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
CtxSyn [137]3.1 9.38 1 14.7 1 2.58 2 11.5 1 16.1 1 3.65 22 9.04 2 12.7 1 3.00 2 12.6 1 19.2 1 7.33 3 38.7 3 47.5 2 9.56 5 22.9 2 38.0 1 4.76 3 31.6 4 64.3 3 3.92 5 24.8 2 36.2 2 3.37 4
PMMST [114]12.8 11.2 13 21.1 8 2.71 3 13.8 9 19.7 8 3.65 22 10.3 3 19.2 10 2.71 1 16.8 5 30.8 25 7.53 34 41.1 8 51.1 10 10.0 20 24.6 5 43.0 9 4.93 17 34.2 13 70.9 15 4.04 11 28.8 17 45.4 28 3.42 12
MDP-Flow2 [68]13.2 11.0 6 20.7 7 2.71 3 13.9 11 19.9 10 3.46 2 10.3 3 20.3 17 3.00 2 16.7 4 30.0 17 7.35 8 41.0 7 50.7 7 10.1 32 27.1 40 44.9 23 4.97 24 33.6 6 70.1 10 3.92 5 29.2 21 47.0 39 3.42 12
SuperSlomo [132]19.9 9.66 2 16.1 2 3.37 120 15.4 37 20.4 16 6.06 131 8.43 1 14.4 2 3.00 2 17.1 7 23.8 2 8.58 121 38.5 2 47.8 3 8.76 3 23.1 3 40.8 4 4.80 5 30.2 2 62.5 2 3.87 2 25.2 3 37.4 3 3.32 2
NNF-Local [87]23.2 11.4 19 21.6 12 2.71 3 12.8 2 18.4 3 3.56 4 10.4 5 20.0 15 3.00 2 19.8 63 37.3 97 7.35 8 41.5 14 51.4 12 10.0 20 28.2 69 47.3 42 5.07 53 34.5 16 71.9 28 4.04 11 29.1 20 46.1 34 3.37 4
SepConv-v1 [127]24.3 9.68 3 19.1 3 2.52 1 15.4 37 20.1 13 5.26 114 11.0 12 16.7 4 3.87 113 20.4 77 26.8 3 9.59 135 41.9 15 52.5 19 9.00 4 24.7 6 42.4 6 4.69 2 30.7 3 67.4 4 3.92 5 24.7 1 35.8 1 3.32 2
NN-field [71]26.3 11.5 27 22.9 26 2.71 3 13.0 4 18.6 4 3.42 1 12.3 85 19.7 11 3.00 2 21.1 88 39.8 113 7.44 20 41.4 12 51.4 12 10.0 20 27.5 48 46.4 33 4.97 24 33.8 9 71.0 17 4.04 11 29.3 23 46.2 35 3.37 4
FGIK [136]29.6 10.7 4 21.1 8 3.00 69 15.6 44 20.3 14 5.35 116 14.1 104 16.0 3 3.56 98 20.7 82 29.1 10 9.76 136 33.3 1 41.7 1 8.43 2 21.2 1 40.2 3 4.55 1 25.6 1 56.0 1 3.70 1 25.8 4 39.6 5 3.16 1
NNF-EAC [103]30.5 11.5 27 21.7 13 3.11 85 14.5 24 21.0 28 3.70 25 12.3 85 22.6 39 3.00 2 17.7 18 32.4 45 7.55 41 43.2 42 55.1 46 10.1 32 25.1 9 43.8 12 4.90 11 34.0 11 70.5 12 4.08 42 29.4 25 47.5 45 3.42 12
DeepFlow2 [108]33.2 11.4 19 23.5 30 3.00 69 16.7 67 23.0 71 4.04 62 11.0 12 20.3 17 3.00 2 19.0 51 29.8 15 7.53 34 42.7 28 54.0 28 10.3 58 25.0 7 43.0 9 4.93 17 35.2 32 73.8 39 4.04 11 28.9 18 44.9 25 3.56 77
DeepFlow [86]33.4 11.3 17 24.2 44 3.00 69 16.6 66 23.0 71 4.32 78 11.0 12 20.3 17 3.00 2 19.3 54 28.1 8 7.59 49 42.7 28 54.5 33 10.2 52 25.2 11 44.1 13 5.00 46 32.9 5 68.2 5 4.04 11 28.4 13 44.6 20 3.56 77
PH-Flow [101]34.5 11.9 60 25.7 74 2.83 23 13.3 6 19.7 8 3.56 4 10.7 7 22.7 40 3.00 2 16.5 3 30.2 18 7.33 3 42.3 21 52.1 16 10.1 32 28.7 86 50.9 101 5.20 80 35.6 39 77.0 66 4.04 11 29.6 31 47.0 39 3.51 57
SuperFlow [81]35.0 11.0 6 22.1 20 3.11 85 17.1 73 22.7 61 4.69 93 11.7 50 18.7 5 3.37 77 18.7 43 27.4 5 7.70 72 41.3 10 51.2 11 9.98 16 26.3 26 46.9 36 4.80 5 34.7 20 76.0 54 4.08 42 28.1 11 41.5 8 3.42 12
CombBMOF [113]35.1 12.0 67 24.3 45 2.83 23 14.3 18 20.6 20 3.56 4 11.3 30 25.7 67 3.00 2 20.3 76 34.9 72 7.55 41 43.2 42 54.0 28 10.1 32 26.4 27 47.7 49 4.90 11 36.2 62 71.4 21 4.08 42 29.5 28 45.7 31 3.37 4
DF-Auto [115]36.1 10.9 5 19.2 4 3.11 85 17.2 78 23.4 82 4.43 84 10.4 5 20.6 25 3.00 2 18.1 29 29.7 12 7.55 41 41.4 12 52.1 16 10.0 20 26.2 21 47.2 39 4.97 24 35.2 32 79.3 79 4.08 42 29.6 31 44.7 21 3.56 77
LME [70]38.5 11.4 19 22.0 18 2.71 3 15.1 32 21.8 40 3.87 53 11.3 30 36.0 133 3.00 2 17.4 10 32.0 42 7.48 24 44.5 68 57.0 66 11.4 139 27.6 50 47.2 39 4.97 24 33.6 6 69.7 7 4.04 11 30.0 38 48.6 57 3.42 12
CBF [12]38.5 11.0 6 19.8 5 3.00 69 17.1 73 22.9 67 4.24 75 12.0 65 19.0 7 3.00 2 17.8 23 28.0 7 7.85 88 40.6 6 49.9 5 9.97 12 26.2 21 44.6 18 4.97 24 36.3 64 76.3 59 4.12 93 27.9 7 41.2 7 3.70 121
Aniso. Huber-L1 [22]39.0 11.4 19 21.7 13 3.11 85 19.7 117 24.7 116 4.55 88 12.0 65 19.7 11 3.11 70 18.4 35 29.8 15 7.55 41 42.5 24 54.4 32 9.98 16 25.2 11 42.2 5 4.83 7 35.6 39 71.5 22 4.04 11 27.9 7 42.0 10 3.56 77
IROF++ [58]39.7 11.9 60 24.1 41 2.83 23 14.7 27 21.3 30 3.56 4 12.1 82 29.0 97 3.00 2 16.3 2 27.9 6 7.35 8 43.9 54 56.0 55 11.1 102 26.4 27 47.0 38 4.93 17 34.5 16 72.3 29 4.08 42 30.3 48 49.3 65 3.56 77
WLIF-Flow [93]39.7 11.5 27 22.1 20 2.83 23 15.2 33 21.6 36 3.79 43 11.3 30 26.4 76 3.00 2 17.4 10 30.3 20 7.59 49 42.5 24 53.5 24 10.4 67 29.0 92 51.1 104 5.29 98 34.8 23 69.7 7 4.04 11 30.0 38 48.4 53 3.46 42
