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
PyrWarp [159]1.9 8.70 2 12.6 2 2.38 1 11.7 3 16.2 3 3.32 1 4.76 1 9.00 1 2.38 1 11.6 1 16.1 1 6.95 1 26.7 1 32.4 1 8.29 5 18.3 2 33.7 2 4.24 1 23.6 2 52.3 2 3.70 3 21.6 2 29.8 2 3.11 4
CtxSyn [136]7.7 9.38 6 14.7 4 2.58 4 11.5 1 16.1 2 3.65 23 9.04 6 12.7 6 3.00 5 12.6 2 19.2 3 7.33 4 38.7 10 47.5 8 9.56 13 22.9 9 38.0 8 4.76 9 31.6 12 64.3 10 3.92 11 24.8 9 36.2 9 3.37 10
DAIN [158]15.2 9.06 4 15.1 6 2.83 27 13.0 6 17.6 4 5.03 114 8.35 4 12.4 5 2.71 2 15.7 6 22.7 8 8.68 131 30.7 3 37.6 3 8.27 4 19.1 4 34.6 4 4.32 4 28.7 7 59.7 5 3.65 2 23.6 5 33.1 5 3.00 2
CFRF [156]16.7 9.26 5 15.1 6 2.45 2 15.0 36 19.7 14 5.07 115 7.00 2 11.3 3 3.00 5 14.3 4 19.5 4 8.74 134 32.7 6 40.4 6 8.60 8 19.6 5 36.2 6 4.65 6 25.9 4 58.1 4 3.74 6 23.7 6 34.2 7 3.16 6
PMMST [114]19.2 11.2 21 21.1 17 2.71 5 13.8 13 19.7 14 3.65 23 10.3 9 19.2 17 2.71 2 16.8 12 30.8 33 7.53 36 41.1 16 51.1 18 10.0 28 24.6 13 43.0 17 4.93 26 34.2 21 70.9 23 4.04 17 28.8 25 45.4 37 3.42 19
InterpCNN [160]19.8 9.49 8 16.1 8 3.42 136 13.1 9 17.7 5 4.55 92 9.68 7 12.0 4 3.56 106 15.3 5 21.9 6 7.59 51 31.6 5 39.4 5 7.94 1 18.3 2 34.6 4 4.24 1 25.0 3 54.4 3 3.70 3 22.8 3 32.7 4 3.11 4
MDP-Flow2 [68]19.8 11.0 14 20.7 16 2.71 5 13.9 16 19.9 18 3.46 3 10.3 9 20.3 24 3.00 5 16.7 10 30.0 25 7.35 9 41.0 15 50.7 15 10.1 40 27.1 49 44.9 31 4.97 33 33.6 14 70.1 18 3.92 11 29.2 29 47.0 48 3.42 19
OFRI [161]20.0 8.70 2 12.8 3 3.00 77 13.8 13 18.7 10 4.83 107 7.00 2 9.04 2 2.71 2 13.4 3 18.7 2 8.74 134 31.1 4 38.2 4 8.50 6 22.0 7 37.5 7 4.43 5 28.5 6 61.2 7 4.08 50 23.0 4 32.6 3 3.42 19
MPRN [157]23.9 10.0 11 16.4 10 2.71 5 15.9 57 19.8 17 4.24 77 11.7 57 21.7 39 3.46 101 17.5 22 24.3 10 7.62 58 38.3 8 47.6 9 8.98 10 22.6 8 39.0 10 4.76 9 30.9 11 64.5 11 3.83 7 24.9 10 36.8 10 3.16 6
CyclicGen [153]24.2 8.29 1 11.7 1 3.46 138 11.6 2 15.3 1 5.94 138 9.68 7 15.0 10 3.42 100 16.7 10 21.0 5 10.3 146 29.8 2 37.0 2 8.04 2 12.4 1 21.2 1 4.65 6 18.4 1 39.9 1 3.70 3 16.6 1 22.9 1 2.94 1
MEMC-Net+ [155]25.2 9.42 7 14.9 5 2.94 62 14.0 17 18.4 7 5.00 112 13.8 110 14.0 7 3.37 81 16.0 7 22.1 7 8.54 125 35.2 7 44.1 7 8.58 7 19.7 6 34.2 3 4.24 1 28.1 5 60.7 6 3.56 1 23.9 7 33.5 6 3.00 2
SuperSlomo [132]26.7 9.66 9 16.1 8 3.37 128 15.4 44 20.4 23 6.06 141 8.43 5 14.4 9 3.00 5 17.1 14 23.8 9 8.58 127 38.5 9 47.8 10 8.76 9 23.1 11 40.8 12 4.80 12 30.2 9 62.5 8 3.87 8 25.2 11 37.4 12 3.32 8
