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
CtxSyn [137]13.3 2.24 1 3.72 2 1.04 1 2.96 1 4.16 2 1.35 30 4.32 69 3.42 1 3.18 110 4.21 1 5.46 1 3.00 2 9.59 5 11.9 4 3.46 7 5.22 4 9.76 4 2.22 5 7.02 6 15.4 5 1.58 40 6.66 4 10.2 3 1.69 12
CFRF [155]16.4 2.39 3 4.20 3 1.08 2 3.72 43 5.10 18 1.98 140 2.86 2 3.55 2 1.84 36 4.71 2 5.68 2 3.53 107 8.49 2 10.5 2 3.25 3 5.03 3 9.47 3 2.17 2 6.30 3 14.0 3 1.50 5 6.11 2 9.45 2 1.63 4
PMMST [114]18.6 2.90 11 5.43 13 1.20 8 3.50 16 5.05 13 1.27 6 3.56 6 5.46 9 1.82 34 5.38 22 7.92 43 3.41 92 10.2 8 12.8 10 3.60 23 5.76 8 11.0 8 2.26 11 7.39 12 16.9 12 1.53 16 7.57 12 11.8 12 1.72 42
MDP-Flow2 [68]18.7 2.89 10 5.38 11 1.19 4 3.47 11 5.07 15 1.26 1 3.66 15 6.10 43 2.48 80 5.20 6 7.48 15 3.14 15 10.2 8 12.8 10 3.61 29 6.13 29 11.8 26 2.31 32 7.36 11 16.8 9 1.49 3 7.75 27 12.1 26 1.69 12
CyclicGen [154]19.7 2.26 2 3.32 1 1.42 145 3.19 2 4.01 1 2.21 146 2.76 1 4.05 4 1.62 20 4.97 3 5.92 3 3.79 131 8.00 1 9.84 1 3.13 1 3.36 1 5.65 1 2.17 2 4.55 1 9.68 1 1.42 1 4.48 1 6.84 1 1.52 1
SuperSlomo [132]20.6 2.51 4 4.32 4 1.25 93 3.66 35 5.06 14 1.93 133 2.91 3 4.00 3 1.41 7 5.05 4 6.27 4 3.66 121 9.56 4 11.9 4 3.30 5 5.37 6 10.2 6 2.24 6 6.69 4 15.0 4 1.53 16 6.73 5 10.4 5 1.66 5
SepConv-v1 [127]26.8 2.52 5 4.83 5 1.11 3 3.56 24 5.04 11 1.90 124 4.17 55 4.15 5 2.86 97 5.41 31 6.81 5 3.88 132 10.2 8 12.8 10 3.37 6 5.47 7 10.4 7 2.21 4 6.88 5 15.6 6 1.72 83 6.63 3 10.3 4 1.62 3
DeepFlow [86]28.1 2.98 23 5.67 28 1.22 49 3.88 63 5.78 62 1.52 69 3.62 8 5.93 36 1.34 3 5.39 27 7.20 10 3.17 19 11.0 39 13.9 46 3.63 39 5.91 14 11.3 13 2.29 23 7.14 7 16.3 7 1.49 3 7.80 35 12.2 33 1.70 19
CBF [12]32.4 2.83 6 5.20 6 1.23 69 3.97 75 5.79 65 1.56 73 3.62 8 5.47 10 1.60 19 5.21 7 7.12 7 3.29 58 10.1 6 12.6 6 3.62 33 5.97 17 11.5 17 2.31 32 7.76 45 17.8 46 1.61 49 7.60 15 11.9 15 1.76 94
FGIK [136]32.5 2.83 6 5.28 7 1.31 128 3.84 58 5.31 27 1.94 134 4.16 54 4.27 6 2.20 61 5.75 69 7.49 16 3.94 135 8.57 3 10.6 3 3.25 3 4.99 2 9.42 2 2.14 1 5.86 2 13.1 2 1.60 48 6.83 6 10.7 6 1.57 2
DeepFlow2 [108]33.2 2.99 26 5.65 25 1.22 49 3.88 63 5.79 65 1.48 63 3.62 8 6.03 38 1.34 3 5.38 22 7.44 14 3.22 38 11.0 39 13.8 39 3.67 47 5.83 9 11.2 9 2.25 10 7.60 26 17.4 27 1.50 5 7.82 36 12.2 33 1.77 103
SuperFlow [81]35.2 2.94 15 5.56 21 1.24 83 3.99 78 5.78 62 1.67 96 4.06 43 5.55 12 1.83 35 5.52 42 7.07 6 3.20 32 10.2 8 12.7 8 3.68 50 6.13 29 11.8 26 2.24 6 7.68 35 17.5 32 1.77 95 7.44 10 11.6 9 1.69 12
NN-field [71]35.6 2.98 23 5.70 29 1.20 8 3.31 5 4.73 5 1.26 1 4.69 93 5.91 34 2.03 50 5.99 94 9.13 111 3.57 113 10.3 14 12.8 10 3.60 23 6.24 40 12.0 38 2.31 32 7.39 12 16.9 12 1.54 22 7.69 23 12.0 21 1.72 42
NNF-Local [87]35.8 2.92 14 5.51 19 1.19 4 3.30 4 4.71 4 1.26 1 3.65 13 5.91 34 2.29 70 5.76 72 8.70 93 3.55 111 10.3 14 12.9 16 3.60 23 6.42 59 12.4 58 2.34 44 7.57 22 17.4 27 1.74 85 7.61 16 11.9 15 1.72 42
Aniso. Huber-L1 [22]36.6 2.95 18 5.44 15 1.24 83 4.42 112 6.27 112 1.67 96 3.79 26 5.70 19 1.50 12 5.31 12 7.42 13 3.24 47 11.1 50 14.0 58 3.61 29 5.91 14 11.4 15 2.24 6 7.60 26 17.3 21 1.51 10 7.62 18 11.9 15 1.73 51
IROF-TV [53]37.6 3.07 41 5.91 51 1.23 69 3.71 41 5.47 40 1.40 42 3.70 21 6.27 49 1.58 18 5.25 9 7.60 23 3.17 19 11.0 39 13.9 46 4.47 109 6.37 55 12.4 58 2.30 29 7.79 49 17.9 50 1.50 5 7.63 19 11.9 15 1.66 5
CLG-TV [48]37.8 2.94 15 5.45 16 1.25 93 4.26 99 6.17 99 1.60 81 3.68 19 5.73 21 1.73 30 5.36 18 7.41 12 3.32 75 11.1 50 14.0 58 3.57 12 5.88 13 11.3 13 2.26 11 7.58 23 17.0 16 1.57 37 7.75 27 12.1 26 1.72 42
LME [70]38.2 2.95 18 5.59 23 1.19 4 3.68 38 5.50 43 1.38 35 4.06 43 7.00 87 1.71 29 5.38 22 7.92 43 3.18 23 11.2 63 14.1 66 4.51 137 6.29 45 12.2 45 2.31 32 7.33 9 16.8 9 1.51 10 7.83 37 12.3 37 1.70 19
IROF++ [58]38.8 3.03 32 5.77 37 1.20 8 3.59 27 5.31 27 1.33 24 4.32 69 6.61 66 2.25 65 5.06 5 7.14 8 3.16 18 11.0 39 13.9 46 4.44 105 6.34 50 12.3 52 2.27 16 7.54 21 17.3 21 1.64 63 8.09 60 12.7 61 1.69 12
NNF-EAC [103]40.1 3.01 29 5.60 24 1.25 93 3.63 30 5.36 33 1.29 13 4.17 55 7.03 89 2.99 100 5.50 41 7.96 45 3.28 55 11.2 63 14.1 66 3.60 23 5.86 12 11.2 9 2.26 11 7.43 16 17.0 16 1.54 22 7.79 34 12.2 33 1.73 51
CombBMOF [113]40.2 3.16 71 5.88 46 1.24 83 3.54 20 5.24 22 1.34 28 4.01 39 6.45 60 2.20 61 5.62 61 8.22 61 3.29 58 10.7 24 13.5 25 3.62 33 6.20 37 11.9 34 2.27 16 7.78 48 17.3 21 1.56 33 7.75 27 12.1 26 1.71 32
DF-Auto [115]41.5 2.94 15 5.34 9 1.23 69 3.99 78 5.84 70 1.65 90 3.85 31 6.73 70 1.55 17 5.38 22 7.54 18 3.25 49 10.4 17 13.0 17 3.70 52 6.17 36 11.9 34 2.28 19 7.94 59 18.2 61 1.75 90 7.68 21 12.0 21 1.71 32
ALD-Flow [66]43.0 3.28 99 6.45 101 1.24 83 3.81 53 5.73 60 1.41 46 3.62 8 6.28 50 1.35 5 5.58 51 8.39 74 3.04 6 10.8 27 13.5 25 4.15 85 5.96 16 11.4 15 2.29 23 7.34 10 16.8 9 1.51 10 8.25 82 12.9 75 1.70 19
WLIF-Flow [93]43.3 2.95 18 5.53 20 1.20 8 3.66 35 5.41 36 1.39 38 4.26 64 7.17 97 2.54 83 5.30 11 7.57 21 3.29 58 10.7 24 13.5 25 3.70 52 6.74 106 13.1 102 2.48 107 7.40 14 16.9 12 1.53 16 7.87 43 12.3 37 1.69 12
