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        
A99
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
PMMST [114]11.0 11.2 11 21.1 7 2.71 2 13.8 8 19.7 7 3.65 22 10.3 2 19.2 8 2.71 1 16.8 4 30.8 23 7.53 30 41.1 6 51.1 8 10.0 18 24.6 3 43.0 7 4.93 13 34.2 11 70.9 13 4.04 9 28.8 15 45.4 25 3.42 10
MDP-Flow2 [68]11.4 11.0 4 20.7 6 2.71 2 13.9 10 19.9 9 3.46 2 10.3 2 20.3 15 3.00 2 16.7 3 30.0 15 7.35 7 41.0 5 50.7 5 10.1 30 27.1 36 44.9 20 4.97 20 33.6 4 70.1 8 3.92 4 29.2 19 47.0 36 3.42 10
SuperSlomo [132]17.2 9.66 1 16.1 1 3.37 107 15.4 35 20.4 13 6.06 117 8.43 1 14.4 1 3.00 2 17.1 6 23.8 1 8.58 109 38.5 1 47.8 1 8.76 2 23.1 1 40.8 2 4.80 3 30.2 1 62.5 1 3.87 1 25.2 2 37.4 2 3.32 1
NNF-Local [87]20.7 11.4 17 21.6 10 2.71 2 12.8 1 18.4 2 3.56 4 10.4 4 20.0 13 3.00 2 19.8 60 37.3 89 7.35 7 41.5 12 51.4 10 10.0 18 28.2 62 47.3 38 5.07 47 34.5 14 71.9 24 4.04 9 29.1 18 46.1 31 3.37 3
SepConv-v1 [127]21.5 9.68 2 19.1 2 2.52 1 15.4 35 20.1 11 5.26 103 11.0 11 16.7 2 3.87 99 20.4 74 26.8 2 9.59 121 41.9 13 52.5 17 9.00 3 24.7 4 42.4 4 4.69 1 30.7 2 67.4 2 3.92 4 24.7 1 35.8 1 3.32 1
NN-field [71]23.7 11.5 25 22.9 24 2.71 2 13.0 3 18.6 3 3.42 1 12.3 78 19.7 9 3.00 2 21.1 82 39.8 105 7.44 17 41.4 10 51.4 10 10.0 18 27.5 44 46.4 29 4.97 20 33.8 7 71.0 15 4.04 9 29.3 21 46.2 32 3.37 3
NNF-EAC [103]27.5 11.5 25 21.7 11 3.11 74 14.5 22 21.0 25 3.70 24 12.3 78 22.6 36 3.00 2 17.7 17 32.4 42 7.55 37 43.2 39 55.1 43 10.1 30 25.1 7 43.8 10 4.90 7 34.0 9 70.5 10 4.08 39 29.4 23 47.5 41 3.42 10
DeepFlow2 [108]29.7 11.4 17 23.5 28 3.00 61 16.7 59 23.0 61 4.04 56 11.0 11 20.3 15 3.00 2 19.0 48 29.8 13 7.53 30 42.7 26 54.0 26 10.3 54 25.0 5 43.0 7 4.93 13 35.2 28 73.8 35 4.04 9 28.9 16 44.9 22 3.56 70
DeepFlow [86]29.9 11.3 15 24.2 41 3.00 61 16.6 58 23.0 61 4.32 70 11.0 11 20.3 15 3.00 2 19.3 51 28.1 7 7.59 45 42.7 26 54.5 31 10.2 49 25.2 9 44.1 11 5.00 41 32.9 3 68.2 3 4.04 9 28.4 11 44.6 18 3.56 70
SuperFlow [81]31.0 11.0 4 22.1 18 3.11 74 17.1 65 22.7 53 4.69 84 11.7 47 18.7 3 3.37 70 18.7 41 27.4 4 7.70 66 41.3 8 51.2 9 9.98 14 26.3 23 46.9 32 4.80 3 34.7 17 76.0 46 4.08 39 28.1 9 41.5 6 3.42 10
PH-Flow [101]31.2 11.9 57 25.7 70 2.83 18 13.3 5 19.7 7 3.56 4 10.7 6 22.7 37 3.00 2 16.5 2 30.2 16 7.33 3 42.3 19 52.1 14 10.1 30 28.7 78 50.9 92 5.20 71 35.6 35 77.0 56 4.04 9 29.6 29 47.0 36 3.51 53
DF-Auto [115]31.9 10.9 3 19.2 3 3.11 74 17.2 68 23.4 70 4.43 75 10.4 4 20.6 22 3.00 2 18.1 28 29.7 10 7.55 37 41.4 10 52.1 14 10.0 18 26.2 18 47.2 35 4.97 20 35.2 28 79.3 69 4.08 39 29.6 29 44.7 19 3.56 70
CombBMOF [113]32.0 12.0 62 24.3 42 2.83 18 14.3 16 20.6 17 3.56 4 11.3 28 25.7 63 3.00 2 20.3 73 34.9 67 7.55 37 43.2 39 54.0 26 10.1 30 26.4 24 47.7 45 4.90 7 36.2 53 71.4 19 4.08 39 29.5 26 45.7 28 3.37 3
CBF [12]34.0 11.0 4 19.8 4 3.00 61 17.1 65 22.9 58 4.24 67 12.0 62 19.0 5 3.00 2 17.8 22 28.0 6 7.85 81 40.6 4 49.9 3 9.97 10 26.2 18 44.6 15 4.97 20 36.3 55 76.3 51 4.12 84 27.9 5 41.2 5 3.70 108
Aniso. Huber-L1 [22]34.8 11.4 17 21.7 11 3.11 74 19.7 104 24.7 103 4.55 79 12.0 62 19.7 9 3.11 64 18.4 33 29.8 13 7.55 37 42.5 22 54.4 30 9.98 14 25.2 9 42.2 3 4.83 5 35.6 35 71.5 20 4.04 9 27.9 5 42.0 8 3.56 70
LME [70]35.0 11.4 17 22.0 16 2.71 2 15.1 30 21.8 36 3.87 48 11.3 28 36.0 123 3.00 2 17.4 9 32.0 39 7.48 21 44.5 63 57.0 61 11.4 127 27.6 46 47.2 35 4.97 20 33.6 4 69.7 5 4.04 9 30.0 35 48.6 53 3.42 10
WLIF-Flow [93]36.1 11.5 25 22.1 18 2.83 18 15.2 31 21.6 33 3.79 39 11.3 28 26.4 71 3.00 2 17.4 9 30.3 18 7.59 45 42.5 22 53.5 22 10.4 63 29.0 84 51.1 95 5.29 88 34.8 20 69.7 5 4.04 9 30.0 35 48.4 49 3.46 38
