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
MDP-Flow2 [68]14.6 2.89 6 5.38 7 1.19 2 3.47 9 5.07 12 1.26 1 3.66 13 6.10 37 2.48 69 5.20 3 7.48 12 3.14 11 10.2 4 12.8 6 3.61 25 6.13 22 11.8 19 2.31 25 7.36 7 16.8 5 1.49 2 7.75 22 12.1 22 1.69 9
PMMST [114]14.7 2.90 7 5.43 9 1.20 6 3.50 13 5.05 10 1.27 6 3.56 4 5.46 4 1.82 31 5.38 19 7.92 38 3.41 81 10.2 4 12.8 6 3.60 19 5.76 4 11.0 4 2.26 6 7.39 8 16.9 8 1.53 13 7.57 8 11.8 8 1.72 36
SuperSlomo [132]16.4 2.51 1 4.32 1 1.25 82 3.66 32 5.06 11 1.93 118 2.91 1 4.00 1 1.41 7 5.05 1 6.27 1 3.66 106 9.56 1 11.9 1 3.30 2 5.37 2 10.2 2 2.24 2 6.69 1 15.0 1 1.53 13 6.73 2 10.4 2 1.66 2
SepConv-v1 [127]21.8 2.52 2 4.83 2 1.11 1 3.56 21 5.04 9 1.90 110 4.17 49 4.15 2 2.86 83 5.41 28 6.81 2 3.88 115 10.2 4 12.8 6 3.37 3 5.47 3 10.4 3 2.21 1 6.88 2 15.6 2 1.72 71 6.63 1 10.3 1 1.62 1
DeepFlow [86]23.4 2.98 19 5.67 24 1.22 44 3.88 54 5.78 53 1.52 62 3.62 6 5.93 31 1.34 3 5.39 24 7.20 7 3.17 15 11.0 34 13.9 39 3.63 35 5.91 9 11.3 8 2.29 17 7.14 3 16.3 3 1.49 2 7.80 28 12.2 26 1.70 15
CBF [12]26.7 2.83 3 5.20 3 1.23 62 3.97 63 5.79 56 1.56 64 3.62 6 5.47 5 1.60 18 5.21 4 7.12 4 3.29 50 10.1 2 12.6 2 3.62 29 5.97 12 11.5 12 2.31 25 7.76 36 17.8 37 1.61 42 7.60 11 11.9 11 1.76 84
DeepFlow2 [108]28.1 2.99 22 5.65 21 1.22 44 3.88 54 5.79 56 1.48 57 3.62 6 6.03 32 1.34 3 5.38 19 7.44 11 3.22 31 11.0 34 13.8 34 3.67 41 5.83 5 11.2 5 2.25 5 7.60 20 17.4 22 1.50 4 7.82 29 12.2 26 1.77 93
SuperFlow [81]29.2 2.94 11 5.56 17 1.24 73 3.99 66 5.78 53 1.67 85 4.06 39 5.55 7 1.83 32 5.52 38 7.07 3 3.20 25 10.2 4 12.7 4 3.68 44 6.13 22 11.8 19 2.24 2 7.68 28 17.5 26 1.77 82 7.44 6 11.6 5 1.69 9
NN-field [71]30.3 2.98 19 5.70 25 1.20 6 3.31 3 4.73 3 1.26 1 4.69 82 5.91 29 2.03 43 5.99 86 9.13 100 3.57 99 10.3 10 12.8 6 3.60 19 6.24 33 12.0 31 2.31 25 7.39 8 16.9 8 1.54 19 7.69 19 12.0 17 1.72 36
NNF-Local [87]30.3 2.92 10 5.51 15 1.19 2 3.30 2 4.71 2 1.26 1 3.65 11 5.91 29 2.29 61 5.76 64 8.70 83 3.55 97 10.3 10 12.9 12 3.60 19 6.42 51 12.4 50 2.34 37 7.57 17 17.4 22 1.74 73 7.61 12 11.9 11 1.72 36
Aniso. Huber-L1 [22]30.6 2.95 14 5.44 11 1.24 73 4.42 96 6.27 95 1.67 85 3.79 24 5.70 14 1.50 11 5.31 9 7.42 10 3.24 40 11.1 43 14.0 51 3.61 25 5.91 9 11.4 10 2.24 2 7.60 20 17.3 16 1.51 7 7.62 14 11.9 11 1.73 45
CLG-TV [48]31.6 2.94 11 5.45 12 1.25 82 4.26 84 6.17 83 1.60 71 3.68 17 5.73 16 1.73 27 5.36 15 7.41 9 3.32 66 11.1 43 14.0 51 3.57 8 5.88 8 11.3 8 2.26 6 7.58 18 17.0 12 1.57 32 7.75 22 12.1 22 1.72 36
IROF-TV [53]32.4 3.07 37 5.91 46 1.23 62 3.71 38 5.47 35 1.40 37 3.70 19 6.27 43 1.58 17 5.25 6 7.60 19 3.17 15 11.0 34 13.9 39 4.47 100 6.37 47 12.4 50 2.30 22 7.79 40 17.9 40 1.50 4 7.63 15 11.9 11 1.66 2
LME [70]32.8 2.95 14 5.59 19 1.19 2 3.68 35 5.50 38 1.38 32 4.06 39 7.00 78 1.71 26 5.38 19 7.92 38 3.18 18 11.2 56 14.1 59 4.51 120 6.29 38 12.2 38 2.31 25 7.33 5 16.8 5 1.51 7 7.83 30 12.3 30 1.70 15
IROF++ [58]33.5 3.03 28 5.77 33 1.20 6 3.59 24 5.31 23 1.33 24 4.32 62 6.61 60 2.25 56 5.06 2 7.14 5 3.16 14 11.0 34 13.9 39 4.44 96 6.34 43 12.3 45 2.27 11 7.54 16 17.3 16 1.64 54 8.09 52 12.7 53 1.69 9
NNF-EAC [103]34.5 3.01 25 5.60 20 1.25 82 3.63 27 5.36 28 1.29 13 4.17 49 7.03 80 2.99 86 5.50 37 7.96 40 3.28 48 11.2 56 14.1 59 3.60 19 5.86 7 11.2 5 2.26 6 7.43 12 17.0 12 1.54 19 7.79 27 12.2 26 1.73 45
CombBMOF [113]35.0 3.16 65 5.88 42 1.24 73 3.54 17 5.24 18 1.34 28 4.01 35 6.45 54 2.20 53 5.62 56 8.22 56 3.29 50 10.7 20 13.5 21 3.62 29 6.20 30 11.9 27 2.27 11 7.78 39 17.3 16 1.56 29 7.75 22 12.1 22 1.71 27
DF-Auto [115]35.2 2.94 11 5.34 5 1.23 62 3.99 66 5.84 60 1.65 79 3.85 29 6.73 63 1.55 16 5.38 19 7.54 14 3.25 42 10.4 13 13.0 13 3.70 46 6.17 29 11.9 27 2.28 14 7.94 49 18.2 51 1.75 77 7.68 17 12.0 17 1.71 27