PH-Flow [101]44.3 3.12 57 6.01 66 1.20 8 3.39 7 4.94 8 1.28 11 3.70 21 6.43 55 2.48 80 5.23 8 7.58 22 3.22 38 10.4 17 13.1 19 3.62 33 6.84 117 13.3 115 2.47 101 7.84 52 18.1 57 1.58 40 7.87 43 12.3 37 1.73 51
Second-order prior [8]44.6 2.91 13 5.39 12 1.24 83 4.26 99 6.21 105 1.56 73 3.82 28 6.34 52 1.62 20 5.39 27 7.68 25 3.04 6 11.1 50 13.9 46 3.59 16 6.14 32 11.9 34 2.31 32 7.61 28 17.4 27 1.63 62 7.90 45 12.4 47 1.78 109
p-harmonic [29]45.5 3.00 27 5.72 31 1.21 22 4.33 104 6.24 110 1.69 101 3.60 7 6.07 42 1.39 6 5.70 63 7.87 38 3.29 58 11.0 39 13.8 39 3.63 39 6.02 20 11.6 20 2.34 44 7.67 33 17.5 32 1.70 78 7.92 49 12.4 47 1.72 42
Brox et al. [5]46.2 3.08 44 5.94 56 1.21 22 3.83 56 5.67 52 1.45 56 3.93 35 5.76 23 1.67 24 5.32 13 7.19 9 3.22 38 10.6 21 13.4 23 3.56 10 6.60 87 12.7 74 2.42 86 8.61 102 19.7 104 3.04 147 7.43 9 11.6 9 1.68 10
FMOF [94]47.4 3.16 71 5.92 54 1.23 69 3.48 12 5.07 15 1.28 11 4.59 88 6.82 74 2.78 93 5.71 65 8.42 75 3.40 89 10.4 17 13.0 17 3.67 47 6.49 66 12.6 67 2.28 19 7.64 30 17.5 32 1.48 2 8.06 59 12.6 57 1.67 8
SIOF [67]48.2 3.06 39 5.74 35 1.24 83 4.40 111 6.40 123 1.63 88 4.17 55 7.43 110 1.93 42 5.40 30 7.75 30 3.44 95 10.1 6 12.6 6 3.58 14 6.10 26 11.8 26 2.29 23 7.52 19 17.2 20 1.53 16 7.96 53 12.5 56 1.73 51
MDP-Flow [26]50.0 2.86 8 5.34 9 1.20 8 3.49 15 5.15 19 1.34 28 4.01 39 5.51 11 2.28 67 5.58 51 7.91 42 3.33 78 11.2 63 14.0 58 4.49 119 6.72 100 13.1 102 2.54 125 7.71 38 17.7 42 1.74 85 7.83 37 12.3 37 1.70 19
Local-TV-L1 [65]50.2 3.00 27 5.47 17 1.30 124 4.43 114 6.23 109 1.75 110 3.50 4 5.35 8 1.45 8 5.39 27 7.56 19 3.29 58 11.2 63 14.1 66 3.91 74 6.16 34 11.8 26 2.47 101 7.67 33 17.6 37 1.55 28 7.57 12 11.8 12 1.76 94
OAR-Flow [125]52.0 3.13 62 5.95 58 1.22 49 3.83 56 5.70 55 1.48 63 3.65 13 6.06 39 1.16 1 5.60 56 8.48 80 3.03 3 11.2 63 14.1 66 4.51 137 6.12 28 11.8 26 2.41 83 7.97 62 17.9 50 1.59 42 8.11 63 12.7 61 1.71 32
JOF [141]52.4 3.08 44 5.89 48 1.24 83 3.48 12 5.04 11 1.37 33 3.85 31 5.98 37 2.07 51 5.43 34 7.81 36 3.28 55 11.3 81 14.2 81 4.51 137 6.72 100 13.1 102 2.37 60 7.48 18 17.1 18 1.54 22 8.01 55 12.6 57 1.73 51
Ad-TV-NDC [36]56.2 3.23 88 5.70 29 1.44 147 4.78 139 6.46 126 1.92 128 3.67 16 5.86 30 1.50 12 5.97 91 8.14 59 3.51 103 10.8 27 13.5 25 3.63 39 6.24 40 12.0 38 2.40 72 7.70 36 17.3 21 1.51 10 7.48 11 11.7 11 1.73 51
F-TV-L1 [15]56.2 3.30 101 6.36 94 1.29 120 4.39 110 6.32 118 1.62 87 3.80 27 5.90 33 1.76 31 5.61 58 7.97 47 3.31 72 10.9 35 13.6 30 3.59 16 5.84 10 11.2 9 2.33 42 7.70 36 17.6 37 1.79 97 7.61 16 11.9 15 1.78 109
Modified CLG [34]56.2 2.87 9 5.32 8 1.24 83 4.51 119 6.21 105 1.96 137 4.15 52 6.45 60 2.67 90 5.56 48 7.69 26 3.64 120 10.8 27 13.5 25 3.63 39 6.36 54 12.3 52 2.39 69 7.46 17 17.1 18 1.56 33 7.86 40 12.3 37 1.75 82
CPM-Flow [116]57.4 3.17 77 6.31 89 1.21 22 3.54 20 5.26 24 1.31 19 4.22 61 5.88 32 1.45 8 6.11 102 9.48 123 3.31 72 11.1 50 13.9 46 4.50 124 6.28 44 12.1 42 2.32 39 7.66 31 17.6 37 1.74 85 8.18 68 12.8 69 1.76 94
2DHMM-SAS [92]57.9 3.10 51 5.91 51 1.21 22 4.10 87 6.05 87 1.46 60 4.38 74 7.10 94 2.07 51 5.38 22 7.78 34 3.22 38 11.3 81 14.3 91 4.42 101 6.33 47 12.2 45 2.26 11 7.95 61 18.2 61 1.64 63 8.19 70 12.8 69 1.70 19
TC/T-Flow [76]59.3 3.21 85 6.24 80 1.22 49 3.90 68 5.86 72 1.43 51 3.69 20 5.83 26 1.50 12 5.88 84 8.93 101 3.15 16 11.1 50 13.9 46 4.50 124 6.23 38 12.0 38 2.26 11 8.61 102 19.0 84 1.93 111 8.16 67 12.8 69 1.70 19
COFM [59]59.6 3.03 32 5.76 36 1.22 49 3.55 23 5.21 21 1.32 22 3.82 28 6.98 85 2.81 94 5.41 31 7.97 47 3.30 67 10.8 27 13.6 30 3.62 33 7.01 131 13.7 128 2.40 72 8.00 67 18.5 72 1.98 114 7.91 46 12.4 47 1.80 129
LDOF [28]60.1 3.03 32 5.66 27 1.28 114 4.06 84 5.53 45 2.40 150 4.32 69 6.43 55 2.00 46 5.45 37 7.56 19 3.60 117 10.2 8 12.7 8 3.59 16 6.39 56 12.4 58 2.29 23 8.36 88 19.4 95 2.21 130 7.57 12 11.8 12 1.86 142
DMF_ROB [140]60.2 3.15 68 6.13 74 1.22 49 3.96 72 5.87 73 1.56 73 5.24 115 7.74 122 2.62 86 5.73 68 8.32 67 3.19 28 11.0 39 13.8 39 4.50 124 6.07 23 11.7 23 2.37 60 7.66 31 17.5 32 1.50 5 8.10 61 12.7 61 1.73 51
FlowFields [110]61.3 3.15 68 6.30 86 1.21 22 3.57 25 5.34 31 1.32 22 4.73 95 6.89 78 3.23 113 5.85 79 8.96 104 3.08 8 10.8 27 13.6 30 4.19 86 6.57 80 12.8 86 2.36 56 7.72 39 17.8 46 1.67 71 8.20 72 12.9 75 1.74 72
ComplOF-FED-GPU [35]61.6 3.23 88 6.40 96 1.22 49 3.73 45 5.62 51 1.44 53 5.23 114 6.06 39 3.23 113 5.53 43 8.25 62 3.29 58 11.1 50 13.9 46 4.21 87 6.11 27 11.8 26 2.32 39 8.16 75 18.5 72 1.61 49 8.29 89 12.9 75 1.71 32
Layers++ [37]61.6 2.96 21 5.56 21 1.22 49 3.29 3 4.64 3 1.26 1 4.07 45 7.24 98 3.08 104 5.48 38 8.10 55 3.25 49 12.0 146 15.2 147 4.62 149 7.29 139 14.3 139 2.44 93 7.63 29 17.5 32 1.54 22 7.84 39 12.3 37 1.70 19
