Optical flow evaluation results Statistics:     Average   SD   R2.5   R5.0   R10.0   A90   A95   A99  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
SD
interpolation
error
avg. Mequon
(Hidden texture)
im0   GT   im1
Schefflera
(Hidden texture)
im0   GT   im1
Urban
(Synthetic)
im0   GT   im1
Teddy
(Stereo)
im0   GT   im1
Backyard
(High-speed camera)
im0   GT   im1
Basketball
(High-speed camera)
im0   GT   im1
Dumptruck
(High-speed camera)
im0   GT   im1
Evergreen
(High-speed camera)
im0   GT   im1
rank all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext
SuperSlomo [132]13.5 7.27 1 10.8 1 4.59 128 7.40 8 9.09 3 5.23 90 11.7 1 11.2 1 6.26 3 11.1 1 12.9 1 10.9 57 21.1 1 23.9 1 8.02 2 14.2 3 20.0 3 4.85 1 19.9 1 30.4 1 6.69 3 17.4 2 21.8 2 6.97 8
MDP-Flow2 [68]22.8 8.94 32 13.9 30 1.56 1 7.36 7 9.57 10 2.68 3 15.9 35 20.5 77 16.3 78 13.4 16 18.2 30 8.87 28 24.1 8 27.3 8 12.1 18 17.6 29 25.0 34 6.01 21 22.8 12 34.9 13 7.11 5 20.9 18 26.2 18 7.78 17
CBF [12]23.2 8.02 3 12.4 3 1.75 38 8.18 50 10.3 33 4.84 74 13.2 6 15.5 15 9.17 19 11.5 2 15.0 3 7.94 17 22.8 2 25.8 2 12.2 29 16.2 10 22.9 11 6.24 39 23.4 22 35.8 22 8.06 53 21.2 23 26.7 25 8.24 56
PMMST [114]25.1 8.93 28 14.0 37 1.57 2 7.21 3 9.34 5 2.66 1 14.1 18 16.2 26 11.0 36 15.6 77 21.2 88 14.7 117 24.1 8 27.3 8 12.1 18 16.3 12 23.0 12 5.91 12 22.6 10 34.5 10 7.52 20 19.9 5 25.0 5 8.18 45
SepConv-v1 [127]27.9 8.19 5 12.5 4 5.08 131 7.89 26 9.09 3 8.08 129 20.8 93 12.1 2 18.4 93 12.5 8 14.8 2 11.7 84 23.5 5 26.6 5 9.13 3 14.1 2 19.9 2 5.12 2 21.1 2 32.2 2 8.37 59 17.2 1 21.5 1 6.71 5
DeepFlow [86]28.3 8.76 17 13.7 20 1.59 3 8.08 44 10.4 43 4.72 65 13.8 13 18.1 48 7.83 12 12.1 3 15.2 5 8.41 22 28.8 61 32.7 61 12.1 18 17.0 23 24.1 25 5.99 19 21.6 4 33.0 5 7.45 13 23.0 68 28.9 69 7.80 19
DeepFlow2 [108]32.1 8.59 12 13.4 13 1.64 8 8.06 42 10.4 43 4.45 56 13.8 13 18.6 52 8.12 14 12.4 5 16.1 7 10.6 50 28.5 55 32.3 54 12.3 40 16.7 15 23.6 15 5.92 14 23.0 16 35.0 14 7.49 16 22.6 54 28.4 55 8.47 108
SuperFlow [81]32.8 8.83 21 13.8 22 1.68 12 8.19 51 10.3 33 5.04 81 16.0 37 16.6 29 10.9 34 14.9 56 15.1 4 7.67 11 23.0 4 26.0 3 12.5 47 18.0 41 25.5 43 6.55 64 23.6 26 35.8 22 9.80 85 20.7 13 26.0 14 8.12 34
CLG-TV [48]35.7 8.34 9 12.9 8 1.98 84 8.74 72 10.8 64 4.75 70 14.0 16 16.0 21 9.23 20 12.4 5 16.1 7 9.95 41 29.7 85 33.7 85 12.0 15 16.8 16 23.9 19 5.46 3 22.2 6 32.9 4 8.02 48 21.8 39 27.4 40 8.33 80
SIOF [67]36.2 8.78 19 13.5 15 1.80 56 8.97 83 11.2 89 4.51 58 16.7 50 23.2 98 11.6 40 13.2 12 17.7 21 9.61 37 23.7 7 26.8 7 11.8 9 17.8 34 25.2 37 5.98 18 23.4 22 35.9 25 7.33 8 22.1 42 27.8 44 8.15 38
AdaConv-v1 [126]37.4 9.51 66 14.1 44 4.99 130 9.04 86 9.51 9 9.70 131 18.8 79 13.8 4 18.3 92 14.5 45 16.5 12 15.2 121 25.9 20 29.4 20 7.81 1 13.1 1 18.4 1 5.63 6 21.4 3 32.7 3 7.45 13 17.4 2 21.8 2 6.73 7
Aniso. Huber-L1 [22]38.0 8.22 6 12.7 6 1.84 66 9.12 97 11.1 84 5.11 83 13.6 10 16.3 28 7.58 10 12.2 4 16.1 7 9.16 31 29.8 91 33.8 90 12.7 53 16.9 19 23.9 19 5.57 5 23.2 19 35.5 19 7.30 7 21.8 39 27.4 40 8.32 79
CombBMOF [113]38.9 9.74 81 14.3 52 3.85 125 7.82 20 10.2 25 3.81 35 16.2 39 19.1 60 12.8 54 13.8 25 18.5 35 10.2 46 26.5 21 30.0 21 12.2 29 17.8 34 25.2 37 6.09 30 23.1 17 35.2 17 7.64 27 21.3 26 26.7 25 8.21 53
MDP-Flow [26]39.4 8.27 7 12.8 7 1.74 33 7.26 5 9.42 6 3.90 38 17.2 59 16.1 25 15.0 73 13.6 20 18.0 26 10.9 57 28.8 61 32.7 61 15.3 97 17.9 40 25.2 37 7.36 91 23.6 26 36.1 27 12.2 105 20.6 10 25.9 11 8.07 24
LME [70]39.6 8.97 34 14.0 37 1.62 5 8.07 43 10.5 50 3.69 28 16.9 53 17.7 41 9.29 22 14.5 45 19.6 58 9.68 38 29.2 78 33.1 78 15.3 97 18.1 43 25.7 45 6.15 32 22.7 11 34.7 11 7.37 10 21.0 20 26.4 21 8.20 50