FMOF [94]41.0 12.2 89 24.5 54 2.94 55 14.0 12 20.0 11 3.56 4 12.3 85 27.7 84 3.00 2 19.8 63 35.4 77 7.70 72 42.4 22 52.1 16 10.1 32 28.1 65 49.1 66 4.93 17 34.6 19 72.7 33 3.87 2 30.2 44 47.6 48 3.42 12
CLG-TV [48]41.3 11.1 11 21.8 16 3.11 85 18.8 100 24.0 96 4.43 84 11.3 30 20.0 15 3.70 99 18.6 41 28.9 9 7.72 77 42.8 31 55.0 45 10.0 20 25.0 7 42.9 8 4.93 17 36.0 54 71.6 23 4.04 11 29.0 19 44.0 16 3.56 77
IROF-TV [53]42.5 11.7 41 24.7 61 3.00 69 15.5 41 22.0 48 3.70 25 11.0 12 23.7 50 3.00 2 17.3 8 31.3 29 7.57 48 43.8 52 56.0 55 11.2 110 27.6 50 48.4 56 4.97 24 35.9 52 74.5 48 4.08 42 28.0 9 42.6 12 3.56 77
Brox et al. [5]43.0 11.4 19 24.9 66 2.94 55 15.9 50 22.2 51 4.04 62 11.3 30 21.0 26 3.37 77 18.4 35 27.0 4 7.59 49 42.2 19 53.3 22 10.0 20 28.2 69 51.5 107 5.00 46 36.8 68 88.0 109 4.04 11 28.4 13 42.3 11 3.42 12
ALD-Flow [66]44.2 12.0 67 28.4 104 3.11 85 16.3 58 22.8 63 3.83 48 11.0 12 21.7 32 3.00 2 17.9 26 33.6 58 7.39 15 43.4 47 54.6 38 10.8 88 25.8 16 44.8 22 5.00 46 34.1 12 70.4 11 4.04 11 31.9 81 50.3 76 3.46 42
nLayers [57]44.3 11.8 49 22.9 26 2.83 23 14.1 14 20.4 16 3.56 4 11.0 12 19.7 11 3.00 2 18.3 33 34.2 67 7.39 15 46.7 123 60.1 119 11.0 96 27.9 57 50.1 76 5.20 80 35.5 37 72.6 32 4.08 42 30.8 53 49.3 65 3.42 12
MDP-Flow [26]46.7 11.2 13 21.2 10 2.71 3 14.2 16 20.5 19 3.70 25 10.7 7 19.0 7 3.00 2 19.7 61 32.4 45 7.70 72 44.2 58 57.0 66 11.2 110 30.0 116 51.4 106 5.51 129 36.1 59 72.9 36 4.08 42 30.8 53 48.4 53 3.42 12
Layers++ [37]46.8 11.4 19 21.7 13 2.94 55 12.8 2 18.2 2 3.46 2 11.0 12 26.7 79 3.00 2 17.7 18 32.9 50 7.53 34 46.6 121 60.9 131 10.6 80 30.9 130 60.2 139 5.00 46 34.9 29 72.7 33 3.87 2 29.9 37 47.5 45 3.46 42
JOF [141]46.8 12.0 67 23.6 32 3.11 85 14.0 12 20.0 11 3.70 25 11.0 12 23.8 53 3.00 2 18.1 29 31.5 34 7.35 8 44.7 71 57.6 74 11.3 129 29.5 108 50.1 76 5.07 53 34.5 16 71.6 23 4.04 11 31.2 60 50.3 76 3.51 57
LDOF [28]47.5 11.4 19 22.5 23 3.56 131 16.1 52 21.4 35 6.35 137 12.0 65 20.3 17 3.70 99 19.0 51 29.7 12 7.94 93 41.2 9 50.9 8 10.1 32 26.8 33 50.2 79 4.90 11 34.8 23 80.2 83 4.08 42 29.4 25 44.5 18 3.46 42
p-harmonic [29]47.5 11.4 19 23.5 30 2.83 23 19.1 105 24.3 105 4.80 99 11.3 30 22.0 34 3.70 99 20.9 86 31.7 36 7.62 55 42.6 27 54.2 30 10.1 32 25.7 15 43.5 11 5.07 53 36.1 59 71.8 25 4.08 42 29.6 31 46.5 36 3.51 57
Second-order prior [8]48.2 11.3 17 22.0 18 3.11 85 19.0 104 24.2 103 4.32 78 13.3 98 27.7 84 3.70 99 18.8 46 31.6 35 7.51 28 42.9 33 54.7 40 10.0 20 26.2 21 45.0 24 4.97 24 35.6 39 71.2 18 4.04 11 29.5 28 45.4 28 3.56 77
SIOF [67]48.8 11.7 41 23.1 28 3.11 85 19.4 112 24.8 119 4.76 95 11.3 30 25.7 67 3.11 70 18.4 35 31.4 31 8.04 100 40.3 5 50.3 6 9.95 10 25.8 16 45.3 26 4.97 24 33.9 10 71.2 18 4.08 42 30.0 38 47.4 42 3.70 121
COFM [59]49.0 11.8 49 24.3 45 2.94 55 14.5 24 20.9 25 3.65 22 11.0 12 26.4 76 3.00 2 17.4 10 32.3 43 7.35 8 44.2 58 55.1 46 10.1 32 30.0 116 54.4 127 5.20 80 35.8 47 79.3 79 4.08 42 31.2 60 48.8 60 3.51 57
Local-TV-L1 [65]49.8 11.2 13 21.5 11 3.56 131 19.6 115 24.4 108 5.57 123 11.0 12 19.1 9 3.00 2 18.3 33 30.4 23 7.87 91 42.8 31 54.5 33 10.2 52 26.2 21 44.7 19 5.45 117 34.2 13 76.1 57 4.08 42 28.0 9 42.8 14 3.65 116
ProbFlowFields [128]50.5 11.6 33 25.4 70 2.83 23 14.4 20 21.1 29 3.56 4 10.7 7 23.7 50 3.00 2 18.4 35 33.4 55 7.59 49 46.2 111 59.2 105 11.2 110 28.5 82 50.7 95 5.32 104 34.7 20 76.9 64 4.08 42 29.4 25 46.5 36 3.46 42
FlowFields [110]50.7 11.8 49 25.6 73 2.83 23 14.4 20 20.9 25 3.56 4 11.3 30 24.3 58 3.00 2 20.0 69 38.1 102 7.51 28 43.6 49 54.5 33 11.0 96 28.2 69 50.7 95 5.16 75 34.8 23 75.1 52 4.04 11 32.0 87 52.0 101 3.46 42
TV-L1-MCT [64]53.8 12.4 105 24.7 61 2.83 23 16.4 59 23.1 74 3.83 48 11.9 64 32.7 123 3.00 2 17.6 15 31.7 36 7.53 34 47.0 132 61.2 132 11.0 96 25.5 13 44.7 19 4.97 24 36.0 54 80.7 88 4.04 11 28.4 13 44.8 23 3.46 42
Sparse-NonSparse [56]55.0 12.0 67 24.3 45 2.83 23 15.0 30 21.3 30 3.56 4 11.7 50 29.0 97 3.00 2 17.6 15 29.7 12 7.39 15 45.7 95 59.3 106 11.0 96 28.8 87 48.7 62 5.07 53 38.6 94 90.1 120 4.04 11 32.4 96 51.8 97 3.42 12
HAST [109]55.4 11.7 41 23.6 32 2.94 55 13.8 9 19.6 7 3.56 4 12.0 65 31.7 119 3.00 2 17.8 23 31.7 36 7.14 1 45.3 85 57.0 66 9.97 12 33.7 143 62.8 146 5.10 70 38.4 89 88.4 111 4.04 11 33.0 106 51.0 84 3.42 12