WLIF-Flow [93]37.2 2.95 14 5.53 16 1.20 6 3.66 32 5.41 31 1.39 34 4.26 58 7.17 87 2.54 72 5.30 8 7.57 17 3.29 50 10.7 20 13.5 21 3.70 46 6.74 93 13.1 90 2.48 91 7.40 10 16.9 8 1.53 13 7.87 36 12.3 30 1.69 9
ALD-Flow [66]37.2 3.28 91 6.45 92 1.24 73 3.81 45 5.73 52 1.41 41 3.62 6 6.28 44 1.35 5 5.58 47 8.39 67 3.04 4 10.8 23 13.5 21 4.15 78 5.96 11 11.4 10 2.29 17 7.34 6 16.8 5 1.51 7 8.25 70 12.9 64 1.70 15
Second-order prior [8]38.0 2.91 9 5.39 8 1.24 73 4.26 84 6.21 88 1.56 64 3.82 26 6.34 46 1.62 19 5.39 24 7.68 21 3.04 4 11.1 43 13.9 39 3.59 12 6.14 25 11.9 27 2.31 25 7.61 22 17.4 22 1.63 53 7.90 38 12.4 40 1.78 99
PH-Flow [101]38.1 3.12 52 6.01 61 1.20 6 3.39 5 4.94 6 1.28 11 3.70 19 6.43 49 2.48 69 5.23 5 7.58 18 3.22 31 10.4 13 13.1 15 3.62 29 6.84 103 13.3 101 2.47 87 7.84 42 18.1 47 1.58 35 7.87 36 12.3 30 1.73 45
p-harmonic [29]38.9 3.00 23 5.72 27 1.21 19 4.33 89 6.24 93 1.69 90 3.60 5 6.07 36 1.39 6 5.70 57 7.87 33 3.29 50 11.0 34 13.8 34 3.63 35 6.02 15 11.6 15 2.34 37 7.67 26 17.5 26 1.70 66 7.92 42 12.4 40 1.72 36
Brox et al. [5]39.8 3.08 40 5.94 51 1.21 19 3.83 48 5.67 45 1.45 50 3.93 31 5.76 18 1.67 21 5.32 10 7.19 6 3.22 31 10.6 17 13.4 19 3.56 6 6.60 77 12.7 65 2.42 74 8.61 89 19.7 91 3.04 130 7.43 5 11.6 5 1.68 7
SIOF [67]41.2 3.06 35 5.74 31 1.24 73 4.40 95 6.40 106 1.63 77 4.17 49 7.43 99 1.93 37 5.40 27 7.75 26 3.44 84 10.1 2 12.6 2 3.58 10 6.10 19 11.8 19 2.29 17 7.52 14 17.2 15 1.53 13 7.96 46 12.5 49 1.73 45
FMOF [94]41.3 3.16 65 5.92 49 1.23 62 3.48 10 5.07 12 1.28 11 4.59 77 6.82 66 2.78 79 5.71 59 8.42 68 3.40 79 10.4 13 13.0 13 3.67 41 6.49 58 12.6 59 2.28 14 7.64 24 17.5 26 1.48 1 8.06 51 12.6 50 1.67 5
Local-TV-L1 [65]43.0 3.00 23 5.47 13 1.30 110 4.43 98 6.23 92 1.75 98 3.50 2 5.35 3 1.45 8 5.39 24 7.56 15 3.29 50 11.2 56 14.1 59 3.91 68 6.16 27 11.8 19 2.47 87 7.67 26 17.6 30 1.55 24 7.57 8 11.8 8 1.76 84
MDP-Flow [26]43.2 2.86 4 5.34 5 1.20 6 3.49 12 5.15 15 1.34 28 4.01 35 5.51 6 2.28 58 5.58 47 7.91 37 3.33 69 11.2 56 14.0 51 4.49 108 6.72 88 13.1 90 2.54 108 7.71 31 17.7 34 1.74 73 7.83 30 12.3 30 1.70 15
OAR-Flow [125]45.2 3.13 57 5.95 53 1.22 44 3.83 48 5.70 48 1.48 57 3.65 11 6.06 33 1.16 1 5.60 52 8.48 72 3.03 1 11.2 56 14.1 59 4.51 120 6.12 21 11.8 19 2.41 71 7.97 52 17.9 40 1.59 36 8.11 53 12.7 53 1.71 27
Modified CLG [34]48.4 2.87 5 5.32 4 1.24 73 4.51 103 6.21 88 1.96 120 4.15 47 6.45 54 2.67 76 5.56 44 7.69 22 3.64 105 10.8 23 13.5 21 3.63 35 6.36 46 12.3 45 2.39 58 7.46 13 17.1 14 1.56 29 7.86 33 12.3 30 1.75 73
Ad-TV-NDC [36]48.8 3.23 81 5.70 25 1.44 128 4.78 122 6.46 109 1.92 113 3.67 14 5.86 25 1.50 11 5.97 83 8.14 54 3.51 92 10.8 23 13.5 21 3.63 35 6.24 33 12.0 31 2.40 61 7.70 29 17.3 16 1.51 7 7.48 7 11.7 7 1.73 45
F-TV-L1 [15]48.9 3.30 93 6.36 85 1.29 107 4.39 94 6.32 101 1.62 76 3.80 25 5.90 28 1.76 28 5.61 53 7.97 42 3.31 63 10.9 30 13.6 26 3.59 12 5.84 6 11.2 5 2.33 35 7.70 29 17.6 30 1.79 84 7.61 12 11.9 11 1.78 99
2DHMM-SAS [92]50.2 3.10 46 5.91 46 1.21 19 4.10 73 6.05 74 1.46 54 4.38 66 7.10 84 2.07 44 5.38 19 7.78 30 3.22 31 11.3 73 14.3 82 4.42 92 6.33 40 12.2 38 2.26 6 7.95 51 18.2 51 1.64 54 8.19 59 12.8 58 1.70 15
CPM-Flow [116]50.3 3.17 70 6.31 80 1.21 19 3.54 17 5.26 20 1.31 19 4.22 55 5.88 27 1.45 8 6.11 94 9.48 112 3.31 63 11.1 43 13.9 39 4.50 111 6.28 37 12.1 35 2.32 32 7.66 25 17.6 30 1.74 73 8.18 57 12.8 58 1.76 84
TC/T-Flow [76]51.6 3.21 78 6.24 74 1.22 44 3.90 58 5.86 62 1.43 46 3.69 18 5.83 21 1.50 11 5.88 76 8.93 91 3.15 12 11.1 43 13.9 39 4.50 111 6.23 31 12.0 31 2.26 6 8.61 89 19.0 72 1.93 96 8.16 56 12.8 58 1.70 15
