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]12.0 2.24 1 3.72 1 1.04 1 2.96 1 4.16 1 1.35 30 4.32 66 3.42 1 3.18 107 4.21 1 5.46 1 3.00 1 9.59 3 11.9 2 3.46 5 5.22 2 9.76 2 2.22 3 7.02 4 15.4 3 1.58 38 6.66 2 10.2 1 1.69 10
MDP-Flow2 [68]16.8 2.89 8 5.38 9 1.19 3 3.47 10 5.07 14 1.26 1 3.66 13 6.10 41 2.48 77 5.20 4 7.48 13 3.14 15 10.2 6 12.8 8 3.61 27 6.13 26 11.8 23 2.31 29 7.36 9 16.8 7 1.49 2 7.75 25 12.1 24 1.69 10
PMMST [114]16.9 2.90 9 5.43 11 1.20 7 3.50 15 5.05 12 1.27 6 3.56 4 5.46 7 1.82 33 5.38 20 7.92 41 3.41 91 10.2 6 12.8 8 3.60 21 5.76 6 11.0 6 2.26 9 7.39 10 16.9 10 1.53 14 7.57 10 11.8 10 1.72 40
SuperSlomo [132]18.9 2.51 2 4.32 2 1.25 92 3.66 34 5.06 13 1.93 131 2.91 1 4.00 2 1.41 7 5.05 2 6.27 2 3.66 119 9.56 2 11.9 2 3.30 3 5.37 4 10.2 4 2.24 4 6.69 2 15.0 2 1.53 14 6.73 3 10.4 3 1.66 3
SepConv-v1 [127]24.8 2.52 3 4.83 3 1.11 2 3.56 23 5.04 10 1.90 122 4.17 53 4.15 3 2.86 94 5.41 29 6.81 3 3.88 128 10.2 6 12.8 8 3.37 4 5.47 5 10.4 5 2.21 2 6.88 3 15.6 4 1.72 81 6.63 1 10.3 2 1.62 2
DeepFlow [86]26.3 2.98 21 5.67 26 1.22 48 3.88 60 5.78 59 1.52 69 3.62 6 5.93 34 1.34 3 5.39 25 7.20 8 3.17 19 11.0 37 13.9 44 3.63 38 5.91 12 11.3 11 2.29 21 7.14 5 16.3 5 1.49 2 7.80 32 12.2 30 1.70 17
CBF [12]30.5 2.83 4 5.20 4 1.23 68 3.97 72 5.79 62 1.56 72 3.62 6 5.47 8 1.60 19 5.21 5 7.12 5 3.29 57 10.1 4 12.6 4 3.62 32 5.97 15 11.5 15 2.31 29 7.76 42 17.8 43 1.61 48 7.60 13 11.9 13 1.76 92
FGIK [136]30.8 2.83 4 5.28 5 1.31 126 3.84 55 5.31 25 1.94 132 4.16 52 4.27 4 2.20 60 5.75 66 7.49 14 3.94 131 8.57 1 10.6 1 3.25 2 4.99 1 9.42 1 2.14 1 5.86 1 13.1 1 1.60 46 6.83 4 10.7 4 1.57 1
DeepFlow2 [108]31.4 2.99 24 5.65 23 1.22 48 3.88 60 5.79 62 1.48 63 3.62 6 6.03 36 1.34 3 5.38 20 7.44 12 3.22 37 11.0 37 13.8 37 3.67 46 5.83 7 11.2 7 2.25 8 7.60 24 17.4 25 1.50 4 7.82 33 12.2 30 1.77 101
SuperFlow [81]33.2 2.94 13 5.56 19 1.24 82 3.99 75 5.78 59 1.67 94 4.06 41 5.55 10 1.83 34 5.52 40 7.07 4 3.20 31 10.2 6 12.7 6 3.68 49 6.13 26 11.8 23 2.24 4 7.68 33 17.5 30 1.77 93 7.44 8 11.6 7 1.69 10
NN-field [71]33.6 2.98 21 5.70 27 1.20 7 3.31 4 4.73 4 1.26 1 4.69 91 5.91 32 2.03 49 5.99 91 9.13 107 3.57 111 10.3 12 12.8 8 3.60 21 6.24 37 12.0 35 2.31 29 7.39 10 16.9 10 1.54 20 7.69 21 12.0 19 1.72 40
NNF-Local [87]33.8 2.92 12 5.51 17 1.19 3 3.30 3 4.71 3 1.26 1 3.65 11 5.91 32 2.29 69 5.76 69 8.70 90 3.55 109 10.3 12 12.9 14 3.60 21 6.42 55 12.4 54 2.34 42 7.57 20 17.4 25 1.74 83 7.61 14 11.9 13 1.72 40
Aniso. Huber-L1 [22]34.6 2.95 16 5.44 13 1.24 82 4.42 108 6.27 108 1.67 94 3.79 24 5.70 17 1.50 12 5.31 10 7.42 11 3.24 46 11.1 48 14.0 57 3.61 27 5.91 12 11.4 13 2.24 4 7.60 24 17.3 19 1.51 8 7.62 16 11.9 13 1.73 49
IROF-TV [53]35.6 3.07 39 5.91 49 1.23 68 3.71 40 5.47 38 1.40 42 3.70 19 6.27 47 1.58 18 5.25 7 7.60 21 3.17 19 11.0 37 13.9 44 4.47 106 6.37 51 12.4 54 2.30 26 7.79 46 17.9 47 1.50 4 7.63 17 11.9 13 1.66 3
CLG-TV [48]35.8 2.94 13 5.45 14 1.25 92 4.26 96 6.17 95 1.60 80 3.68 17 5.73 19 1.73 29 5.36 16 7.41 10 3.32 74 11.1 48 14.0 57 3.57 10 5.88 11 11.3 11 2.26 9 7.58 21 17.0 14 1.57 35 7.75 25 12.1 24 1.72 40
LME [70]36.3 2.95 16 5.59 21 1.19 3 3.68 37 5.50 41 1.38 35 4.06 41 7.00 86 1.71 28 5.38 20 7.92 41 3.18 22 11.2 62 14.1 65 4.51 133 6.29 42 12.2 42 2.31 29 7.33 7 16.8 7 1.51 8 7.83 34 12.3 34 1.70 17
IROF++ [58]36.9 3.03 30 5.77 35 1.20 7 3.59 26 5.31 25 1.33 24 4.32 66 6.61 64 2.25 64 5.06 3 7.14 6 3.16 18 11.0 37 13.9 44 4.44 102 6.34 47 12.3 49 2.27 14 7.54 19 17.3 19 1.64 61 8.09 57 12.7 58 1.69 10
NNF-EAC [103]38.3 3.01 27 5.60 22 1.25 92 3.63 29 5.36 31 1.29 13 4.17 53 7.03 88 2.99 97 5.50 39 7.96 43 3.28 54 11.2 62 14.1 65 3.60 21 5.86 10 11.2 7 2.26 9 7.43 14 17.0 14 1.54 20 7.79 31 12.2 30 1.73 49
CombBMOF [113]38.4 3.16 69 5.88 44 1.24 82 3.54 19 5.24 20 1.34 28 4.01 37 6.45 58 2.20 60 5.62 58 8.22 59 3.29 57 10.7 22 13.5 23 3.62 32 6.20 34 11.9 31 2.27 14 7.78 45 17.3 19 1.56 31 7.75 25 12.1 24 1.71 30
DF-Auto [115]39.6 2.94 13 5.34 7 1.23 68 3.99 75 5.84 67 1.65 88 3.85 29 6.73 68 1.55 17 5.38 20 7.54 16 3.25 48 10.4 15 13.0 15 3.70 51 6.17 33 11.9 31 2.28 17 7.94 57 18.2 59 1.75 88 7.68 19 12.0 19 1.71 30