BlockOverlap [61]55.4 11.1 11 20.1 6 3.56 131 19.3 109 23.7 89 6.16 133 11.3 30 20.4 23 3.70 99 18.4 35 29.6 11 8.72 125 43.1 39 54.5 33 10.2 52 27.4 45 48.6 59 5.35 111 34.8 23 72.8 35 4.08 42 27.2 6 40.9 6 3.56 77
OAR-Flow [125]56.0 12.0 67 24.9 66 3.00 69 16.4 59 22.4 54 4.08 67 11.0 12 20.5 24 3.00 2 17.4 10 33.6 58 7.33 3 46.2 111 60.0 118 11.3 129 27.0 36 47.6 46 5.23 88 37.6 78 74.0 42 4.08 42 31.0 58 49.2 63 3.46 42
CPM-Flow [116]56.3 11.8 49 27.3 91 2.83 23 14.4 20 20.4 16 3.70 25 11.7 50 24.0 54 3.00 2 21.4 96 40.1 116 7.77 81 45.5 91 58.1 85 11.2 110 26.6 32 48.0 52 5.07 53 36.0 54 72.3 29 4.04 11 30.9 56 50.4 78 3.56 77
Modified CLG [34]57.0 11.0 6 21.9 17 3.11 85 19.6 115 23.9 93 5.94 129 12.4 89 26.3 74 3.87 113 19.8 63 30.8 25 8.12 105 42.1 17 52.9 20 10.1 32 27.0 36 48.1 54 5.23 88 34.7 20 70.8 14 4.08 42 29.5 28 45.3 27 3.56 77
FlowFields+ [130]57.4 11.8 49 26.1 82 2.71 3 14.1 14 20.6 20 3.70 25 11.2 29 24.8 63 3.00 2 20.1 71 40.2 118 7.53 34 45.5 91 58.0 82 11.2 110 28.6 85 50.6 91 5.20 80 35.6 39 77.5 71 4.04 11 32.2 91 52.5 105 3.42 12
AGIF+OF [85]57.7 12.2 89 24.3 45 2.71 3 15.2 33 21.8 40 3.70 25 11.7 50 27.7 84 3.00 2 18.0 27 33.0 52 7.55 41 45.8 99 58.8 102 11.2 110 30.0 116 53.4 121 5.07 53 35.4 34 74.8 50 3.92 5 32.2 91 52.6 108 3.37 4
2DHMM-SAS [92]57.8 12.2 89 24.5 54 2.83 23 17.9 88 24.1 100 3.87 53 12.0 65 28.7 94 3.00 2 17.3 8 31.4 31 7.51 28 45.1 81 58.2 91 11.2 110 27.9 57 49.0 64 4.83 7 37.0 70 76.1 57 4.08 42 31.9 81 50.5 79 3.42 12
ComponentFusion [96]58.2 12.0 67 29.6 112 2.71 3 14.5 24 21.3 30 3.56 4 11.0 12 22.0 34 3.00 2 18.8 46 36.2 90 7.33 3 45.5 91 58.2 91 10.7 85 27.2 41 46.3 31 4.97 24 40.5 116 93.3 130 4.12 93 34.4 123 58.3 134 3.42 12
F-TV-L1 [15]58.6 12.0 67 26.5 86 3.56 131 19.2 107 24.7 116 4.83 102 11.7 50 21.5 30 4.00 115 19.3 54 32.7 48 7.68 65 43.1 39 55.3 49 9.83 6 25.1 9 42.8 7 5.07 53 34.8 23 74.0 42 4.16 102 28.5 16 42.7 13 3.56 77
AdaConv-v1 [126]59.0 15.0 140 28.2 102 3.70 135 17.6 85 20.7 23 7.68 145 17.4 122 22.0 34 7.00 138 27.5 131 33.7 63 17.0 146 39.9 4 49.8 4 8.19 1 23.8 4 39.5 2 4.76 3 34.2 13 68.5 6 4.12 93 26.9 5 39.5 4 3.42 12
TC/T-Flow [76]59.7 12.4 105 26.4 84 2.83 23 16.5 64 23.1 74 3.83 48 11.0 12 22.4 38 3.00 2 18.9 48 34.5 68 7.33 3 45.5 91 58.1 85 11.4 139 27.3 44 47.6 46 4.93 17 41.1 118 80.4 86 4.20 109 30.9 56 49.7 69 3.37 4
DPOF [18]60.3 12.3 98 29.4 111 3.11 85 13.3 6 19.1 6 3.56 4 15.7 112 25.2 65 3.70 99 19.4 56 37.5 99 7.59 49 43.1 39 54.6 38 10.0 20 29.1 97 49.7 71 4.90 11 36.6 66 77.0 66 4.08 42 31.5 71 50.5 79 3.51 57
PGM-C [120]61.8 11.8 49 27.3 91 2.83 23 14.4 20 20.7 23 3.70 25 12.3 85 23.0 44 3.00 2 20.6 81 42.3 124 7.62 55 45.8 99 59.5 112 11.2 110 27.2 41 47.4 43 4.97 24 37.1 72 79.2 76 4.04 11 32.4 96 55.0 121 3.51 57
PMF [73]62.2 12.2 89 25.9 77 2.71 3 15.4 37 21.8 40 3.56 4 12.7 91 35.7 131 3.00 2 20.2 74 35.9 83 7.51 28 44.4 66 54.9 44 10.1 32 28.4 75 50.5 89 5.32 104 37.9 83 81.1 91 4.04 11 34.2 120 54.1 115 3.37 4
Ramp [62]62.4 12.0 67 24.6 57 2.94 55 14.8 28 21.3 30 3.70 25 11.7 50 29.4 103 3.00 2 16.9 6 30.3 20 7.39 15 45.4 88 58.5 94 11.0 96 30.2 123 50.9 101 5.23 88 39.8 108 89.6 117 4.04 11 32.4 96 52.5 105 3.42 12
TF+OM [100]62.5 11.6 33 30.1 117 3.11 85 15.0 30 21.6 36 4.04 62 11.7 50 24.0 54 3.00 2 21.3 92 39.0 112 7.68 65 44.3 61 56.7 64 10.3 58 28.8 87 50.4 86 5.07 53 37.7 79 83.5 102 4.08 42 29.2 21 46.0 32 3.56 77
Ad-TV-NDC [36]62.7 12.2 89 22.5 23 4.32 144 20.6 137 24.8 119 5.80 124 11.7 50 21.6 31 3.37 77 21.6 97 31.8 39 8.04 100 42.5 24 53.4 23 9.97 12 26.4 27 47.6 46 5.16 75 36.8 68 70.9 15 4.08 42 28.3 12 41.8 9 3.70 121
AggregFlow [97]63.4 13.7 129 37.1 135 3.11 85 16.2 56 22.6 57 4.04 62 11.0 12 23.3 49 3.00 2 21.8 99 40.7 120 7.66 63 43.2 42 53.5 24 10.3 58 27.0 36 46.0 29 5.00 46 38.0 84 82.4 99 4.08 42 31.9 81 51.9 100 3.42 12
ComplOF-FED-GPU [35]63.5 12.0 67 27.9 99 2.94 55 15.7 47 22.2 51 3.79 43 16.0 113 21.4 28 3.70 99 18.4 35 33.6 58 7.48 24 44.9 78 57.7 75 10.7 85 27.4 45 45.9 28 5.00 46 36.6 66 78.7 75 4.08 42 32.6 104 52.3 103 3.51 57