NN-field [71]40.0 9.03 40 14.1 44 1.74 33 7.01 2 9.05 2 2.74 8 18.3 74 19.1 60 12.6 52 16.8 103 22.7 108 15.8 123 24.2 10 27.5 10 12.1 18 17.8 34 25.1 35 6.07 26 23.1 17 35.4 18 7.69 31 20.6 10 25.9 11 8.36 92
WLIF-Flow [93]40.6 8.64 13 13.4 13 1.69 17 7.89 26 10.2 25 3.94 39 17.0 55 22.0 87 14.5 69 13.7 23 18.4 33 11.5 75 26.7 24 30.3 24 12.3 40 19.8 99 28.0 100 8.12 114 22.4 8 34.2 8 7.58 24 21.1 22 26.4 21 7.62 15
NNF-Local [87]40.8 8.84 23 13.8 22 1.61 4 7.25 4 9.44 7 2.76 9 14.6 24 19.3 66 14.5 69 16.0 90 21.6 95 15.8 123 24.2 10 27.5 10 12.2 29 18.4 51 26.0 54 6.42 56 24.2 33 37.1 37 9.54 78 20.3 8 25.4 8 8.27 68
p-harmonic [29]40.8 8.89 26 13.9 30 1.68 12 8.86 77 10.9 71 5.20 89 13.4 7 17.5 38 6.45 4 13.7 23 17.9 25 10.0 43 28.9 66 32.8 67 12.8 54 17.6 29 24.9 31 6.53 63 22.9 13 35.0 14 8.88 64 22.5 51 28.3 53 8.10 30
IROF-TV [53]41.3 8.93 28 13.9 30 1.82 62 8.15 48 10.6 55 4.01 42 13.9 15 17.6 39 8.70 17 13.3 13 18.0 26 9.04 29 28.5 55 32.3 54 15.3 97 18.5 57 26.2 59 6.57 65 24.7 47 37.8 49 6.81 4 22.2 46 28.0 49 6.71 5
Second-order prior [8]41.4 8.06 4 12.5 4 1.93 77 8.80 73 11.0 75 4.80 73 12.8 3 16.2 26 7.51 9 12.6 9 16.7 13 6.25 4 28.9 66 32.8 67 12.2 29 18.1 43 25.7 45 6.10 31 23.3 20 35.5 19 9.35 75 22.7 59 28.6 63 8.45 106
OAR-Flow [125]42.6 9.14 48 14.0 37 1.71 23 7.90 28 10.1 19 4.04 44 14.3 21 18.8 55 5.59 1 16.6 100 22.6 105 6.23 3 27.7 41 31.4 41 15.3 97 15.9 6 22.4 6 6.89 76 24.2 33 36.4 30 7.80 38 22.9 66 28.8 67 8.15 38
ALD-Flow [66]42.7 10.4 98 16.0 96 1.76 40 7.99 36 10.3 33 3.78 33 14.1 18 19.3 66 6.64 5 16.1 92 21.9 99 5.92 2 26.5 21 30.0 21 14.0 69 16.9 19 23.9 19 6.23 38 22.5 9 34.4 9 7.50 18 23.2 76 29.2 81 8.09 27
Ad-TV-NDC [36]43.1 9.09 44 13.8 22 2.24 107 9.50 114 11.1 84 6.94 125 14.2 20 15.4 14 6.85 6 14.5 45 18.6 36 9.51 36 27.4 34 31.1 34 12.3 40 18.2 48 25.8 51 6.40 55 22.9 13 34.7 11 7.43 11 20.6 10 25.8 10 8.26 64
IROF++ [58]44.3 8.58 11 13.3 11 1.68 12 7.99 36 10.4 43 3.84 36 17.3 60 18.5 50 12.5 50 12.4 5 16.7 13 9.15 30 28.4 54 32.3 54 15.3 97 19.5 91 27.6 92 6.06 24 23.3 20 35.6 21 8.55 63 23.4 84 29.4 89 7.79 18
DF-Auto [115]44.8 9.30 58 14.4 61 1.99 85 8.37 58 10.6 55 4.99 77 15.5 32 22.3 89 8.88 18 13.3 13 17.6 20 9.86 40 25.7 17 29.1 17 13.9 68 18.1 43 25.7 45 5.96 17 25.2 54 38.6 59 10.8 97 20.7 13 25.9 11 8.09 27
Modified CLG [34]45.7 7.87 2 12.2 2 1.68 12 8.96 81 10.7 61 5.94 119 16.8 51 16.7 31 15.9 77 13.3 13 16.4 11 12.6 104 27.6 39 31.3 39 11.9 10 18.8 68 26.6 69 6.50 61 22.3 7 34.0 7 7.67 29 22.2 46 27.9 46 8.64 112
Brox et al. [5]45.8 9.33 60 14.7 66 1.62 5 7.86 24 10.1 19 4.14 47 15.9 35 16.0 21 10.4 30 13.5 19 17.7 21 8.77 26 26.8 25 30.4 25 11.9 10 19.1 79 27.0 80 9.52 128 28.6 107 43.6 105 23.0 133 19.9 5 25.0 5 8.05 23
NNF-EAC [103]48.1 9.00 37 14.0 37 1.99 85 7.79 18 10.2 25 2.85 12 17.5 65 25.1 113 19.2 97 15.4 70 20.6 76 11.6 79 29.9 95 33.9 95 12.1 18 16.5 13 23.4 13 5.99 19 22.9 13 35.1 16 7.51 19 20.9 18 26.2 18 8.42 103
F-TV-L1 [15]50.9 10.4 98 16.2 98 1.94 79 9.02 84 11.2 89 4.72 65 14.6 24 16.7 31 11.0 36 14.2 34 18.9 45 10.3 47 27.5 36 31.2 37 12.3 40 16.0 7 22.6 7 6.38 53 23.9 30 36.6 33 9.23 71 21.3 26 26.7 25 10.2 126
Local-TV-L1 [65]50.9 8.65 14 13.3 11 1.90 73 9.07 91 11.0 75 5.04 81 13.1 5 15.3 13 8.62 16 12.8 10 17.0 15 7.89 16 30.8 122 35.0 123 15.5 124 18.4 51 26.0 54 6.98 80 23.9 30 36.5 32 7.66 28 21.4 29 26.9 29 8.40 99
PH-Flow [101]52.1 9.30 58 14.3 52 1.70 21 7.70 15 10.1 19 2.82 11 14.9 28 20.6 80 14.8 71 14.3 38 19.4 54 11.5 75 25.0 14 28.3 14 12.2 29 21.6 128 30.7 129 9.38 127 25.0 52 38.3 54 7.76 35 22.6 54 28.4 55 8.15 38
FMOF [94]53.0 9.22 54 13.9 30 1.96 81 7.58 12 9.87 15 2.87 13 19.5 83 22.4 90 17.7 87 15.3 66 20.6 76 12.5 103 24.5 12 27.7 12 13.7 64 19.3 87 27.3 88 6.05 23 24.6 45 37.7 47 6.64 2 23.4 84 29.4 89 6.98 9