nLayers [57]61.6 3.03 32 5.72 31 1.21 22 3.48 12 5.09 17 1.31 19 5.60 120 7.52 113 4.26 135 5.61 58 8.33 68 3.29 58 11.6 124 14.6 123 4.31 92 6.66 93 12.9 95 2.40 72 7.58 23 17.3 21 1.59 42 7.94 50 12.4 47 1.69 12
TV-L1-MCT [64]61.8 3.17 77 6.05 69 1.22 49 3.87 60 5.82 68 1.40 42 4.48 81 7.75 123 2.24 64 5.37 20 7.76 32 3.24 47 11.6 124 14.7 130 4.31 92 6.08 24 11.7 23 2.31 32 8.07 71 18.6 75 2.15 128 7.68 21 12.0 21 1.68 10
AdaConv-v1 [126]63.0 3.57 128 6.88 121 1.41 143 4.34 107 5.67 52 2.52 152 5.00 107 5.86 30 2.98 99 6.91 130 8.89 100 4.89 148 10.2 8 12.8 10 3.21 2 5.33 5 10.1 5 2.27 16 7.30 8 16.6 8 1.92 110 6.94 7 10.8 7 1.67 8
CRTflow [80]63.2 3.09 49 5.91 51 1.27 110 4.35 108 6.31 116 1.68 99 4.15 52 7.26 99 1.84 36 5.33 15 7.51 17 3.38 84 11.0 39 13.8 39 4.48 112 6.09 25 11.7 23 2.30 29 8.55 99 19.8 105 1.55 28 8.19 70 12.8 69 1.72 42
TC-Flow [46]63.2 3.31 103 6.70 113 1.22 49 3.91 70 5.95 75 1.45 56 3.64 12 5.84 27 1.28 2 5.70 63 8.50 82 3.22 38 11.2 63 14.1 66 4.44 105 6.34 50 12.3 52 2.41 83 7.79 49 17.9 50 1.55 28 8.42 104 13.2 106 1.74 72
DPOF [18]63.5 3.34 109 6.82 117 1.29 120 3.40 8 4.93 7 1.29 13 5.00 107 6.36 53 3.40 116 5.86 80 8.94 102 3.51 103 11.0 39 13.8 39 3.59 16 6.56 77 12.7 74 2.28 19 7.99 64 18.2 61 1.55 28 8.24 79 12.9 75 1.70 19
AGIF+OF [85]63.8 3.12 57 5.95 58 1.20 8 3.64 32 5.39 34 1.40 42 3.96 37 6.44 59 2.28 67 5.48 38 8.03 51 3.25 49 11.4 92 14.3 91 4.49 119 6.91 122 13.5 123 2.37 60 7.85 54 17.9 50 1.54 22 8.44 108 13.2 106 1.73 51
PGM-C [120]65.1 3.17 77 6.29 84 1.21 22 3.58 26 5.32 29 1.33 24 5.01 109 6.14 46 1.90 40 6.14 105 9.63 128 3.23 44 11.2 63 14.1 66 4.50 124 6.14 32 11.8 26 2.34 44 8.20 77 18.9 81 1.59 42 8.46 111 13.3 112 1.73 51
Classic++ [32]65.7 3.05 37 5.85 42 1.24 83 4.08 86 6.08 90 1.52 69 3.74 24 5.58 15 1.53 16 5.72 67 8.12 57 3.21 34 11.4 92 14.3 91 3.74 63 6.68 95 13.0 97 2.42 86 8.35 87 19.2 88 1.62 58 8.21 74 12.9 75 1.73 51
Sparse-NonSparse [56]65.9 3.07 41 5.88 46 1.21 22 3.61 28 5.33 30 1.33 24 4.29 67 7.47 111 2.19 60 5.37 20 7.74 28 3.21 34 11.5 108 14.5 113 4.36 96 6.66 93 12.9 95 2.41 83 8.69 108 20.1 111 1.67 71 8.27 86 13.0 88 1.70 19
EAI-Flow [152]66.1 3.37 112 6.27 83 1.32 131 3.79 50 5.59 48 1.52 69 4.30 68 7.09 92 2.39 76 5.60 56 8.34 69 2.96 1 11.2 63 14.1 66 4.34 95 6.04 22 11.6 20 2.34 44 7.72 39 17.6 37 3.12 148 7.77 32 12.1 26 1.82 139
ProbFlowFields [128]67.3 3.15 68 6.32 91 1.21 22 3.53 17 5.26 24 1.29 13 5.03 110 7.35 105 3.73 123 5.43 34 7.97 47 3.25 49 11.1 50 14.0 58 4.50 124 6.48 64 12.6 67 2.55 128 7.99 64 18.4 71 2.57 139 7.78 33 12.2 33 1.75 82
BlockOverlap [61]67.4 2.98 23 5.47 17 1.33 134 4.38 109 6.09 91 1.88 122 4.26 64 5.57 14 3.14 107 5.56 48 7.32 11 4.14 141 11.1 50 13.9 46 3.77 66 6.41 57 12.3 52 2.54 125 7.75 43 17.4 27 3.02 146 7.32 8 11.4 8 1.78 109
ProFlow_ROB [147]68.0 3.16 71 6.30 86 1.21 22 3.77 49 5.71 57 1.39 38 4.12 49 5.27 7 1.62 20 6.15 106 9.68 129 3.11 12 11.5 108 14.5 113 4.50 124 5.85 11 11.2 9 2.24 6 8.50 96 19.4 95 1.56 33 8.70 126 13.6 124 1.85 141
PMF [73]68.2 3.14 64 6.13 74 1.20 8 3.73 45 5.60 49 1.27 6 5.24 115 8.98 138 3.76 124 5.75 69 8.56 88 3.28 55 10.8 27 13.6 30 3.62 33 6.55 74 12.7 74 2.35 53 8.41 93 19.5 101 1.64 63 8.57 118 13.4 117 1.70 19
MLDP_OF [89]68.2 3.08 44 5.98 63 1.21 22 4.01 80 6.01 84 1.49 66 3.67 16 6.14 46 1.47 10 5.78 73 8.13 58 3.95 136 11.3 81 14.2 81 3.87 71 6.71 98 13.0 97 2.51 117 7.73 42 17.7 42 1.71 80 8.18 68 12.8 69 1.76 94
S2F-IF [123]68.2 3.26 94 6.66 110 1.20 8 3.53 17 5.25 23 1.29 13 4.11 48 6.64 67 2.34 72 5.89 85 9.06 109 3.08 8 11.4 92 14.3 91 4.51 137 6.41 57 12.4 58 2.40 72 7.84 52 18.1 57 1.76 93 8.33 96 13.1 97 1.75 82
OFLAF [77]69.0 3.10 51 5.98 63 1.20 8 3.44 9 5.03 10 1.26 1 3.73 23 5.82 25 1.66 23 5.33 15 7.74 28 3.10 11 11.6 124 14.7 130 4.50 124 6.58 84 12.8 86 2.48 107 9.33 133 21.6 134 2.06 122 8.45 110 13.2 106 1.80 129
Sparse Occlusion [54]69.0 3.16 71 6.18 78 1.23 69 4.14 94 6.24 110 1.45 56 3.67 16 5.84 27 1.52 15 5.61 58 8.26 63 3.15 16 11.5 108 14.4 102 4.48 112 6.26 42 12.1 42 2.46 98 8.52 97 19.6 103 1.54 22 8.28 88 13.0 88 1.75 82
FlowNetS+ft+v [112]69.1 3.07 41 5.81 39 1.28 114 4.57 128 6.29 114 2.41 151 4.01 39 5.64 17 2.13 57 5.55 46 7.77 33 3.88 132 11.3 81 14.2 81 4.46 108 5.99 19 11.5 17 2.35 53 8.63 105 20.0 108 1.62 58 7.70 24 12.0 21 1.74 72
TF+OM [100]69.3 3.33 108 6.83 118 1.25 93 3.65 33 5.43 38 1.47 62 3.82 28 6.43 55 1.68 26 6.01 96 9.04 108 3.19 28 11.2 63 14.1 66 4.38 98 6.46 63 12.5 63 2.34 44 8.30 86 19.2 88 1.86 103 8.05 58 12.6 57 1.75 82
HAST [109]69.3 3.01 29 5.73 33 1.21 22 3.45 10 5.01 9 1.27 6 6.39 134 8.24 130 4.09 129 5.43 34 7.96 45 3.03 3 11.2 63 14.2 81 3.59 16 7.47 143 14.7 143 2.47 101 8.68 107 20.1 111 1.53 16 8.35 99 13.1 97 1.77 103
FlowFields+ [130]69.4 3.14 64 6.26 82 1.22 49 3.54 20 5.27 26 1.30 18 4.74 98 7.10 94 3.20 111 6.01 96 9.35 119 3.11 12 11.1 50 13.9 46 4.50 124 6.57 80 12.8 86 2.40 72 7.89 58 18.2 61 1.80 98 8.22 76 12.9 75 1.73 51