LDOF [28]51.8 3.03 28 5.66 23 1.28 101 4.06 71 5.53 40 2.40 131 4.32 62 6.43 49 2.00 40 5.45 33 7.56 15 3.60 103 10.2 4 12.7 4 3.59 12 6.39 48 12.4 50 2.29 17 8.36 76 19.4 83 2.21 113 7.57 8 11.8 8 1.86 124
COFM [59]52.1 3.03 28 5.76 32 1.22 44 3.55 20 5.21 17 1.32 22 3.82 26 6.98 76 2.81 80 5.41 28 7.97 42 3.30 58 10.8 23 13.6 26 3.62 29 7.01 117 13.7 114 2.40 61 8.00 56 18.5 60 1.98 99 7.91 39 12.4 40 1.80 114
Layers++ [37]53.4 2.96 17 5.56 17 1.22 44 3.29 1 4.64 1 1.26 1 4.07 41 7.24 88 3.08 89 5.48 34 8.10 50 3.25 42 12.0 129 15.2 129 4.62 130 7.29 122 14.3 122 2.44 79 7.63 23 17.5 26 1.54 19 7.84 32 12.3 30 1.70 15
ComplOF-FED-GPU [35]53.6 3.23 81 6.40 87 1.22 44 3.73 41 5.62 44 1.44 48 5.23 100 6.06 33 3.23 97 5.53 39 8.25 57 3.29 50 11.1 43 13.9 39 4.21 80 6.11 20 11.8 19 2.32 32 8.16 63 18.5 60 1.61 42 8.29 77 12.9 64 1.71 27
FlowFields [110]53.8 3.15 63 6.30 78 1.21 19 3.57 22 5.34 26 1.32 22 4.73 83 6.89 70 3.23 97 5.85 71 8.96 94 3.08 6 10.8 23 13.6 26 4.19 79 6.57 70 12.8 76 2.36 47 7.72 32 17.8 37 1.67 61 8.20 61 12.9 64 1.74 64
TV-L1-MCT [64]53.9 3.17 70 6.05 64 1.22 44 3.87 51 5.82 58 1.40 37 4.48 73 7.75 110 2.24 55 5.37 17 7.76 28 3.24 40 11.6 111 14.7 117 4.31 85 6.08 17 11.7 17 2.31 25 8.07 59 18.6 63 2.15 111 7.68 17 12.0 17 1.68 7
AdaConv-v1 [126]54.0 3.57 115 6.88 109 1.41 125 4.34 91 5.67 45 2.52 133 5.00 93 5.86 25 2.98 85 6.91 118 8.89 90 4.89 129 10.2 4 12.8 6 3.21 1 5.33 1 10.1 1 2.27 11 7.30 4 16.6 4 1.92 95 6.94 3 10.8 3 1.67 5
nLayers [57]54.2 3.03 28 5.72 27 1.21 19 3.48 10 5.09 14 1.31 19 5.60 104 7.52 102 4.26 118 5.61 53 8.33 62 3.29 50 11.6 111 14.6 111 4.31 85 6.66 81 12.9 83 2.40 61 7.58 18 17.3 16 1.59 36 7.94 43 12.4 40 1.69 9
CRTflow [80]54.8 3.09 44 5.91 46 1.27 97 4.35 92 6.31 99 1.68 88 4.15 47 7.26 89 1.84 33 5.33 12 7.51 13 3.38 74 11.0 34 13.8 34 4.48 102 6.09 18 11.7 17 2.30 22 8.55 86 19.8 92 1.55 24 8.19 59 12.8 58 1.72 36
DPOF [18]55.5 3.34 100 6.82 105 1.29 107 3.40 6 4.93 5 1.29 13 5.00 93 6.36 47 3.40 100 5.86 72 8.94 92 3.51 92 11.0 34 13.8 34 3.59 12 6.56 67 12.7 65 2.28 14 7.99 53 18.2 51 1.55 24 8.24 68 12.9 64 1.70 15
TC-Flow [46]55.6 3.31 95 6.70 102 1.22 44 3.91 60 5.95 64 1.45 50 3.64 10 5.84 22 1.28 2 5.70 57 8.50 74 3.22 31 11.2 56 14.1 59 4.44 96 6.34 43 12.3 45 2.41 71 7.79 40 17.9 40 1.55 24 8.42 92 13.2 94 1.74 64
AGIF+OF [85]56.3 3.12 52 5.95 53 1.20 6 3.64 29 5.39 29 1.40 37 3.96 33 6.44 53 2.28 58 5.48 34 8.03 46 3.25 42 11.4 83 14.3 82 4.49 108 6.91 108 13.5 109 2.37 51 7.85 44 17.9 40 1.54 19 8.44 96 13.2 94 1.73 45
Classic++ [32]57.4 3.05 33 5.85 38 1.24 73 4.08 72 6.08 75 1.52 62 3.74 22 5.58 10 1.53 15 5.72 61 8.12 52 3.21 27 11.4 83 14.3 82 3.74 57 6.68 83 13.0 85 2.42 74 8.35 75 19.2 76 1.62 50 8.21 63 12.9 64 1.73 45
PGM-C [120]57.5 3.17 70 6.29 76 1.21 19 3.58 23 5.32 24 1.33 24 5.01 95 6.14 40 1.90 36 6.14 97 9.63 117 3.23 37 11.2 56 14.1 59 4.50 111 6.14 25 11.8 19 2.34 37 8.20 65 18.9 69 1.59 36 8.46 99 13.3 100 1.73 45
Sparse-NonSparse [56]58.1 3.07 37 5.88 42 1.21 19 3.61 25 5.33 25 1.33 24 4.29 61 7.47 100 2.19 52 5.37 17 7.74 24 3.21 27 11.5 98 14.5 103 4.36 88 6.66 81 12.9 83 2.41 71 8.69 95 20.1 97 1.67 61 8.27 74 13.0 76 1.70 15
BlockOverlap [61]58.2 2.98 19 5.47 13 1.33 117 4.38 93 6.09 76 1.88 109 4.26 58 5.57 9 3.14 92 5.56 44 7.32 8 4.14 122 11.1 43 13.9 39 3.77 60 6.41 49 12.3 45 2.54 108 7.75 34 17.4 22 3.02 129 7.32 4 11.4 4 1.78 99
ProbFlowFields [128]58.9 3.15 63 6.32 82 1.21 19 3.53 14 5.26 20 1.29 13 5.03 96 7.35 95 3.73 107 5.43 31 7.97 42 3.25 42 11.1 43 14.0 51 4.50 111 6.48 56 12.6 59 2.55 110 7.99 53 18.4 59 2.57 122 7.78 26 12.2 26 1.75 73
MLDP_OF [89]59.7 3.08 40 5.98 58 1.21 19 4.01 68 6.01 72 1.49 60 3.67 14 6.14 40 1.47 10 5.78 65 8.13 53 3.95 117 11.3 73 14.2 73 3.87 65 6.71 86 13.0 85 2.51 101 7.73 33 17.7 34 1.71 68 8.18 57 12.8 58 1.76 84