ALD-Flow [66]41.0 3.28 97 6.45 98 1.24 82 3.81 50 5.73 57 1.41 46 3.62 6 6.28 48 1.35 5 5.58 49 8.39 71 3.04 5 10.8 25 13.5 23 4.15 83 5.96 14 11.4 13 2.29 21 7.34 8 16.8 7 1.51 8 8.25 79 12.9 72 1.70 17
WLIF-Flow [93]41.3 2.95 16 5.53 18 1.20 7 3.66 34 5.41 34 1.39 38 4.26 62 7.17 95 2.54 80 5.30 9 7.57 19 3.29 57 10.7 22 13.5 23 3.70 51 6.74 103 13.1 99 2.48 104 7.40 12 16.9 10 1.53 14 7.87 40 12.3 34 1.69 10
PH-Flow [101]42.2 3.12 55 6.01 64 1.20 7 3.39 6 4.94 7 1.28 11 3.70 19 6.43 53 2.48 77 5.23 6 7.58 20 3.22 37 10.4 15 13.1 17 3.62 32 6.84 114 13.3 112 2.47 98 7.84 49 18.1 54 1.58 38 7.87 40 12.3 34 1.73 49
Second-order prior [8]42.5 2.91 11 5.39 10 1.24 82 4.26 96 6.21 101 1.56 72 3.82 26 6.34 50 1.62 20 5.39 25 7.68 23 3.04 5 11.1 48 13.9 44 3.59 14 6.14 29 11.9 31 2.31 29 7.61 26 17.4 25 1.63 60 7.90 42 12.4 44 1.78 107
p-harmonic [29]43.5 3.00 25 5.72 29 1.21 21 4.33 101 6.24 106 1.69 100 3.60 5 6.07 40 1.39 6 5.70 60 7.87 36 3.29 57 11.0 37 13.8 37 3.63 38 6.02 18 11.6 18 2.34 42 7.67 31 17.5 30 1.70 76 7.92 46 12.4 44 1.72 40
Brox et al. [5]44.2 3.08 42 5.94 54 1.21 21 3.83 53 5.67 49 1.45 56 3.93 33 5.76 21 1.67 23 5.32 11 7.19 7 3.22 37 10.6 19 13.4 21 3.56 8 6.60 84 12.7 71 2.42 83 8.61 100 19.7 102 3.04 145 7.43 7 11.6 7 1.68 8
FMOF [94]45.3 3.16 69 5.92 52 1.23 68 3.48 11 5.07 14 1.28 11 4.59 86 6.82 72 2.78 90 5.71 62 8.42 72 3.40 88 10.4 15 13.0 15 3.67 46 6.49 62 12.6 63 2.28 17 7.64 28 17.5 30 1.48 1 8.06 56 12.6 54 1.67 6
SIOF [67]46.0 3.06 37 5.74 33 1.24 82 4.40 107 6.40 119 1.63 86 4.17 53 7.43 108 1.93 41 5.40 28 7.75 28 3.44 94 10.1 4 12.6 4 3.58 12 6.10 23 11.8 23 2.29 21 7.52 17 17.2 18 1.53 14 7.96 50 12.5 53 1.73 49
MDP-Flow [26]48.0 2.86 6 5.34 7 1.20 7 3.49 14 5.15 17 1.34 28 4.01 37 5.51 9 2.28 66 5.58 49 7.91 40 3.33 77 11.2 62 14.0 57 4.49 116 6.72 97 13.1 99 2.54 122 7.71 36 17.7 39 1.74 83 7.83 34 12.3 34 1.70 17
Local-TV-L1 [65]48.2 3.00 25 5.47 15 1.30 122 4.43 110 6.23 105 1.75 109 3.50 2 5.35 6 1.45 8 5.39 25 7.56 17 3.29 57 11.2 62 14.1 65 3.91 73 6.16 31 11.8 23 2.47 98 7.67 31 17.6 35 1.55 26 7.57 10 11.8 10 1.76 92
OAR-Flow [125]49.9 3.13 60 5.95 56 1.22 48 3.83 53 5.70 52 1.48 63 3.65 11 6.06 37 1.16 1 5.60 54 8.48 77 3.03 2 11.2 62 14.1 65 4.51 133 6.12 25 11.8 23 2.41 80 7.97 60 17.9 47 1.59 40 8.11 60 12.7 58 1.71 30
JOF [141]50.4 3.08 42 5.89 46 1.24 82 3.48 11 5.04 10 1.37 33 3.85 29 5.98 35 2.07 50 5.43 32 7.81 34 3.28 54 11.3 79 14.2 79 4.51 133 6.72 97 13.1 99 2.37 57 7.48 16 17.1 16 1.54 20 8.01 52 12.6 54 1.73 49
Modified CLG [34]53.9 2.87 7 5.32 6 1.24 82 4.51 115 6.21 101 1.96 135 4.15 50 6.45 58 2.67 87 5.56 46 7.69 24 3.64 118 10.8 25 13.5 23 3.63 38 6.36 50 12.3 49 2.39 66 7.46 15 17.1 16 1.56 31 7.86 37 12.3 34 1.75 80
Ad-TV-NDC [36]54.0 3.23 86 5.70 27 1.44 143 4.78 135 6.46 122 1.92 126 3.67 14 5.86 28 1.50 12 5.97 88 8.14 57 3.51 102 10.8 25 13.5 23 3.63 38 6.24 37 12.0 35 2.40 69 7.70 34 17.3 19 1.51 8 7.48 9 11.7 9 1.73 49
F-TV-L1 [15]54.1 3.30 99 6.36 91 1.29 118 4.39 106 6.32 114 1.62 85 3.80 25 5.90 31 1.76 30 5.61 55 7.97 45 3.31 71 10.9 33 13.6 28 3.59 14 5.84 8 11.2 7 2.33 40 7.70 34 17.6 35 1.79 95 7.61 14 11.9 13 1.78 107
CPM-Flow [116]55.3 3.17 75 6.31 86 1.21 21 3.54 19 5.26 22 1.31 19 4.22 59 5.88 30 1.45 8 6.11 99 9.48 119 3.31 71 11.1 48 13.9 44 4.50 120 6.28 41 12.1 39 2.32 37 7.66 29 17.6 35 1.74 83 8.18 65 12.8 66 1.76 92
2DHMM-SAS [92]55.9 3.10 49 5.91 49 1.21 21 4.10 84 6.05 85 1.46 60 4.38 72 7.10 92 2.07 50 5.38 20 7.78 32 3.22 37 11.3 79 14.3 89 4.42 98 6.33 44 12.2 42 2.26 9 7.95 59 18.2 59 1.64 61 8.19 67 12.8 66 1.70 17
TC/T-Flow [76]57.2 3.21 83 6.24 78 1.22 48 3.90 65 5.86 69 1.43 51 3.69 18 5.83 24 1.50 12 5.88 81 8.93 98 3.15 16 11.1 48 13.9 44 4.50 120 6.23 35 12.0 35 2.26 9 8.61 100 19.0 82 1.93 109 8.16 64 12.8 66 1.70 17
COFM [59]57.6 3.03 30 5.76 34 1.22 48 3.55 22 5.21 19 1.32 22 3.82 26 6.98 84 2.81 91 5.41 29 7.97 45 3.30 66 10.8 25 13.6 28 3.62 32 7.01 128 13.7 125 2.40 69 8.00 65 18.5 70 1.98 112 7.91 43 12.4 44 1.80 126
LDOF [28]57.8 3.03 30 5.66 25 1.28 112 4.06 81 5.53 43 2.40 146 4.32 66 6.43 53 2.00 45 5.45 35 7.56 17 3.60 115 10.2 6 12.7 6 3.59 14 6.39 52 12.4 54 2.29 21 8.36 86 19.4 93 2.21 128 7.57 10 11.8 10 1.86 138