IROF++ [58]36.4 11.9 57 24.1 38 2.83 18 14.7 25 21.3 27 3.56 4 12.1 75 29.0 91 3.00 2 16.3 1 27.9 5 7.35 7 43.9 51 56.0 51 11.1 97 26.4 24 47.0 34 4.93 13 34.5 14 72.3 25 4.08 39 30.3 45 49.3 61 3.56 70
CLG-TV [48]36.7 11.1 9 21.8 14 3.11 74 18.8 88 24.0 84 4.43 75 11.3 28 20.0 13 3.70 86 18.6 39 28.9 8 7.72 71 42.8 29 55.0 42 10.0 18 25.0 5 42.9 6 4.93 13 36.0 47 71.6 21 4.04 9 29.0 17 44.0 14 3.56 70
FMOF [94]37.5 12.2 82 24.5 51 2.94 49 14.0 11 20.0 10 3.56 4 12.3 78 27.7 79 3.00 2 19.8 60 35.4 72 7.70 66 42.4 20 52.1 14 10.1 30 28.1 58 49.1 61 4.93 13 34.6 16 72.7 29 3.87 1 30.2 41 47.6 44 3.42 10
Brox et al. [5]38.6 11.4 17 24.9 63 2.94 49 15.9 44 22.2 45 4.04 56 11.3 28 21.0 23 3.37 70 18.4 33 27.0 3 7.59 45 42.2 17 53.3 20 10.0 18 28.2 62 51.5 98 5.00 41 36.8 58 88.0 97 4.04 9 28.4 11 42.3 9 3.42 10
IROF-TV [53]39.0 11.7 39 24.7 58 3.00 61 15.5 39 22.0 42 3.70 24 11.0 11 23.7 47 3.00 2 17.3 7 31.3 27 7.57 44 43.8 49 56.0 51 11.2 104 27.6 46 48.4 52 4.97 20 35.9 45 74.5 42 4.08 39 28.0 7 42.6 10 3.56 70
ALD-Flow [66]40.0 12.0 62 28.4 96 3.11 74 16.3 51 22.8 55 3.83 43 11.0 11 21.7 29 3.00 2 17.9 25 33.6 55 7.39 12 43.4 44 54.6 35 10.8 83 25.8 13 44.8 19 5.00 41 34.1 10 70.4 9 4.04 9 31.9 75 50.3 69 3.46 38
nLayers [57]40.6 11.8 47 22.9 24 2.83 18 14.1 12 20.4 13 3.56 4 11.0 11 19.7 9 3.00 2 18.3 31 34.2 63 7.39 12 46.7 115 60.1 111 11.0 91 27.9 52 50.1 68 5.20 71 35.5 33 72.6 28 4.08 39 30.8 50 49.3 61 3.42 10
LDOF [28]42.5 11.4 17 22.5 21 3.56 117 16.1 46 21.4 32 6.35 122 12.0 62 20.3 15 3.70 86 19.0 48 29.7 10 7.94 86 41.2 7 50.9 6 10.1 30 26.8 29 50.2 70 4.90 7 34.8 20 80.2 73 4.08 39 29.4 23 44.5 16 3.46 38
Layers++ [37]42.6 11.4 17 21.7 11 2.94 49 12.8 1 18.2 1 3.46 2 11.0 11 26.7 74 3.00 2 17.7 17 32.9 47 7.53 30 46.6 113 60.9 122 10.6 75 30.9 116 60.2 124 5.00 41 34.9 26 72.7 29 3.87 1 29.9 34 47.5 41 3.46 38
MDP-Flow [26]42.6 11.2 11 21.2 8 2.71 2 14.2 14 20.5 16 3.70 24 10.7 6 19.0 5 3.00 2 19.7 58 32.4 42 7.70 66 44.2 55 57.0 61 11.2 104 30.0 104 51.4 97 5.51 117 36.1 51 72.9 32 4.08 39 30.8 50 48.4 49 3.42 10
p-harmonic [29]42.6 11.4 17 23.5 28 2.83 18 19.1 92 24.3 92 4.80 89 11.3 28 22.0 31 3.70 86 20.9 80 31.7 33 7.62 51 42.6 25 54.2 28 10.1 30 25.7 12 43.5 9 5.07 47 36.1 51 71.8 22 4.08 39 29.6 29 46.5 33 3.51 53
Second-order prior [8]43.2 11.3 15 22.0 16 3.11 74 19.0 91 24.2 90 4.32 70 13.3 90 27.7 79 3.70 86 18.8 44 31.6 32 7.51 25 42.9 31 54.7 37 10.0 18 26.2 18 45.0 21 4.97 20 35.6 35 71.2 16 4.04 9 29.5 26 45.4 25 3.56 70
SIOF [67]43.9 11.7 39 23.1 26 3.11 74 19.4 99 24.8 106 4.76 86 11.3 28 25.7 63 3.11 64 18.4 33 31.4 29 8.04 91 40.3 3 50.3 4 9.95 8 25.8 13 45.3 23 4.97 20 33.9 8 71.2 16 4.08 39 30.0 35 47.4 38 3.70 108
Local-TV-L1 [65]44.6 11.2 11 21.5 9 3.56 117 19.6 102 24.4 95 5.57 110 11.0 11 19.1 7 3.00 2 18.3 31 30.4 21 7.87 84 42.8 29 54.5 31 10.2 49 26.2 18 44.7 16 5.45 105 34.2 11 76.1 49 4.08 39 28.0 7 42.8 12 3.65 105
COFM [59]44.9 11.8 47 24.3 42 2.94 49 14.5 22 20.9 22 3.65 22 11.0 11 26.4 71 3.00 2 17.4 9 32.3 40 7.35 7 44.2 55 55.1 43 10.1 30 30.0 104 54.4 116 5.20 71 35.8 41 79.3 69 4.08 39 31.2 57 48.8 56 3.51 53
ProbFlowFields [128]46.2 11.6 31 25.4 67 2.83 18 14.4 18 21.1 26 3.56 4 10.7 6 23.7 47 3.00 2 18.4 33 33.4 52 7.59 45 46.2 103 59.2 97 11.2 104 28.5 74 50.7 86 5.32 93 34.7 17 76.9 54 4.08 39 29.4 23 46.5 33 3.46 38
FlowFields [110]46.4 11.8 47 25.6 69 2.83 18 14.4 18 20.9 22 3.56 4 11.3 28 24.3 54 3.00 2 20.0 66 38.1 94 7.51 25 43.6 46 54.5 31 11.0 91 28.2 62 50.7 86 5.16 66 34.8 20 75.1 45 4.04 9 32.0 80 52.0 92 3.46 38
TV-L1-MCT [64]48.9 12.4 98 24.7 58 2.83 18 16.4 52 23.1 63 3.83 43 11.9 61 32.7 113 3.00 2 17.6 14 31.7 33 7.53 30 47.0 123 61.2 123 11.0 91 25.5 11 44.7 16 4.97 20 36.0 47 80.7 78 4.04 9 28.4 11 44.8 21 3.46 38