ProFlow_ROB [147]63.5 11.8 49 27.5 95 2.83 23 15.8 49 22.6 57 3.79 43 11.4 46 20.3 17 3.00 2 18.9 48 37.0 95 7.35 8 47.3 134 61.8 139 11.2 110 25.5 13 44.2 14 4.83 7 40.0 113 81.4 93 4.08 42 34.3 122 56.5 128 3.56 77
OFLAF [77]64.0 11.7 41 24.5 54 2.71 3 13.6 8 20.3 14 3.56 4 11.0 12 23.0 44 3.00 2 17.6 15 31.3 29 7.39 15 47.3 134 61.7 137 11.2 110 29.6 109 51.9 114 5.32 104 41.8 125 95.6 135 4.16 102 33.6 112 52.1 102 3.42 12
S2F-IF [123]64.0 12.1 81 29.8 114 2.71 3 14.2 16 20.6 20 3.56 4 11.3 30 26.3 74 3.00 2 20.2 74 40.1 116 7.53 34 45.9 104 58.7 101 11.3 129 28.4 75 50.7 95 5.20 80 35.7 44 76.0 54 4.08 42 32.3 94 53.1 109 3.46 42
Classic+NL [31]64.7 12.1 81 24.3 45 3.00 69 15.3 36 21.8 40 3.70 25 11.7 50 29.4 103 3.00 2 17.4 10 31.4 31 7.53 34 45.7 95 59.4 108 10.8 88 29.0 92 49.8 74 5.10 70 39.6 105 90.4 122 4.08 42 32.2 91 51.8 97 3.46 42
DMF_ROB [140]65.2 11.9 60 25.4 70 3.00 69 17.1 73 22.8 63 4.08 67 19.4 130 29.7 106 3.70 99 20.4 77 34.5 68 7.68 65 45.3 85 58.1 85 11.1 102 26.4 27 45.6 27 4.97 24 35.7 44 73.8 39 4.08 42 31.2 60 50.2 71 3.42 12
Classic++ [32]65.3 11.6 33 23.7 34 3.11 85 17.8 87 24.4 108 4.08 67 11.7 50 20.3 17 3.37 77 20.1 71 33.8 64 7.62 55 44.7 71 57.8 78 10.0 20 28.0 61 49.7 71 5.35 111 37.4 76 81.4 93 4.08 42 30.7 52 49.5 67 3.56 77
LSM [39]66.5 12.3 98 24.7 61 2.83 23 15.4 37 21.9 45 3.56 4 12.0 65 30.3 112 3.00 2 18.7 43 33.2 54 7.44 20 46.1 109 59.4 108 11.1 102 29.3 101 51.9 114 5.07 53 39.2 99 91.0 125 4.04 11 32.3 94 52.5 105 3.42 12
FC-2Layers-FF [74]66.6 12.1 81 26.0 81 2.83 23 13.0 4 18.7 5 3.56 4 11.4 46 25.7 67 3.00 2 17.8 23 33.5 57 7.48 24 46.5 117 60.3 124 11.2 110 30.4 126 52.3 119 5.32 104 39.8 108 90.0 119 4.08 42 31.8 77 51.6 93 3.46 42
FlowNetS+ft+v [112]66.8 11.5 27 23.7 34 3.46 129 19.9 122 24.6 114 7.87 147 12.0 65 21.1 27 3.37 77 19.5 58 30.6 24 8.91 128 43.7 50 56.6 63 11.2 110 26.0 18 44.5 17 4.97 24 38.6 94 87.8 107 4.08 42 30.0 38 46.0 32 3.51 57
MLDP_OF [89]67.4 11.9 60 24.7 61 2.83 23 17.4 82 23.8 91 3.87 53 10.7 7 24.6 61 3.00 2 20.5 80 33.6 58 8.35 114 44.1 56 56.5 61 10.1 32 29.3 101 50.5 89 5.57 130 35.8 47 73.4 38 4.20 109 31.2 60 50.6 82 3.70 121
RNLOD-Flow [121]68.4 11.8 49 24.6 57 2.89 51 17.3 81 24.0 96 3.74 39 12.7 91 36.0 133 3.11 70 18.1 29 31.2 28 7.48 24 45.8 99 59.6 113 11.1 102 29.3 101 50.6 91 5.16 75 35.4 34 74.1 45 4.08 42 32.0 87 51.6 93 3.42 12
TCOF [69]68.7 12.0 67 24.7 61 2.83 23 20.3 132 26.4 147 5.07 107 11.1 28 29.0 97 3.00 2 17.7 18 32.4 45 7.68 65 43.2 42 55.5 50 9.97 12 28.8 87 46.3 31 5.07 53 41.2 121 94.9 133 4.08 42 31.8 77 51.3 88 3.70 121
CRTflow [80]69.0 11.7 41 24.4 52 3.32 116 19.5 114 24.9 123 4.51 86 12.0 65 22.7 40 4.00 115 18.1 29 30.3 20 7.68 65 45.0 79 58.1 85 11.3 129 26.0 18 45.1 25 4.97 24 37.7 79 87.9 108 4.08 42 30.8 53 50.2 71 3.56 77
Fusion [6]69.0 11.6 33 24.3 45 2.89 51 15.6 44 21.9 45 3.83 48 11.0 12 23.7 50 3.37 77 21.0 87 33.4 55 7.62 55 44.1 56 56.3 59 10.1 32 30.3 125 54.1 125 5.45 117 38.0 84 83.7 103 4.08 42 34.0 118 54.7 117 3.56 77
RFlow [90]69.1 11.6 33 24.3 45 3.00 69 19.3 109 24.8 119 4.36 80 11.6 49 29.7 106 3.37 77 20.0 69 36.1 86 7.72 77 43.0 34 55.2 48 10.1 32 27.9 57 51.8 113 4.97 24 37.1 72 82.8 101 4.08 42 31.6 73 49.5 67 3.56 77
Sparse Occlusion [54]69.8 11.7 41 25.9 77 3.00 69 18.1 92 24.6 114 3.83 48 11.3 30 22.7 40 3.11 70 18.7 43 34.1 66 7.70 72 45.0 79 58.0 82 11.1 102 28.5 82 44.2 14 5.26 92 39.3 102 83.7 103 3.92 5 31.9 81 51.7 95 3.56 77
S2D-Matching [84]70.3 12.3 98 25.7 74 2.94 55 17.2 78 23.7 89 4.00 59 11.7 50 28.7 94 3.00 2 17.7 18 31.9 41 7.55 41 46.8 127 60.1 119 10.4 67 30.0 116 51.5 107 5.29 98 37.0 70 77.7 72 4.04 11 31.8 77 50.9 83 3.46 42
TC-Flow [46]70.8 12.0 67 30.3 119 2.89 51 16.8 69 23.4 82 3.92 58 11.7 50 21.4 28 3.00 2 19.5 58 36.1 86 8.12 105 46.5 117 59.8 116 11.3 129 27.0 36 48.4 56 5.26 92 35.5 37 74.6 49 4.04 11 33.3 109 54.5 116 3.51 57
SVFilterOh [111]71.0 11.9 60 26.1 82 2.94 55 14.3 18 20.9 25 3.70 25 12.0 65 26.7 79 3.00 2 19.9 67 36.1 86 7.62 55 46.7 123 59.8 116 11.4 139 30.7 129 55.1 128 5.07 53 36.0 54 77.2 68 4.04 11 32.4 96 53.2 111 3.51 57