DMF_ROB [140]57.8 3.15 66 6.13 72 1.22 48 3.96 69 5.87 70 1.56 72 5.24 112 7.74 119 2.62 83 5.73 65 8.32 65 3.19 27 11.0 37 13.8 37 4.50 120 6.07 20 11.7 20 2.37 57 7.66 29 17.5 30 1.50 4 8.10 58 12.7 58 1.73 49
FlowFields [110]59.1 3.15 66 6.30 83 1.21 21 3.57 24 5.34 29 1.32 22 4.73 93 6.89 77 3.23 110 5.85 76 8.96 101 3.08 7 10.8 25 13.6 28 4.19 84 6.57 77 12.8 83 2.36 53 7.72 37 17.8 43 1.67 69 8.20 69 12.9 72 1.74 70
Layers++ [37]59.4 2.96 19 5.56 19 1.22 48 3.29 2 4.64 2 1.26 1 4.07 43 7.24 96 3.08 101 5.48 36 8.10 53 3.25 48 12.0 143 15.2 144 4.62 145 7.29 136 14.3 136 2.44 90 7.63 27 17.5 30 1.54 20 7.84 36 12.3 34 1.70 17
ComplOF-FED-GPU [35]59.5 3.23 86 6.40 93 1.22 48 3.73 43 5.62 48 1.44 53 5.23 111 6.06 37 3.23 110 5.53 41 8.25 60 3.29 57 11.1 48 13.9 44 4.21 85 6.11 24 11.8 23 2.32 37 8.16 73 18.5 70 1.61 48 8.29 86 12.9 72 1.71 30
nLayers [57]59.5 3.03 30 5.72 29 1.21 21 3.48 11 5.09 16 1.31 19 5.60 117 7.52 111 4.26 132 5.61 55 8.33 66 3.29 57 11.6 122 14.6 121 4.31 90 6.66 90 12.9 92 2.40 69 7.58 21 17.3 19 1.59 40 7.94 47 12.4 44 1.69 10
TV-L1-MCT [64]59.8 3.17 75 6.05 67 1.22 48 3.87 57 5.82 65 1.40 42 4.48 79 7.75 120 2.24 63 5.37 18 7.76 30 3.24 46 11.6 122 14.7 128 4.31 90 6.08 21 11.7 20 2.31 29 8.07 69 18.6 73 2.15 126 7.68 19 12.0 19 1.68 8
AdaConv-v1 [126]60.3 3.57 124 6.88 117 1.41 140 4.34 103 5.67 49 2.52 148 5.00 104 5.86 28 2.98 96 6.91 127 8.89 97 4.89 144 10.2 6 12.8 8 3.21 1 5.33 3 10.1 3 2.27 14 7.30 6 16.6 6 1.92 108 6.94 5 10.8 5 1.67 6
CRTflow [80]60.8 3.09 47 5.91 49 1.27 108 4.35 104 6.31 112 1.68 97 4.15 50 7.26 97 1.84 35 5.33 13 7.51 15 3.38 83 11.0 37 13.8 37 4.48 109 6.09 22 11.7 20 2.30 26 8.55 97 19.8 103 1.55 26 8.19 67 12.8 66 1.72 40
TC-Flow [46]61.0 3.31 101 6.70 110 1.22 48 3.91 67 5.95 72 1.45 56 3.64 10 5.84 25 1.28 2 5.70 60 8.50 79 3.22 37 11.2 62 14.1 65 4.44 102 6.34 47 12.3 49 2.41 80 7.79 46 17.9 47 1.55 26 8.42 101 13.2 103 1.74 70
DPOF [18]61.3 3.34 107 6.82 113 1.29 118 3.40 7 4.93 6 1.29 13 5.00 104 6.36 51 3.40 113 5.86 77 8.94 99 3.51 102 11.0 37 13.8 37 3.59 14 6.56 74 12.7 71 2.28 17 7.99 62 18.2 59 1.55 26 8.24 76 12.9 72 1.70 17
AGIF+OF [85]61.7 3.12 55 5.95 56 1.20 7 3.64 31 5.39 32 1.40 42 3.96 35 6.44 57 2.28 66 5.48 36 8.03 49 3.25 48 11.4 90 14.3 89 4.49 116 6.91 119 13.5 120 2.37 57 7.85 51 17.9 47 1.54 20 8.44 105 13.2 103 1.73 49
PGM-C [120]63.0 3.17 75 6.29 81 1.21 21 3.58 25 5.32 27 1.33 24 5.01 106 6.14 44 1.90 38 6.14 102 9.63 124 3.23 43 11.2 62 14.1 65 4.50 120 6.14 29 11.8 23 2.34 42 8.20 75 18.9 79 1.59 40 8.46 108 13.3 109 1.73 49
Classic++ [32]63.7 3.05 35 5.85 40 1.24 82 4.08 83 6.08 87 1.52 69 3.74 22 5.58 13 1.53 16 5.72 64 8.12 55 3.21 33 11.4 90 14.3 89 3.74 62 6.68 92 13.0 94 2.42 83 8.35 85 19.2 86 1.62 56 8.21 71 12.9 72 1.73 49
Sparse-NonSparse [56]63.9 3.07 39 5.88 44 1.21 21 3.61 27 5.33 28 1.33 24 4.29 65 7.47 109 2.19 59 5.37 18 7.74 26 3.21 33 11.5 106 14.5 111 4.36 93 6.66 90 12.9 92 2.41 80 8.69 106 20.1 108 1.67 69 8.27 83 13.0 85 1.70 17
BlockOverlap [61]65.0 2.98 21 5.47 15 1.33 131 4.38 105 6.09 88 1.88 121 4.26 62 5.57 12 3.14 104 5.56 46 7.32 9 4.14 137 11.1 48 13.9 44 3.77 65 6.41 53 12.3 49 2.54 122 7.75 40 17.4 25 3.02 144 7.32 6 11.4 6 1.78 107
ProbFlowFields [128]65.1 3.15 66 6.32 88 1.21 21 3.53 16 5.26 22 1.29 13 5.03 107 7.35 103 3.73 120 5.43 32 7.97 45 3.25 48 11.1 48 14.0 57 4.50 120 6.48 60 12.6 63 2.55 125 7.99 62 18.4 69 2.57 137 7.78 30 12.2 30 1.75 80
S2F-IF [123]65.9 3.26 92 6.66 107 1.20 7 3.53 16 5.25 21 1.29 13 4.11 46 6.64 65 2.34 71 5.89 82 9.06 105 3.08 7 11.4 90 14.3 89 4.51 133 6.41 53 12.4 54 2.40 69 7.84 49 18.1 54 1.76 91 8.33 93 13.1 94 1.75 80
ProFlow_ROB [147]65.9 3.16 69 6.30 83 1.21 21 3.77 47 5.71 54 1.39 38 4.12 47 5.27 5 1.62 20 6.15 103 9.68 125 3.11 12 11.5 106 14.5 111 4.50 120 5.85 9 11.2 7 2.24 4 8.50 94 19.4 93 1.56 31 8.70 124 13.6 122 1.85 137
PMF [73]66.0 3.14 62 6.13 72 1.20 7 3.73 43 5.60 46 1.27 6 5.24 112 8.98 134 3.76 121 5.75 66 8.56 85 3.28 54 10.8 25 13.6 28 3.62 32 6.55 71 12.7 71 2.35 50 8.41 91 19.5 99 1.64 61 8.57 116 13.4 114 1.70 17