Filter Flow [19]53.6 9.35 62 14.5 62 1.79 52 9.19 99 11.1 84 5.50 107 17.6 68 16.8 34 12.2 44 14.0 30 18.0 26 11.3 65 24.6 13 27.9 13 12.2 29 18.4 51 26.0 54 7.54 97 24.8 48 37.9 51 7.77 36 21.5 31 27.0 32 8.40 99
CRTflow [80]56.2 8.75 16 13.6 17 2.04 89 9.27 104 11.5 111 5.28 91 16.2 39 22.5 92 9.27 21 12.8 10 17.0 15 11.5 75 27.0 27 30.6 27 15.3 97 17.6 29 24.9 31 6.06 24 27.8 94 42.7 97 7.62 26 23.4 84 29.4 89 8.16 43
TC/T-Flow [76]56.5 9.42 64 14.6 65 2.39 111 8.67 70 11.2 89 4.00 40 13.6 10 16.0 21 8.03 13 17.5 115 23.5 118 10.8 54 27.3 32 31.0 32 15.3 97 17.4 27 24.6 27 5.89 11 25.8 68 37.8 49 9.59 80 22.8 62 28.7 65 8.13 36
CNN-flow-warp+ref [117]56.6 8.33 8 13.0 9 2.06 93 8.26 55 10.3 33 5.85 116 18.3 74 22.7 94 11.1 38 13.6 20 16.0 6 11.1 61 29.1 76 33.0 76 15.3 97 15.7 4 22.1 4 6.96 79 28.2 100 43.1 100 7.67 29 21.8 39 27.3 38 8.49 109
ComplOF-FED-GPU [35]56.8 9.91 89 15.5 89 1.77 47 7.74 16 10.1 19 4.25 52 19.8 87 17.7 41 17.0 82 15.3 66 20.7 79 11.8 85 28.2 53 32.0 53 14.5 74 16.2 10 22.8 10 5.95 16 26.2 74 39.6 75 9.25 72 22.7 59 28.4 55 8.25 61
COFM [59]57.0 8.95 33 13.8 22 1.90 73 7.42 9 9.61 11 3.19 21 15.3 30 22.1 88 16.3 78 15.4 70 20.9 82 14.6 113 26.8 25 30.4 25 12.2 29 21.4 125 30.3 125 6.26 43 26.3 75 40.4 77 10.4 93 20.8 15 26.1 15 8.36 92
Sparse Occlusion [54]57.2 9.75 82 15.2 80 2.05 92 8.71 71 11.2 89 4.19 49 13.5 8 15.9 20 7.80 11 14.6 50 19.7 63 7.51 10 30.4 107 34.5 108 15.3 97 16.1 8 22.7 8 6.27 44 26.9 85 41.1 87 7.45 13 23.2 76 29.2 81 8.12 34
2DHMM-SAS [92]57.7 8.83 21 13.6 17 1.76 40 8.88 79 11.3 97 4.29 53 17.5 65 20.9 81 12.5 50 14.5 45 19.6 58 11.3 65 30.1 100 34.1 99 15.1 87 17.6 29 24.9 31 5.84 7 25.2 54 38.7 61 8.23 57 23.1 71 29.1 74 8.16 43
Horn & Schunck [3]58.4 8.92 27 13.6 17 1.73 26 9.79 123 11.4 101 6.31 122 24.1 111 18.7 53 18.6 95 15.8 86 19.4 54 11.1 61 28.0 46 31.8 47 10.4 6 17.8 34 25.2 37 5.54 4 25.3 59 38.4 57 9.70 82 22.1 42 27.7 43 8.27 68
2D-CLG [1]58.6 8.51 10 13.2 10 1.76 40 8.84 76 10.4 43 5.71 114 19.4 82 15.6 17 15.0 73 14.2 34 16.3 10 14.0 109 31.1 127 35.3 127 20.9 134 16.1 8 22.7 8 6.34 49 27.7 93 42.3 92 8.19 56 21.4 29 26.9 29 8.13 36
PMF [73]58.7 9.35 62 14.5 62 1.77 47 7.80 19 10.1 19 2.68 3 24.0 110 28.7 122 22.5 118 15.3 66 20.6 76 11.6 79 25.7 17 29.2 18 12.1 18 19.1 79 27.0 80 5.92 14 27.6 91 42.4 94 9.09 69 23.1 71 29.0 73 6.47 1
LDOF [28]58.7 8.85 24 13.8 22 2.04 89 10.2 130 9.70 14 10.8 135 17.0 55 20.4 76 12.0 41 13.4 16 17.4 19 12.3 98 22.9 3 26.0 3 11.9 10 18.9 72 26.7 72 6.27 44 30.1 121 46.3 123 16.0 117 19.7 4 24.7 4 8.89 117
CPM-Flow [116]58.8 9.82 86 15.4 88 1.69 17 7.60 13 9.90 16 3.04 18 15.6 34 15.7 18 7.43 8 16.9 105 23.0 113 12.0 90 27.6 39 31.3 39 15.3 97 18.5 57 26.2 59 7.13 86 23.4 22 35.8 22 9.99 87 23.8 101 29.9 103 8.37 94
FlowNetS+ft+v [112]59.3 9.02 39 14.1 44 2.07 96 10.0 128 11.0 75 9.60 130 16.3 42 14.4 5 13.5 60 13.8 25 17.7 21 13.3 107 29.7 85 33.8 90 15.3 97 16.8 16 23.8 17 6.25 41 27.8 94 42.6 95 7.83 42 20.4 9 25.5 9 8.24 56
Black & Anandan [4]59.6 9.24 56 14.1 44 1.95 80 9.65 121 11.4 101 5.28 91 28.3 120 24.2 104 20.2 106 14.8 54 18.7 40 10.5 49 27.7 41 31.5 42 9.57 5 19.0 76 27.0 80 6.35 51 24.2 33 36.7 34 8.42 61 21.0 20 26.3 20 6.55 2
TC-Flow [46]59.8 10.9 106 17.1 107 1.71 23 8.86 77 11.6 114 4.00 40 13.0 4 16.0 21 6.24 2 15.6 77 21.1 85 8.58 23 27.9 43 31.7 45 15.1 87 18.7 65 26.4 66 6.72 69 24.6 45 37.6 45 7.95 46 23.4 84 29.4 89 8.28 71
Fusion [6]60.3 8.82 20 13.8 22 2.62 114 7.96 34 10.1 19 4.47 57 16.5 45 13.6 3 17.3 86 14.0 30 18.1 29 9.97 42 29.8 91 33.8 90 12.8 54 19.4 88 27.4 89 10.1 131 26.4 76 40.4 77 8.14 54 21.7 35 27.2 36 10.1 125
MLDP_OF [89]60.5 9.06 41 14.1 44 1.83 65 8.81 74 11.3 97 4.78 72 14.0 16 17.6 39 8.56 15 15.5 74 20.3 72 15.8 123 29.7 85 33.7 85 13.6 60 19.1 79 27.0 80 5.86 9 23.8 28 36.3 28 8.15 55 23.2 76 29.1 74 8.25 61