HBM-GC [105]72.1 11.8 49 23.8 37 3.11 85 16.8 69 24.2 103 3.87 53 10.7 7 18.7 5 3.00 2 18.9 48 32.9 50 7.68 65 46.8 127 60.8 128 11.5 146 34.5 146 61.7 141 5.48 125 37.7 79 81.9 98 4.04 11 30.5 51 47.8 49 3.51 57
Black & Anandan [4]72.5 12.3 98 24.0 39 3.46 129 21.2 140 25.4 131 5.35 116 18.1 125 25.0 64 5.35 130 24.4 121 34.9 72 7.77 81 42.2 19 53.5 24 10.1 32 26.9 35 46.5 34 4.97 24 39.5 103 77.2 68 4.08 42 29.3 23 42.8 14 3.56 77
3DFlow [135]72.6 12.4 105 27.1 90 2.83 23 15.5 41 22.1 49 3.87 53 13.7 100 24.0 54 3.00 2 19.2 53 38.7 109 7.68 65 44.0 55 56.0 55 10.1 32 31.2 133 53.8 124 5.60 132 39.5 103 79.2 76 4.16 102 31.1 59 48.0 50 3.56 77
Classic+CPF [83]72.9 12.2 89 24.6 57 2.83 23 15.6 44 22.1 49 3.74 39 12.0 65 30.7 114 3.00 2 17.7 18 30.9 27 7.44 20 47.2 133 61.3 133 11.2 110 31.2 133 55.9 129 5.26 92 39.9 110 88.8 114 4.04 11 33.6 112 54.0 114 3.42 12
FESL [72]73.5 12.2 89 25.1 69 2.83 23 14.9 29 21.6 36 3.70 25 12.1 82 33.7 127 3.00 2 19.7 61 35.0 74 7.72 77 46.2 111 60.2 123 11.3 129 29.3 101 50.4 86 5.32 104 39.6 105 88.6 113 3.92 5 32.4 96 51.2 86 3.42 12
CostFilter [40]74.0 13.1 122 33.1 126 2.71 3 15.2 33 21.3 30 3.56 4 14.0 102 42.7 143 3.00 2 22.0 101 44.4 131 7.26 2 45.8 99 57.2 71 10.4 67 27.2 41 48.1 54 5.45 117 39.9 110 89.4 116 4.08 42 35.6 129 56.1 126 3.37 4
Efficient-NL [60]74.9 11.8 49 23.8 37 2.83 23 16.7 67 23.3 79 3.70 25 18.4 127 29.0 97 3.70 99 19.4 56 34.0 65 7.51 28 45.1 81 58.5 94 11.1 102 30.0 116 51.5 107 5.07 53 40.1 114 88.9 115 4.08 42 33.0 106 52.4 104 3.42 12
EpicFlow [102]75.0 11.9 60 27.6 96 2.83 23 16.0 51 22.2 51 3.79 43 11.8 63 21.7 32 3.00 2 21.3 92 42.9 126 7.85 88 46.3 114 59.4 108 11.2 110 27.4 45 47.5 45 5.16 75 38.2 86 76.6 61 4.12 93 35.2 128 58.0 132 3.56 77
SRR-TVOF-NL [91]75.8 12.9 117 28.7 105 3.00 69 16.9 72 23.1 74 4.69 93 11.5 48 27.0 82 3.00 2 22.2 103 37.3 97 7.59 49 44.8 76 57.9 80 11.0 96 29.1 97 51.9 114 4.90 11 35.7 44 77.7 72 4.08 42 33.0 106 51.5 92 3.56 77
Filter Flow [19]76.1 11.8 49 23.1 28 3.37 120 20.0 124 25.1 125 5.23 113 12.2 84 26.0 71 3.70 99 22.1 102 32.7 48 7.94 93 42.1 17 51.9 14 10.4 67 28.1 65 49.0 64 5.07 53 38.4 89 81.6 95 4.16 102 30.0 38 45.5 30 3.74 137
Bartels [41]76.4 12.2 89 29.9 115 3.37 120 17.4 82 24.3 105 4.83 102 11.3 30 24.7 62 3.70 99 21.2 89 35.4 77 9.15 133 41.3 10 51.0 9 9.87 7 29.7 111 50.2 79 6.32 147 33.7 8 70.7 13 4.20 109 30.2 44 48.4 53 3.79 140
2D-CLG [1]76.5 11.6 33 24.1 41 3.11 85 19.4 112 23.3 79 6.24 135 18.7 128 24.3 58 4.69 124 22.4 105 31.8 39 8.66 124 43.3 46 56.1 58 10.4 67 26.0 18 44.2 14 5.35 111 40.2 115 91.5 128 4.20 109 29.6 31 44.5 18 3.51 57
Steered-L1 [118]77.2 11.2 13 22.6 25 2.89 51 16.2 56 22.6 57 4.55 88 21.7 132 32.4 122 5.00 127 23.4 115 38.3 104 10.7 138 44.7 71 57.4 72 9.88 8 28.0 61 48.5 58 5.32 104 37.1 72 79.2 76 4.12 93 31.4 67 51.1 85 3.51 57
Occlusion-TV-L1 [63]80.0 11.6 33 25.0 68 3.11 85 19.8 120 26.0 141 4.83 102 11.3 30 23.0 44 3.46 94 22.5 108 43.0 128 7.94 93 43.0 34 54.8 43 9.88 8 28.0 61 50.7 95 5.32 104 39.6 105 76.6 61 4.62 136 31.5 71 50.5 79 3.56 77
EPPM w/o HM [88]80.5 12.7 114 30.9 121 2.71 3 16.1 52 23.1 74 3.70 25 17.7 123 42.4 142 3.70 99 21.3 92 42.5 125 7.70 72 43.0 34 53.1 21 10.3 58 30.2 123 57.1 132 4.97 24 38.5 92 89.6 117 4.12 93 32.4 96 51.3 88 3.42 12
OFH [38]80.6 12.0 67 27.3 91 3.00 69 18.1 92 23.4 82 4.20 74 12.4 89 32.7 123 3.00 2 18.6 41 35.4 77 7.35 8 46.5 117 60.1 119 10.8 88 27.5 48 47.2 39 5.26 92 41.1 118 81.1 91 4.20 109 35.7 130 56.1 126 3.46 42
Adaptive [20]81.0 11.6 33 26.7 87 3.11 85 20.2 128 25.9 138 5.07 107 12.0 65 23.0 44 3.37 77 20.4 77 36.6 93 7.77 81 44.3 61 58.5 94 9.98 16 28.3 73 49.1 66 5.16 75 42.5 130 90.6 124 4.08 42 31.6 73 48.8 60 3.65 116
LFNet_ROB [151]82.0 13.4 126 37.5 137 2.71 3 16.1 52 21.8 40 4.08 67 12.0 65 36.3 136 3.37 77 20.7 82 36.0 84 7.94 93 45.4 88 57.8 78 11.6 149 30.6 127 57.4 133 5.20 80 34.9 29 71.8 25 4.08 42 31.3 65 49.9 70 3.70 121
CNN-flow-warp+ref [117]82.2 11.0 6 22.4 22 3.11 85 17.6 85 22.9 67 5.92 128 16.1 114 28.3 92 4.00 115 23.5 116 30.2 18 10.7 138 44.8 76 58.5 94 11.3 129 26.5 31 46.5 34 5.29 98 41.5 123 91.5 128 4.32 124 30.4 49 47.5 45 3.51 57