MLDP_OF [89]66.0 3.08 42 5.98 61 1.21 21 4.01 77 6.01 82 1.49 66 3.67 14 6.14 44 1.47 10 5.78 70 8.13 56 3.95 132 11.3 79 14.2 79 3.87 70 6.71 95 13.0 94 2.51 114 7.73 39 17.7 39 1.71 78 8.18 65 12.8 66 1.76 92
FlowNetS+ft+v [112]66.7 3.07 39 5.81 37 1.28 112 4.57 124 6.29 110 2.41 147 4.01 37 5.64 15 2.13 56 5.55 44 7.77 31 3.88 128 11.3 79 14.2 79 4.46 105 5.99 17 11.5 15 2.35 50 8.63 103 20.0 106 1.62 56 7.70 22 12.0 19 1.74 70
Sparse Occlusion [54]66.9 3.16 69 6.18 76 1.23 68 4.14 91 6.24 106 1.45 56 3.67 14 5.84 25 1.52 15 5.61 55 8.26 61 3.15 16 11.5 106 14.4 100 4.48 109 6.26 39 12.1 39 2.46 95 8.52 95 19.6 101 1.54 20 8.28 85 13.0 85 1.75 80
OFLAF [77]66.9 3.10 49 5.98 61 1.20 7 3.44 8 5.03 9 1.26 1 3.73 21 5.82 23 1.66 22 5.33 13 7.74 26 3.10 11 11.6 122 14.7 128 4.50 120 6.58 81 12.8 83 2.48 104 9.33 130 21.6 131 2.06 120 8.45 107 13.2 103 1.80 126
TF+OM [100]67.2 3.33 106 6.83 114 1.25 92 3.65 32 5.43 36 1.47 62 3.82 26 6.43 53 1.68 25 6.01 93 9.04 104 3.19 27 11.2 62 14.1 65 4.38 95 6.46 59 12.5 59 2.34 42 8.30 84 19.2 86 1.86 101 8.05 55 12.6 54 1.75 80
FlowFields+ [130]67.2 3.14 62 6.26 80 1.22 48 3.54 19 5.27 24 1.30 18 4.74 96 7.10 92 3.20 108 6.01 93 9.35 115 3.11 12 11.1 48 13.9 44 4.50 120 6.57 77 12.8 83 2.40 69 7.89 55 18.2 59 1.80 96 8.22 73 12.9 72 1.73 49
HAST [109]67.2 3.01 27 5.73 31 1.21 21 3.45 9 5.01 8 1.27 6 6.39 131 8.24 126 4.09 126 5.43 32 7.96 43 3.03 2 11.2 62 14.2 79 3.59 14 7.47 140 14.7 140 2.47 98 8.68 105 20.1 108 1.53 14 8.35 96 13.1 94 1.77 101
Filter Flow [19]68.1 3.13 60 5.90 47 1.28 112 4.56 123 6.38 118 1.85 119 4.22 59 6.28 48 2.10 54 5.91 83 7.97 45 3.44 94 10.4 15 13.1 17 3.69 50 6.43 57 12.5 59 2.40 69 8.17 74 18.8 78 1.62 56 7.94 47 12.4 44 1.78 107
EpicFlow [102]71.5 3.17 75 6.34 89 1.21 21 3.79 48 5.70 52 1.44 53 4.28 64 5.73 19 1.67 23 6.37 115 10.1 130 3.39 86 11.2 62 14.1 65 4.50 120 6.23 35 12.0 35 2.38 64 8.11 71 18.5 70 1.76 91 8.76 128 13.8 129 1.74 70
Black & Anandan [4]71.5 3.22 85 5.87 42 1.30 122 4.82 138 6.55 127 1.78 114 7.16 135 7.10 92 3.93 123 6.25 109 8.49 78 3.35 81 10.9 33 13.7 34 3.56 8 6.33 44 12.2 42 2.37 57 8.23 78 18.6 73 1.64 61 7.67 18 11.9 13 1.69 10
LSM [39]71.5 3.12 55 6.05 67 1.21 21 3.68 37 5.47 38 1.33 24 4.38 72 7.66 117 2.01 46 5.55 44 8.19 58 3.19 27 11.5 106 14.5 111 4.43 99 6.83 111 13.3 112 2.37 57 8.70 107 20.1 108 1.72 81 8.34 95 13.1 94 1.71 30
TCOF [69]72.2 3.12 55 5.94 54 1.21 21 4.60 127 6.64 134 1.76 112 4.13 48 7.30 99 1.81 31 5.42 31 7.88 37 3.25 48 11.3 79 14.2 79 3.63 38 6.42 55 12.4 54 2.36 53 9.08 127 21.0 127 1.59 40 8.37 97 13.1 94 1.76 92
RNLOD-Flow [121]72.2 3.06 37 5.87 42 1.21 21 3.96 69 5.97 79 1.42 48 4.39 74 8.08 123 2.44 75 5.35 15 7.75 28 3.18 22 11.5 106 14.5 111 4.49 116 6.71 95 13.1 99 2.43 87 7.85 51 18.0 52 2.18 127 8.44 105 13.2 103 1.73 49
Ramp [62]73.3 3.11 53 5.96 58 1.22 48 3.61 27 5.34 29 1.40 42 4.91 101 8.45 129 3.20 108 5.29 8 7.66 22 3.21 33 11.5 106 14.5 111 4.31 90 6.88 118 13.4 116 2.48 104 8.73 112 20.2 112 1.52 13 8.29 86 13.0 85 1.73 49
Fusion [6]74.0 3.04 34 5.86 41 1.22 48 3.75 46 5.47 38 1.42 48 4.08 44 5.55 10 3.08 101 5.80 72 8.10 53 3.19 27 11.4 90 14.3 89 3.73 59 6.99 125 13.7 125 2.60 131 8.40 90 19.4 93 1.65 66 8.50 110 13.3 109 1.80 126
AggregFlow [97]74.4 3.80 135 8.08 136 1.23 68 3.87 57 5.83 66 1.43 51 4.21 58 6.79 70 2.85 93 6.11 99 9.36 116 3.31 71 10.6 19 13.3 19 3.67 46 6.13 26 11.8 23 2.34 42 8.70 107 19.8 103 2.30 132 8.27 83 13.0 85 1.75 80
Classic+NL [31]74.4 3.10 49 5.92 52 1.23 68 3.66 34 5.40 33 1.39 38 4.78 98 8.42 128 3.01 99 5.36 16 7.78 32 3.30 66 11.5 106 14.5 111 4.24 87 6.73 99 13.1 99 2.40 69 8.74 113 20.2 112 1.70 76 8.29 86 13.0 85 1.71 30
ComponentFusion [96]74.6 3.41 111 7.08 120 1.20 7 3.63 29 5.44 37 1.27 6 4.20 57 6.49 60 2.43 74 5.59 52 8.38 70 3.32 74 11.4 90 14.4 100 4.11 81 6.26 39 12.1 39 2.35 50 9.30 129 21.6 131 2.80 142 8.68 121 13.6 122 1.73 49
Bartels [41]76.0 3.48 117 7.24 124 1.30 122 4.02 78 6.12 92 1.68 97 3.74 22 5.80 22 1.95 43 5.87 79 8.44 74 3.78 127 10.3 12 12.8 8 3.75 64 6.77 106 13.0 94 2.73 147 7.53 18 17.3 19 2.72 140 8.13 61 12.7 58 1.77 101