PMF [73]60.1 3.14 59 6.13 69 1.20 6 3.73 41 5.60 42 1.27 6 5.24 101 8.98 122 3.76 108 5.75 62 8.56 79 3.28 48 10.8 23 13.6 26 3.62 29 6.55 64 12.7 65 2.35 44 8.41 81 19.5 88 1.64 54 8.57 106 13.4 105 1.70 15
S2F-IF [123]60.2 3.26 87 6.66 101 1.20 6 3.53 14 5.25 19 1.29 13 4.11 44 6.64 61 2.34 63 5.89 77 9.06 98 3.08 6 11.4 83 14.3 82 4.51 120 6.41 49 12.4 50 2.40 61 7.84 42 18.1 47 1.76 80 8.33 84 13.1 85 1.75 73
FlowNetS+ft+v [112]60.3 3.07 37 5.81 35 1.28 101 4.57 111 6.29 97 2.41 132 4.01 35 5.64 12 2.13 49 5.55 42 7.77 29 3.88 115 11.3 73 14.2 73 4.46 99 5.99 14 11.5 12 2.35 44 8.63 92 20.0 95 1.62 50 7.70 20 12.0 17 1.74 64
Sparse Occlusion [54]60.8 3.16 65 6.18 72 1.23 62 4.14 79 6.24 93 1.45 50 3.67 14 5.84 22 1.52 14 5.61 53 8.26 58 3.15 12 11.5 98 14.4 93 4.48 102 6.26 35 12.1 35 2.46 84 8.52 84 19.6 90 1.54 19 8.28 76 13.0 76 1.75 73
HAST [109]60.8 3.01 25 5.73 29 1.21 19 3.45 8 5.01 7 1.27 6 6.39 117 8.24 116 4.09 113 5.43 31 7.96 40 3.03 1 11.2 56 14.2 73 3.59 12 7.47 125 14.7 125 2.47 87 8.68 94 20.1 97 1.53 13 8.35 87 13.1 85 1.77 93
OFLAF [77]60.8 3.10 46 5.98 58 1.20 6 3.44 7 5.03 8 1.26 1 3.73 21 5.82 20 1.66 20 5.33 12 7.74 24 3.10 9 11.6 111 14.7 117 4.50 111 6.58 74 12.8 76 2.48 91 9.33 117 21.6 118 2.06 107 8.45 98 13.2 94 1.80 114
FlowFields+ [130]61.0 3.14 59 6.26 75 1.22 44 3.54 17 5.27 22 1.30 18 4.74 86 7.10 84 3.20 95 6.01 88 9.35 108 3.11 10 11.1 43 13.9 39 4.50 111 6.57 70 12.8 76 2.40 61 7.89 48 18.2 51 1.80 85 8.22 65 12.9 64 1.73 45
TF+OM [100]61.5 3.33 99 6.83 106 1.25 82 3.65 30 5.43 33 1.47 56 3.82 26 6.43 49 1.68 23 6.01 88 9.04 97 3.19 22 11.2 56 14.1 59 4.38 90 6.46 55 12.5 55 2.34 37 8.30 74 19.2 76 1.86 89 8.05 50 12.6 50 1.75 73
Filter Flow [19]61.7 3.13 57 5.90 44 1.28 101 4.56 110 6.38 105 1.85 107 4.22 55 6.28 44 2.10 47 5.91 78 7.97 42 3.44 84 10.4 13 13.1 15 3.69 45 6.43 53 12.5 55 2.40 61 8.17 64 18.8 68 1.62 50 7.94 43 12.4 40 1.78 99
Black & Anandan [4]64.5 3.22 80 5.87 40 1.30 110 4.82 124 6.55 114 1.78 102 7.16 121 7.10 84 3.93 110 6.25 102 8.49 73 3.35 72 10.9 30 13.7 31 3.56 6 6.33 40 12.2 38 2.37 51 8.23 68 18.6 63 1.64 54 7.67 16 11.9 11 1.69 9
EpicFlow [102]64.8 3.17 70 6.34 83 1.21 19 3.79 44 5.70 48 1.44 48 4.28 60 5.73 16 1.67 21 6.37 107 10.1 122 3.39 77 11.2 56 14.1 59 4.50 111 6.23 31 12.0 31 2.38 56 8.11 61 18.5 60 1.76 80 8.76 116 13.8 116 1.74 64
LSM [39]65.5 3.12 52 6.05 64 1.21 19 3.68 35 5.47 35 1.33 24 4.38 66 7.66 108 2.01 41 5.55 42 8.19 55 3.19 22 11.5 98 14.5 103 4.43 93 6.83 100 13.3 101 2.37 51 8.70 96 20.1 97 1.72 71 8.34 86 13.1 85 1.71 27
RNLOD-Flow [121]65.5 3.06 35 5.87 40 1.21 19 3.96 61 5.97 70 1.42 43 4.39 68 8.08 113 2.44 67 5.35 14 7.75 26 3.18 18 11.5 98 14.5 103 4.49 108 6.71 86 13.1 90 2.43 77 7.85 44 18.0 45 2.18 112 8.44 96 13.2 94 1.73 45
TCOF [69]65.8 3.12 52 5.94 51 1.21 19 4.60 114 6.64 121 1.76 100 4.13 45 7.30 91 1.81 29 5.42 30 7.88 34 3.25 42 11.3 73 14.2 73 3.63 35 6.42 51 12.4 50 2.36 47 9.08 114 21.0 114 1.59 36 8.37 88 13.1 85 1.76 84
Ramp [62]66.5 3.11 50 5.96 55 1.22 44 3.61 25 5.34 26 1.40 37 4.91 90 8.45 119 3.20 95 5.29 7 7.66 20 3.21 27 11.5 98 14.5 103 4.31 85 6.88 107 13.4 105 2.48 91 8.73 101 20.2 101 1.52 12 8.29 77 13.0 76 1.73 45
AggregFlow [97]67.1 3.80 122 8.08 123 1.23 62 3.87 51 5.83 59 1.43 46 4.21 54 6.79 64 2.85 82 6.11 94 9.36 109 3.31 63 10.6 17 13.3 17 3.67 41 6.13 22 11.8 19 2.34 37 8.70 96 19.8 92 2.30 117 8.27 74 13.0 76 1.75 73
Fusion [6]67.2 3.04 32 5.86 39 1.22 44 3.75 43 5.47 35 1.42 43 4.08 42 5.55 7 3.08 89 5.80 67 8.10 50 3.19 22 11.4 83 14.3 82 3.73 54 6.99 114 13.7 114 2.60 116 8.40 80 19.4 83 1.65 59 8.50 101 13.3 100 1.80 114