BlockOverlap [61]49.6 11.1 9 20.1 5 3.56 117 19.3 96 23.7 77 6.16 118 11.3 28 20.4 20 3.70 86 18.4 33 29.6 9 8.72 113 43.1 36 54.5 31 10.2 49 27.4 41 48.6 55 5.35 100 34.8 20 72.8 31 4.08 39 27.2 4 40.9 4 3.56 70
Sparse-NonSparse [56]50.1 12.0 62 24.3 42 2.83 18 15.0 28 21.3 27 3.56 4 11.7 47 29.0 91 3.00 2 17.6 14 29.7 10 7.39 12 45.7 87 59.3 98 11.0 91 28.8 79 48.7 57 5.07 47 38.6 84 90.1 108 4.04 9 32.4 88 51.8 88 3.42 10
HAST [109]50.3 11.7 39 23.6 30 2.94 49 13.8 8 19.6 6 3.56 4 12.0 62 31.7 109 3.00 2 17.8 22 31.7 33 7.14 1 45.3 79 57.0 61 9.97 10 33.7 128 62.8 131 5.10 63 38.4 79 88.4 99 4.04 9 33.0 97 51.0 76 3.42 10
OAR-Flow [125]51.2 12.0 62 24.9 63 3.00 61 16.4 52 22.4 48 4.08 61 11.0 11 20.5 21 3.00 2 17.4 9 33.6 55 7.33 3 46.2 103 60.0 110 11.3 120 27.0 32 47.6 42 5.23 78 37.6 68 74.0 37 4.08 39 31.0 55 49.2 59 3.46 38
Modified CLG [34]51.3 11.0 4 21.9 15 3.11 74 19.6 102 23.9 81 5.94 115 12.4 82 26.3 69 3.87 99 19.8 60 30.8 23 8.12 96 42.1 15 52.9 18 10.1 30 27.0 32 48.1 50 5.23 78 34.7 17 70.8 12 4.08 39 29.5 26 45.3 24 3.56 70
CPM-Flow [116]51.6 11.8 47 27.3 86 2.83 18 14.4 18 20.4 13 3.70 24 11.7 47 24.0 50 3.00 2 21.4 89 40.1 108 7.77 75 45.5 83 58.1 78 11.2 104 26.6 28 48.0 48 5.07 47 36.0 47 72.3 25 4.04 9 30.9 53 50.4 70 3.56 70
2DHMM-SAS [92]52.4 12.2 82 24.5 51 2.83 18 17.9 76 24.1 87 3.87 48 12.0 62 28.7 88 3.00 2 17.3 7 31.4 29 7.51 25 45.1 75 58.2 83 11.2 104 27.9 52 49.0 59 4.83 5 37.0 60 76.1 49 4.08 39 31.9 75 50.5 71 3.42 10
FlowFields+ [130]52.6 11.8 47 26.1 78 2.71 2 14.1 12 20.6 17 3.70 24 11.2 27 24.8 59 3.00 2 20.1 68 40.2 110 7.53 30 45.5 83 58.0 75 11.2 104 28.6 77 50.6 82 5.20 71 35.6 35 77.5 61 4.04 9 32.2 83 52.5 96 3.42 10
AdaConv-v1 [126]52.7 15.0 126 28.2 95 3.70 121 17.6 73 20.7 20 7.68 130 17.4 110 22.0 31 7.00 124 27.5 119 33.7 59 17.0 131 39.9 2 49.8 2 8.19 1 23.8 2 39.5 1 4.76 2 34.2 11 68.5 4 4.12 84 26.9 3 39.5 3 3.42 10
F-TV-L1 [15]52.8 12.0 62 26.5 81 3.56 117 19.2 94 24.7 103 4.83 91 11.7 47 21.5 27 4.00 101 19.3 51 32.7 45 7.68 60 43.1 36 55.3 46 9.83 4 25.1 7 42.8 5 5.07 47 34.8 20 74.0 37 4.16 92 28.5 14 42.7 11 3.56 70
AGIF+OF [85]52.9 12.2 82 24.3 42 2.71 2 15.2 31 21.8 36 3.70 24 11.7 47 27.7 79 3.00 2 18.0 26 33.0 49 7.55 37 45.8 91 58.8 94 11.2 104 30.0 104 53.4 110 5.07 47 35.4 30 74.8 44 3.92 4 32.2 83 52.6 99 3.37 3
ComponentFusion [96]53.2 12.0 62 29.6 104 2.71 2 14.5 22 21.3 27 3.56 4 11.0 11 22.0 31 3.00 2 18.8 44 36.2 84 7.33 3 45.5 83 58.2 83 10.7 80 27.2 37 46.3 27 4.97 20 40.5 105 93.3 117 4.12 84 34.4 112 58.3 122 3.42 10
TC/T-Flow [76]54.4 12.4 98 26.4 80 2.83 18 16.5 56 23.1 63 3.83 43 11.0 11 22.4 35 3.00 2 18.9 46 34.5 64 7.33 3 45.5 83 58.1 78 11.4 127 27.3 40 47.6 42 4.93 13 41.1 107 80.4 76 4.20 99 30.9 53 49.7 65 3.37 3
DPOF [18]54.5 12.3 91 29.4 103 3.11 74 13.3 5 19.1 5 3.56 4 15.7 101 25.2 61 3.70 86 19.4 53 37.5 91 7.59 45 43.1 36 54.6 35 10.0 18 29.1 89 49.7 64 4.90 7 36.6 56 77.0 56 4.08 39 31.5 65 50.5 71 3.51 53
Ad-TV-NDC [36]56.5 12.2 82 22.5 21 4.32 129 20.6 124 24.8 106 5.80 111 11.7 47 21.6 28 3.37 70 21.6 90 31.8 36 8.04 91 42.5 22 53.4 21 9.97 10 26.4 24 47.6 42 5.16 66 36.8 58 70.9 13 4.08 39 28.3 10 41.8 7 3.70 108
PGM-C [120]56.8 11.8 47 27.3 86 2.83 18 14.4 18 20.7 20 3.70 24 12.3 78 23.0 41 3.00 2 20.6 77 42.3 116 7.62 51 45.8 91 59.5 104 11.2 104 27.2 37 47.4 39 4.97 20 37.1 62 79.2 66 4.04 9 32.4 88 55.0 112 3.51 53
Ramp [62]57.0 12.0 62 24.6 54 2.94 49 14.8 26 21.3 27 3.70 24 11.7 47 29.4 97 3.00 2 16.9 5 30.3 18 7.39 12 45.4 81 58.5 86 11.0 91 30.2 110 50.9 92 5.23 78 39.8 98 89.6 105 4.04 9 32.4 88 52.5 96 3.42 10