Occlusion-TV-L1 [63]76.2 3.14 62 6.13 72 1.25 92 4.47 114 6.61 130 1.66 91 3.51 3 5.71 18 1.70 27 6.33 111 9.58 123 3.51 102 11.0 37 13.9 44 3.57 10 6.48 60 12.6 63 2.52 119 8.36 86 18.1 54 2.00 115 8.32 92 13.0 85 1.79 120
ContFlow_ROB [150]76.7 3.65 129 7.66 130 1.23 68 4.04 79 5.96 75 1.68 97 4.36 71 6.86 75 1.92 40 7.21 135 11.9 142 3.09 9 11.1 48 13.9 44 3.61 27 6.50 63 12.6 63 2.31 29 7.90 56 18.1 54 1.60 46 8.50 110 13.4 114 1.83 136
CNN-flow-warp+ref [117]77.2 2.90 9 5.43 11 1.25 92 4.10 84 5.95 72 1.83 118 4.92 102 7.63 115 2.45 76 6.13 101 7.85 35 3.72 124 11.3 79 14.2 79 4.51 133 6.03 19 11.6 18 2.46 95 9.00 120 20.8 125 1.65 66 7.91 43 12.4 44 1.76 92
LFNet_ROB [151]77.2 3.65 129 7.73 131 1.23 68 3.88 60 5.80 64 1.49 66 4.57 83 8.96 133 2.02 48 5.62 58 8.44 74 3.18 22 11.0 37 13.8 37 4.47 106 7.19 135 14.1 135 2.47 98 7.59 23 17.4 25 1.82 98 8.10 58 12.7 58 1.78 107
HBM-GC [105]77.6 3.08 42 5.90 47 1.26 104 3.97 72 6.04 84 1.41 46 3.92 32 5.62 14 2.87 95 5.54 43 8.03 49 3.21 33 11.7 132 14.7 128 4.58 144 7.66 145 15.0 145 2.69 143 8.36 86 19.3 89 1.55 26 7.86 37 12.3 34 1.76 92
Classic+CPF [83]77.8 3.12 55 5.96 58 1.21 21 3.72 42 5.51 42 1.39 38 4.39 74 7.38 106 2.27 65 5.32 11 7.70 25 3.18 22 11.7 132 14.8 134 4.50 120 7.18 134 14.0 134 2.45 92 8.79 114 20.2 112 1.57 35 8.71 126 13.7 125 1.73 49
Efficient-NL [60]77.8 3.05 35 5.77 35 1.21 21 3.90 65 5.84 67 1.38 35 5.90 123 6.94 81 4.19 129 5.59 52 8.09 52 3.20 31 11.5 106 14.4 100 4.40 97 6.87 115 13.4 116 2.40 69 8.85 115 20.5 117 1.68 73 8.57 116 13.4 114 1.66 3
2D-CLG [1]77.8 3.01 27 5.65 23 1.28 112 4.59 126 6.17 95 1.95 134 5.18 109 6.06 37 3.15 106 6.01 93 7.88 37 3.97 133 11.4 90 14.4 100 4.69 146 5.98 16 11.5 15 2.45 92 8.89 118 20.5 117 1.67 69 7.74 24 12.0 19 1.71 30
Horn & Schunck [3]78.1 3.16 69 5.83 38 1.26 104 4.91 139 6.65 135 1.92 126 6.13 126 6.85 73 3.53 116 6.80 124 9.10 106 3.57 111 10.9 33 13.7 34 3.59 14 6.16 31 11.9 31 2.32 37 8.63 103 19.5 99 1.84 100 7.91 43 12.3 34 1.73 49
FC-2Layers-FF [74]78.8 3.18 79 6.16 75 1.22 48 3.33 5 4.73 4 1.35 30 4.34 70 7.09 91 3.11 103 5.56 46 8.29 62 3.29 57 11.5 106 14.5 111 4.48 109 7.00 126 13.7 125 2.48 104 8.92 119 20.6 120 1.71 78 8.30 89 13.0 85 1.73 49
SRR-TVOF-NL [91]79.2 3.32 104 6.46 99 1.23 68 3.96 69 5.96 75 1.59 76 4.68 89 7.90 122 3.52 115 5.99 91 8.77 92 3.23 43 11.2 62 14.1 65 4.45 104 6.79 109 13.2 109 2.31 29 7.88 53 18.0 52 1.50 4 8.37 97 13.1 94 1.75 80
FESL [72]79.3 3.16 69 6.02 65 1.21 21 3.65 32 5.42 35 1.35 30 4.39 74 7.61 114 2.18 58 5.71 62 8.35 68 3.30 66 11.6 122 14.7 128 4.51 133 6.73 99 13.1 99 2.47 98 8.70 107 20.1 108 1.56 31 8.42 101 13.2 103 1.75 80
RFlow [90]79.4 3.08 42 5.99 63 1.23 68 4.33 101 6.31 112 1.66 91 4.83 99 7.32 100 3.14 104 5.87 79 8.72 91 3.47 97 11.1 48 14.0 57 3.60 21 6.54 70 12.7 71 2.39 66 8.54 96 19.8 103 1.61 48 8.26 81 12.9 72 1.80 126
TriFlow [95]81.0 3.71 133 7.95 135 1.25 92 4.31 100 6.36 117 1.71 103 4.05 40 6.86 75 1.84 35 6.21 107 9.44 118 3.17 19 11.3 79 14.2 79 4.48 109 6.76 105 13.1 99 2.29 21 8.01 67 18.2 59 1.75 88 8.24 76 12.9 72 1.70 17
OFH [38]81.4 3.18 79 6.29 81 1.23 68 4.11 86 5.96 75 1.61 83 4.68 89 8.40 127 1.68 25 5.84 74 8.99 102 3.03 2 11.3 79 14.2 79 4.25 89 6.30 43 12.2 42 2.40 69 8.59 98 19.3 89 1.89 104 8.55 113 13.4 114 1.97 144
3DFlow [135]82.2 3.26 92 6.37 92 1.21 21 3.70 39 5.55 44 1.46 60 4.51 81 6.52 61 2.28 66 5.84 74 8.84 95 3.59 113 11.2 62 14.1 65 3.79 67 7.04 131 13.7 125 2.68 142 8.59 98 19.4 93 1.82 98 8.26 81 12.9 72 1.77 101
Nguyen [33]82.4 3.26 92 6.11 71 1.33 131 4.94 140 6.51 125 1.91 124 4.09 45 7.32 100 1.96 44 6.19 106 8.53 82 3.60 115 11.1 48 13.9 44 3.58 12 6.55 71 12.7 71 2.36 53 9.44 132 21.8 135 1.80 96 7.86 37 12.3 34 1.74 70
CostFilter [40]82.9 3.46 116 7.24 124 1.19 3 3.71 40 5.60 46 1.27 6 5.63 119 9.41 140 3.86 122 6.37 115 10.1 130 3.23 43 11.2 62 14.0 57 3.78 66 6.35 49 12.2 42 2.40 69 8.86 117 20.6 120 1.69 74 8.80 130 13.8 129 1.74 70
PWC-Net_ROB [148]82.9 3.66 132 7.76 132 1.21 21 3.91 67 5.97 79 1.37 33 3.88 31 6.73 68 1.48 11 6.36 113 10.1 130 3.13 14 11.8 137 14.9 138 4.49 116 6.78 108 13.1 99 2.34 42 7.72 37 17.7 39 1.66 68 8.57 116 13.5 120 1.88 139