NNF-Local [87]29.7 11.4 27 21.6 20 2.71 5 12.8 4 18.4 7 3.56 5 10.4 11 20.0 22 3.00 5 19.8 73 37.3 106 7.35 9 41.5 22 51.4 20 10.0 28 28.2 78 47.3 51 5.07 62 34.5 24 71.9 36 4.04 17 29.1 28 46.1 43 3.37 10
TOF-M [154]30.5 10.2 12 16.8 11 2.71 5 15.9 57 20.5 26 5.74 132 11.1 34 14.0 7 3.70 107 17.7 26 24.3 10 7.94 97 39.4 11 49.1 11 9.11 12 23.0 10 38.8 9 4.80 12 29.5 8 63.4 9 4.04 17 25.8 12 37.1 11 3.56 85
SepConv-v1 [127]31.8 9.68 10 19.1 12 2.52 3 15.4 44 20.1 21 5.26 123 11.0 18 16.7 11 3.87 122 20.4 87 26.8 12 9.59 145 41.9 23 52.5 27 9.00 11 24.7 14 42.4 14 4.69 8 30.7 10 67.4 12 3.92 11 24.7 8 35.8 8 3.32 8
NN-field [71]33.1 11.5 35 22.9 34 2.71 5 13.0 6 18.6 9 3.42 2 12.3 93 19.7 18 3.00 5 21.1 97 39.8 123 7.44 22 41.4 20 51.4 20 10.0 28 27.5 58 46.4 42 4.97 33 33.8 17 71.0 25 4.04 17 29.3 31 46.2 44 3.37 10
NNF-EAC [103]37.7 11.5 35 21.7 21 3.11 93 14.5 30 21.0 36 3.70 26 12.3 93 22.6 47 3.00 5 17.7 26 32.4 53 7.55 43 43.2 50 55.1 54 10.1 40 25.1 17 43.8 20 4.90 19 34.0 19 70.5 20 4.08 50 29.4 34 47.5 54 3.42 19
DeepFlow2 [108]40.5 11.4 27 23.5 38 3.00 77 16.7 76 23.0 80 4.04 63 11.0 18 20.3 24 3.00 5 19.0 60 29.8 23 7.53 36 42.7 36 54.0 36 10.3 65 25.0 15 43.0 17 4.93 26 35.2 40 73.8 48 4.04 17 28.9 26 44.9 33 3.56 85
DeepFlow [86]40.7 11.3 25 24.2 52 3.00 77 16.6 75 23.0 80 4.32 81 11.0 18 20.3 24 3.00 5 19.3 63 28.1 17 7.59 51 42.7 36 54.5 41 10.2 60 25.2 19 44.1 21 5.00 55 32.9 13 68.2 13 4.04 17 28.4 21 44.6 28 3.56 85
PH-Flow [101]41.2 11.9 68 25.7 82 2.83 27 13.3 10 19.7 14 3.56 5 10.7 13 22.7 48 3.00 5 16.5 9 30.2 26 7.33 4 42.3 29 52.1 24 10.1 40 28.7 95 50.9 110 5.20 89 35.6 47 77.0 74 4.04 17 29.6 40 47.0 48 3.51 65
CombBMOF [113]42.2 12.0 75 24.3 53 2.83 27 14.3 24 20.6 28 3.56 5 11.3 37 25.7 75 3.00 5 20.3 86 34.9 81 7.55 43 43.2 50 54.0 36 10.1 40 26.4 36 47.7 58 4.90 19 36.2 70 71.4 29 4.08 50 29.5 37 45.7 40 3.37 10
SuperFlow [81]42.7 11.0 14 22.1 28 3.11 93 17.1 83 22.7 70 4.69 98 11.7 57 18.7 12 3.37 81 18.7 52 27.4 14 7.70 75 41.3 18 51.2 19 9.98 24 26.3 35 46.9 45 4.80 12 34.7 28 76.0 62 4.08 50 28.1 19 41.5 16 3.42 19
DF-Auto [115]43.6 10.9 13 19.2 13 3.11 93 17.2 88 23.4 90 4.43 87 10.4 11 20.6 32 3.00 5 18.1 38 29.7 20 7.55 43 41.4 20 52.1 24 10.0 28 26.2 30 47.2 48 4.97 33 35.2 40 79.3 87 4.08 50 29.6 40 44.7 29 3.56 85