Classic+NL [31]67.5 3.10 46 5.92 49 1.23 62 3.66 32 5.40 30 1.39 34 4.78 88 8.42 118 3.01 87 5.36 15 7.78 30 3.30 58 11.5 98 14.5 103 4.24 82 6.73 89 13.1 90 2.40 61 8.74 102 20.2 101 1.70 66 8.29 77 13.0 76 1.71 27
ComponentFusion [96]68.3 3.41 104 7.08 112 1.20 6 3.63 27 5.44 34 1.27 6 4.20 53 6.49 56 2.43 66 5.59 50 8.38 66 3.32 66 11.4 83 14.4 93 4.11 76 6.26 35 12.1 35 2.35 44 9.30 116 21.6 118 2.80 127 8.68 110 13.6 111 1.73 45
Bartels [41]68.9 3.48 109 7.24 116 1.30 110 4.02 69 6.12 80 1.68 88 3.74 22 5.80 19 1.95 38 5.87 74 8.44 70 3.78 114 10.3 10 12.8 6 3.75 59 6.77 96 13.0 85 2.73 132 7.53 15 17.3 16 2.72 125 8.13 54 12.7 53 1.77 93
Occlusion-TV-L1 [63]69.1 3.14 59 6.13 69 1.25 82 4.47 102 6.61 117 1.66 82 3.51 3 5.71 15 1.70 25 6.33 104 9.58 116 3.51 92 11.0 34 13.9 39 3.57 8 6.48 56 12.6 59 2.52 105 8.36 76 18.1 47 2.00 102 8.32 83 13.0 76 1.79 108
CNN-flow-warp+ref [117]69.5 2.90 7 5.43 9 1.25 82 4.10 73 5.95 64 1.83 106 4.92 91 7.63 106 2.45 68 6.13 96 7.85 32 3.72 111 11.3 73 14.2 73 4.51 120 6.03 16 11.6 15 2.46 84 9.00 109 20.8 112 1.65 59 7.91 39 12.4 40 1.76 84
HBM-GC [105]69.8 3.08 40 5.90 44 1.26 93 3.97 63 6.04 73 1.41 41 3.92 30 5.62 11 2.87 84 5.54 41 8.03 46 3.21 27 11.7 121 14.7 117 4.58 129 7.66 130 15.0 130 2.69 128 8.36 76 19.3 79 1.55 24 7.86 33 12.3 30 1.76 84
2D-CLG [1]69.9 3.01 25 5.65 21 1.28 101 4.59 113 6.17 83 1.95 119 5.18 98 6.06 33 3.15 94 6.01 88 7.88 34 3.97 118 11.4 83 14.4 93 4.69 131 5.98 13 11.5 12 2.45 81 8.89 107 20.5 105 1.67 61 7.74 21 12.0 17 1.71 27
Horn & Schunck [3]70.5 3.16 65 5.83 36 1.26 93 4.91 125 6.65 122 1.92 113 6.13 113 6.85 67 3.53 103 6.80 115 9.10 99 3.57 99 10.9 30 13.7 31 3.59 12 6.16 27 11.9 27 2.32 32 8.63 92 19.5 88 1.84 88 7.91 39 12.3 30 1.73 45
Efficient-NL [60]70.6 3.05 33 5.77 33 1.21 19 3.90 58 5.84 60 1.38 32 5.90 110 6.94 73 4.19 115 5.59 50 8.09 49 3.20 25 11.5 98 14.4 93 4.40 91 6.87 104 13.4 105 2.40 61 8.85 104 20.5 105 1.68 64 8.57 106 13.4 105 1.66 2
Classic+CPF [83]70.8 3.12 52 5.96 55 1.21 19 3.72 40 5.51 39 1.39 34 4.39 68 7.38 98 2.27 57 5.32 10 7.70 23 3.18 18 11.7 121 14.8 123 4.50 111 7.18 121 14.0 121 2.45 81 8.79 103 20.2 101 1.57 32 8.71 114 13.7 113 1.73 45
RFlow [90]71.6 3.08 40 5.99 60 1.23 62 4.33 89 6.31 99 1.66 82 4.83 89 7.32 92 3.14 92 5.87 74 8.72 84 3.47 87 11.1 43 14.0 51 3.60 19 6.54 63 12.7 65 2.39 58 8.54 85 19.8 92 1.61 42 8.26 72 12.9 64 1.80 114
SRR-TVOF-NL [91]71.9 3.32 98 6.46 93 1.23 62 3.96 61 5.96 67 1.59 67 4.68 80 7.90 112 3.52 102 5.99 86 8.77 85 3.23 37 11.2 56 14.1 59 4.45 98 6.79 98 13.2 98 2.31 25 7.88 46 18.0 45 1.50 4 8.37 88 13.1 85 1.75 73
FC-2Layers-FF [74]71.9 3.18 74 6.16 71 1.22 44 3.33 4 4.73 3 1.35 30 4.34 65 7.09 83 3.11 91 5.56 44 8.29 59 3.29 50 11.5 98 14.5 103 4.48 102 7.00 115 13.7 114 2.48 91 8.92 108 20.6 108 1.71 68 8.30 80 13.0 76 1.73 45
FESL [72]72.4 3.16 65 6.02 62 1.21 19 3.65 30 5.42 32 1.35 30 4.39 68 7.61 105 2.18 51 5.71 59 8.35 64 3.30 58 11.6 111 14.7 117 4.51 120 6.73 89 13.1 90 2.47 87 8.70 96 20.1 97 1.56 29 8.42 92 13.2 94 1.75 73
TriFlow [95]73.3 3.71 121 7.95 122 1.25 82 4.31 88 6.36 104 1.71 93 4.05 38 6.86 69 1.84 33 6.21 101 9.44 111 3.17 15 11.3 73 14.2 73 4.48 102 6.76 95 13.1 90 2.29 17 8.01 58 18.2 51 1.75 77 8.24 68 12.9 64 1.70 15
OFH [38]74.0 3.18 74 6.29 76 1.23 62 4.11 75 5.96 67 1.61 74 4.68 80 8.40 117 1.68 23 5.84 69 8.99 95 3.03 1 11.3 73 14.2 73 4.25 84 6.30 39 12.2 38 2.40 61 8.59 87 19.3 79 1.89 92 8.55 103 13.4 105 1.97 129
3DFlow [135]74.8 3.26 87 6.37 86 1.21 19 3.70 37 5.55 41 1.46 54 4.51 74 6.52 57 2.28 58 5.84 69 8.84 88 3.59 101 11.2 56 14.1 59 3.79 62 7.04 119 13.7 114 2.68 127 8.59 87 19.4 83 1.82 87 8.26 72 12.9 64 1.77 93