S2D-Matching [84]83.0 3.21 83 6.22 77 1.22 48 3.97 72 5.95 72 1.48 63 4.57 83 7.70 118 2.84 92 5.48 36 8.06 51 3.48 99 11.4 90 14.3 89 4.14 82 6.97 123 13.6 123 2.56 129 8.09 70 18.6 73 1.74 83 8.21 71 12.9 72 1.76 92
SVFilterOh [111]83.3 3.23 86 6.35 90 1.23 68 3.53 16 5.19 18 1.31 19 5.91 124 8.20 125 4.22 130 5.75 66 8.52 81 3.43 92 11.4 90 14.3 89 4.53 141 6.97 123 13.6 123 2.38 64 7.94 57 18.3 66 1.57 35 8.31 91 13.0 85 1.79 120
Steered-L1 [118]84.0 2.97 20 5.73 31 1.21 21 3.81 50 5.72 56 1.60 80 8.15 138 9.24 137 6.46 145 6.42 117 9.21 113 4.28 140 11.4 90 14.3 89 3.80 68 6.52 67 12.7 71 2.43 87 8.20 75 19.0 82 2.54 135 8.33 93 13.1 94 1.70 17
Adaptive [20]84.4 3.24 89 6.44 96 1.25 92 4.57 124 6.61 130 1.72 104 3.94 34 6.12 43 1.81 31 5.86 77 8.66 88 3.47 97 11.6 122 14.6 121 3.59 14 6.55 71 12.7 71 2.51 114 9.03 122 20.6 120 1.59 40 8.13 61 12.7 58 1.78 107
FlowNet2 [122]84.5 4.84 144 10.1 145 1.29 118 4.11 86 6.13 93 1.61 83 4.73 93 7.06 89 2.36 72 6.36 113 10.0 128 3.38 83 11.2 62 14.1 65 3.71 54 6.44 58 12.5 59 2.33 40 8.45 92 19.4 93 1.61 48 8.03 54 12.6 54 1.77 101
TVL1_ROB [139]84.5 3.32 104 6.25 79 1.36 137 5.03 142 6.77 142 1.94 132 4.50 80 6.70 67 2.55 81 6.22 108 8.66 88 3.63 117 10.8 25 13.6 28 3.63 38 6.52 67 12.7 71 2.43 87 9.03 122 20.7 124 2.13 124 7.72 23 12.1 24 1.70 17
IAOF [50]84.7 3.53 122 6.60 105 1.32 129 5.39 148 7.19 148 1.96 135 5.81 121 7.32 100 3.63 118 6.15 103 8.34 67 3.72 124 11.1 48 14.0 57 3.60 21 6.50 63 12.6 63 2.34 42 8.28 82 19.0 82 1.53 14 7.94 47 12.4 44 1.73 49
Complementary OF [21]86.5 3.48 117 7.32 128 1.20 7 3.89 63 5.96 75 1.45 56 8.94 142 6.94 81 5.45 140 6.33 111 10.0 128 3.09 9 11.3 79 14.2 79 4.24 87 6.33 44 12.3 49 2.42 83 8.62 102 19.3 89 1.75 88 9.07 139 14.3 140 1.72 40
FF++_ROB [146]87.8 3.27 95 6.67 108 1.20 7 3.74 45 5.58 45 1.38 35 4.86 100 7.42 107 2.99 97 6.57 121 10.4 133 3.54 108 11.5 106 14.5 111 4.51 133 6.62 88 12.8 83 2.47 98 7.97 60 18.3 66 1.90 105 8.24 76 12.9 72 1.78 107
TV-L1-improved [17]88.1 3.09 47 6.03 66 1.25 92 4.55 121 6.59 129 1.70 101 5.88 122 5.66 16 4.09 126 5.53 41 7.88 37 3.22 37 11.4 90 14.4 100 3.61 27 6.73 99 13.1 99 2.51 114 9.48 133 22.1 137 1.94 110 8.25 79 12.9 72 1.79 120
AugFNG_ROB [144]88.2 3.73 134 7.90 134 1.25 92 4.12 89 6.02 83 1.74 106 4.70 92 8.79 132 1.94 42 8.14 144 13.4 145 3.29 57 12.0 143 15.1 143 4.50 120 6.50 63 12.6 63 2.28 17 8.03 68 18.3 66 1.62 56 7.75 25 12.1 24 1.75 80
TI-DOFE [24]88.4 3.41 111 6.44 96 1.44 143 5.20 146 6.82 145 2.01 139 4.19 56 6.41 52 1.88 37 6.98 128 9.50 120 3.70 122 10.8 25 13.6 28 3.61 27 6.59 82 12.8 83 2.36 53 8.13 72 18.2 59 1.77 93 8.53 112 12.4 44 2.33 148
EPPM w/o HM [88]89.1 3.35 108 6.86 116 1.21 21 3.85 56 5.88 71 1.29 13 7.03 133 9.47 143 3.97 125 6.15 103 9.51 121 3.38 83 10.6 19 13.3 19 3.62 32 7.00 126 13.7 125 2.37 57 8.85 115 20.5 117 2.62 139 8.42 101 13.2 103 1.76 92
GraphCuts [14]90.5 3.65 129 7.01 119 1.27 108 3.89 63 5.71 54 1.59 76 7.54 136 5.84 25 4.31 133 5.98 90 8.42 72 3.45 96 11.4 90 14.4 100 4.09 79 6.56 74 12.8 83 2.30 26 8.70 107 20.2 112 1.98 112 8.59 120 13.5 120 1.73 49
BriefMatch [124]90.9 3.25 91 6.49 100 1.25 92 3.87 57 5.67 49 1.97 137 6.16 127 6.17 46 4.79 136 6.83 126 8.37 69 5.73 147 11.0 37 13.8 37 3.73 59 6.75 104 13.0 94 2.61 133 7.99 62 17.9 47 3.29 146 8.22 73 12.8 66 2.32 147
NL-TV-NCC [25]92.6 3.37 110 6.58 104 1.24 82 4.23 95 6.41 120 1.49 66 4.39 74 6.68 66 2.07 50 7.19 134 11.2 139 3.35 81 10.7 22 13.4 21 4.00 76 6.95 120 13.4 116 2.44 90 9.06 124 20.0 106 2.13 124 8.42 101 13.1 94 1.78 107
EPMNet [133]93.2 4.90 145 10.5 149 1.28 112 4.04 79 5.98 81 1.60 80 4.73 93 7.06 89 2.36 72 8.74 147 15.0 148 3.48 99 11.2 62 14.1 65 3.71 54 6.70 94 13.0 94 2.34 42 8.45 92 19.4 93 1.61 48 8.38 99 13.1 94 1.78 107
IAOF2 [51]94.2 3.43 113 6.70 110 1.28 112 4.62 129 6.77 142 1.74 106 4.41 78 6.89 77 2.12 55 5.97 88 8.53 82 3.33 77 11.6 122 14.7 128 4.06 78 6.87 115 13.4 116 2.51 114 8.26 79 18.7 77 1.61 48 8.22 73 12.9 72 1.74 70