LME [70]45.5 11.4 27 22.0 26 2.71 5 15.1 39 21.8 48 3.87 54 11.3 37 36.0 143 3.00 5 17.4 17 32.0 50 7.48 26 44.5 75 57.0 73 11.4 149 27.6 60 47.2 48 4.97 33 33.6 14 69.7 15 4.04 17 30.0 47 48.6 66 3.42 19
CBF [12]46.3 11.0 14 19.8 14 3.00 77 17.1 83 22.9 76 4.24 77 12.0 73 19.0 14 3.00 5 17.8 32 28.0 16 7.85 92 40.6 14 49.9 13 9.97 20 26.2 30 44.6 26 4.97 33 36.3 72 76.3 67 4.12 103 27.9 15 41.2 15 3.70 131
Aniso. Huber-L1 [22]46.5 11.4 27 21.7 21 3.11 93 19.7 127 24.7 126 4.55 92 12.0 73 19.7 18 3.11 75 18.4 44 29.8 23 7.55 43 42.5 32 54.4 40 9.98 24 25.2 19 42.2 13 4.83 15 35.6 47 71.5 30 4.04 17 27.9 15 42.0 18 3.56 85
IROF++ [58]46.7 11.9 68 24.1 49 2.83 27 14.7 33 21.3 38 3.56 5 12.1 90 29.0 104 3.00 5 16.3 8 27.9 15 7.35 9 43.9 62 56.0 62 11.1 110 26.4 36 47.0 47 4.93 26 34.5 24 72.3 37 4.08 50 30.3 57 49.3 74 3.56 85
WLIF-Flow [93]46.7 11.5 35 22.1 28 2.83 27 15.2 40 21.6 44 3.79 44 11.3 37 26.4 84 3.00 5 17.4 17 30.3 28 7.59 51 42.5 32 53.5 32 10.4 74 29.0 101 51.1 113 5.29 107 34.8 31 69.7 15 4.04 17 30.0 47 48.4 62 3.46 50
FMOF [94]48.4 12.2 97 24.5 62 2.94 62 14.0 17 20.0 19 3.56 5 12.3 93 27.7 92 3.00 5 19.8 73 35.4 86 7.70 75 42.4 30 52.1 24 10.1 40 28.1 74 49.1 75 4.93 26 34.6 27 72.7 42 3.87 8 30.2 53 47.6 57 3.42 19
CLG-TV [48]49.0 11.1 19 21.8 24 3.11 93 18.8 109 24.0 106 4.43 87 11.3 37 20.0 22 3.70 107 18.6 50 28.9 18 7.72 81 42.8 39 55.0 53 10.0 28 25.0 15 42.9 16 4.93 26 36.0 62 71.6 31 4.04 17 29.0 27 44.0 24 3.56 85
IROF-TV [53]49.9 11.7 49 24.7 69 3.00 77 15.5 48 22.0 57 3.70 26 11.0 18 23.7 58 3.00 5 17.3 15 31.3 37 7.57 50 43.8 60 56.0 62 11.2 119 27.6 60 48.4 65 4.97 33 35.9 60 74.5 57 4.08 50 28.0 17 42.6 20 3.56 85
Brox et al. [5]50.2 11.4 27 24.9 74 2.94 62 15.9 57 22.2 60 4.04 63 11.3 37 21.0 33 3.37 81 18.4 44 27.0 13 7.59 51 42.2 27 53.3 30 10.0 28 28.2 78 51.5 116 5.00 55 36.8 76 88.0 118 4.04 17 28.4 21 42.3 19 3.42 19
nLayers [57]51.5 11.8 57 22.9 34 2.83 27 14.1 20 20.4 23 3.56 5 11.0 18 19.7 18 3.00 5 18.3 42 34.2 76 7.39 16 46.7 131 60.1 127 11.0 104 27.9 67 50.1 85 5.20 89 35.5 45 72.6 41 4.08 50 30.8 62 49.3 74 3.42 19
ALD-Flow [66]51.5 12.0 75 28.4 113 3.11 93 16.3 67 22.8 72 3.83 49 11.0 18 21.7 39 3.00 5 17.9 35 33.6 66 7.39 16 43.4 55 54.6 46 10.8 96 25.8 24 44.8 30 5.00 55 34.1 20 70.4 19 4.04 17 31.9 90 50.3 85 3.46 50
