 8.80 138 13.8 137 1.72 47
PGAM+LK [55]131.2 4.08 150 8.41 150 1.65 156 4.74 144 6.45 131 2.27 154 8.87 150 12.2 157 6.88 157 8.06 153 10.9 145 4.83 153 11.4 98 14.3 97 3.90 79 6.83 120 13.2 118 2.55 134 8.26 87 18.9 87 2.27 138 8.55 121 13.3 118 1.90 151
Heeger++ [104]131.5 4.76 153 9.63 154 1.33 138 4.65 141 6.22 114 1.90 130 7.84 146 9.26 149 3.57 126 7.12 142 9.16 119 3.98 144 11.9 149 15.0 149 4.47 115 6.52 76 12.2 51 2.61 142 9.82 147 20.6 129 2.00 123 9.02 145 14.0 144 1.79 129
SLK [47]132.9 3.51 129 6.96 128 1.41 148 4.72 143 6.10 98 1.98 146 9.84 153 7.59 122 5.20 148 7.98 152 11.0 148 6.14 158 11.8 145 14.9 146 3.71 61 6.60 93 12.7 80 2.50 119 9.87 150 22.8 150 2.08 129 8.94 144 14.0 144 2.03 155
WRT [150]135.2 3.42 122 6.71 121 1.23 72 4.33 110 6.06 95 1.89 129 9.93 155 8.00 132 5.95 152 6.98 137 9.01 113 3.77 135 11.9 149 15.1 151 3.97 83 7.82 156 15.4 156 2.64 148 12.5 160 29.5 161 3.47 157 10.5 158 16.6 159 1.80 135
HCIC-L [99]135.3 4.98 157 9.28 153 1.77 159 4.97 151 6.87 157 2.11 149 5.70 129 10.0 155 4.41 144 7.85 150 11.8 151 3.68 129 10.9 41 13.7 42 3.72 65 8.18 158 16.1 158 2.55 134 9.06 133 21.0 136 2.58 146 9.57 154 15.0 154 1.81 143
WOLF_ROB [148]137.4 5.06 158 10.3 157 1.30 128 4.79 147 6.72 150 1.75 113 6.29 138 9.03 145 4.14 137 7.37 146 11.8 151 3.33 81 11.9 149 15.0 149 4.48 118 7.40 146 14.3 145 2.51 123 10.5 154 23.9 153 1.74 90 9.44 152 14.8 152 1.78 115
Pyramid LK [2]145.4 4.16 152 8.44 151 1.74 158 5.83 159 6.82 155 2.76 159 11.4 158 8.60 141 5.89 151 12.4 160 16.7 159 7.03 160 14.3 159 18.1 159 3.92 82 6.69 102 12.2 51 2.63 146 10.3 153 24.0 154 2.45 141 11.1 160 17.4 160 2.55 160
GroupFlow [9]147.9 4.94 156 10.2 156 1.36 145 4.51 125 6.50 134 1.92 135 8.67 148 9.13 146 4.38 143 8.83 158 13.0 154 5.40 155 12.9 157 16.3 157 4.53 151 7.89 157 15.5 157 2.65 150 9.85 148 22.6 148 1.91 115 9.52 153 14.9 153 1.88 149
Periodicity [78]158.6 5.27 159 11.1 160 1.83 160 7.09 160 7.33 160 2.86 160 11.4 158 12.2 157 7.13 158 10.5 159 17.1 160 6.14 158 14.9 160 19.0 160 4.71 158 9.13 160 17.9 160 3.16 160 11.9 156 27.8 156 3.76 158 10.4 156 15.8 157 2.29 156
AVG_FLOW_ROB [141]160.8 14.6 161 20.0 161 3.66 161 11.3 161 12.1 161 4.33 161 13.4 161 14.1 161 7.93 161 19.0 161 25.3 161 10.2 161 18.3 161 23.1 161 5.58 160 16.7 161 32.2 161 4.90 161 16.6 161 28.6 159 4.56 160 15.9 161 19.8 161 4.61 161
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.