FF++_ROB [146]82.5 12.1 81 28.2 102 2.71 3 15.5 41 21.6 36 3.74 39 12.0 65 29.4 103 3.00 2 23.3 114 49.1 137 7.83 87 48.1 138 61.6 136 11.3 129 29.1 97 49.5 69 5.94 142 36.5 65 76.4 60 4.08 42 32.1 89 51.3 88 3.65 116
ContFlow_ROB [150]83.0 13.3 124 34.9 131 2.94 55 17.2 78 23.0 71 4.76 95 12.7 91 28.6 93 3.11 70 22.7 109 55.2 142 7.62 55 44.3 61 55.7 53 10.2 52 27.9 57 49.6 70 5.03 52 36.0 54 75.7 53 4.12 93 34.7 126 56.9 129 3.56 77
Horn & Schunck [3]83.8 12.1 81 23.7 34 3.32 116 21.4 142 25.6 134 5.89 127 17.0 119 28.2 91 5.35 130 27.3 130 37.9 100 8.04 100 42.4 22 54.3 31 10.3 58 26.2 21 44.7 19 5.07 53 40.9 117 81.7 96 4.20 109 30.2 44 44.3 17 3.70 121
IAOF [50]84.1 13.0 120 29.2 109 3.37 120 23.7 148 27.4 150 6.45 139 16.4 116 28.7 94 3.46 94 22.7 109 33.1 53 8.37 116 43.4 47 55.6 52 10.0 20 27.6 50 50.1 76 4.97 24 38.3 87 82.7 100 4.08 42 30.0 38 46.8 38 3.56 77
TriFlow [95]84.3 12.5 110 36.7 134 3.00 69 18.7 98 24.5 111 4.76 95 11.7 50 28.1 90 3.00 2 21.7 98 41.4 122 7.62 55 46.8 127 60.4 125 11.2 110 29.9 113 51.7 112 4.97 24 37.8 82 76.9 64 4.08 42 31.7 76 48.6 57 3.51 57
PWC-Net_ROB [148]84.9 13.5 128 35.8 132 2.71 3 16.4 59 23.3 79 3.74 39 12.0 65 30.3 112 3.00 2 21.3 92 45.6 132 7.51 28 48.8 145 63.0 141 11.2 110 29.7 111 53.0 120 5.29 98 35.8 47 74.9 51 4.08 42 34.2 120 56.0 125 3.51 57
TV-L1-improved [17]85.0 11.5 27 25.4 70 3.11 85 20.1 127 26.0 141 5.26 114 16.8 117 19.7 11 4.04 120 19.5 58 32.3 43 7.79 84 43.8 52 56.5 61 10.0 20 28.9 91 51.1 104 5.07 53 43.2 133 98.9 139 4.43 131 31.4 67 50.2 71 3.70 121
TVL1_ROB [139]85.4 11.9 60 26.4 84 3.70 135 21.7 143 25.8 135 6.06 131 12.0 65 25.7 67 3.46 94 23.1 112 36.3 92 8.35 114 43.0 34 54.5 33 10.1 32 28.2 69 50.0 75 5.10 70 41.3 122 91.4 127 4.24 120 29.7 35 44.8 23 3.56 77
HBpMotionGpu [43]85.6 12.3 98 32.0 124 3.79 139 20.6 137 25.4 131 6.00 130 11.3 30 26.1 73 3.00 2 23.2 113 44.0 130 7.85 88 44.3 61 56.9 65 10.8 88 29.0 92 53.5 123 5.26 92 34.9 29 69.8 9 4.04 11 31.8 77 51.4 91 3.70 121
Nguyen [33]86.5 12.0 67 25.9 77 3.37 120 21.2 140 24.5 111 6.27 136 12.7 91 28.0 88 3.70 99 23.8 117 34.7 70 8.58 121 43.0 34 54.7 40 10.1 32 27.7 55 50.7 95 4.97 24 43.4 135 93.7 131 4.43 131 30.2 44 47.4 42 3.56 77
BriefMatch [124]87.1 12.1 81 29.2 109 3.11 85 16.5 64 22.5 55 6.61 141 18.0 124 22.7 40 5.69 133 26.2 125 35.5 81 18.2 148 43.7 50 54.7 40 10.4 67 29.6 109 50.2 79 5.94 142 35.8 47 72.5 31 4.16 102 32.1 89 50.2 71 3.56 77
GraphCuts [14]87.3 13.9 134 30.2 118 3.32 116 16.4 59 22.5 55 4.36 80 33.4 146 24.1 57 5.35 130 22.3 104 34.7 70 7.87 91 44.5 68 57.0 66 9.98 16 28.3 73 50.3 84 4.90 11 38.5 92 88.2 110 4.20 109 33.9 117 53.6 113 3.56 77
FlowNet2 [122]88.7 19.1 144 47.5 145 3.11 85 17.1 73 24.1 100 4.55 88 14.2 106 29.8 109 3.37 77 23.8 117 42.9 126 8.33 112 45.9 104 58.1 85 10.6 80 27.6 50 49.4 68 4.93 17 39.2 99 81.0 89 4.08 42 31.6 73 49.2 63 3.56 77
TI-DOFE [24]89.3 12.7 114 27.6 96 3.87 143 22.2 146 25.3 127 6.66 142 14.1 104 25.3 66 4.36 122 27.7 132 38.7 109 9.06 131 42.7 28 53.6 27 10.1 32 26.8 33 48.8 63 4.97 24 38.3 87 76.0 54 4.24 120 31.9 81 44.7 21 3.87 142
AugFNG_ROB [144]90.6 13.7 129 36.6 133 3.00 69 17.5 84 22.9 67 4.80 99 14.3 108 36.0 133 3.37 77 27.8 133 64.0 145 7.96 99 48.6 144 63.0 141 11.4 139 28.0 61 51.6 111 4.83 7 36.1 59 76.6 61 4.08 42 31.9 81 47.2 41 3.42 12
ROF-ND [107]92.0 12.4 105 24.4 52 2.83 23 17.9 88 23.9 93 4.08 67 12.0 65 26.6 78 3.00 2 29.5 138 48.9 136 8.72 125 45.4 88 58.6 98 11.1 102 31.1 132 53.4 121 5.26 92 38.9 97 74.2 46 4.20 109 38.0 136 60.3 138 3.56 77
NL-TV-NCC [25]93.7 13.7 129 27.3 91 2.94 55 18.5 94 24.7 116 4.04 62 15.0 110 29.0 97 3.70 99 25.6 123 46.4 134 7.94 93 42.0 16 51.9 14 10.4 67 30.6 127 51.9 114 5.29 98 41.9 126 81.7 96 4.40 126 31.3 65 48.6 57 3.79 140
TriangleFlow [30]94.0 12.5 110 25.9 77 3.11 85 18.8 100 24.3 105 4.24 75 13.2 97 29.7 106 3.46 94 21.2 89 35.4 77 7.94 93 44.4 66 57.7 75 9.95 10 29.4 106 48.6 59 5.07 53 43.9 137 99.9 140 4.43 131 42.1 145 69.7 148 3.56 77