PMF [73]57.0 12.2 82 25.9 73 2.71 2 15.4 35 21.8 36 3.56 4 12.7 84 35.7 121 3.00 2 20.2 71 35.9 78 7.51 25 44.4 61 54.9 41 10.1 30 28.4 67 50.5 80 5.32 93 37.9 73 81.1 81 4.04 9 34.2 111 54.1 106 3.37 3
TF+OM [100]57.1 11.6 31 30.1 109 3.11 74 15.0 28 21.6 33 4.04 56 11.7 47 24.0 50 3.00 2 21.3 86 39.0 104 7.68 60 44.3 57 56.7 59 10.3 54 28.8 79 50.4 77 5.07 47 37.7 69 83.5 91 4.08 39 29.2 19 46.0 29 3.56 70
ComplOF-FED-GPU [35]57.5 12.0 62 27.9 92 2.94 49 15.7 43 22.2 45 3.79 39 16.0 102 21.4 25 3.70 86 18.4 33 33.6 55 7.48 21 44.9 72 57.7 69 10.7 80 27.4 41 45.9 24 5.00 41 36.6 56 78.7 65 4.08 39 32.6 95 52.3 94 3.51 53
AggregFlow [97]57.6 13.7 118 37.1 123 3.11 74 16.2 49 22.6 51 4.04 56 11.0 11 23.3 46 3.00 2 21.8 92 40.7 112 7.66 58 43.2 39 53.5 22 10.3 54 27.0 32 46.0 25 5.00 41 38.0 74 82.4 88 4.08 39 31.9 75 51.9 91 3.42 10
OFLAF [77]58.6 11.7 39 24.5 51 2.71 2 13.6 7 20.3 12 3.56 4 11.0 11 23.0 41 3.00 2 17.6 14 31.3 27 7.39 12 47.3 125 61.7 127 11.2 104 29.6 99 51.9 104 5.32 93 41.8 113 95.6 122 4.16 92 33.6 103 52.1 93 3.42 10
S2F-IF [123]58.6 12.1 75 29.8 106 2.71 2 14.2 14 20.6 17 3.56 4 11.3 28 26.3 69 3.00 2 20.2 71 40.1 108 7.53 30 45.9 96 58.7 93 11.3 120 28.4 67 50.7 86 5.20 71 35.7 39 76.0 46 4.08 39 32.3 86 53.1 100 3.46 38
Classic+NL [31]59.3 12.1 75 24.3 42 3.00 61 15.3 34 21.8 36 3.70 24 11.7 47 29.4 97 3.00 2 17.4 9 31.4 29 7.53 30 45.7 87 59.4 100 10.8 83 29.0 84 49.8 67 5.10 63 39.6 95 90.4 110 4.08 39 32.2 83 51.8 88 3.46 38
Classic++ [32]59.3 11.6 31 23.7 31 3.11 74 17.8 75 24.4 95 4.08 61 11.7 47 20.3 15 3.37 70 20.1 68 33.8 60 7.62 51 44.7 66 57.8 72 10.0 18 28.0 55 49.7 64 5.35 100 37.4 66 81.4 83 4.08 39 30.7 49 49.5 63 3.56 70
FlowNetS+ft+v [112]60.6 11.5 25 23.7 31 3.46 115 19.9 109 24.6 101 7.87 132 12.0 62 21.1 24 3.37 70 19.5 55 30.6 22 8.91 116 43.7 47 56.6 58 11.2 104 26.0 15 44.5 14 4.97 20 38.6 84 87.8 95 4.08 39 30.0 35 46.0 29 3.51 53
LSM [39]61.1 12.3 91 24.7 58 2.83 18 15.4 35 21.9 40 3.56 4 12.0 62 30.3 104 3.00 2 18.7 41 33.2 51 7.44 17 46.1 101 59.4 100 11.1 97 29.3 92 51.9 104 5.07 47 39.2 89 91.0 113 4.04 9 32.3 86 52.5 96 3.42 10
FC-2Layers-FF [74]61.2 12.1 75 26.0 77 2.83 18 13.0 3 18.7 4 3.56 4 11.4 44 25.7 63 3.00 2 17.8 22 33.5 54 7.48 21 46.5 109 60.3 116 11.2 104 30.4 113 52.3 109 5.32 93 39.8 98 90.0 107 4.08 39 31.8 71 51.6 84 3.46 38
MLDP_OF [89]61.4 11.9 57 24.7 58 2.83 18 17.4 71 23.8 79 3.87 48 10.7 6 24.6 57 3.00 2 20.5 76 33.6 55 8.35 104 44.1 53 56.5 56 10.1 30 29.3 92 50.5 80 5.57 118 35.8 41 73.4 34 4.20 99 31.2 57 50.6 74 3.70 108
RNLOD-Flow [121]62.4 11.8 47 24.6 54 2.89 45 17.3 70 24.0 84 3.74 37 12.7 84 36.0 123 3.11 64 18.1 28 31.2 26 7.48 21 45.8 91 59.6 105 11.1 97 29.3 92 50.6 82 5.16 66 35.4 30 74.1 39 4.08 39 32.0 80 51.6 84 3.42 10
TCOF [69]62.5 12.0 62 24.7 58 2.83 18 20.3 119 26.4 132 5.07 96 11.1 26 29.0 91 3.00 2 17.7 17 32.4 42 7.68 60 43.2 39 55.5 47 9.97 10 28.8 79 46.3 27 5.07 47 41.2 110 94.9 120 4.08 39 31.8 71 51.3 80 3.70 108
CRTflow [80]62.6 11.7 39 24.4 49 3.32 103 19.5 101 24.9 110 4.51 77 12.0 62 22.7 37 4.00 101 18.1 28 30.3 18 7.68 60 45.0 73 58.1 78 11.3 120 26.0 15 45.1 22 4.97 20 37.7 69 87.9 96 4.08 39 30.8 50 50.2 66 3.56 70
RFlow [90]63.0 11.6 31 24.3 42 3.00 61 19.3 96 24.8 106 4.36 72 11.6 46 29.7 99 3.37 70 20.0 66 36.1 80 7.72 71 43.0 32 55.2 45 10.1 30 27.9 52 51.8 103 4.97 20 37.1 62 82.8 90 4.08 39 31.6 67 49.5 63 3.56 70
Fusion [6]63.1 11.6 31 24.3 42 2.89 45 15.6 41 21.9 40 3.83 43 11.0 11 23.7 47 3.37 70 21.0 81 33.4 52 7.62 51 44.1 53 56.3 55 10.1 30 30.3 112 54.1 114 5.45 105 38.0 74 83.7 92 4.08 39 34.0 109 54.7 108 3.56 70