OFLAF [77]60.7 9.70 76 15.0 75 1.69 17 7.94 33 10.4 43 2.73 7 14.3 21 15.0 10 10.2 26 13.8 25 18.6 36 8.40 21 30.0 97 34.0 97 15.4 117 17.0 23 23.9 19 6.73 70 30.1 121 46.1 121 13.9 112 23.4 84 29.3 85 9.45 121
PGM-C [120]60.7 9.70 76 15.2 80 1.69 17 7.84 23 10.2 25 3.70 29 21.2 95 17.2 36 12.3 47 17.4 112 23.6 119 8.69 24 28.0 46 31.8 47 15.3 97 16.6 14 23.4 13 6.17 33 26.4 76 40.5 81 8.04 50 24.3 116 30.5 118 8.34 83
EpicFlow [102]60.8 9.69 75 15.2 80 1.67 11 7.90 28 10.2 25 4.37 55 16.0 37 14.5 6 9.75 24 19.1 124 25.8 126 12.3 98 27.9 43 31.6 43 15.3 97 16.9 19 23.9 19 6.21 37 24.9 50 38.0 52 10.3 92 24.6 121 30.9 122 8.30 75
TV-L1-MCT [64]61.9 9.18 51 14.2 50 1.78 49 8.53 64 11.1 84 3.70 29 17.7 70 23.3 101 13.6 61 14.4 42 19.5 57 11.6 79 30.5 113 34.6 111 13.8 65 18.1 43 25.7 45 6.02 22 25.8 68 39.5 73 15.0 115 21.7 35 27.3 38 7.99 21
AGIF+OF [85]62.4 9.07 42 14.0 37 1.78 49 7.93 32 10.3 33 3.78 33 14.4 23 17.8 43 12.4 48 14.9 56 20.2 69 11.4 70 28.9 66 32.8 67 15.3 97 20.0 101 28.3 101 6.98 80 25.5 62 39.0 64 7.74 33 23.9 108 30.1 112 8.28 71
Bartels [41]62.5 12.7 121 20.1 122 2.13 102 8.52 63 11.0 75 4.96 76 13.5 8 14.5 6 10.2 26 14.4 42 18.9 45 10.8 54 23.5 5 26.6 5 12.9 57 19.0 76 26.9 77 6.94 78 24.5 40 37.5 43 19.7 128 23.4 84 29.4 89 8.31 77
S2F-IF [123]64.0 10.3 96 16.3 100 1.79 52 7.83 22 10.2 25 2.90 15 17.0 55 20.0 73 13.9 65 16.1 92 21.6 95 6.69 5 29.2 78 33.2 79 15.3 97 16.8 16 23.7 16 6.34 49 24.9 50 38.2 53 10.7 95 23.9 108 30.0 110 8.35 89
BlockOverlap [61]64.4 9.09 44 14.3 52 2.04 89 8.96 81 10.9 71 5.37 101 18.1 72 15.5 15 18.0 90 14.2 34 17.2 17 14.0 109 28.9 66 32.8 67 13.8 65 18.8 68 26.7 72 7.92 108 24.8 48 37.2 38 21.0 130 20.0 7 25.1 7 8.38 95
OFH [38]65.2 9.54 68 15.0 75 1.74 33 8.49 62 10.6 55 5.13 84 18.1 72 24.9 111 10.4 30 17.4 112 23.7 121 5.72 1 28.7 59 32.5 57 14.6 77 17.6 29 24.8 29 5.85 8 26.0 72 39.2 68 10.2 90 22.7 59 28.5 61 14.1 132
nLayers [57]65.5 9.15 49 14.3 52 1.76 40 7.42 9 9.62 12 3.57 25 27.8 118 29.9 125 25.8 128 15.9 88 21.5 93 11.9 86 30.2 101 34.3 102 14.7 80 20.3 107 28.8 108 6.45 58 23.5 25 36.0 26 7.87 44 21.6 32 27.1 33 8.10 30
HAST [109]65.7 8.87 25 13.8 22 1.76 40 7.34 6 9.50 8 2.70 5 28.8 122 28.6 121 24.0 123 14.9 56 20.2 69 7.68 12 28.9 66 32.8 67 12.1 18 21.3 124 30.2 124 7.57 99 28.6 107 43.9 108 7.55 22 22.8 62 28.7 65 8.43 105
TCOF [69]65.8 9.34 61 14.3 52 1.89 69 9.50 114 11.7 120 5.42 102 16.2 39 21.7 85 10.3 28 13.8 25 18.6 36 9.45 35 30.4 107 34.6 111 13.6 60 18.2 48 25.7 45 6.20 36 28.5 104 43.5 104 7.54 21 22.9 66 28.8 67 8.18 45
Layers++ [37]66.4 8.93 28 14.0 37 1.76 40 6.74 1 8.61 1 2.71 6 18.3 74 25.8 115 19.3 98 15.3 66 20.8 80 11.3 65 33.1 132 37.6 132 19.8 131 21.6 128 30.6 128 8.73 121 24.4 38 37.4 41 7.81 40 21.6 32 27.1 33 8.09 27
DPOF [18]66.8 11.0 107 17.4 111 3.88 126 7.78 17 10.2 25 3.01 16 18.7 77 18.1 48 18.4 93 16.5 97 22.4 102 14.6 113 28.8 61 32.7 61 12.1 18 18.9 72 26.7 72 6.18 35 25.2 54 38.4 57 7.59 25 23.6 96 29.6 96 8.07 24
FlowFields [110]67.5 9.98 90 15.7 91 2.08 98 7.96 34 10.4 43 3.62 26 23.1 103 23.2 98 20.3 108 16.0 90 21.5 93 7.08 8 27.0 27 30.6 27 14.2 71 19.2 85 27.1 85 6.08 29 24.4 38 37.4 41 10.2 90 23.2 76 29.2 81 8.35 89
Classic++ [32]68.0 9.48 65 14.9 70 1.80 56 8.59 65 11.0 75 4.61 61 13.7 12 15.0 10 9.57 23 14.4 42 19.0 47 8.76 25 29.9 95 33.9 95 13.6 60 20.2 105 28.7 106 6.87 75 27.4 89 42.0 89 9.63 81 23.8 101 29.9 103 8.34 83
SRR-TVOF-NL [91]68.6 9.65 72 14.8 67 1.82 62 8.21 53 10.6 55 4.76 71 22.7 101 28.1 119 21.9 113 15.6 77 20.9 82 9.18 32 28.9 66 32.8 67 15.3 97 20.7 114 29.3 114 5.91 12 24.5 40 37.6 45 6.56 1 22.5 51 28.2 52 8.34 83