Correlation Flow [75]94.2 12.6 113 28.0 100 2.71 3 20.0 124 25.8 135 4.36 80 11.3 30 22.3 37 3.00 2 20.7 82 38.6 108 7.72 77 45.7 95 59.0 104 10.3 58 33.4 141 60.4 140 5.45 117 45.6 141 99.9 140 4.40 126 33.4 110 54.9 120 3.56 77
Complementary OF [21]94.2 12.4 105 34.5 129 2.83 23 16.4 59 23.5 86 3.79 43 30.7 139 32.2 121 7.05 141 19.9 67 43.9 129 7.44 20 46.9 130 60.4 125 10.7 85 28.1 65 47.7 49 5.23 88 41.1 118 80.3 85 4.12 93 42.0 144 62.0 141 3.56 77
LocallyOriented [52]95.0 12.2 89 28.1 101 3.27 114 20.5 135 25.9 138 5.07 107 14.3 108 30.0 111 3.37 77 24.2 120 41.7 123 7.66 63 44.7 71 57.1 70 10.1 32 28.8 87 47.4 43 5.48 125 42.4 128 80.6 87 4.12 93 32.4 96 51.2 86 3.56 77
IAOF2 [51]95.3 12.7 114 28.7 105 3.32 116 20.4 133 25.9 138 4.76 95 12.7 91 31.7 119 3.11 70 22.4 105 35.8 82 8.06 104 45.9 104 59.6 113 10.8 88 29.9 113 51.5 107 5.10 70 39.0 98 79.7 81 4.08 42 31.2 60 49.0 62 3.56 77
EPMNet [133]97.5 19.3 145 47.9 146 3.11 85 16.8 69 23.2 78 4.55 88 14.2 106 29.8 109 3.37 77 33.0 143 78.1 150 8.29 110 45.9 104 58.1 85 10.6 80 30.0 116 51.9 114 4.97 24 39.2 99 81.0 89 4.08 42 33.8 116 53.1 109 3.51 57
Aniso-Texture [82]98.1 11.5 27 24.1 41 2.83 23 20.2 128 26.0 141 4.97 105 20.0 131 24.4 60 3.37 77 26.9 128 50.7 138 9.11 132 46.1 109 60.5 127 11.4 139 32.7 140 62.2 145 5.94 142 37.3 75 80.2 83 4.04 11 34.1 119 55.0 121 3.42 12
ACK-Prior [27]99.4 12.5 110 29.7 113 2.83 23 16.1 52 22.7 61 4.00 59 25.6 135 27.7 84 5.72 135 22.4 105 36.0 84 10.7 138 45.7 95 59.3 106 11.4 139 31.8 137 50.6 91 5.35 111 38.8 96 79.9 82 4.16 102 33.5 111 51.7 95 3.70 121
Rannacher [23]100.0 11.7 41 28.7 105 3.16 113 20.4 133 26.3 145 5.07 107 19.0 129 26.0 71 4.80 126 19.8 63 38.1 102 7.79 84 44.5 68 57.4 72 10.1 32 29.0 92 50.3 84 5.20 80 42.6 131 97.0 136 4.40 126 33.7 114 55.9 124 3.70 121
IIOF-NLDP [131]100.7 12.9 117 29.0 108 2.71 3 18.6 97 24.8 119 4.08 67 13.4 99 26.7 79 3.00 2 21.9 100 39.8 113 8.16 107 45.8 99 59.4 108 10.4 67 31.6 136 59.9 137 6.06 146 54.7 150 99.9 140 6.03 149 35.7 130 57.2 131 3.42 12
LiteFlowNet [143]101.5 14.1 136 39.6 141 2.71 3 15.7 47 21.9 45 4.00 59 14.0 102 43.0 144 3.00 2 36.3 148 70.9 148 9.02 129 48.3 140 63.2 144 11.5 146 30.1 122 57.7 134 5.10 70 42.1 127 87.4 106 4.24 120 32.4 96 50.2 71 3.51 57
Learning Flow [11]101.7 12.1 81 24.6 57 3.27 114 19.7 117 25.2 126 5.00 106 39.7 148 47.7 149 7.68 143 24.6 122 35.0 74 8.19 109 45.2 84 58.6 98 10.5 79 28.4 75 48.0 52 5.45 117 38.4 89 77.8 74 4.40 126 32.6 104 48.4 53 3.92 144
2bit-BM-tele [98]102.6 11.7 41 27.0 89 3.79 139 20.2 128 26.3 145 5.07 107 12.0 65 23.2 48 4.00 115 21.2 89 36.1 86 8.16 107 45.3 85 58.0 82 10.3 58 34.0 145 61.8 142 5.92 140 54.1 149 99.9 140 5.72 147 29.8 36 47.4 42 3.74 137
FOLKI [16]103.5 13.0 120 30.9 121 4.97 148 22.2 146 24.9 123 9.00 148 17.3 121 33.0 125 7.00 138 33.4 144 38.7 109 17.0 146 44.3 61 55.8 54 10.4 67 27.6 50 49.7 71 5.48 125 36.2 62 74.2 46 4.80 139 30.4 49 44.9 25 4.08 146
SimpleFlow [49]104.4 12.0 67 24.0 39 2.94 55 18.5 94 24.4 108 4.24 75 32.7 142 39.0 137 5.69 133 18.0 27 36.2 90 7.55 41 46.9 130 60.8 128 11.1 102 31.4 135 58.1 135 5.35 111 49.4 145 99.9 140 5.16 145 40.0 140 63.0 144 3.46 42
SILK [79]104.7 13.3 124 30.7 120 3.83 142 22.0 145 25.3 127 7.16 143 34.7 147 40.0 139 7.77 145 26.6 126 36.6 93 8.60 123 45.1 81 57.9 80 10.0 20 28.4 75 50.9 101 6.03 145 34.8 23 71.8 25 4.51 135 31.4 67 48.0 50 3.74 137
ResPWCR_ROB [145]105.4 12.9 117 34.8 130 2.94 55 17.1 73 24.0 96 4.36 80 16.8 117 31.4 118 3.37 77 25.7 124 57.3 143 8.29 110 46.7 123 60.8 128 11.2 110 29.9 113 58.2 136 5.92 140 35.6 39 74.0 42 4.20 109 36.6 133 60.5 139 3.56 77
StereoFlow [44]106.6 22.8 150 48.3 147 3.74 138 20.5 135 26.8 148 5.07 107 11.3 30 29.3 102 3.37 77 20.1 71 37.0 95 7.62 55 59.3 148 75.2 148 10.8 88 39.3 150 71.4 149 5.45 117 35.8 47 73.9 41 4.08 42 35.7 130 55.1 123 3.70 121
H+S_ROB [138]106.7 13.7 129 27.7 98 3.11 85 18.8 100 22.6 57 5.80 124 33.0 143 43.0 144 8.00 146 26.7 127 33.6 58 9.04 130 44.2 58 56.3 59 10.4 67 27.8 56 48.6 59 5.35 111 43.7 136 99.9 140 5.10 144 37.1 134 58.3 134 3.70 121
StereoOF-V1MT [119]108.5 13.7 129 32.7 125 3.00 69 18.7 98 23.6 87 4.80 99 21.8 134 28.0 88 5.07 129 31.6 139 40.6 119 9.57 134 46.5 117 58.9 103 11.5 146 29.2 100 50.2 79 6.45 149 42.4 128 94.7 132 4.80 139 31.4 67 48.3 52 3.46 42