Nguyen [33]74.8 3.26 87 6.11 68 1.33 117 4.94 126 6.51 112 1.91 112 4.09 43 7.32 92 1.96 39 6.19 100 8.53 76 3.60 103 11.1 43 13.9 39 3.58 10 6.55 64 12.7 65 2.36 47 9.44 119 21.8 122 1.80 85 7.86 33 12.3 30 1.74 64
S2D-Matching [84]75.1 3.21 78 6.22 73 1.22 44 3.97 63 5.95 64 1.48 57 4.57 76 7.70 109 2.84 81 5.48 34 8.06 48 3.48 89 11.4 83 14.3 82 4.14 77 6.97 112 13.6 112 2.56 114 8.09 60 18.6 63 1.74 73 8.21 63 12.9 64 1.76 84
CostFilter [40]75.4 3.46 108 7.24 116 1.19 2 3.71 38 5.60 42 1.27 6 5.63 106 9.41 127 3.86 109 6.37 107 10.1 122 3.23 37 11.2 56 14.0 51 3.78 61 6.35 45 12.2 38 2.40 61 8.86 106 20.6 108 1.69 65 8.80 118 13.8 116 1.74 64
SVFilterOh [111]75.5 3.23 81 6.35 84 1.23 62 3.53 14 5.19 16 1.31 19 5.91 111 8.20 115 4.22 116 5.75 62 8.52 75 3.43 82 11.4 83 14.3 82 4.53 126 6.97 112 13.6 112 2.38 56 7.94 49 18.3 58 1.57 32 8.31 82 13.0 76 1.79 108
Steered-L1 [118]76.0 2.97 18 5.73 29 1.21 19 3.81 45 5.72 51 1.60 71 8.15 124 9.24 124 6.46 131 6.42 109 9.21 106 4.28 125 11.4 83 14.3 82 3.80 63 6.52 61 12.7 65 2.43 77 8.20 65 19.0 72 2.54 120 8.33 84 13.1 85 1.70 15
FlowNet2 [122]76.4 4.84 130 10.1 131 1.29 107 4.11 75 6.13 81 1.61 74 4.73 83 7.06 81 2.36 64 6.36 106 10.0 120 3.38 74 11.2 56 14.1 59 3.71 49 6.44 54 12.5 55 2.33 35 8.45 82 19.4 83 1.61 42 8.03 49 12.6 50 1.77 93
IAOF [50]76.8 3.53 113 6.60 99 1.32 115 5.39 133 7.19 133 1.96 120 5.81 108 7.32 92 3.63 105 6.15 98 8.34 63 3.72 111 11.1 43 14.0 51 3.60 19 6.50 59 12.6 59 2.34 37 8.28 72 19.0 72 1.53 13 7.94 43 12.4 40 1.73 45
Adaptive [20]76.8 3.24 84 6.44 90 1.25 82 4.57 111 6.61 117 1.72 94 3.94 32 6.12 39 1.81 29 5.86 72 8.66 82 3.47 87 11.6 111 14.6 111 3.59 12 6.55 64 12.7 65 2.51 101 9.03 111 20.6 108 1.59 36 8.13 54 12.7 53 1.78 99
Complementary OF [21]78.7 3.48 109 7.32 120 1.20 6 3.89 56 5.96 67 1.45 50 8.94 128 6.94 73 5.45 126 6.33 104 10.0 120 3.09 8 11.3 73 14.2 73 4.24 82 6.33 40 12.3 45 2.42 74 8.62 91 19.3 79 1.75 77 9.07 125 14.3 126 1.72 36
TV-L1-improved [17]79.5 3.09 44 6.03 63 1.25 82 4.55 109 6.59 116 1.70 91 5.88 109 5.66 13 4.09 113 5.53 39 7.88 34 3.22 31 11.4 83 14.4 93 3.61 25 6.73 89 13.1 90 2.51 101 9.48 120 22.1 124 1.94 97 8.25 70 12.9 64 1.79 108
TI-DOFE [24]80.2 3.41 104 6.44 90 1.44 128 5.20 131 6.82 130 2.01 124 4.19 52 6.41 48 1.88 35 6.98 119 9.50 113 3.70 109 10.8 23 13.6 26 3.61 25 6.59 75 12.8 76 2.36 47 8.13 62 18.2 51 1.77 82 8.53 102 12.4 40 2.33 133
EPPM w/o HM [88]81.1 3.35 101 6.86 108 1.21 19 3.85 50 5.88 63 1.29 13 7.03 119 9.47 129 3.97 112 6.15 98 9.51 114 3.38 74 10.6 17 13.3 17 3.62 29 7.00 115 13.7 114 2.37 51 8.85 104 20.5 105 2.62 124 8.42 92 13.2 94 1.76 84
BriefMatch [124]82.1 3.25 86 6.49 94 1.25 82 3.87 51 5.67 45 1.97 122 6.16 114 6.17 42 4.79 122 6.83 117 8.37 65 5.73 132 11.0 34 13.8 34 3.73 54 6.75 94 13.0 85 2.61 118 7.99 53 17.9 40 3.29 131 8.22 65 12.8 58 2.32 132
GraphCuts [14]82.4 3.65 120 7.01 111 1.27 97 3.89 56 5.71 50 1.59 67 7.54 122 5.84 22 4.31 119 5.98 85 8.42 68 3.45 86 11.4 83 14.4 93 4.09 74 6.56 67 12.8 76 2.30 22 8.70 96 20.2 101 1.98 99 8.59 109 13.5 110 1.73 45
EPMNet [133]83.8 4.90 131 10.5 134 1.28 101 4.04 70 5.98 71 1.60 71 4.73 83 7.06 81 2.36 64 8.74 132 15.0 133 3.48 89 11.2 56 14.1 59 3.71 49 6.70 85 13.0 85 2.34 37 8.45 82 19.4 83 1.61 42 8.38 90 13.1 85 1.78 99
NL-TV-NCC [25]84.1 3.37 103 6.58 98 1.24 73 4.23 83 6.41 107 1.49 60 4.39 68 6.68 62 2.07 44 7.19 124 11.2 129 3.35 72 10.7 20 13.4 19 4.00 71 6.95 109 13.4 105 2.44 79 9.06 112 20.0 95 2.13 110 8.42 92 13.1 85 1.78 99