HBM-GC [105]69.2 9.25 57 14.5 62 1.81 60 9.08 93 11.9 127 3.75 32 17.3 60 18.7 53 17.9 88 14.3 38 19.2 49 8.85 27 30.0 97 34.0 97 15.5 124 21.5 126 30.4 126 8.27 117 27.4 89 42.1 91 7.15 6 20.8 15 26.1 15 7.05 11
NL-TV-NCC [25]69.5 9.19 53 14.3 52 2.18 103 9.02 84 11.6 114 4.13 46 14.8 26 16.7 31 10.9 34 20.8 128 28.1 129 8.19 19 26.5 21 30.0 21 13.1 58 18.9 72 26.7 72 6.43 57 26.6 80 40.4 77 15.1 116 23.7 100 29.7 100 8.29 74
Nguyen [33]69.9 9.83 87 15.2 80 1.73 26 9.59 119 11.0 75 5.65 113 15.3 30 20.5 77 10.3 28 14.6 50 18.8 41 12.1 92 28.8 61 32.7 61 12.2 29 19.4 88 27.4 89 8.01 112 29.7 116 45.5 116 8.29 58 21.2 23 26.6 24 8.34 83
Complementary OF [21]70.2 11.4 113 18.1 116 1.70 21 9.23 102 12.1 128 4.19 49 31.6 127 19.0 59 23.6 120 19.5 127 26.5 127 6.72 6 28.1 51 31.8 47 14.6 77 17.3 26 24.4 26 6.38 53 26.1 73 39.0 64 8.92 66 22.3 48 27.9 46 7.57 14
Efficient-NL [60]70.5 8.71 15 13.5 15 1.68 12 8.66 69 11.2 89 3.65 27 22.5 98 20.0 73 19.9 102 14.3 38 19.3 51 11.0 59 30.5 113 34.7 116 15.0 82 20.1 102 28.4 102 6.27 44 28.5 104 43.7 106 8.92 66 23.8 101 29.9 103 6.66 4
AggregFlow [97]71.0 12.9 123 20.3 123 1.75 38 8.34 57 10.8 64 4.14 47 20.0 88 24.4 107 19.5 101 16.5 97 22.3 101 12.2 96 25.2 15 28.6 15 12.2 29 16.9 19 23.9 19 6.60 66 29.0 113 43.9 108 16.7 119 23.0 68 28.9 69 8.03 22
FESL [72]71.5 9.09 44 13.9 30 1.74 33 7.90 28 10.3 33 3.35 23 16.5 45 21.9 86 12.0 41 15.1 63 20.3 72 11.4 70 30.8 122 35.0 123 15.4 117 19.6 93 27.8 96 6.48 59 27.8 94 42.6 95 7.75 34 23.9 108 30.0 110 8.39 96
ProbFlowFields [128]71.5 10.1 91 16.0 96 1.78 49 8.04 40 10.5 50 3.08 20 25.8 117 28.8 123 24.3 124 14.5 45 19.6 58 11.4 70 27.2 30 30.9 31 15.3 97 17.4 27 24.6 27 8.78 122 27.3 88 42.0 89 18.8 126 22.4 50 28.1 50 8.39 96
RNLOD-Flow [121]72.6 8.93 28 13.8 22 1.65 9 8.48 61 11.0 75 4.06 45 16.3 42 23.2 98 12.8 54 14.1 32 19.1 48 11.1 61 29.7 85 33.7 85 15.6 126 20.3 107 28.7 106 8.92 125 25.7 65 39.4 71 16.4 118 24.2 114 30.4 116 8.20 50
StereoOF-V1MT [119]72.7 11.1 109 17.3 109 1.73 26 8.61 66 10.6 55 5.28 91 23.4 107 17.3 37 17.1 84 16.6 100 19.9 66 12.3 98 27.4 34 31.1 34 15.0 82 17.0 23 23.8 17 6.80 73 30.2 123 46.2 122 12.3 106 21.6 32 26.9 29 9.58 122
FlowFields+ [130]72.9 9.67 74 15.2 80 3.33 124 7.86 24 10.3 33 3.02 17 23.3 105 24.6 108 20.8 109 17.0 107 23.0 113 6.91 7 27.3 32 31.0 32 15.4 117 19.0 76 26.9 77 6.24 39 25.3 59 38.8 62 13.1 108 23.2 76 29.1 74 8.39 96
FlowNet2 [122]73.4 15.6 132 23.6 133 1.96 81 9.34 106 12.1 128 4.72 65 17.3 60 19.2 64 13.0 57 17.1 110 23.1 115 10.1 44 28.0 46 31.8 47 12.3 40 18.6 59 26.3 62 6.35 51 26.7 81 40.8 84 8.04 50 21.7 35 27.2 36 8.30 75
TI-DOFE [24]73.9 9.80 84 15.2 80 2.80 118 9.94 126 11.4 101 5.62 111 15.5 32 15.7 18 10.5 33 17.0 107 21.7 97 10.6 50 27.1 29 30.8 29 12.1 18 20.9 118 29.6 119 6.99 82 24.0 32 36.3 28 8.92 66 24.3 116 28.1 50 12.5 130
Sparse-NonSparse [56]74.2 9.18 51 14.3 52 1.73 26 8.14 47 10.6 55 3.31 22 16.6 48 22.9 96 13.8 64 14.8 54 19.8 65 11.3 65 30.5 113 34.6 111 15.0 82 20.1 102 28.5 104 7.48 95 28.5 104 43.7 106 9.49 76 23.5 94 29.5 94 8.24 56
ACK-Prior [27]75.0 9.81 85 15.1 78 2.07 96 8.01 39 10.4 43 3.86 37 25.1 114 19.1 60 22.0 115 15.1 63 20.1 68 10.1 44 30.4 107 34.4 105 15.4 117 19.1 79 26.9 77 7.57 99 25.8 68 39.3 69 19.5 127 22.3 48 27.9 46 7.73 16
LSM [39]75.1 9.10 47 14.2 50 1.73 26 8.33 56 10.9 71 3.40 24 16.6 48 22.7 94 12.2 44 15.0 62 20.3 72 11.0 59 30.5 113 34.7 116 15.1 87 20.7 114 29.4 115 6.17 33 28.1 99 43.0 99 11.5 101 23.8 101 29.9 103 8.27 68
Occlusion-TV-L1 [63]75.3 10.1 91 15.9 94 2.43 112 9.36 107 11.8 125 5.01 80 12.7 2 14.7 8 7.22 7 17.0 107 22.7 108 11.4 70 28.6 57 32.5 57 12.0 15 18.7 65 26.5 68 7.48 95 25.2 54 37.7 47 10.0 88 24.3 116 30.3 115 9.33 119