Filter Flow [19]70.5 3.13 62 5.90 49 1.28 114 4.56 127 6.38 122 1.85 120 4.22 61 6.28 50 2.10 55 5.91 86 7.97 47 3.44 95 10.4 17 13.1 19 3.69 51 6.43 61 12.5 63 2.40 72 8.17 76 18.8 80 1.62 58 7.94 50 12.4 47 1.78 109
EpicFlow [102]73.6 3.17 77 6.34 92 1.21 22 3.79 50 5.70 55 1.44 53 4.28 66 5.73 21 1.67 24 6.37 118 10.1 134 3.39 87 11.2 63 14.1 66 4.50 124 6.23 38 12.0 38 2.38 67 8.11 73 18.5 72 1.76 93 8.76 130 13.8 131 1.74 72
LSM [39]73.6 3.12 57 6.05 69 1.21 22 3.68 38 5.47 40 1.33 24 4.38 74 7.66 120 2.01 47 5.55 46 8.19 60 3.19 28 11.5 108 14.5 113 4.43 102 6.83 114 13.3 115 2.37 60 8.70 109 20.1 111 1.72 83 8.34 98 13.1 97 1.71 32
Black & Anandan [4]73.9 3.22 87 5.87 44 1.30 124 4.82 142 6.55 131 1.78 115 7.16 138 7.10 94 3.93 126 6.25 112 8.49 81 3.35 82 10.9 35 13.7 36 3.56 10 6.33 47 12.2 45 2.37 60 8.23 80 18.6 75 1.64 63 7.67 20 11.9 15 1.69 12
TCOF [69]74.5 3.12 57 5.94 56 1.21 22 4.60 131 6.64 138 1.76 113 4.13 50 7.30 101 1.81 32 5.42 33 7.88 39 3.25 49 11.3 81 14.2 81 3.63 39 6.42 59 12.4 58 2.36 56 9.08 130 21.0 130 1.59 42 8.37 100 13.1 97 1.76 94
RNLOD-Flow [121]74.6 3.06 39 5.87 44 1.21 22 3.96 72 5.97 81 1.42 48 4.39 76 8.08 127 2.44 78 5.35 17 7.75 30 3.18 23 11.5 108 14.5 113 4.49 119 6.71 98 13.1 102 2.43 90 7.85 54 18.0 55 2.18 129 8.44 108 13.2 106 1.73 51
Ramp [62]75.6 3.11 55 5.96 60 1.22 49 3.61 28 5.34 31 1.40 42 4.91 104 8.45 133 3.20 111 5.29 10 7.66 24 3.21 34 11.5 108 14.5 113 4.31 92 6.88 121 13.4 119 2.48 107 8.73 115 20.2 115 1.52 15 8.29 89 13.0 88 1.73 51
Fusion [6]76.1 3.04 36 5.86 43 1.22 49 3.75 48 5.47 40 1.42 48 4.08 46 5.55 12 3.08 104 5.80 75 8.10 55 3.19 28 11.4 92 14.3 91 3.73 60 6.99 128 13.7 128 2.60 134 8.40 92 19.4 95 1.65 68 8.50 113 13.3 112 1.80 129
Classic+NL [31]76.7 3.10 51 5.92 54 1.23 69 3.66 35 5.40 35 1.39 38 4.78 101 8.42 132 3.01 102 5.36 18 7.78 34 3.30 67 11.5 108 14.5 113 4.24 89 6.73 102 13.1 102 2.40 72 8.74 116 20.2 115 1.70 78 8.29 89 13.0 88 1.71 32
AggregFlow [97]76.7 3.80 139 8.08 139 1.23 69 3.87 60 5.83 69 1.43 51 4.21 60 6.79 72 2.85 96 6.11 102 9.36 120 3.31 72 10.6 21 13.3 21 3.67 47 6.13 29 11.8 26 2.34 44 8.70 109 19.8 105 2.30 134 8.27 86 13.0 88 1.75 82
ComponentFusion [96]76.8 3.41 114 7.08 124 1.20 8 3.63 30 5.44 39 1.27 6 4.20 59 6.49 62 2.43 77 5.59 54 8.38 73 3.32 75 11.4 92 14.4 102 4.11 83 6.26 42 12.1 42 2.35 53 9.30 132 21.6 134 2.80 144 8.68 123 13.6 124 1.73 51
Bartels [41]78.6 3.48 121 7.24 128 1.30 124 4.02 81 6.12 96 1.68 99 3.74 24 5.80 24 1.95 44 5.87 82 8.44 77 3.78 130 10.3 14 12.8 10 3.75 65 6.77 109 13.0 97 2.73 151 7.53 20 17.3 21 2.72 142 8.13 64 12.7 61 1.77 103
Occlusion-TV-L1 [63]78.8 3.14 64 6.13 74 1.25 93 4.47 118 6.61 134 1.66 93 3.51 5 5.71 20 1.70 28 6.33 114 9.58 127 3.51 103 11.0 39 13.9 46 3.57 12 6.48 64 12.6 67 2.52 122 8.36 88 18.1 57 2.00 117 8.32 95 13.0 88 1.79 123
CNN-flow-warp+ref [117]79.6 2.90 11 5.43 13 1.25 93 4.10 87 5.95 75 1.83 119 4.92 105 7.63 118 2.45 79 6.13 104 7.85 37 3.72 126 11.3 81 14.2 81 4.51 137 6.03 21 11.6 20 2.46 98 9.00 123 20.8 128 1.65 68 7.91 46 12.4 47 1.76 94
LFNet_ROB [150]79.6 3.65 133 7.73 134 1.23 69 3.88 63 5.80 67 1.49 66 4.57 85 8.96 137 2.02 49 5.62 61 8.44 77 3.18 23 11.0 39 13.8 39 4.47 109 7.19 138 14.1 138 2.47 101 7.59 25 17.4 27 1.82 100 8.10 61 12.7 61 1.78 109
Classic+CPF [83]79.8 3.12 57 5.96 60 1.21 22 3.72 43 5.51 44 1.39 38 4.39 76 7.38 108 2.27 66 5.32 13 7.70 27 3.18 23 11.7 134 14.8 136 4.50 124 7.18 137 14.0 137 2.45 95 8.79 117 20.2 115 1.57 37 8.71 128 13.7 127 1.73 51
HBM-GC [105]79.9 3.08 44 5.90 49 1.26 106 3.97 75 6.04 86 1.41 46 3.92 34 5.62 16 2.87 98 5.54 45 8.03 51 3.21 34 11.7 134 14.7 130 4.58 148 7.66 148 15.0 148 2.69 147 8.36 88 19.3 91 1.55 28 7.86 40 12.3 37 1.76 94
Efficient-NL [60]80.0 3.05 37 5.77 37 1.21 22 3.90 68 5.84 70 1.38 35 5.90 126 6.94 82 4.19 132 5.59 54 8.09 54 3.20 32 11.5 108 14.4 102 4.40 100 6.87 118 13.4 119 2.40 72 8.85 118 20.5 120 1.68 75 8.57 118 13.4 117 1.66 5
2D-CLG [1]80.4 3.01 29 5.65 25 1.28 114 4.59 130 6.17 99 1.95 136 5.18 112 6.06 39 3.15 109 6.01 96 7.88 39 3.97 137 11.4 92 14.4 102 4.69 150 5.98 18 11.5 17 2.45 95 8.89 121 20.5 120 1.67 71 7.74 26 12.0 21 1.71 32
Horn & Schunck [3]80.7 3.16 71 5.83 40 1.26 106 4.91 143 6.65 139 1.92 128 6.13 129 6.85 75 3.53 119 6.80 127 9.10 110 3.57 113 10.9 35 13.7 36 3.59 16 6.16 34 11.9 34 2.32 39 8.63 105 19.5 101 1.84 102 7.91 46 12.3 37 1.73 51
FC-2Layers-FF [74]80.9 3.18 81 6.16 77 1.22 49 3.33 6 4.73 5 1.35 30 4.34 73 7.09 92 3.11 106 5.56 48 8.29 64 3.29 58 11.5 108 14.5 113 4.48 112 7.00 129 13.7 128 2.48 107 8.92 122 20.6 123 1.71 80 8.30 92 13.0 88 1.73 51
FESL [72]81.5 3.16 71 6.02 67 1.21 22 3.65 33 5.42 37 1.35 30 4.39 76 7.61 117 2.18 59 5.71 65 8.35 71 3.30 67 11.6 124 14.7 130 4.51 137 6.73 102 13.1 102 2.47 101 8.70 109 20.1 111 1.56 33 8.42 104 13.2 106 1.75 82