IAOF2 [51]85.4 3.43 106 6.70 102 1.28 101 4.62 116 6.77 128 1.74 96 4.41 72 6.89 70 2.12 48 5.97 83 8.53 76 3.33 69 11.6 111 14.7 117 4.06 73 6.87 104 13.4 105 2.51 101 8.26 69 18.7 67 1.61 42 8.22 65 12.9 64 1.74 64
TriangleFlow [30]86.0 3.24 84 6.31 80 1.26 93 4.29 87 6.29 97 1.66 82 4.67 79 6.85 67 2.48 69 5.78 65 8.47 71 3.30 58 11.4 83 14.4 93 3.47 4 6.63 80 12.8 76 2.37 51 9.67 124 22.5 125 2.08 108 9.69 131 15.2 131 1.90 126
LocallyOriented [52]87.4 3.29 92 6.53 96 1.26 93 4.64 117 6.69 124 1.74 96 5.61 105 7.56 103 3.67 106 6.73 113 9.84 119 3.18 18 11.5 98 14.4 93 3.71 49 6.57 70 12.7 65 2.45 81 8.71 100 19.3 79 1.71 68 8.40 91 13.1 85 1.72 36
Correlation Flow [75]88.9 3.27 90 6.50 95 1.20 6 4.42 96 6.56 115 1.65 79 3.98 34 6.10 37 2.30 62 5.93 80 8.94 92 3.32 66 11.6 111 14.6 111 3.84 64 7.63 129 14.8 127 2.65 125 9.95 128 23.0 128 2.01 104 8.73 115 13.7 113 1.71 27
ROF-ND [107]89.0 3.18 74 5.83 36 1.21 19 4.13 78 6.13 81 1.92 113 4.22 55 7.51 101 2.22 54 7.10 120 10.8 124 3.53 95 11.4 83 14.3 82 4.48 102 6.95 109 13.5 109 2.53 106 8.21 67 18.6 63 1.90 93 9.08 126 14.2 125 1.81 121
ACK-Prior [27]89.9 3.30 93 6.56 97 1.21 19 3.81 45 5.78 53 1.42 43 7.13 120 6.90 72 5.04 123 6.02 91 8.78 86 3.70 109 11.7 121 14.7 117 4.57 128 6.95 109 13.5 109 2.50 97 8.36 76 19.2 76 2.53 119 8.56 105 13.4 105 1.73 45
StereoOF-V1MT [119]90.1 3.56 114 7.20 115 1.22 44 4.27 86 6.18 86 1.70 91 6.10 112 6.80 65 3.43 101 7.17 123 9.52 115 4.01 121 11.2 56 14.1 59 4.43 93 6.61 79 12.5 55 2.60 116 9.49 121 21.6 118 2.05 105 8.01 48 12.4 40 1.78 99
HBpMotionGpu [43]90.2 3.63 118 7.28 118 1.35 122 4.78 122 6.69 124 1.92 113 4.33 64 7.01 79 2.56 73 6.46 110 9.81 118 3.40 79 11.5 98 14.4 93 5.69 135 6.83 100 13.3 101 2.55 110 7.40 10 16.9 8 1.51 7 8.30 80 13.0 76 1.79 108
Aniso-Texture [82]92.2 3.11 50 6.09 66 1.21 19 4.51 103 6.62 119 1.75 98 4.77 87 6.43 49 2.08 46 7.44 126 10.9 125 4.80 127 11.6 111 14.6 111 4.51 120 7.49 126 14.7 125 2.71 130 8.28 72 19.1 75 1.61 42 8.68 110 13.6 111 1.74 64
Dynamic MRF [7]93.9 3.19 77 6.41 88 1.22 44 4.11 75 6.21 88 1.56 64 5.37 102 7.35 95 2.70 77 6.74 114 9.18 104 4.19 123 11.1 43 13.9 39 4.48 102 7.02 118 13.7 114 2.62 121 9.26 115 21.4 117 2.23 114 8.57 106 13.3 100 1.80 114
FOLKI [16]94.3 3.64 119 7.12 113 1.65 131 5.22 132 6.72 127 2.36 130 5.20 99 8.08 113 3.96 111 7.93 128 9.33 107 5.52 131 11.2 56 14.0 51 3.70 46 6.56 67 12.6 59 2.74 133 8.00 56 18.2 51 2.88 128 7.96 46 12.3 30 1.78 99
Shiralkar [42]95.2 3.57 115 7.31 119 1.22 44 4.46 101 6.33 103 1.65 79 5.49 103 6.98 76 2.73 78 7.42 125 10.9 125 3.43 82 11.5 98 14.4 93 3.73 54 6.57 70 12.7 65 2.48 91 9.58 122 21.9 123 1.88 91 9.18 128 14.4 127 1.75 73
SILK [79]95.7 3.45 107 6.85 107 1.36 123 5.11 129 6.70 126 2.21 128 11.1 132 9.96 130 6.24 130 6.49 111 8.82 87 3.59 101 11.4 83 14.3 82 3.54 5 6.87 104 13.3 101 2.63 122 7.76 36 17.7 34 1.87 90 8.20 61 12.7 53 1.80 114
SimpleFlow [49]96.0 3.10 46 5.97 57 1.22 44 4.19 81 6.11 79 1.64 78 9.91 131 9.43 128 6.53 132 5.58 47 8.29 59 3.30 58 11.6 111 14.6 111 4.43 93 7.42 123 14.6 124 2.56 114 10.7 131 25.2 131 2.73 126 9.16 127 14.4 127 1.73 45
Learning Flow [11]96.5 3.14 59 6.09 66 1.27 97 4.51 103 6.53 113 1.67 85 11.5 135 12.9 135 7.17 135 6.31 103 8.30 61 3.66 106 11.7 121 14.8 123 3.89 66 6.59 75 12.8 76 2.48 91 8.27 71 18.9 69 1.96 98 8.68 110 13.4 105 1.80 114
Rannacher [23]96.6 3.31 95 6.72 104 1.25 82 4.60 114 6.66 123 1.72 94 6.36 116 6.54 58 4.25 117 5.91 78 8.87 89 3.49 91 11.5 98 14.5 103 3.63 35 6.73 89 13.1 90 2.53 106 9.35 118 21.7 121 1.98 99 8.70 113 13.7 113 1.75 73
Adaptive flow [45]99.0 3.60 117 6.30 78 1.54 130 5.14 130 6.79 129 2.14 127 4.52 75 6.60 59 3.01 87 6.54 112 8.64 81 4.23 124 12.1 131 15.2 129 4.09 74 7.57 127 14.9 129 2.64 124 7.75 34 17.8 37 2.28 116 8.47 100 13.3 100 1.71 27