Classic+CPF [83]75.4 9.07 42 14.0 37 1.80 56 8.09 45 10.5 50 3.71 31 17.0 55 21.5 83 12.9 56 13.9 29 18.8 41 11.4 70 30.7 120 34.9 121 15.4 117 21.2 121 30.0 122 7.73 106 28.2 100 43.2 101 7.80 38 24.7 124 31.0 124 7.89 20
3DFlow [135]75.5 9.65 72 14.9 70 1.89 69 7.82 20 10.0 18 4.94 75 16.9 53 19.9 71 13.7 62 16.5 97 22.4 102 15.8 123 29.3 81 33.2 79 12.5 47 18.4 51 25.9 53 8.56 120 27.2 86 41.4 88 10.1 89 23.4 84 29.3 85 8.87 116
FFV1MT [106]75.8 11.6 114 17.7 113 2.19 104 9.20 100 10.9 71 5.96 120 22.6 99 30.3 126 16.3 78 15.5 74 18.8 41 12.4 101 27.5 36 31.2 37 11.6 8 18.6 59 25.7 45 7.42 94 27.2 86 40.7 82 8.88 64 21.2 23 26.4 21 9.73 123
TriFlow [95]76.3 13.1 124 20.8 124 2.06 93 9.53 117 12.2 130 5.29 96 16.5 45 18.5 50 10.1 25 17.2 111 22.8 110 7.74 13 27.9 43 31.6 43 15.1 87 19.4 88 27.4 89 6.07 26 24.5 40 37.2 38 10.9 98 23.8 101 29.8 102 8.15 38
CostFilter [40]76.8 10.8 105 17.0 106 1.80 56 7.90 28 10.3 33 2.66 1 24.6 113 27.7 118 21.9 113 18.7 121 25.4 125 13.7 108 27.5 36 31.1 34 12.6 50 18.2 48 25.8 51 5.87 10 28.9 111 44.2 112 9.34 74 24.4 119 30.7 120 8.20 50
TF+OM [100]76.8 11.8 116 18.7 118 3.19 121 8.23 54 10.8 64 4.54 59 15.1 29 19.7 69 10.4 30 16.3 95 21.9 99 7.87 15 28.9 66 32.8 67 19.1 130 18.6 59 26.3 62 6.68 68 26.5 79 40.7 82 11.5 101 23.8 101 29.9 103 8.23 55
Ramp [62]77.0 9.22 54 14.3 52 1.73 26 8.19 51 10.7 61 4.24 51 21.9 97 28.8 123 21.1 112 14.2 34 19.2 49 11.6 79 30.6 118 34.8 119 14.8 81 20.4 110 29.0 112 7.40 92 28.0 98 42.9 98 7.57 23 23.0 68 28.9 69 8.28 71
EPMNet [133]78.1 16.1 134 24.7 134 2.22 105 9.04 86 11.7 120 4.55 60 17.3 60 19.2 64 13.0 57 26.7 135 36.3 135 12.1 92 28.0 46 31.8 47 12.3 40 18.4 51 26.0 54 6.25 41 26.7 81 40.8 84 8.04 50 22.6 54 28.4 55 8.35 89
IAOF2 [51]78.3 10.7 104 16.6 103 2.36 109 9.40 108 11.6 114 5.33 97 17.4 64 18.0 45 12.4 48 14.1 32 18.2 30 9.32 34 30.3 105 34.4 105 14.0 69 20.5 113 29.1 113 8.20 115 25.2 54 38.3 54 8.49 62 23.1 71 29.1 74 8.24 56
Heeger++ [104]78.8 14.5 129 21.7 128 4.63 129 9.50 114 11.0 75 5.73 115 25.4 116 23.5 103 14.4 68 15.5 74 18.8 41 12.4 101 28.7 59 32.5 57 15.2 94 15.8 5 22.2 5 6.73 70 27.6 91 39.8 76 9.28 73 22.1 42 27.6 42 8.34 83
SVFilterOh [111]79.2 10.5 101 16.4 101 1.97 83 7.65 14 9.98 17 3.05 19 28.0 119 30.4 127 25.4 126 15.6 77 21.2 88 14.7 117 28.9 66 32.7 61 15.4 117 20.1 102 28.4 102 6.61 67 25.8 68 39.5 73 7.84 43 22.5 51 28.3 53 8.49 109
Dynamic MRF [7]79.8 10.1 91 15.9 94 1.81 60 8.42 60 10.8 64 4.73 69 19.5 83 19.1 60 12.2 44 15.6 77 19.3 51 12.8 106 27.2 30 30.8 29 15.2 94 18.6 59 26.3 62 7.28 89 28.8 110 44.1 111 12.4 107 24.6 121 30.7 120 9.73 123
TV-L1-improved [17]79.8 9.53 67 14.9 70 1.99 85 9.46 111 11.7 120 5.17 86 22.6 99 14.8 9 20.1 105 13.4 16 17.8 24 8.05 18 30.2 101 34.3 102 11.9 10 19.6 93 27.7 93 8.09 113 29.9 119 45.8 119 9.73 83 23.4 84 29.3 85 8.42 103
Classic+NL [31]79.8 8.97 34 13.9 30 1.79 52 8.11 46 10.5 50 4.01 42 20.8 93 28.3 120 19.9 102 14.3 38 19.3 51 11.5 75 30.7 120 34.8 119 14.6 77 20.3 107 28.8 108 7.40 92 28.3 102 43.4 102 11.9 104 23.5 94 29.6 96 8.25 61
IAOF [50]80.0 11.1 109 16.6 103 5.32 132 10.6 132 12.3 131 5.87 117 23.3 105 24.2 104 19.4 99 15.4 70 19.7 63 12.0 90 28.9 66 32.8 67 12.1 18 18.8 68 26.6 69 7.26 88 25.6 64 39.1 67 7.35 9 22.1 42 27.8 44 8.26 64
Adaptive [20]80.2 11.0 107 17.3 109 1.89 69 9.41 110 11.6 114 5.19 88 14.8 26 17.1 35 11.1 38 15.7 83 21.1 85 12.1 92 31.1 127 35.3 127 12.0 15 18.8 68 26.6 69 8.00 111 27.8 94 42.3 92 8.01 47 22.6 54 28.4 55 8.63 111
ROF-ND [107]80.5 9.00 37 13.9 30 1.62 5 9.53 117 10.8 64 10.7 134 16.4 44 22.9 96 12.7 53 18.3 119 24.1 122 11.9 86 29.4 83 33.3 83 15.2 94 18.6 59 26.2 59 7.60 102 24.5 40 37.3 40 13.2 110 24.4 119 30.5 118 9.33 119