SRR-TVOF-NL [91]81.6 3.32 106 6.46 102 1.23 69 3.96 72 5.96 78 1.59 77 4.68 91 7.90 125 3.52 118 5.99 94 8.77 95 3.23 44 11.2 63 14.1 66 4.45 107 6.79 112 13.2 112 2.31 32 7.88 56 18.0 55 1.50 5 8.37 100 13.1 97 1.75 82
RFlow [90]81.8 3.08 44 5.99 65 1.23 69 4.33 104 6.31 116 1.66 93 4.83 102 7.32 102 3.14 107 5.87 82 8.72 94 3.47 98 11.1 50 14.0 58 3.60 23 6.54 73 12.7 74 2.39 69 8.54 98 19.8 105 1.61 49 8.26 84 12.9 75 1.80 129
TriFlow [95]83.4 3.71 136 7.95 138 1.25 93 4.31 103 6.36 121 1.71 104 4.05 42 6.86 77 1.84 36 6.21 110 9.44 122 3.17 19 11.3 81 14.2 81 4.48 112 6.76 108 13.1 102 2.29 23 8.01 69 18.2 61 1.75 90 8.24 79 12.9 75 1.70 19
OFH [38]83.8 3.18 81 6.29 84 1.23 69 4.11 89 5.96 78 1.61 84 4.68 91 8.40 131 1.68 26 5.84 77 8.99 105 3.03 3 11.3 81 14.2 81 4.25 91 6.30 46 12.2 45 2.40 72 8.59 100 19.3 91 1.89 106 8.55 115 13.4 117 1.97 148
3DFlow [135]84.2 3.26 94 6.37 95 1.21 22 3.70 40 5.55 46 1.46 60 4.51 83 6.52 63 2.28 67 5.84 77 8.84 98 3.59 115 11.2 63 14.1 66 3.79 68 7.04 134 13.7 128 2.68 146 8.59 100 19.4 95 1.82 100 8.26 84 12.9 75 1.77 103
Nguyen [33]85.0 3.26 94 6.11 73 1.33 134 4.94 144 6.51 129 1.91 126 4.09 47 7.32 102 1.96 45 6.19 109 8.53 85 3.60 117 11.1 50 13.9 46 3.58 14 6.55 74 12.7 74 2.36 56 9.44 135 21.8 138 1.80 98 7.86 40 12.3 37 1.74 72
PWC-Net_ROB [148]85.1 3.66 135 7.76 135 1.21 22 3.91 70 5.97 81 1.37 33 3.88 33 6.73 70 1.48 11 6.36 116 10.1 134 3.13 14 11.8 139 14.9 140 4.49 119 6.78 111 13.1 102 2.34 44 7.72 39 17.7 42 1.66 70 8.57 118 13.5 122 1.88 143
S2D-Matching [84]85.2 3.21 85 6.22 79 1.22 49 3.97 75 5.95 75 1.48 63 4.57 85 7.70 121 2.84 95 5.48 38 8.06 53 3.48 100 11.4 92 14.3 91 4.14 84 6.97 126 13.6 126 2.56 132 8.09 72 18.6 75 1.74 85 8.21 74 12.9 75 1.76 94
CostFilter [40]85.2 3.46 120 7.24 128 1.19 4 3.71 41 5.60 49 1.27 6 5.63 122 9.41 144 3.86 125 6.37 118 10.1 134 3.23 44 11.2 63 14.0 58 3.78 67 6.35 52 12.2 45 2.40 72 8.86 120 20.6 123 1.69 76 8.80 132 13.8 131 1.74 72
SVFilterOh [111]85.7 3.23 88 6.35 93 1.23 69 3.53 17 5.19 20 1.31 19 5.91 127 8.20 129 4.22 133 5.75 69 8.52 84 3.43 93 11.4 92 14.3 91 4.53 145 6.97 126 13.6 126 2.38 67 7.94 59 18.3 68 1.57 37 8.31 94 13.0 88 1.79 123
Steered-L1 [118]86.6 2.97 22 5.73 33 1.21 22 3.81 53 5.72 59 1.60 81 8.15 141 9.24 141 6.46 149 6.42 120 9.21 117 4.28 144 11.4 92 14.3 91 3.80 69 6.52 70 12.7 74 2.43 90 8.20 77 19.0 84 2.54 137 8.33 96 13.1 97 1.70 19
FlowNet2 [122]86.8 4.84 148 10.1 149 1.29 120 4.11 89 6.13 97 1.61 84 4.73 95 7.06 90 2.36 73 6.36 116 10.0 132 3.38 84 11.2 63 14.1 66 3.71 55 6.44 62 12.5 63 2.33 42 8.45 94 19.4 95 1.61 49 8.03 57 12.6 57 1.77 103
Adaptive [20]86.8 3.24 91 6.44 99 1.25 93 4.57 128 6.61 134 1.72 105 3.94 36 6.12 45 1.81 32 5.86 80 8.66 91 3.47 98 11.6 124 14.6 123 3.59 16 6.55 74 12.7 74 2.51 117 9.03 125 20.6 123 1.59 42 8.13 64 12.7 61 1.78 109
TVL1_ROB [139]87.0 3.32 106 6.25 81 1.36 140 5.03 146 6.77 146 1.94 134 4.50 82 6.70 69 2.55 84 6.22 111 8.66 91 3.63 119 10.8 27 13.6 30 3.63 39 6.52 70 12.7 74 2.43 90 9.03 125 20.7 127 2.13 126 7.72 25 12.1 26 1.70 19
IAOF [50]87.3 3.53 126 6.60 108 1.32 131 5.39 152 7.19 152 1.96 137 5.81 124 7.32 102 3.63 121 6.15 106 8.34 69 3.72 126 11.1 50 14.0 58 3.60 23 6.50 67 12.6 67 2.34 44 8.28 84 19.0 84 1.53 16 7.94 50 12.4 47 1.73 51
Complementary OF [21]89.0 3.48 121 7.32 132 1.20 8 3.89 66 5.96 78 1.45 56 8.94 145 6.94 82 5.45 143 6.33 114 10.0 132 3.09 10 11.3 81 14.2 81 4.24 89 6.33 47 12.3 52 2.42 86 8.62 104 19.3 91 1.75 90 9.07 142 14.3 143 1.72 42
FF++_ROB [146]90.2 3.27 97 6.67 111 1.20 8 3.74 47 5.58 47 1.38 35 4.86 103 7.42 109 2.99 100 6.57 124 10.4 137 3.54 110 11.5 108 14.5 113 4.51 137 6.62 91 12.8 86 2.47 101 7.97 62 18.3 68 1.90 107 8.24 79 12.9 75 1.78 109
TV-L1-improved [17]90.6 3.09 49 6.03 68 1.25 93 4.55 125 6.59 133 1.70 102 5.88 125 5.66 18 4.09 129 5.53 43 7.88 39 3.22 38 11.4 92 14.4 102 3.61 29 6.73 102 13.1 102 2.51 117 9.48 136 22.1 140 1.94 112 8.25 82 12.9 75 1.79 123
AugFNG_ROB [144]90.8 3.73 137 7.90 137 1.25 93 4.12 92 6.02 85 1.74 107 4.70 94 8.79 136 1.94 43 8.14 148 13.4 149 3.29 58 12.0 146 15.1 145 4.50 124 6.50 67 12.6 67 2.28 19 8.03 70 18.3 68 1.62 58 7.75 27 12.1 26 1.75 82
TI-DOFE [24]91.1 3.41 114 6.44 99 1.44 147 5.20 150 6.82 149 2.01 142 4.19 58 6.41 54 1.88 39 6.98 131 9.50 124 3.70 124 10.8 27 13.6 30 3.61 29 6.59 85 12.8 86 2.36 56 8.13 74 18.2 61 1.77 95 8.53 114 12.4 47 2.33 152
EPPM w/o HM [88]91.6 3.35 110 6.86 120 1.21 22 3.85 59 5.88 74 1.29 13 7.03 136 9.47 147 3.97 128 6.15 106 9.51 125 3.38 84 10.6 21 13.3 21 3.62 33 7.00 129 13.7 128 2.37 60 8.85 118 20.5 120 2.62 141 8.42 104 13.2 106 1.76 94
GraphCuts [14]93.0 3.65 133 7.01 123 1.27 110 3.89 66 5.71 57 1.59 77 7.54 139 5.84 27 4.31 136 5.98 93 8.42 75 3.45 97 11.4 92 14.4 102 4.09 81 6.56 77 12.8 86 2.30 29 8.70 109 20.2 115 1.98 114 8.59 122 13.5 122 1.73 51