TriangleFlow [30]95.1 3.24 89 6.31 86 1.26 104 4.29 99 6.29 110 1.66 91 4.67 88 6.85 73 2.48 77 5.78 70 8.47 76 3.30 66 11.4 90 14.4 100 3.47 6 6.63 89 12.8 83 2.37 57 9.67 137 22.5 138 2.08 121 9.69 146 15.2 146 1.90 141
ResPWCR_ROB [145]96.1 3.52 121 7.36 129 1.23 68 4.06 81 6.18 98 1.53 71 4.57 83 6.90 79 1.91 39 7.44 138 12.2 143 3.40 88 11.5 106 14.6 121 4.39 96 7.10 132 13.7 125 2.54 122 7.81 48 17.8 43 1.67 69 9.04 138 14.2 138 1.71 30
LocallyOriented [52]96.2 3.29 98 6.53 102 1.26 104 4.64 130 6.69 137 1.74 106 5.61 118 7.56 112 3.67 119 6.73 122 9.84 127 3.18 22 11.5 106 14.4 100 3.71 54 6.57 77 12.7 71 2.45 92 8.71 111 19.3 89 1.71 78 8.40 100 13.1 94 1.72 40
Correlation Flow [75]98.0 3.27 95 6.50 101 1.20 7 4.42 108 6.56 128 1.65 88 3.98 36 6.10 41 2.30 70 5.93 85 8.94 99 3.32 74 11.6 122 14.6 121 3.84 69 7.63 144 14.8 142 2.65 140 9.95 142 23.0 142 2.01 117 8.73 127 13.7 125 1.71 30
ROF-ND [107]98.4 3.18 79 5.83 38 1.21 21 4.13 90 6.13 93 1.92 126 4.22 59 7.51 110 2.22 62 7.10 130 10.8 134 3.53 106 11.4 90 14.3 89 4.48 109 6.95 120 13.5 120 2.53 120 8.21 77 18.6 73 1.90 105 9.08 140 14.2 138 1.81 133
ACK-Prior [27]99.1 3.30 99 6.56 103 1.21 21 3.81 50 5.78 59 1.42 48 7.13 134 6.90 79 5.04 137 6.02 96 8.78 93 3.70 122 11.7 132 14.7 128 4.57 143 6.95 120 13.5 120 2.50 110 8.36 86 19.2 86 2.53 134 8.56 115 13.4 114 1.73 49
StereoOF-V1MT [119]99.2 3.56 123 7.20 123 1.22 48 4.27 98 6.18 98 1.70 101 6.10 125 6.80 71 3.43 114 7.17 133 9.52 122 4.01 136 11.2 62 14.1 65 4.43 99 6.61 87 12.5 59 2.60 131 9.49 134 21.6 131 2.05 118 8.01 52 12.4 44 1.78 107
HBpMotionGpu [43]99.4 3.63 127 7.28 126 1.35 136 4.78 135 6.69 137 1.92 126 4.33 69 7.01 87 2.56 82 6.46 118 9.81 126 3.40 88 11.5 106 14.4 100 5.69 151 6.83 111 13.3 112 2.55 125 7.40 12 16.9 10 1.51 8 8.30 89 13.0 85 1.79 120
Aniso-Texture [82]102.0 3.11 53 6.09 69 1.21 21 4.51 115 6.62 132 1.75 109 4.77 97 6.43 53 2.08 53 7.44 138 10.9 135 4.80 142 11.6 122 14.6 121 4.51 133 7.49 141 14.7 140 2.71 145 8.28 82 19.1 85 1.61 48 8.68 121 13.6 122 1.74 70
Dynamic MRF [7]103.8 3.19 82 6.41 94 1.22 48 4.11 86 6.21 101 1.56 72 5.37 115 7.35 103 2.70 88 6.74 123 9.18 111 4.19 138 11.1 48 13.9 44 4.48 109 7.02 129 13.7 125 2.62 136 9.26 128 21.4 130 2.23 129 8.57 116 13.3 109 1.80 126
FOLKI [16]104.1 3.64 128 7.12 121 1.65 146 5.22 147 6.72 140 2.36 145 5.20 110 8.08 123 3.96 124 7.93 141 9.33 114 5.52 146 11.2 62 14.0 57 3.70 51 6.56 74 12.6 63 2.74 148 8.00 65 18.2 59 2.88 143 7.96 50 12.3 34 1.78 107
LiteFlowNet [143]104.2 3.86 136 8.34 138 1.22 48 3.80 49 5.75 58 1.44 53 5.33 114 9.45 142 2.66 86 8.72 146 14.4 147 3.88 128 11.8 137 14.8 134 4.50 120 7.03 130 13.7 125 2.40 69 9.07 126 20.4 116 1.69 74 8.13 61 12.7 58 1.78 107
Shiralkar [42]105.1 3.57 124 7.31 127 1.22 48 4.46 113 6.33 116 1.65 88 5.49 116 6.98 84 2.73 89 7.42 137 10.9 135 3.43 92 11.5 106 14.4 100 3.73 59 6.57 77 12.7 71 2.48 104 9.58 135 21.9 136 1.88 103 9.18 142 14.4 141 1.75 80
SILK [79]105.8 3.45 115 6.85 115 1.36 137 5.11 144 6.70 139 2.21 143 11.1 146 9.96 144 6.24 144 6.49 119 8.82 94 3.59 113 11.4 90 14.3 89 3.54 7 6.87 115 13.3 112 2.63 137 7.76 42 17.7 39 1.87 102 8.20 69 12.7 58 1.80 126
SimpleFlow [49]106.2 3.10 49 5.97 60 1.22 48 4.19 93 6.11 91 1.64 87 9.91 145 9.43 141 6.53 146 5.58 49 8.29 62 3.30 66 11.6 122 14.6 121 4.43 99 7.42 138 14.6 139 2.56 129 10.7 146 25.2 146 2.73 141 9.16 141 14.4 141 1.73 49
Learning Flow [11]106.4 3.14 62 6.09 69 1.27 108 4.51 115 6.53 126 1.67 94 11.5 150 12.9 150 7.17 149 6.31 110 8.30 64 3.66 119 11.7 132 14.8 134 3.89 71 6.59 82 12.8 83 2.48 104 8.27 81 18.9 79 1.96 111 8.68 121 13.4 114 1.80 126
Rannacher [23]106.4 3.31 101 6.72 112 1.25 92 4.60 127 6.66 136 1.72 104 6.36 130 6.54 62 4.25 131 5.91 83 8.87 96 3.49 101 11.5 106 14.5 111 3.63 38 6.73 99 13.1 99 2.53 120 9.35 131 21.7 134 1.98 112 8.70 124 13.7 125 1.75 80
Adaptive flow [45]109.6 3.60 126 6.30 83 1.54 145 5.14 145 6.79 144 2.14 142 4.52 82 6.60 63 3.01 99 6.54 120 8.64 87 4.23 139 12.1 146 15.2 144 4.09 79 7.57 142 14.9 144 2.64 139 7.75 40 17.8 43 2.28 131 8.47 109 13.3 109 1.71 30
OFRF [134]109.7 4.02 138 8.26 137 1.33 131 4.53 119 6.49 123 1.81 116 4.60 87 7.27 98 2.13 56 6.02 96 9.15 108 3.39 86 11.8 137 14.9 138 4.23 86 7.13 133 13.9 133 2.39 66 9.02 121 20.8 125 1.59 40 8.79 129 13.8 129 1.77 101