Steered-L1 [118]80.5 8.76 17 13.7 20 1.82 62 8.00 38 10.3 33 4.72 65 31.9 128 33.2 132 29.2 131 17.4 112 22.8 110 14.1 111 29.5 84 33.5 84 14.2 71 19.7 97 27.9 98 6.28 48 26.4 76 40.4 77 18.7 125 23.8 101 29.9 103 7.04 10
TriangleFlow [30]80.8 9.59 70 14.8 67 2.06 93 9.07 91 11.4 101 5.47 105 19.2 80 20.2 75 13.9 65 13.6 20 18.2 30 8.31 20 30.0 97 34.1 99 9.31 4 17.8 34 25.2 37 7.56 98 30.8 125 47.2 125 13.9 112 25.5 131 31.9 132 11.3 128
FOLKI [16]81.1 10.6 102 16.5 102 2.43 112 9.94 126 11.2 89 6.70 124 19.6 85 21.6 84 19.9 102 18.3 119 19.4 54 17.3 128 28.0 46 31.7 45 13.6 60 19.1 79 27.1 85 10.9 133 24.2 33 36.9 35 17.3 122 21.3 26 26.7 25 8.10 30
SILK [79]82.5 9.72 80 15.1 78 2.69 115 10.2 130 11.4 101 7.82 128 39.2 134 32.9 131 28.5 130 14.6 50 18.4 33 9.73 39 29.0 75 32.9 75 10.4 6 21.2 121 30.0 122 7.00 83 24.5 40 37.5 43 8.03 49 23.1 71 28.9 69 8.31 77
LocallyOriented [52]82.8 10.1 91 15.7 91 1.79 52 9.46 111 11.6 114 5.28 91 23.1 103 24.2 104 20.9 111 19.3 126 23.2 116 7.35 9 30.4 107 34.6 111 12.6 50 18.9 72 26.8 76 6.27 44 25.7 65 38.6 59 7.89 45 23.6 96 29.6 96 8.19 48
S2D-Matching [84]84.2 9.57 69 14.9 70 1.76 40 8.37 58 10.8 64 4.36 54 20.1 90 24.9 111 18.2 91 15.7 83 21.3 92 15.7 122 28.8 61 32.7 61 14.5 74 21.5 126 30.4 126 11.0 134 25.7 65 39.3 69 11.5 101 23.1 71 29.1 74 8.75 115
GraphCuts [14]85.0 11.7 115 17.8 114 2.02 88 8.15 48 10.5 50 4.65 63 25.3 115 15.2 12 19.4 99 14.9 56 19.6 58 11.9 86 29.8 91 33.8 90 17.8 128 19.6 93 27.8 96 6.50 61 28.6 107 43.9 108 11.1 99 24.0 112 30.2 113 8.15 38
BriefMatch [124]85.0 9.89 88 15.5 89 2.11 100 8.05 41 10.2 25 5.90 118 23.5 108 18.0 45 22.7 119 18.2 118 18.6 36 18.7 131 28.1 51 31.9 52 13.8 65 19.5 91 27.7 93 7.05 84 26.7 81 39.4 71 21.6 131 23.4 84 29.3 85 14.3 134
RFlow [90]85.8 9.71 78 15.2 80 1.91 76 9.06 89 11.2 89 5.42 102 22.8 102 22.6 93 17.9 88 15.8 86 21.2 88 12.7 105 29.2 78 33.2 79 11.9 10 19.2 85 27.2 87 7.63 103 28.9 111 44.4 113 7.73 32 23.4 84 29.5 94 8.46 107
ComponentFusion [96]86.2 12.3 120 19.5 120 1.66 10 8.65 68 11.4 101 2.88 14 19.7 86 21.0 82 15.1 75 15.4 70 20.9 82 14.4 112 29.7 85 33.7 85 14.5 74 18.6 59 26.3 62 7.67 104 31.9 127 49.0 128 20.5 129 24.2 114 30.4 116 8.18 45
Learning Flow [11]86.6 8.99 36 14.1 44 1.85 68 9.10 95 11.3 97 4.99 77 40.2 135 42.5 135 31.6 135 14.9 56 17.2 17 12.2 96 30.8 122 35.0 123 15.1 87 18.7 65 26.4 66 7.58 101 25.1 53 38.3 54 11.4 100 25.5 131 31.7 130 8.24 56
Adaptive flow [45]87.0 10.3 96 14.8 67 2.37 110 9.87 125 11.5 111 5.57 108 18.0 71 17.9 44 17.1 84 16.4 96 20.0 67 14.8 119 32.3 130 36.7 130 16.6 127 21.1 120 29.8 120 8.41 118 23.8 28 36.4 30 13.1 108 21.7 35 27.1 33 7.17 12
Shiralkar [42]87.7 12.0 119 18.8 119 1.72 25 9.11 96 11.1 84 5.14 85 21.2 95 16.6 29 13.7 62 19.2 125 24.3 124 10.6 50 29.7 85 33.7 85 12.8 54 18.0 41 25.4 42 7.19 87 29.4 114 44.9 114 10.4 93 25.1 129 31.5 129 9.03 118
FC-2Layers-FF [74]87.7 9.71 78 14.9 70 2.11 100 7.51 11 9.66 13 4.67 64 20.5 91 25.1 113 20.2 106 15.6 77 21.1 85 11.9 86 30.5 113 34.6 111 15.3 97 20.8 116 29.4 115 7.31 90 29.7 116 45.6 118 9.76 84 23.6 96 29.7 100 8.22 54
SLK [47]87.9 9.63 71 15.0 75 1.90 73 9.14 98 10.3 33 5.63 112 34.7 130 19.7 69 22.4 117 18.9 122 24.2 123 20.4 134 29.8 91 33.8 90 12.2 29 18.1 43 25.5 43 6.93 77 31.9 127 48.8 127 9.12 70 22.8 62 28.5 61 14.2 133
EPPM w/o HM [88]88.8 10.4 98 16.2 98 2.97 120 8.62 67 11.3 97 2.76 9 29.0 123 27.4 117 22.2 116 16.8 103 22.6 105 10.8 54 25.8 19 29.2 18 12.1 18 20.2 105 28.6 105 6.49 60 29.8 118 45.8 119 18.0 123 24.0 112 30.2 113 8.72 114
UnFlow [129]89.4 13.4 125 21.2 127 2.71 117 8.81 74 10.7 61 6.35 123 18.7 77 18.9 56 14.8 71 14.6 50 19.6 58 7.77 14 31.8 129 36.1 129 15.0 82 22.2 131 31.4 131 7.79 107 24.2 33 37.0 36 7.49 16 28.1 135 33.7 135 11.6 129