BriefMatch [124]93.6 3.25 93 6.49 103 1.25 93 3.87 60 5.67 52 1.97 139 6.16 130 6.17 48 4.79 139 6.83 129 8.37 72 5.73 151 11.0 39 13.8 39 3.73 60 6.75 107 13.0 97 2.61 136 7.99 64 17.9 50 3.29 149 8.22 76 12.8 69 2.32 151
NL-TV-NCC [25]95.0 3.37 112 6.58 107 1.24 83 4.23 98 6.41 124 1.49 66 4.39 76 6.68 68 2.07 51 7.19 139 11.2 143 3.35 82 10.7 24 13.4 23 4.00 78 6.95 123 13.4 119 2.44 93 9.06 127 20.0 108 2.13 126 8.42 104 13.1 97 1.78 109
EPMNet [133]95.5 4.90 149 10.5 153 1.28 114 4.04 83 5.98 83 1.60 81 4.73 95 7.06 90 2.36 73 8.74 151 15.0 152 3.48 100 11.2 63 14.1 66 3.71 55 6.70 97 13.0 97 2.34 44 8.45 94 19.4 95 1.61 49 8.38 102 13.1 97 1.78 109
IAOF2 [51]96.6 3.43 117 6.70 113 1.28 114 4.62 133 6.77 146 1.74 107 4.41 80 6.89 78 2.12 56 5.97 91 8.53 85 3.33 78 11.6 124 14.7 130 4.06 80 6.87 118 13.4 119 2.51 117 8.26 81 18.7 79 1.61 49 8.22 76 12.9 75 1.74 72
TriangleFlow [30]97.8 3.24 91 6.31 89 1.26 106 4.29 102 6.29 114 1.66 93 4.67 90 6.85 75 2.48 80 5.78 73 8.47 79 3.30 67 11.4 92 14.4 102 3.47 8 6.63 92 12.8 86 2.37 60 9.67 140 22.5 141 2.08 123 9.69 149 15.2 149 1.90 145
ResPWCR_ROB [145]98.7 3.52 125 7.36 133 1.23 69 4.06 84 6.18 102 1.53 72 4.57 85 6.90 80 1.91 41 7.44 142 12.2 147 3.40 89 11.5 108 14.6 123 4.39 99 7.10 135 13.7 128 2.54 125 7.81 51 17.8 46 1.67 71 9.04 141 14.2 140 1.71 32
LocallyOriented [52]98.7 3.29 100 6.53 105 1.26 106 4.64 134 6.69 141 1.74 107 5.61 121 7.56 114 3.67 122 6.73 125 9.84 131 3.18 23 11.5 108 14.4 102 3.71 55 6.57 80 12.7 74 2.45 95 8.71 113 19.3 91 1.71 80 8.40 103 13.1 97 1.72 42
Correlation Flow [75]100.4 3.27 97 6.50 104 1.20 8 4.42 112 6.56 132 1.65 90 3.98 38 6.10 43 2.30 71 5.93 88 8.94 102 3.32 75 11.6 124 14.6 123 3.84 70 7.63 147 14.8 145 2.65 144 9.95 145 23.0 145 2.01 119 8.73 129 13.7 127 1.71 32
ContinualFlow_ROB [153]100.9 3.79 138 8.09 140 1.25 93 4.03 82 6.11 94 1.61 84 4.76 99 7.58 115 2.38 75 7.09 134 11.7 144 3.17 19 12.2 150 15.4 150 4.49 119 6.35 52 12.3 52 2.29 23 8.71 113 20.0 108 1.61 49 9.02 139 14.2 140 1.78 109
ROF-ND [107]100.9 3.18 81 5.83 40 1.21 22 4.13 93 6.13 97 1.92 128 4.22 61 7.51 112 2.22 63 7.10 135 10.8 138 3.53 107 11.4 92 14.3 91 4.48 112 6.95 123 13.5 123 2.53 123 8.21 79 18.6 75 1.90 107 9.08 143 14.2 140 1.81 137
ACK-Prior [27]101.5 3.30 101 6.56 106 1.21 22 3.81 53 5.78 62 1.42 48 7.13 137 6.90 80 5.04 140 6.02 99 8.78 96 3.70 124 11.7 134 14.7 130 4.57 147 6.95 123 13.5 123 2.50 113 8.36 88 19.2 88 2.53 136 8.56 117 13.4 117 1.73 51
StereoOF-V1MT [119]102.1 3.56 127 7.20 127 1.22 49 4.27 101 6.18 102 1.70 102 6.10 128 6.80 73 3.43 117 7.17 138 9.52 126 4.01 140 11.2 63 14.1 66 4.43 102 6.61 90 12.5 63 2.60 134 9.49 137 21.6 134 2.05 120 8.01 55 12.4 47 1.78 109
HBpMotionGpu [43]102.2 3.63 131 7.28 130 1.35 139 4.78 139 6.69 141 1.92 128 4.33 72 7.01 88 2.56 85 6.46 121 9.81 130 3.40 89 11.5 108 14.4 102 5.69 155 6.83 114 13.3 115 2.55 128 7.40 14 16.9 12 1.51 10 8.30 92 13.0 88 1.79 123
Aniso-Texture [82]104.5 3.11 55 6.09 71 1.21 22 4.51 119 6.62 136 1.75 110 4.77 100 6.43 55 2.08 54 7.44 142 10.9 139 4.80 146 11.6 124 14.6 123 4.51 137 7.49 144 14.7 143 2.71 149 8.28 84 19.1 87 1.61 49 8.68 123 13.6 124 1.74 72
Dynamic MRF [7]106.5 3.19 84 6.41 97 1.22 49 4.11 89 6.21 105 1.56 73 5.37 118 7.35 105 2.70 91 6.74 126 9.18 115 4.19 142 11.1 50 13.9 46 4.48 112 7.02 132 13.7 128 2.62 139 9.26 131 21.4 133 2.23 131 8.57 118 13.3 112 1.80 129
FOLKI [16]107.2 3.64 132 7.12 125 1.65 150 5.22 151 6.72 144 2.36 149 5.20 113 8.08 127 3.96 127 7.93 145 9.33 118 5.52 150 11.2 63 14.0 58 3.70 52 6.56 77 12.6 67 2.74 152 8.00 67 18.2 61 2.88 145 7.96 53 12.3 37 1.78 109
LiteFlowNet [143]107.2 3.86 140 8.34 142 1.22 49 3.80 52 5.75 61 1.44 53 5.33 117 9.45 146 2.66 89 8.72 150 14.4 151 3.88 132 11.8 139 14.8 136 4.50 124 7.03 133 13.7 128 2.40 72 9.07 129 20.4 119 1.69 76 8.13 64 12.7 61 1.78 109
Shiralkar [42]107.8 3.57 128 7.31 131 1.22 49 4.46 117 6.33 120 1.65 90 5.49 119 6.98 85 2.73 92 7.42 141 10.9 139 3.43 93 11.5 108 14.4 102 3.73 60 6.57 80 12.7 74 2.48 107 9.58 138 21.9 139 1.88 105 9.18 145 14.4 144 1.75 82
SimpleFlow [49]108.8 3.10 51 5.97 62 1.22 49 4.19 96 6.11 94 1.64 89 9.91 148 9.43 145 6.53 150 5.58 51 8.29 64 3.30 67 11.6 124 14.6 123 4.43 102 7.42 141 14.6 142 2.56 132 10.7 149 25.2 149 2.73 143 9.16 144 14.4 144 1.73 51
Rannacher [23]108.9 3.31 103 6.72 116 1.25 93 4.60 131 6.66 140 1.72 105 6.36 133 6.54 64 4.25 134 5.91 86 8.87 99 3.49 102 11.5 108 14.5 113 3.63 39 6.73 102 13.1 102 2.53 123 9.35 134 21.7 137 1.98 114 8.70 126 13.7 127 1.75 82
SILK [79]108.9 3.45 119 6.85 119 1.36 140 5.11 148 6.70 143 2.21 146 11.1 150 9.96 148 6.24 148 6.49 122 8.82 97 3.59 115 11.4 92 14.3 91 3.54 9 6.87 118 13.3 115 2.63 140 7.76 45 17.7 42 1.87 104 8.20 72 12.7 61 1.80 129
Learning Flow [11]109.0 3.14 64 6.09 71 1.27 110 4.51 119 6.53 130 1.67 96 11.5 154 12.9 154 7.17 153 6.31 113 8.30 66 3.66 121 11.7 134 14.8 136 3.89 72 6.59 85 12.8 86 2.48 107 8.27 83 18.9 81 1.96 113 8.68 123 13.4 117 1.80 129