Layers++ [37]53.7 11.4 27 21.7 21 2.94 62 12.8 4 18.2 6 3.46 3 11.0 18 26.7 87 3.00 5 17.7 26 32.9 58 7.53 36 46.6 129 60.9 139 10.6 88 30.9 139 60.2 148 5.00 55 34.9 37 72.7 42 3.87 8 29.9 46 47.5 54 3.46 50
MDP-Flow [26]53.8 11.2 21 21.2 18 2.71 5 14.2 22 20.5 26 3.70 26 10.7 13 19.0 14 3.00 5 19.7 71 32.4 53 7.70 75 44.2 66 57.0 73 11.2 119 30.0 125 51.4 115 5.51 138 36.1 67 72.9 45 4.08 50 30.8 62 48.4 62 3.42 19
JOF [140]54.0 12.0 75 23.6 40 3.11 93 14.0 17 20.0 19 3.70 26 11.0 18 23.8 61 3.00 5 18.1 38 31.5 42 7.35 9 44.7 78 57.6 82 11.3 138 29.5 117 50.1 85 5.07 62 34.5 24 71.6 31 4.04 17 31.2 69 50.3 85 3.51 65
p-harmonic [29]55.2 11.4 27 23.5 38 2.83 27 19.1 115 24.3 115 4.80 104 11.3 37 22.0 42 3.70 107 20.9 95 31.7 44 7.62 58 42.6 35 54.2 38 10.1 40 25.7 23 43.5 19 5.07 62 36.1 67 71.8 33 4.08 50 29.6 40 46.5 45 3.51 65
LDOF [28]55.6 11.4 27 22.5 31 3.56 141 16.1 61 21.4 43 6.35 147 12.0 73 20.3 24 3.70 107 19.0 60 29.7 20 7.94 97 41.2 17 50.9 16 10.1 40 26.8 42 50.2 88 4.90 19 34.8 31 80.2 91 4.08 50 29.4 34 44.5 26 3.46 50
Second-order prior [8]56.1 11.3 25 22.0 26 3.11 93 19.0 114 24.2 113 4.32 81 13.3 106 27.7 92 3.70 107 18.8 55 31.6 43 7.51 30 42.9 41 54.7 48 10.0 28 26.2 30 45.0 32 4.97 33 35.6 47 71.2 26 4.04 17 29.5 37 45.4 37 3.56 85
COFM [59]56.1 11.8 57 24.3 53 2.94 62 14.5 30 20.9 33 3.65 23 11.0 18 26.4 84 3.00 5 17.4 17 32.3 51 7.35 9 44.2 66 55.1 54 10.1 40 30.0 125 54.4 136 5.20 89 35.8 55 79.3 87 4.08 50 31.2 69 48.8 69 3.51 65
SIOF [67]56.8 11.7 49 23.1 36 3.11 93 19.4 122 24.8 129 4.76 101 11.3 37 25.7 75 3.11 75 18.4 44 31.4 39 8.04 105 40.3 13 50.3 14 9.95 18 25.8 24 45.3 34 4.97 33 33.9 18 71.2 26 4.08 50 30.0 47 47.4 51 3.70 131
Local-TV-L1 [65]57.8 11.2 21 21.5 19 3.56 141 19.6 125 24.4 118 5.57 131 11.0 18 19.1 16 3.00 5 18.3 42 30.4 31 7.87 95 42.8 39 54.5 41 10.2 60 26.2 30 44.7 27 5.45 126 34.2 21 76.1 65 4.08 50 28.0 17 42.8 22 3.65 126
ProbFlowFields [128]57.8 11.6 41 25.4 78 2.83 27 14.4 26 21.1 37 3.56 5 10.7 13 23.7 58 3.00 5 18.4 44 33.4 63 7.59 51 46.2 119 59.2 113 11.2 119 28.5 91 50.7 104 5.32 113 34.7 28 76.9 72 4.08 50 29.4 34 46.5 45 3.46 50
FlowFields [110]57.9 11.8 57 25.6 81 2.83 27 14.4 26 20.9 33 3.56 5 11.3 37 24.3 66 3.00 5 20.0 79 38.1 111 7.51 30 43.6 57 54.5 41 11.0 104 28.2 78 50.7 104 5.16 84 34.8 31 75.1 61 4.04 17 32.0 96 52.0 110 3.46 50