OFRF [134]108.9 14.4 137 38.4 139 3.70 135 19.9 122 25.3 127 5.48 120 13.0 96 33.0 125 3.11 70 20.7 82 38.4 105 7.79 84 47.8 137 61.4 134 10.9 94 31.9 138 56.8 131 5.29 98 41.5 123 90.5 123 4.08 42 34.4 123 54.7 117 3.42 12
Shiralkar [42]109.0 13.2 123 31.6 123 3.00 69 19.7 117 24.5 111 4.65 92 17.0 119 30.7 114 4.08 121 32.1 141 53.1 140 8.04 100 46.3 114 59.7 115 10.3 58 28.4 75 50.2 79 5.45 117 45.5 140 95.2 134 4.24 120 39.2 139 62.6 142 3.42 12
Dynamic MRF [7]111.1 12.1 81 26.8 88 2.94 55 18.0 91 23.9 93 4.16 73 18.3 126 30.7 114 5.00 127 28.9 135 39.8 113 10.5 137 45.9 104 58.6 98 11.2 110 30.9 130 56.0 130 5.80 139 43.0 132 90.3 121 4.65 137 33.7 114 51.8 97 3.70 121
Adaptive flow [45]111.8 13.4 126 25.8 76 4.51 145 21.8 144 25.4 131 7.26 144 13.7 100 27.5 83 4.69 124 24.1 119 35.2 76 8.76 127 47.3 134 61.5 135 10.2 52 33.8 144 61.9 143 5.45 117 35.9 52 73.2 37 4.20 109 34.7 126 54.7 117 3.70 121
UnFlow [129]114.5 14.9 139 40.2 142 3.11 85 18.5 94 23.4 82 5.48 120 15.3 111 31.3 117 4.36 122 22.8 111 38.0 101 8.45 118 48.3 140 63.0 141 10.9 94 32.4 139 62.0 144 5.72 134 35.4 34 71.2 18 4.32 124 45.5 148 66.0 147 3.87 142
SPSA-learn [13]116.8 12.3 98 33.7 128 3.37 120 19.2 107 23.6 87 5.45 119 30.0 138 39.7 138 7.00 138 26.9 128 41.3 121 8.41 117 46.7 123 60.1 119 10.2 52 29.4 106 50.6 91 5.20 80 53.7 148 99.9 140 8.43 150 51.4 149 72.0 150 3.51 57
SegOF [10]119.5 12.3 98 33.1 126 3.11 85 17.9 88 23.8 91 4.51 86 29.0 137 34.3 129 6.16 136 32.8 142 78.9 151 8.33 112 48.1 138 63.6 145 11.2 110 28.5 82 54.3 126 5.72 134 44.6 138 99.9 140 4.97 142 37.9 135 61.4 140 3.51 57
HCIC-L [99]119.6 21.0 149 41.8 143 5.07 149 20.2 128 26.1 144 5.80 124 16.3 115 42.3 141 4.00 115 31.7 140 51.0 139 8.50 119 44.7 71 55.5 50 10.4 67 35.2 147 69.8 148 5.07 53 39.9 110 91.2 126 4.16 102 40.4 143 58.0 132 3.65 116
FFV1MT [106]121.3 17.0 142 37.6 138 3.37 120 19.3 109 22.9 67 6.40 138 28.2 136 46.7 148 6.95 137 29.3 136 38.4 105 11.4 142 46.3 114 58.2 91 10.4 67 29.0 92 50.4 86 5.72 134 46.7 142 88.5 112 4.93 141 39.0 138 56.9 129 4.43 148
PGAM+LK [55]121.5 15.5 141 39.4 140 4.55 146 19.8 120 24.0 96 7.68 145 33.1 145 43.4 146 8.00 146 34.5 146 45.7 133 11.2 141 46.6 121 57.7 75 10.6 80 29.3 101 50.8 100 5.74 138 37.4 76 77.2 68 4.43 131 34.4 123 53.3 112 4.24 147
Heeger++ [104]122.7 19.8 146 44.7 144 3.11 85 18.9 103 22.8 63 6.45 139 33.0 143 35.2 130 7.16 142 29.3 136 38.4 105 11.4 142 51.5 146 65.2 146 11.3 129 28.4 75 46.9 36 6.78 150 47.9 144 84.5 105 4.69 138 40.1 141 58.8 136 3.70 121
SLK [47]123.9 13.9 134 29.9 115 3.79 139 20.0 124 22.8 63 6.22 134 32.0 141 33.7 127 7.72 144 33.4 144 46.4 134 16.1 145 48.5 143 61.7 137 10.3 58 28.4 75 47.9 51 5.72 134 43.2 133 97.9 137 4.97 142 38.7 137 59.8 137 4.04 145
WOLF_ROB [149]132.9 19.8 146 50.0 149 3.37 120 21.0 139 25.8 135 5.42 118 21.7 132 43.4 146 3.37 77 28.0 134 54.1 141 8.54 120 48.3 140 62.7 140 11.3 129 33.4 141 60.0 138 5.57 130 49.5 146 99.9 140 4.40 126 40.3 142 64.3 145 3.65 116
Pyramid LK [2]133.1 14.4 137 37.3 136 4.93 147 23.7 148 25.3 127 9.98 150 42.2 149 35.7 131 12.3 149 56.2 150 64.2 146 35.8 150 65.6 149 83.9 149 10.6 80 28.1 65 46.1 30 5.48 125 45.2 139 99.9 140 5.89 148 53.6 150 75.1 151 5.42 149
GroupFlow [9]134.4 19.9 148 49.6 148 3.42 128 19.1 105 24.1 100 5.48 120 31.4 140 40.0 139 8.19 148 36.2 147 61.9 144 12.1 144 55.6 147 71.3 147 11.4 139 36.3 148 67.0 147 5.60 132 46.7 142 98.5 138 4.20 109 43.6 146 62.8 143 3.56 77
Periodicity [78]148.4 17.6 143 55.7 150 5.45 150 26.8 150 27.0 149 9.75 149 49.4 151 51.5 151 17.7 150 51.3 149 70.3 147 27.9 149 66.6 150 86.3 150 11.7 150 38.7 149 82.5 150 6.38 148 51.8 147 99.9 140 5.48 146 44.3 147 65.5 146 5.80 150
AVG_FLOW_ROB [142]150.3 64.1 151 67.2 151 12.2 151 44.0 151 47.3 151 16.5 151 48.3 150 50.5 150 29.0 151 68.4 151 77.2 149 51.4 151 78.9 151 90.3 151 20.4 151 80.7 151 99.9 151 17.7 151 73.1 151 99.9 140 14.0 151 64.2 151 71.2 149 16.7 151
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

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