OFRF [134]112.3 4.02 142 8.26 141 1.33 134 4.53 123 6.49 127 1.81 117 4.60 89 7.27 100 2.13 57 6.02 99 9.15 112 3.39 87 11.8 139 14.9 140 4.23 88 7.13 136 13.9 136 2.39 69 9.02 124 20.8 128 1.59 42 8.79 131 13.8 131 1.77 103
Adaptive flow [45]112.6 3.60 130 6.30 86 1.54 149 5.14 149 6.79 148 2.14 145 4.52 84 6.60 65 3.01 102 6.54 123 8.64 90 4.23 143 12.1 149 15.2 147 4.09 81 7.57 145 14.9 147 2.64 142 7.75 43 17.8 46 2.28 133 8.47 112 13.3 112 1.71 32
H+S_ROB [138]112.7 3.43 117 6.69 112 1.29 120 4.55 125 6.05 87 1.91 126 11.3 151 12.3 153 7.31 154 6.98 131 8.51 83 3.51 103 11.4 92 14.4 102 3.65 46 6.60 87 12.8 86 2.42 86 9.86 143 22.7 143 2.08 123 8.84 135 13.7 127 1.74 72
UnFlow [129]113.8 4.05 143 8.73 146 1.31 128 4.44 116 6.28 113 1.87 121 4.92 105 7.36 107 2.62 86 5.95 90 9.00 106 3.27 54 12.0 146 15.2 147 4.37 97 7.59 146 14.8 145 2.61 136 7.77 47 17.6 37 1.64 63 10.4 150 15.4 150 2.33 152
StereoFlow [44]114.5 5.35 154 10.3 151 1.42 145 5.03 146 7.21 153 1.76 113 4.14 51 6.94 82 2.01 47 5.83 76 8.55 87 3.33 78 13.7 152 17.3 152 4.70 151 8.71 153 17.2 153 2.70 148 7.88 56 18.1 57 1.61 49 8.82 134 13.9 136 1.79 123
2bit-BM-tele [98]115.5 3.31 103 6.41 97 1.34 138 4.53 123 6.62 136 1.80 116 6.23 131 9.24 141 6.19 147 5.94 89 8.59 89 3.55 111 11.3 81 14.2 81 4.03 79 7.72 149 15.1 149 3.02 153 12.2 153 28.7 154 4.77 155 7.76 31 12.1 26 1.82 139
IIOF-NLDP [131]116.9 3.36 111 6.62 109 1.21 22 4.22 97 6.32 118 1.59 77 5.16 111 7.63 118 2.63 88 6.10 101 9.20 116 3.53 107 11.6 124 14.6 123 4.79 153 7.42 141 14.5 141 2.71 149 12.0 152 28.2 152 3.38 150 8.93 137 13.9 136 1.74 72
SPSA-learn [13]120.2 3.89 141 7.79 136 1.27 110 4.43 114 6.17 99 1.81 117 9.03 146 8.47 134 5.47 144 6.80 127 9.40 121 3.72 126 11.5 108 14.5 113 3.91 74 6.51 69 12.6 67 2.46 98 11.9 150 27.9 151 4.54 153 10.5 152 16.5 152 1.75 82
FFV1MT [106]120.5 4.09 145 8.38 143 1.31 128 4.68 136 6.18 102 2.02 143 6.95 135 11.5 150 3.35 115 7.12 136 9.16 113 3.98 138 11.3 81 14.1 66 3.74 63 6.77 109 12.7 74 2.50 113 9.59 139 21.0 130 2.05 120 8.87 136 13.8 131 1.90 145
SegOF [10]123.3 3.51 123 7.12 125 1.32 131 4.17 95 6.10 92 1.59 77 8.69 143 7.75 123 5.15 141 8.58 149 14.3 150 4.29 145 11.7 134 14.8 136 4.50 124 6.79 112 13.2 112 2.50 113 10.1 146 23.5 146 2.55 138 8.80 132 13.8 131 1.72 42
PGAM+LK [55]125.2 4.08 144 8.41 144 1.65 150 4.74 138 6.45 125 2.27 148 8.87 144 12.2 151 6.88 151 8.06 147 10.9 139 4.83 147 11.4 92 14.3 91 3.90 73 6.83 114 13.2 112 2.55 128 8.26 81 18.9 81 2.27 132 8.55 115 13.3 112 1.90 145
Heeger++ [104]125.5 4.76 147 9.63 148 1.33 134 4.65 135 6.22 108 1.90 124 7.84 140 9.26 143 3.57 120 7.12 136 9.16 113 3.98 138 11.9 143 15.0 143 4.47 109 6.52 70 12.2 45 2.61 136 9.82 141 20.6 123 2.00 117 9.02 139 14.0 138 1.79 123
SLK [47]126.9 3.51 123 6.96 122 1.41 143 4.72 137 6.10 92 1.98 140 9.84 147 7.59 116 5.20 142 7.98 146 11.0 142 6.14 152 11.8 139 14.9 140 3.71 55 6.60 87 12.7 74 2.50 113 9.87 144 22.8 144 2.08 123 8.94 138 14.0 138 2.03 149
HCIC-L [99]129.4 4.98 151 9.28 147 1.77 153 4.97 145 6.87 151 2.11 144 5.70 123 10.0 149 4.41 138 7.85 144 11.8 145 3.68 123 10.9 35 13.7 36 3.72 59 8.18 152 16.1 152 2.55 128 9.06 127 21.0 130 2.58 140 9.57 148 15.0 148 1.81 137
WRT [151]129.4 3.42 116 6.71 115 1.23 69 4.33 104 6.06 89 1.89 123 9.93 149 8.00 126 5.95 146 6.98 131 9.01 107 3.77 129 11.9 143 15.1 145 3.97 77 7.82 150 15.4 150 2.64 142 12.5 154 29.5 155 3.47 151 10.5 152 16.6 153 1.80 129
WOLF_ROB [149]131.8 5.06 152 10.3 151 1.30 124 4.79 141 6.72 144 1.75 110 6.29 132 9.03 139 4.14 131 7.37 140 11.8 145 3.33 78 11.9 143 15.0 143 4.48 112 7.40 140 14.3 139 2.51 117 10.5 148 23.9 147 1.74 85 9.44 146 14.8 146 1.78 109
Pyramid LK [2]139.4 4.16 146 8.44 145 1.74 152 5.83 153 6.82 149 2.76 153 11.4 152 8.60 135 5.89 145 12.4 154 16.7 153 7.03 154 14.3 153 18.1 153 3.92 76 6.69 96 12.2 45 2.63 140 10.3 147 24.0 148 2.45 135 11.1 154 17.4 154 2.55 154
GroupFlow [9]141.9 4.94 150 10.2 150 1.36 140 4.51 119 6.50 128 1.92 128 8.67 142 9.13 140 4.38 137 8.83 152 13.0 148 5.40 149 12.9 151 16.3 151 4.53 145 7.89 151 15.5 151 2.65 144 9.85 142 22.6 142 1.91 109 9.52 147 14.9 147 1.88 143
Periodicity [78]152.6 5.27 153 11.1 154 1.83 154 7.09 154 7.33 154 2.86 154 11.4 152 12.2 151 7.13 152 10.5 153 17.1 154 6.14 152 14.9 154 19.0 154 4.71 152 9.13 154 17.9 154 3.16 154 11.9 150 27.8 150 3.76 152 10.4 150 15.8 151 2.29 150
AVG_FLOW_ROB [142]154.8 14.6 155 20.0 155 3.66 155 11.3 155 12.1 155 4.33 155 13.4 155 14.1 155 7.93 155 19.0 155 25.3 155 10.2 155 18.3 155 23.1 155 5.58 154 16.7 155 32.2 155 4.90 155 16.6 155 28.6 153 4.56 154 15.9 155 19.8 155 4.61 155
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

Methodtime*framescolor Reference and notes
[1] 2D-CLG 844 2 gray The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences.