Sparse Occlusion [54]63.6 11.7 39 25.9 73 3.00 61 18.1 80 24.6 101 3.83 43 11.3 28 22.7 37 3.11 64 18.7 41 34.1 62 7.70 66 45.0 73 58.0 75 11.1 97 28.5 74 44.2 12 5.26 82 39.3 92 83.7 92 3.92 4 31.9 75 51.7 86 3.56 70
S2D-Matching [84]64.0 12.3 91 25.7 70 2.94 49 17.2 68 23.7 77 4.00 54 11.7 47 28.7 88 3.00 2 17.7 17 31.9 38 7.55 37 46.8 118 60.1 111 10.4 63 30.0 104 51.5 98 5.29 88 37.0 60 77.7 62 4.04 9 31.8 71 50.9 75 3.46 38
TC-Flow [46]64.8 12.0 62 30.3 111 2.89 45 16.8 61 23.4 70 3.92 53 11.7 47 21.4 25 3.00 2 19.5 55 36.1 80 8.12 96 46.5 109 59.8 108 11.3 120 27.0 32 48.4 52 5.26 82 35.5 33 74.6 43 4.04 9 33.3 100 54.5 107 3.51 53
SVFilterOh [111]65.2 11.9 57 26.1 78 2.94 49 14.3 16 20.9 22 3.70 24 12.0 62 26.7 74 3.00 2 19.9 64 36.1 80 7.62 51 46.7 115 59.8 108 11.4 127 30.7 115 55.1 117 5.07 47 36.0 47 77.2 58 4.04 9 32.4 88 53.2 102 3.51 53
HBM-GC [105]65.4 11.8 47 23.8 34 3.11 74 16.8 61 24.2 90 3.87 48 10.7 6 18.7 3 3.00 2 18.9 46 32.9 47 7.68 60 46.8 118 60.8 120 11.5 133 34.5 131 61.7 126 5.48 113 37.7 69 81.9 87 4.04 9 30.5 48 47.8 45 3.51 53
Black & Anandan [4]65.7 12.3 91 24.0 36 3.46 115 21.2 126 25.4 118 5.35 105 18.1 113 25.0 60 5.35 116 24.4 111 34.9 67 7.77 75 42.2 17 53.5 22 10.1 30 26.9 31 46.5 30 4.97 20 39.5 93 77.2 58 4.08 39 29.3 21 42.8 12 3.56 70
3DFlow [135]66.4 12.4 98 27.1 85 2.83 18 15.5 39 22.1 43 3.87 48 13.7 92 24.0 50 3.00 2 19.2 50 38.7 101 7.68 60 44.0 52 56.0 51 10.1 30 31.2 119 53.8 113 5.60 119 39.5 93 79.2 66 4.16 92 31.1 56 48.0 46 3.56 70
Classic+CPF [83]66.8 12.2 82 24.6 54 2.83 18 15.6 41 22.1 43 3.74 37 12.0 62 30.7 105 3.00 2 17.7 17 30.9 25 7.44 17 47.2 124 61.3 124 11.2 104 31.2 119 55.9 118 5.26 82 39.9 100 88.8 102 4.04 9 33.6 103 54.0 105 3.42 10
FESL [72]67.4 12.2 82 25.1 66 2.83 18 14.9 27 21.6 33 3.70 24 12.1 75 33.7 117 3.00 2 19.7 58 35.0 69 7.72 71 46.2 103 60.2 115 11.3 120 29.3 92 50.4 77 5.32 93 39.6 95 88.6 101 3.92 4 32.4 88 51.2 78 3.42 10
CostFilter [40]68.0 13.1 114 33.1 118 2.71 2 15.2 31 21.3 27 3.56 4 14.0 94 42.7 131 3.00 2 22.0 94 44.4 123 7.26 2 45.8 91 57.2 66 10.4 63 27.2 37 48.1 50 5.45 105 39.9 100 89.4 104 4.08 39 35.6 117 56.1 116 3.37 3
Efficient-NL [60]68.1 11.8 47 23.8 34 2.83 18 16.7 59 23.3 68 3.70 24 18.4 115 29.0 91 3.70 86 19.4 53 34.0 61 7.51 25 45.1 75 58.5 86 11.1 97 30.0 104 51.5 98 5.07 47 40.1 103 88.9 103 4.08 39 33.0 97 52.4 95 3.42 10
EpicFlow [102]68.6 11.9 57 27.6 90 2.83 18 16.0 45 22.2 45 3.79 39 11.8 60 21.7 29 3.00 2 21.3 86 42.9 118 7.85 81 46.3 106 59.4 100 11.2 104 27.4 41 47.5 41 5.16 66 38.2 76 76.6 52 4.12 84 35.2 116 58.0 120 3.56 70
Bartels [41]68.8 12.2 82 29.9 107 3.37 107 17.4 71 24.3 92 4.83 91 11.3 28 24.7 58 3.70 86 21.2 83 35.4 72 9.15 119 41.3 8 51.0 7 9.87 5 29.7 101 50.2 70 6.32 132 33.7 6 70.7 11 4.20 99 30.2 41 48.4 49 3.79 125
Filter Flow [19]68.9 11.8 47 23.1 26 3.37 107 20.0 111 25.1 112 5.23 102 12.2 77 26.0 66 3.70 86 22.1 95 32.7 45 7.94 86 42.1 15 51.9 12 10.4 63 28.1 58 49.0 59 5.07 47 38.4 79 81.6 84 4.16 92 30.0 35 45.5 27 3.74 122
SRR-TVOF-NL [91]69.0 12.9 110 28.7 97 3.00 61 16.9 64 23.1 63 4.69 84 11.5 45 27.0 77 3.00 2 22.2 96 37.3 89 7.59 45 44.8 70 57.9 73 11.0 91 29.1 89 51.9 104 4.90 7 35.7 39 77.7 62 4.08 39 33.0 97 51.5 83 3.56 70
2D-CLG [1]69.1 11.6 31 24.1 38 3.11 74 19.4 99 23.3 68 6.24 120 18.7 116 24.3 54 4.69 110 22.4 98 31.8 36 8.66 112 43.3 43 56.1 54 10.4 63 26.0 15 44.2 12 5.35 100 40.2 104 91.5 115 4.20 99 29.6 29 44.5 16 3.51 53
Steered-L1 [118]69.6 11.2 11 22.6 23 2.89 45 16.2 49 22.6 51 4.55 79 21.7 119 32.4 112 5.00 113 23.4 105 38.3 96 10.7 123 44.7 66 57.4 67 9.88 6 28.0 55 48.5 54 5.32 93 37.1 62 79.2 66 4.12 84 31.4 61 51.1 77 3.51 53