H+S_ROB [138]110.0 3.43 113 6.69 109 1.29 118 4.55 121 6.05 85 1.91 124 11.3 147 12.3 149 7.31 150 6.98 128 8.51 80 3.51 102 11.4 90 14.4 100 3.65 45 6.60 84 12.8 83 2.42 83 9.86 140 22.7 140 2.08 121 8.84 133 13.7 125 1.74 70
UnFlow [129]110.9 4.05 139 8.73 142 1.31 126 4.44 112 6.28 109 1.87 120 4.92 102 7.36 105 2.62 83 5.95 87 9.00 103 3.27 53 12.0 143 15.2 144 4.37 94 7.59 143 14.8 142 2.61 133 7.77 44 17.6 35 1.64 61 10.4 147 15.4 147 2.33 148
StereoFlow [44]111.6 5.35 150 10.3 147 1.42 142 5.03 142 7.21 149 1.76 112 4.14 49 6.94 81 2.01 46 5.83 73 8.55 84 3.33 77 13.7 148 17.3 148 4.70 147 8.71 149 17.2 149 2.70 144 7.88 53 18.1 54 1.61 48 8.82 132 13.9 134 1.79 120
2bit-BM-tele [98]112.5 3.31 101 6.41 94 1.34 135 4.53 119 6.62 132 1.80 115 6.23 128 9.24 137 6.19 143 5.94 86 8.59 86 3.55 109 11.3 79 14.2 79 4.03 77 7.72 146 15.1 146 3.02 149 12.2 150 28.7 151 4.77 151 7.76 29 12.1 24 1.82 135
IIOF-NLDP [131]114.2 3.36 109 6.62 106 1.21 21 4.22 94 6.32 114 1.59 76 5.16 108 7.63 115 2.63 85 6.10 98 9.20 112 3.53 106 11.6 122 14.6 121 4.79 149 7.42 138 14.5 138 2.71 145 12.0 149 28.2 149 3.38 147 8.93 135 13.9 134 1.74 70
SPSA-learn [13]117.2 3.89 137 7.79 133 1.27 108 4.43 110 6.17 95 1.81 116 9.03 143 8.47 130 5.47 141 6.80 124 9.40 117 3.72 124 11.5 106 14.5 111 3.91 73 6.51 66 12.6 63 2.46 95 11.9 147 27.9 148 4.54 149 10.5 149 16.5 149 1.75 80
FFV1MT [106]117.4 4.09 141 8.38 139 1.31 126 4.68 132 6.18 98 2.02 140 6.95 132 11.5 146 3.35 112 7.12 131 9.16 109 3.98 134 11.3 79 14.1 65 3.74 62 6.77 106 12.7 71 2.50 110 9.59 136 21.0 127 2.05 118 8.87 134 13.8 129 1.90 141
SegOF [10]120.5 3.51 119 7.12 121 1.32 129 4.17 92 6.10 89 1.59 76 8.69 140 7.75 120 5.15 138 8.58 145 14.3 146 4.29 141 11.7 132 14.8 134 4.50 120 6.79 109 13.2 109 2.50 110 10.1 143 23.5 143 2.55 136 8.80 130 13.8 129 1.72 40
PGAM+LK [55]122.0 4.08 140 8.41 140 1.65 146 4.74 134 6.45 121 2.27 144 8.87 141 12.2 147 6.88 147 8.06 143 10.9 135 4.83 143 11.4 90 14.3 89 3.90 72 6.83 111 13.2 109 2.55 125 8.26 79 18.9 79 2.27 130 8.55 113 13.3 109 1.90 141
Heeger++ [104]122.4 4.76 143 9.63 144 1.33 131 4.65 131 6.22 104 1.90 122 7.84 137 9.26 139 3.57 117 7.12 131 9.16 109 3.98 134 11.9 141 15.0 141 4.47 106 6.52 67 12.2 42 2.61 133 9.82 138 20.6 120 2.00 115 9.02 137 14.0 136 1.79 120
SLK [47]124.0 3.51 119 6.96 118 1.41 140 4.72 133 6.10 89 1.98 138 9.84 144 7.59 113 5.20 139 7.98 142 11.0 138 6.14 148 11.8 137 14.9 138 3.71 54 6.60 84 12.7 71 2.50 110 9.87 141 22.8 141 2.08 121 8.94 136 14.0 136 2.03 145
HCIC-L [99]126.1 4.98 147 9.28 143 1.77 149 4.97 141 6.87 147 2.11 141 5.70 120 10.0 145 4.41 135 7.85 140 11.8 140 3.68 121 10.9 33 13.7 34 3.72 58 8.18 148 16.1 148 2.55 125 9.06 124 21.0 127 2.58 138 9.57 145 15.0 145 1.81 133
WOLF_ROB [149]128.8 5.06 148 10.3 147 1.30 122 4.79 137 6.72 140 1.75 109 6.29 129 9.03 135 4.14 128 7.37 136 11.8 140 3.33 77 11.9 141 15.0 141 4.48 109 7.40 137 14.3 136 2.51 114 10.5 145 23.9 144 1.74 83 9.44 143 14.8 143 1.78 107
Pyramid LK [2]135.9 4.16 142 8.44 141 1.74 148 5.83 149 6.82 145 2.76 149 11.4 148 8.60 131 5.89 142 12.4 150 16.7 149 7.03 150 14.3 149 18.1 149 3.92 75 6.69 93 12.2 42 2.63 137 10.3 144 24.0 145 2.45 133 11.1 150 17.4 150 2.55 150
GroupFlow [9]138.4 4.94 146 10.2 146 1.36 137 4.51 115 6.50 124 1.92 126 8.67 139 9.13 136 4.38 134 8.83 148 13.0 144 5.40 145 12.9 147 16.3 147 4.53 141 7.89 147 15.5 147 2.65 140 9.85 139 22.6 139 1.91 107 9.52 144 14.9 144 1.88 139
Periodicity [78]148.8 5.27 149 11.1 150 1.83 150 7.09 150 7.33 150 2.86 150 11.4 148 12.2 147 7.13 148 10.5 149 17.1 150 6.14 148 14.9 150 19.0 150 4.71 148 9.13 150 17.9 150 3.16 150 11.9 147 27.8 147 3.76 148 10.4 147 15.8 148 2.29 146
AVG_FLOW_ROB [142]150.9 14.6 151 20.0 151 3.66 151 11.3 151 12.1 151 4.33 151 13.4 151 14.1 151 7.93 151 19.0 151 25.3 151 10.2 151 18.3 151 23.1 151 5.58 150 16.7 151 32.2 151 4.90 151 16.6 151 28.6 150 4.56 150 15.9 151 19.8 151 4.61 151
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

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