OFRF [134]99.5 4.02 124 8.26 124 1.33 117 4.53 107 6.49 110 1.81 104 4.60 78 7.27 90 2.13 49 6.02 91 9.15 101 3.39 77 11.8 126 14.9 126 4.23 81 7.13 120 13.9 120 2.39 58 9.02 110 20.8 112 1.59 36 8.79 117 13.8 116 1.77 93
UnFlow [129]99.8 4.05 125 8.73 128 1.31 113 4.44 100 6.28 96 1.87 108 4.92 91 7.36 97 2.62 74 5.95 82 9.00 96 3.27 47 12.0 129 15.2 129 4.37 89 7.59 128 14.8 127 2.61 118 7.77 38 17.6 30 1.64 54 10.4 132 15.4 132 2.33 133
StereoFlow [44]100.5 5.35 135 10.3 133 1.42 127 5.03 128 7.21 134 1.76 100 4.14 46 6.94 73 2.01 41 5.83 68 8.55 78 3.33 69 13.7 133 17.3 133 4.70 132 8.71 134 17.2 134 2.70 129 7.88 46 18.1 47 1.61 42 8.82 120 13.9 121 1.79 108
2bit-BM-tele [98]102.0 3.31 95 6.41 88 1.34 121 4.53 107 6.62 119 1.80 103 6.23 115 9.24 124 6.19 129 5.94 81 8.59 80 3.55 97 11.3 73 14.2 73 4.03 72 7.72 131 15.1 131 3.02 134 12.2 135 28.7 135 4.77 135 7.76 25 12.1 22 1.82 123
IIOF-NLDP [131]103.4 3.36 102 6.62 100 1.21 19 4.22 82 6.32 101 1.59 67 5.16 97 7.63 106 2.63 75 6.10 93 9.20 105 3.53 95 11.6 111 14.6 111 4.79 134 7.42 123 14.5 123 2.71 130 12.0 134 28.2 134 3.38 132 8.93 122 13.9 121 1.74 64
FFV1MT [106]105.8 4.09 127 8.38 125 1.31 113 4.68 119 6.18 86 2.02 125 6.95 118 11.5 132 3.35 99 7.12 121 9.16 102 3.98 119 11.3 73 14.1 59 3.74 57 6.77 96 12.7 65 2.50 97 9.59 123 21.0 114 2.05 105 8.87 121 13.8 116 1.90 126
SPSA-learn [13]106.2 3.89 123 7.79 121 1.27 97 4.43 98 6.17 83 1.81 104 9.03 129 8.47 120 5.47 127 6.80 115 9.40 110 3.72 111 11.5 98 14.5 103 3.91 68 6.51 60 12.6 59 2.46 84 11.9 132 27.9 133 4.54 134 10.5 134 16.5 134 1.75 73
SegOF [10]108.7 3.51 111 7.12 113 1.32 115 4.17 80 6.10 77 1.59 67 8.69 126 7.75 110 5.15 124 8.58 131 14.3 132 4.29 126 11.7 121 14.8 123 4.50 111 6.79 98 13.2 98 2.50 97 10.1 129 23.5 129 2.55 121 8.80 118 13.8 116 1.72 36
PGAM+LK [55]110.0 4.08 126 8.41 126 1.65 131 4.74 121 6.45 108 2.27 129 8.87 127 12.2 133 6.88 133 8.06 130 10.9 125 4.83 128 11.4 83 14.3 82 3.90 67 6.83 100 13.2 98 2.55 110 8.26 69 18.9 69 2.27 115 8.55 103 13.3 100 1.90 126
Heeger++ [104]110.5 4.76 129 9.63 130 1.33 117 4.65 118 6.22 91 1.90 110 7.84 123 9.26 126 3.57 104 7.12 121 9.16 102 3.98 119 11.9 128 15.0 128 4.47 100 6.52 61 12.2 38 2.61 118 9.82 125 20.6 108 2.00 102 9.02 124 14.0 123 1.79 108
SLK [47]112.2 3.51 111 6.96 110 1.41 125 4.72 120 6.10 77 1.98 123 9.84 130 7.59 104 5.20 125 7.98 129 11.0 128 6.14 133 11.8 126 14.9 126 3.71 49 6.60 77 12.7 65 2.50 97 9.87 127 22.8 127 2.08 108 8.94 123 14.0 123 2.03 130
HCIC-L [99]113.5 4.98 133 9.28 129 1.77 134 4.97 127 6.87 132 2.11 126 5.70 107 10.0 131 4.41 121 7.85 127 11.8 130 3.68 108 10.9 30 13.7 31 3.72 53 8.18 133 16.1 133 2.55 110 9.06 112 21.0 114 2.58 123 9.57 130 15.0 130 1.81 121
Pyramid LK [2]122.4 4.16 128 8.44 127 1.74 133 5.83 134 6.82 130 2.76 134 11.4 133 8.60 121 5.89 128 12.4 135 16.7 134 7.03 135 14.3 134 18.1 134 3.92 70 6.69 84 12.2 38 2.63 122 10.3 130 24.0 130 2.45 118 11.1 135 17.4 135 2.55 135
GroupFlow [9]124.3 4.94 132 10.2 132 1.36 123 4.51 103 6.50 111 1.92 113 8.67 125 9.13 123 4.38 120 8.83 133 13.0 131 5.40 130 12.9 132 16.3 132 4.53 126 7.89 132 15.5 132 2.65 125 9.85 126 22.6 126 1.91 94 9.52 129 14.9 129 1.88 125
Periodicity [78]133.8 5.27 134 11.1 135 1.83 135 7.09 135 7.33 135 2.86 135 11.4 133 12.2 133 7.13 134 10.5 134 17.1 135 6.14 133 14.9 135 19.0 135 4.71 133 9.13 135 17.9 135 3.16 135 11.9 132 27.8 132 3.76 133 10.4 132 15.8 133 2.29 131
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. Submitted to TIP 2016.
[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.
* 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.