Occlusion-TV-L1 [63]72.5 11.6 31 25.0 65 3.11 74 19.8 107 26.0 126 4.83 91 11.3 28 23.0 41 3.46 83 22.5 101 43.0 120 7.94 86 43.0 32 54.8 40 9.88 6 28.0 55 50.7 86 5.32 93 39.6 95 76.6 52 4.62 122 31.5 65 50.5 71 3.56 70
EPPM w/o HM [88]73.2 12.7 107 30.9 113 2.71 2 16.1 46 23.1 63 3.70 24 17.7 111 42.4 130 3.70 86 21.3 86 42.5 117 7.70 66 43.0 32 53.1 19 10.3 54 30.2 110 57.1 121 4.97 20 38.5 82 89.6 105 4.12 84 32.4 88 51.3 80 3.42 10
OFH [38]73.5 12.0 62 27.3 86 3.00 61 18.1 80 23.4 70 4.20 66 12.4 82 32.7 113 3.00 2 18.6 39 35.4 72 7.35 7 46.5 109 60.1 111 10.8 83 27.5 44 47.2 35 5.26 82 41.1 107 81.1 81 4.20 99 35.7 118 56.1 116 3.46 38
Adaptive [20]73.9 11.6 31 26.7 82 3.11 74 20.2 115 25.9 123 5.07 96 12.0 62 23.0 41 3.37 70 20.4 74 36.6 86 7.77 75 44.3 57 58.5 86 9.98 14 28.3 65 49.1 61 5.16 66 42.5 117 90.6 112 4.08 39 31.6 67 48.8 56 3.65 105
CNN-flow-warp+ref [117]74.0 11.0 4 22.4 20 3.11 74 17.6 73 22.9 58 5.92 114 16.1 103 28.3 87 4.00 101 23.5 106 30.2 16 10.7 123 44.8 70 58.5 86 11.3 120 26.5 27 46.5 30 5.29 88 41.5 111 91.5 115 4.32 111 30.4 46 47.5 41 3.51 53
Horn & Schunck [3]75.8 12.1 75 23.7 31 3.32 103 21.4 128 25.6 121 5.89 113 17.0 107 28.2 86 5.35 116 27.3 118 37.9 92 8.04 91 42.4 20 54.3 29 10.3 54 26.2 18 44.7 16 5.07 47 40.9 106 81.7 85 4.20 99 30.2 41 44.3 15 3.70 108
IAOF [50]76.5 13.0 112 29.2 101 3.37 107 23.7 133 27.4 135 6.45 124 16.4 105 28.7 88 3.46 83 22.7 102 33.1 50 8.37 105 43.4 44 55.6 49 10.0 18 27.6 46 50.1 68 4.97 20 38.3 77 82.7 89 4.08 39 30.0 35 46.8 35 3.56 70
TV-L1-improved [17]77.0 11.5 25 25.4 67 3.11 74 20.1 114 26.0 126 5.26 103 16.8 106 19.7 9 4.04 106 19.5 55 32.3 40 7.79 78 43.8 49 56.5 56 10.0 18 28.9 83 51.1 95 5.07 47 43.2 120 98.9 126 4.43 117 31.4 61 50.2 66 3.70 108
TriFlow [95]77.1 12.5 103 36.7 122 3.00 61 18.7 86 24.5 98 4.76 86 11.7 47 28.1 85 3.00 2 21.7 91 41.4 114 7.62 51 46.8 118 60.4 117 11.2 104 29.9 102 51.7 102 4.97 20 37.8 72 76.9 54 4.08 39 31.7 70 48.6 53 3.51 53
HBpMotionGpu [43]78.1 12.3 91 32.0 116 3.79 124 20.6 124 25.4 118 6.00 116 11.3 28 26.1 68 3.00 2 23.2 104 44.0 122 7.85 81 44.3 57 56.9 60 10.8 83 29.0 84 53.5 112 5.26 82 34.9 26 69.8 7 4.04 9 31.8 71 51.4 82 3.70 108
Nguyen [33]78.5 12.0 62 25.9 73 3.37 107 21.2 126 24.5 98 6.27 121 12.7 84 28.0 83 3.70 86 23.8 107 34.7 65 8.58 109 43.0 32 54.7 37 10.1 30 27.7 51 50.7 86 4.97 20 43.4 122 93.7 118 4.43 117 30.2 41 47.4 38 3.56 70
BriefMatch [124]78.9 12.1 75 29.2 101 3.11 74 16.5 56 22.5 49 6.61 126 18.0 112 22.7 37 5.69 119 26.2 114 35.5 76 18.2 133 43.7 47 54.7 37 10.4 63 29.6 99 50.2 70 5.94 128 35.8 41 72.5 27 4.16 92 32.1 82 50.2 66 3.56 70
GraphCuts [14]79.1 13.9 121 30.2 110 3.32 103 16.4 52 22.5 49 4.36 72 33.4 131 24.1 53 5.35 116 22.3 97 34.7 65 7.87 84 44.5 63 57.0 61 9.98 14 28.3 65 50.3 75 4.90 7 38.5 82 88.2 98 4.20 99 33.9 108 53.6 104 3.56 70
FlowNet2 [122]80.6 19.1 130 47.5 131 3.11 74 17.1 65 24.1 87 4.55 79 14.2 96 29.8 101 3.37 70 23.8 107 42.9 118 8.33 102 45.9 96 58.1 78 10.6 75 27.6 46 49.4 63 4.93 13 39.2 89 81.0 79 4.08 39 31.6 67 49.2 59 3.56 70
TI-DOFE [24]80.9 12.7 107 27.6 90 3.87 128 22.2 131 25.3 114 6.66 127 14.1 95 25.3 62 4.36 108 27.7 120 38.7 101 9.06 117 42.7 26 53.6 25 10.1 30 26.8 29 48.8 58 4.97 20 38.3 77 76.0 46 4.24 109 31.9 75 44.7 19 3.87 127
ROF-ND [107]83.5 12.4 98 24.4 49 2.83 18 17.9 76 23.9 81 4.08 61 12.0 62 26.6 73 3.00 2 29.5 124 48.9 127 8.72 113 45.4 81 58.6 90 11.1 97 31.1 118 53.4 110 5.26 82 38.9 87 74.2 40 4.20 99 38.0 122 60.3 125 3.56 70
NL-TV-NCC [25]85.0 13.7 118 27.3 86 2.94 49 18.5 82 24.7 103 4.04 56 15.0 99 29.0 91 3.70 86 25.6 113 46.4 125 7.94 86 42.0 14 51.9 12 10.4 63 30.6 114 51.9 104 5.29 88 41.9 114 81.7 85 4.40 113 31.3 60 48.6 53 3.79 125