[2] Pyramid LK 12 2 color A modification of Bouguet's pyramidal implementation of Lucas-Kanade.
[3] Horn & Schunck 49 2 gray A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data.
[4] Black & Anandan 328 2 gray A modern Matlab implementation of the Black & Anandan method by Deqing Sun.
[5] Brox et al. 18 2 color T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.)
[6] Fusion 2,666 2 color V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008.
[7] Dynamic MRF 366 2 gray B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.)
[8] Second-order prior 14 2 gray W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[9] GroupFlow 600 2 gray X. Ren. Local Grouping for Optical Flow. CVPR 2008.
[10] SegOF 60 2 color L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available.
[11] Learning Flow 825 2 gray D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008.
[12] CBF 69 2 color W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[13] SPSA-learn 200 2 color Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008.
[14] GraphCuts 1,200 2 color T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008.
[15] F-TV-L1 8 2 gray A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008.
[16] FOLKI 1.4 2 gray G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005.
[17] TV-L1-improved 2.9 2 gray A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision.
[18] DPOF 287 2 color C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.)
[19] Filter Flow 34,000 2 color S. Seitz and S. Baker. Filter flow. ICCV 2009.
[20] Adaptive 9.2 2 gray A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009.
[21] Complementary OF 44 2 color H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[22] Aniso. Huber-L1 2 2 gray M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision.
[23] Rannacher 0.12 2 gray J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009.
[24] TI-DOFE 260 2 gray C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009.
[25] NL-TV-NCC 20 2 color M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010.
[26] MDP-Flow 188 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010.
[27] ACK-Prior 5872 2 color K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010.
[28] LDOF 122 2 color T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011.
[29] p-harmonic 565 2 gray J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010.
[30] TriangleFlow 4200 2 gray B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010.
[31] Classic+NL 972 2 color D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code.
[32] Classic++ 486 2 gray A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010.
[33] Nguyen 33 2 gray D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011.
[34] Modified CLG 133 2 gray R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010.
[35] ComplOF-FED-GPU 0.97 2 color P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010.
[36] Ad-TV-NDC 35 2 gray M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010.
[37] Layers++ 18206 2 color D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010.
[38] OFH 620 3 color H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011.
[39] LSM 1615 2 color K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011.
[40] CostFilter 55 2 color C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011.
[41] Bartels 0.15 2 gray C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU.
[42] Shiralkar 600 2 gray M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242.
[43] HBpMotionGpu 1000 5 gray S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.)
[44] StereoFlow 7200 2 color G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772.
[45] Adaptive flow 121 2 gray T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011.
[46] TC-Flow 2500 5 color S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011.
[47] SLK 300 2 gray T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011.
[48] CLG-TV 29 2 gray M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code.
[49] SimpleFlow 1.7 2 color M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012.
[50] IAOF 57 2 gray D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011.
[51] IAOF2 56 2 gray D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011.
[52] LocallyOriented 9541 2 gray Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012.
[53] IROF-TV 261 2 color H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop.
[54] Sparse Occlusion 2312 2 color A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011.
[55] PGAM+LK 0.37 2 gray A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010.
[56] Sparse-NonSparse 713 2 color L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013.
[57] nLayers 36150 4 color D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012.
[58] IROF++ 187 2 color H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013.
[59] COFM 600 3 color M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013.
[60] Efficient-NL 400 2 color P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012.
[61] BlockOverlap 2 2 gray M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to MMSP 2012.
[62] Ramp 1200 2 color A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012.
[63] Occlusion-TV-L1 538 3 gray C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012.
[64] TV-L1-MCT 90 2 color M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012.
[65] Local-TV-L1 500 2 gray L. Raket. Local smoothness for global optical flow. ICIP 2012.
[66] ALD-Flow 61 2 color M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012.
[67] SIOF 234 2 color L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012.
[68] MDP-Flow2 342 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available.
[69] TCOF 1421 all gray J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013.
[70] LME 476 2 color W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013.
[71] NN-field 362 2 color L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[72] FESL 3310 2 color W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013.
[73] PMF 35 2 color J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013.
[74] FC-2Layers-FF 2662 4 color D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013.
[75] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[76] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[77] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[78] Periodicity 8000 4 color G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013.
[79] SILK 572 2 gray P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP.
[80] CRTflow 13 3 color O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013.
[81] SuperFlow 178 2 color Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507.
[82] Aniso-Texture 300 2 color Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267.
[83] Classic+CPF 640 2 gray Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013.
[84] S2D-Matching 1200 2 color Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479.
[85] AGIF+OF 438 2 gray Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015.
[86] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[87] NNF-Local 673 2 color Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014.
[88] EPPM w/o HM 2.5 2 color L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014.
[89] MLDP_OF 165 2 gray M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014.
[90] RFlow 20 2 gray S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014.
[91] SRR-TVOF-NL 32 all color P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014.
[92] 2DHMM-SAS 157 2 color M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission.
[93] WLIF-Flow 700 2 color Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014.
[94] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[95] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[96] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[97] AggregFlow 1642 2 color D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759.
[98] 2bit-BM-tele 124 2 gray R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013.
[99] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[100] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[101] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[102] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[103] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[104] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[105] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[106] FFV1MT 358 5 gray F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015.
[107] ROF-ND 4 2 color S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015.
[108] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[109] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[110] FlowFields 15 2 color C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015.
[111] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[112] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[113] CombBMOF 51 2 color M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.)
[114] PMMST 182 2 color F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015.
[115] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[116] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[117] CNN-flow-warp+ref 1.4 3 color D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016.
[118] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[119] StereoOF-V1MT 343 2 gray Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132.
[120] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[121] RNLOD-Flow 1040 2 gray C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. IEEE TIP 26(8):4055-4067, 2017.
[122] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[123] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[124] BriefMatch 0.068 2 gray G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62.
[125] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[126] AdaConv-v1 2.8 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[127] SepConv-v1 0.2 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[128] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[129] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[130] FlowFields+ 10.5 2 color C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017.
[131] IIOF-NLDP 150 2 color D.-H. Trinh, W. Blondel, and C. Daul. A general form of illumination-invariant descriptors in variational optical flow estimation. ICIP 2017.
[132] SuperSlomo 0.5 2 color Anonymous. (Interpolation results only.) Super SloMo: High quality estimation of multiple intermediate frames for video interpolation. CVPR 2018 submission 325.
[133] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[134] OFRF 90 2 color T. Mai, M. Gouiffes, and S. Bouchafa. Optical Flow refinement using iterative propagation under color, proximity and flow reliability constraints. Submitted to Signal, Image and Video Processing 2017.
[135] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
[136] FGIK 0.18 2 color Anonymous. (Interpolation results only.) Learning flow-guided interpolation kernels for video frame synthesis. ECCV 2018 submission 433.
[137] CtxSyn 0.07 2 color S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[138] H+S_ROB 5 2 color ROB 2018 baseline submission, based on: E. Meinhardt-Llopis, J. Sanchez, and D. Kondermann. Horn-Schunck optical flow with a multi-scale strategy. Image Processing On Line 3:151–172, 2013.
[139] TVL1_ROB 1 2 color ROB 2018 baseline submission, based on: J. Sanchez, E. Meinhardt-Llopis, and G. Facciolo. TV-L1 optical flow estimation. Image Processing On Line 3:137-150, 2013.
[140] DMF_ROB 10 2 color ROB 2018 baseline submission, based on: P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[141] JOF 657 2 gray C. Zhang, L. Ge, Z. Chen, M. Li, W. Liu, and H. Chen. Refined TV-L1 optical flow estimation using joint filtering. Submitted to IEEE TMM, 2018.
[142] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[143] LiteFlowNet 0.06 2 color T.-W. Hui, X. Tang, and C. C. Loy. LiteFlowNet: A lightweight convolutional neural network for optical flow estimation. CVPR 2018.
[144] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[145] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[146] FF++_ROB 17.43 2 color R. Schuster, C. Bailer, O. Wasenmueller, D. Stricker. FlowFields++: Accurate optical flow correspondences meet robust interpolation. ICIP 2018. Submitted to ROB 2018.
[147] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[148] PWC-Net_ROB 0.069 2 color D. Sun, X. Yang, M.-Y. Liu, and J. Kautz. PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. CVPR 2018.
[149] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[150] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
[151] 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.
[152] 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.
[153] ContinualFlow_ROB 0.5 all color Anonymous. Continual Flow. ACCV 2018 submission 273.
[154] CyclicGen 0.088 2 color Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
[155] CFRF 0.128 2 color Anonymous. (Interpolation results only.) Coarse-to-fine refinement framework for video frame interpolation. AAAI 2019 submission 4489.
* 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.