Correlation Flow [75]91.5 9.75 82 15.3 87 1.84 66 9.28 105 11.6 114 5.17 86 17.5 65 18.9 56 15.2 76 16.1 92 21.7 97 11.3 65 30.2 101 34.3 102 12.5 47 21.2 121 29.9 121 8.24 116 31.3 126 47.8 126 9.82 86 24.9 127 31.3 128 6.61 3
HBpMotionGpu [43]93.3 12.7 121 19.5 120 2.69 115 9.65 121 11.7 120 5.48 106 20.0 88 23.3 101 17.0 82 17.6 116 23.4 117 10.6 50 30.8 122 35.0 123 25.1 135 20.4 110 28.9 111 7.95 109 22.0 5 33.7 6 7.44 12 23.2 76 29.1 74 8.40 99
PGAM+LK [55]94.4 11.9 118 18.0 115 7.26 135 9.48 113 10.8 64 7.62 126 31.5 126 39.9 134 31.4 134 19.0 123 23.6 119 16.3 127 29.1 76 33.0 76 12.6 50 18.4 51 26.0 54 6.80 73 25.5 62 39.0 64 14.8 114 22.6 54 28.4 55 8.41 102
2bit-BM-tele [98]95.3 11.1 109 17.2 108 2.34 108 9.40 108 11.7 120 5.36 99 28.5 121 37.1 133 31.0 133 15.7 83 20.8 80 9.18 32 28.6 57 32.5 57 15.0 82 22.0 130 31.1 130 9.53 129 39.1 135 59.9 135 26.9 135 20.8 15 26.1 15 8.11 33
StereoFlow [44]96.1 14.9 130 22.2 130 3.28 122 10.0 128 12.7 134 4.99 77 16.8 51 18.9 56 12.1 43 15.2 65 20.4 75 10.4 48 33.4 133 37.9 133 20.8 132 23.8 133 33.5 133 8.41 118 25.3 59 38.8 62 7.81 40 23.6 96 29.6 96 8.67 113
Rannacher [23]96.3 11.1 109 17.5 112 1.89 69 9.59 119 11.8 125 5.28 91 24.3 112 18.0 45 20.8 109 15.9 88 21.2 88 11.6 79 30.4 107 34.5 108 12.3 40 19.7 97 27.9 98 7.98 110 29.6 115 45.3 115 9.57 79 24.7 124 31.0 124 8.19 48
OFRF [134]96.5 13.6 126 21.1 126 2.23 106 9.25 103 11.4 101 5.60 109 19.2 80 19.5 68 14.1 67 16.9 105 22.8 110 14.6 113 30.8 122 34.9 121 14.4 73 19.6 93 27.7 93 6.07 26 28.3 102 43.4 102 7.78 37 24.7 124 31.1 126 8.34 83
SimpleFlow [49]98.8 9.15 49 14.3 52 1.73 26 9.05 88 11.4 101 5.35 98 36.0 132 32.6 130 29.4 132 14.9 56 20.2 69 11.2 64 30.6 118 34.7 116 15.1 87 22.6 132 32.0 132 9.11 126 34.7 131 53.2 131 13.8 111 23.9 108 29.9 103 8.33 80
SegOF [10]100.0 11.8 116 18.2 117 5.53 133 8.88 79 11.4 101 4.62 62 31.1 125 20.5 77 23.7 121 25.8 133 34.8 134 18.2 130 30.2 101 34.2 101 15.3 97 19.1 79 27.0 80 7.08 85 32.5 129 49.7 129 16.8 120 22.8 62 28.6 63 8.08 26
Aniso-Texture [82]100.1 10.6 102 16.7 105 1.74 33 9.83 124 12.4 132 5.36 99 17.6 68 19.9 71 13.1 59 22.9 130 27.8 128 19.7 133 30.3 105 34.4 105 15.4 117 20.8 116 29.4 115 8.86 124 26.8 84 41.0 86 8.38 60 24.6 121 30.9 122 8.26 64
SPSA-learn [13]100.2 15.1 131 22.9 131 1.93 77 9.08 93 11.0 75 5.42 102 33.0 129 24.8 109 23.8 122 17.6 116 22.4 102 12.1 92 29.3 81 33.2 79 15.1 87 17.8 34 25.1 35 6.73 70 37.7 132 57.7 133 25.5 134 25.4 130 31.8 131 8.33 80
HCIC-L [99]104.9 14.3 128 20.9 125 2.86 119 11.2 133 13.3 135 7.62 126 23.9 109 31.6 129 25.6 127 21.0 129 28.2 130 14.8 119 25.6 16 29.0 16 12.2 29 24.0 134 33.9 134 10.5 132 30.5 124 46.8 124 18.5 124 23.3 82 29.2 81 7.37 13
IIOF-NLDP [131]106.9 10.2 95 15.8 93 2.10 99 9.06 89 11.2 89 5.60 109 20.6 92 24.8 109 16.9 81 16.7 102 22.6 105 14.6 113 30.4 107 34.5 108 20.8 132 20.4 110 28.8 108 8.81 123 37.7 132 57.6 132 16.8 120 24.9 127 31.2 127 8.26 64
GroupFlow [9]112.9 15.6 132 23.3 132 3.31 123 9.20 100 11.4 101 6.26 121 30.9 124 22.4 90 18.9 96 25.4 132 30.0 132 21.2 135 32.4 131 36.7 130 15.3 97 20.9 118 29.4 115 7.71 105 29.9 119 45.5 116 9.50 77 23.3 82 29.1 74 10.6 127
Pyramid LK [2]119.5 14.0 127 21.7 128 4.34 127 13.7 134 11.5 111 9.94 132 37.6 133 26.8 116 24.6 125 25.9 134 29.3 131 18.7 131 35.0 134 39.7 134 13.3 59 19.9 100 24.8 29 9.57 130 33.3 130 51.1 130 10.7 95 26.0 133 32.4 133 13.0 131
Periodicity [78]133.0 18.1 135 27.0 135 6.22 134 17.4 135 12.4 132 10.2 133 35.2 131 30.7 128 27.8 129 24.1 131 31.6 133 17.5 129 37.6 135 42.6 135 18.8 129 27.7 135 39.3 135 11.2 135 38.6 134 58.9 134 22.9 132 27.3 134 33.2 134 14.3 134
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.