TriangleFlow [30]85.2 12.5 103 25.9 73 3.11 74 18.8 88 24.3 92 4.24 67 13.2 89 29.7 99 3.46 83 21.2 83 35.4 72 7.94 86 44.4 61 57.7 69 9.95 8 29.4 97 48.6 55 5.07 47 43.9 123 99.9 127 4.43 117 42.1 130 69.7 133 3.56 70
Complementary OF [21]85.8 12.4 98 34.5 121 2.83 18 16.4 52 23.5 74 3.79 39 30.7 125 32.2 111 7.05 127 19.9 64 43.9 121 7.44 17 46.9 121 60.4 117 10.7 80 28.1 58 47.7 45 5.23 78 41.1 107 80.3 75 4.12 84 42.0 129 62.0 127 3.56 70
Correlation Flow [75]85.9 12.6 106 28.0 93 2.71 2 20.0 111 25.8 122 4.36 72 11.3 28 22.3 34 3.00 2 20.7 78 38.6 100 7.72 71 45.7 87 59.0 96 10.3 54 33.4 127 60.4 125 5.45 105 45.6 127 99.9 127 4.40 113 33.4 101 54.9 111 3.56 70
LocallyOriented [52]86.5 12.2 82 28.1 94 3.27 101 20.5 122 25.9 123 5.07 96 14.3 98 30.0 103 3.37 70 24.2 110 41.7 115 7.66 58 44.7 66 57.1 65 10.1 30 28.8 79 47.4 39 5.48 113 42.4 115 80.6 77 4.12 84 32.4 88 51.2 78 3.56 70
IAOF2 [51]87.2 12.7 107 28.7 97 3.32 103 20.4 120 25.9 123 4.76 86 12.7 84 31.7 109 3.11 64 22.4 98 35.8 77 8.06 95 45.9 96 59.6 105 10.8 83 29.9 102 51.5 98 5.10 63 39.0 88 79.7 71 4.08 39 31.2 57 49.0 58 3.56 70
EPMNet [133]88.3 19.3 131 47.9 132 3.11 74 16.8 61 23.2 67 4.55 79 14.2 96 29.8 101 3.37 70 33.0 129 78.1 134 8.29 101 45.9 96 58.1 78 10.6 75 30.0 104 51.9 104 4.97 20 39.2 89 81.0 79 4.08 39 33.8 107 53.1 100 3.51 53
Aniso-Texture [82]88.8 11.5 25 24.1 38 2.83 18 20.2 115 26.0 126 4.97 94 20.0 118 24.4 56 3.37 70 26.9 116 50.7 128 9.11 118 46.1 101 60.5 119 11.4 127 32.7 126 62.2 130 5.94 128 37.3 65 80.2 73 4.04 9 34.1 110 55.0 112 3.42 10
ACK-Prior [27]90.1 12.5 103 29.7 105 2.83 18 16.1 46 22.7 53 4.00 54 25.6 121 27.7 79 5.72 121 22.4 98 36.0 79 10.7 123 45.7 87 59.3 98 11.4 127 31.8 123 50.6 82 5.35 100 38.8 86 79.9 72 4.16 92 33.5 102 51.7 86 3.70 108
Rannacher [23]90.9 11.7 39 28.7 97 3.16 100 20.4 120 26.3 130 5.07 96 19.0 117 26.0 66 4.80 112 19.8 60 38.1 94 7.79 78 44.5 63 57.4 67 10.1 30 29.0 84 50.3 75 5.20 71 42.6 118 97.0 123 4.40 113 33.7 105 55.9 115 3.70 108
IIOF-NLDP [131]91.7 12.9 110 29.0 100 2.71 2 18.6 85 24.8 106 4.08 61 13.4 91 26.7 74 3.00 2 21.9 93 39.8 105 8.16 98 45.8 91 59.4 100 10.4 63 31.6 122 59.9 123 6.06 131 54.7 135 99.9 127 6.03 134 35.7 118 57.2 119 3.42 10
Learning Flow [11]92.1 12.1 75 24.6 54 3.27 101 19.7 104 25.2 113 5.00 95 39.7 133 47.7 134 7.68 129 24.6 112 35.0 69 8.19 100 45.2 78 58.6 90 10.5 74 28.4 67 48.0 48 5.45 105 38.4 79 77.8 64 4.40 113 32.6 95 48.4 49 3.92 129
2bit-BM-tele [98]93.1 11.7 39 27.0 84 3.79 124 20.2 115 26.3 130 5.07 96 12.0 62 23.2 45 4.00 101 21.2 83 36.1 80 8.16 98 45.3 79 58.0 75 10.3 54 34.0 130 61.8 127 5.92 127 54.1 134 99.9 127 5.72 132 29.8 33 47.4 38 3.74 122
FOLKI [16]93.8 13.0 112 30.9 113 4.97 133 22.2 131 24.9 110 9.00 133 17.3 109 33.0 115 7.00 124 33.4 130 38.7 101 17.0 131 44.3 57 55.8 50 10.4 63 27.6 46 49.7 64 5.48 113 36.2 53 74.2 40 4.80 125 30.4 46 44.9 22 4.08 131
SimpleFlow [49]94.7 12.0 62 24.0 36 2.94 49 18.5 82 24.4 95 4.24 67 32.7 128 39.0 125 5.69 119 18.0 26 36.2 84 7.55 37 46.9 121 60.8 120 11.1 97 31.4 121 58.1 122 5.35 100 49.4 131 99.9 127 5.16 130 40.0 126 63.0 130 3.46 38
SILK [79]94.8 13.3 116 30.7 112 3.83 127 22.0 130 25.3 114 7.16 128 34.7 132 40.0 127 7.77 131 26.6 115 36.6 86 8.60 111 45.1 75 57.9 73 10.0 18 28.4 67 50.9 92 6.03 130 34.8 20 71.8 22 4.51 121 31.4 61 48.0 46 3.74 122
StereoFlow [44]96.8 22.8 135 48.3 133 3.74 123 20.5 122 26.8 133 5.07 96 11.3 28 29.3 96 3.37 70 20.1 68 37.0 88 7.62 51 59.3 133 75.2 133 10.8 83 39.3 135 71.4 134 5.45 105 35.8 41 73.9 36 4.08 39 35.7 118 55.1 114 3.70 108
StereoOF-V1MT [119]98.2 13.7 118 32.7 117 3.00 61 18.7 86 23.6 75 4.80 89 21.8 120 28.0 83 5.07 115 31.6 125 40.6 111 9.57 120 46.5 109 58.9 95 11.5 133 29.2 91 50.2 70 6.45 134 42.4 115 94.7 119 4.80 125 31.4 61 48.3 48 3.46 38
Shiralkar [42]98.8 13.2 115 31.6 115 3.00 61 19.7 104 24.5 98 4.65 83 17.0 107 30.7 105 4.08 107 32.1 127 53.1 130 8.04 91 46.3 106 59.7 107 10.3 54 28.4 67 50.2 70 5.45 105 45.5 126 95.2 121 4.24 109 39.2 125 62.6 128 3.42 10
OFRF [134]99.3 14.4 123 38.4 126 3.70 121 19.9 109 25.3 114 5.48 107 13.0 88 33.0 115 3.11 64 20.7 78 38.4 97 7.79 78 47.8 127 61.4 125 10.9 89 31.9 124 56.8 120 5.29 88 41.5 111 90.5 111 4.08 39 34.4 112 54.7 108 3.42 10
Dynamic MRF [7]100.6 12.1 75 26.8 83 2.94 49 18.0 79 23.9 81 4.16 65 18.3 114 30.7 105 5.00 113 28.9 121 39.8 105 10.5 122 45.9 96 58.6 90 11.2 104 30.9 116 56.0 119 5.80 126 43.0 119 90.3 109 4.65 123 33.7 105 51.8 88 3.70 108
Adaptive flow [45]101.7 13.4 117 25.8 72 4.51 130 21.8 129 25.4 118 7.26 129 13.7 92 27.5 78 4.69 110 24.1 109 35.2 71 8.76 115 47.3 125 61.5 126 10.2 49 33.8 129 61.9 128 5.45 105 35.9 45 73.2 33 4.20 99 34.7 115 54.7 108 3.70 108
UnFlow [129]103.2 14.9 125 40.2 128 3.11 74 18.5 82 23.4 70 5.48 107 15.3 100 31.3 108 4.36 108 22.8 103 38.0 93 8.45 107 48.3 129 63.0 129 10.9 89 32.4 125 62.0 129 5.72 121 35.4 30 71.2 16 4.32 111 45.5 133 66.0 132 3.87 127
SPSA-learn [13]106.0 12.3 91 33.7 120 3.37 107 19.2 94 23.6 75 5.45 106 30.0 124 39.7 126 7.00 124 26.9 116 41.3 113 8.41 106 46.7 115 60.1 111 10.2 49 29.4 97 50.6 82 5.20 71 53.7 133 99.9 127 8.43 135 51.4 134 72.0 134 3.51 53
SegOF [10]108.1 12.3 91 33.1 118 3.11 74 17.9 76 23.8 79 4.51 77 29.0 123 34.3 119 6.16 122 32.8 128 78.9 135 8.33 102 48.1 128 63.6 130 11.2 104 28.5 74 54.3 115 5.72 121 44.6 124 99.9 127 4.97 128 37.9 121 61.4 126 3.51 53
HCIC-L [99]108.2 21.0 134 41.8 129 5.07 134 20.2 115 26.1 129 5.80 111 16.3 104 42.3 129 4.00 101 31.7 126 51.0 129 8.50 108 44.7 66 55.5 47 10.4 63 35.2 132 69.8 133 5.07 47 39.9 100 91.2 114 4.16 92 40.4 128 58.0 120 3.65 105
FFV1MT [106]109.4 17.0 128 37.6 125 3.37 107 19.3 96 22.9 58 6.40 123 28.2 122 46.7 133 6.95 123 29.3 122 38.4 97 11.4 127 46.3 106 58.2 83 10.4 63 29.0 84 50.4 77 5.72 121 46.7 128 88.5 100 4.93 127 39.0 124 56.9 118 4.43 133
PGAM+LK [55]109.8 15.5 127 39.4 127 4.55 131 19.8 107 24.0 84 7.68 130 33.1 130 43.4 132 8.00 132 34.5 132 45.7 124 11.2 126 46.6 113 57.7 69 10.6 75 29.3 92 50.8 91 5.74 125 37.4 66 77.2 58 4.43 117 34.4 112 53.3 103 4.24 132
Heeger++ [104]110.4 19.8 132 44.7 130 3.11 74 18.9 90 22.8 55 6.45 124 33.0 129 35.2 120 7.16 128 29.3 122 38.4 97 11.4 127 51.5 131 65.2 131 11.3 120 28.4 67 46.9 32 6.78 135 47.9 130 84.5 94 4.69 124 40.1 127 58.8 123 3.70 108
SLK [47]112.1 13.9 121 29.9 107 3.79 124 20.0 111 22.8 55 6.22 119 32.0 127 33.7 117 7.72 130 33.4 130 46.4 125 16.1 130 48.5 130 61.7 127 10.3 54 28.4 67 47.9 47 5.72 121 43.2 120 97.9 124 4.97 128 38.7 123 59.8 124 4.04 130
Pyramid LK [2]120.0 14.4 123 37.3 124 4.93 132 23.7 133 25.3 114 9.98 135 42.2 134 35.7 121 12.3 134 56.2 135 64.2 132 35.8 135 65.6 134 83.9 134 10.6 75 28.1 58 46.1 26 5.48 113 45.2 125 99.9 127 5.89 133 53.6 135 75.1 135 5.42 134
GroupFlow [9]121.0 19.9 133 49.6 134 3.42 114 19.1 92 24.1 87 5.48 107 31.4 126 40.0 127 8.19 133 36.2 133 61.9 131 12.1 129 55.6 132 71.3 132 11.4 127 36.3 133 67.0 132 5.60 119 46.7 128 98.5 125 4.20 99 43.6 131 62.8 129 3.56 70
Periodicity [78]133.5 17.6 129 55.7 135 5.45 135 26.8 135 27.0 134 9.75 134 49.4 135 51.5 135 17.7 135 51.3 134 70.3 133 27.9 134 66.6 135 86.3 135 11.7 135 38.7 134 82.5 135 6.38 133 51.8 132 99.9 127 5.48 131 44.3 132 65.5 131 5.80 135
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.