EAI-Flow [151]58.8 12.5 118 26.8 96 2.83 27 15.8 55 21.8 48 4.20 75 12.3 93 30.4 122 3.00 5 19.3 63 34.0 73 7.39 16 44.9 85 57.1 77 11.1 110 26.1 29 46.0 37 5.00 55 36.0 62 72.4 39 4.08 50 29.3 31 45.2 35 3.37 10
TV-L1-MCT [64]60.9 12.4 113 24.7 69 2.83 27 16.4 68 23.1 82 3.83 49 11.9 72 32.7 132 3.00 5 17.6 23 31.7 44 7.53 36 47.0 140 61.2 140 11.0 104 25.5 21 44.7 27 4.97 33 36.0 62 80.7 96 4.04 17 28.4 21 44.8 31 3.46 50
Sparse-NonSparse [56]62.0 12.0 75 24.3 53 2.83 27 15.0 36 21.3 38 3.56 5 11.7 57 29.0 104 3.00 5 17.6 23 29.7 20 7.39 16 45.7 103 59.3 114 11.0 104 28.8 96 48.7 71 5.07 62 38.6 102 90.1 129 4.04 17 32.4 105 51.8 106 3.42 19
HAST [109]62.5 11.7 49 23.6 40 2.94 62 13.8 13 19.6 13 3.56 5 12.0 73 31.7 128 3.00 5 17.8 32 31.7 44 7.14 2 45.3 93 57.0 73 9.97 20 33.7 152 62.8 155 5.10 79 38.4 97 88.4 120 4.04 17 33.0 115 51.0 93 3.42 19
OAR-Flow [125]63.4 12.0 75 24.9 74 3.00 77 16.4 68 22.4 63 4.08 68 11.0 18 20.5 31 3.00 5 17.4 17 33.6 66 7.33 4 46.2 119 60.0 126 11.3 138 27.0 45 47.6 55 5.23 97 37.6 86 74.0 51 4.08 50 31.0 67 49.2 72 3.46 50
CPM-Flow [116]63.6 11.8 57 27.3 100 2.83 27 14.4 26 20.4 23 3.70 26 11.7 57 24.0 62 3.00 5 21.4 105 40.1 126 7.77 85 45.5 99 58.1 93 11.2 119 26.6 41 48.0 61 5.07 62 36.0 62 72.3 37 4.04 17 30.9 65 50.4 87 3.56 85
BlockOverlap [61]63.9 11.1 19 20.1 15 3.56 141 19.3 119 23.7 99 6.16 143 11.3 37 20.4 30 3.70 107 18.4 44 29.6 19 8.72 132 43.1 47 54.5 41 10.2 60 27.4 55 48.6 68 5.35 120 34.8 31 72.8 44 4.08 50 27.2 14 40.9 14 3.56 85
FlowFields+ [130]64.6 11.8 57 26.1 90 2.71 5 14.1 20 20.6 28 3.70 26 11.2 36 24.8 71 3.00 5 20.1 81 40.2 128 7.53 36 45.5 99 58.0 90 11.2 119 28.6 94 50.6 100 5.20 89 35.6 47 77.5 79 4.04 17 32.2 100 52.5 114 3.42 19
AGIF+OF [85]64.8 12.2 97 24.3 53 2.71 5 15.2 40 21.8 48 3.70 26 11.7 57 27.7 92 3.00 5 18.0 36 33.0 60 7.55 43 45.8 107 58.8 110 11.2 119 30.0 125 53.4 130 5.07 62 35.4 42 74.8 59 3.92 11 32.2 100 52.6 117 3.37 10
2DHMM-SAS [92]65.1 12.2 97 24.5 62 2.83 27 17.9 97 24.1 110 3.87 54 12.0 73 28.7 101 3.00 5 17.3 15 31.4 39 7.51 30 45.1 89 58.2 99 11.2 119 27.9 67 49.0 73 4.83 15 37.0 78 76.1 65 4.08 50 31.9 90 50.5 88 3.42 19
Modified CLG [34]65.5 11.0 14 21.9 25 3.11 93 19.6 125 23.9 103 5.94 138 12.4 98 26.3 82 3.87 122 19.8 73 30.8 33 8.12 110 42.1 25 52.9 28 10.1 40 27.0 45 48.1 63 5.23 97 34.7 28 70.8 22 4.08 50 29.5 37 45.3 36 3.56 85
ComponentFusion [96]65.5 12.0 75 29.6 122 2.71 5 14.5 30 21.3 38 3.56 5 11.0 18 22.0 42 3.00 5 18.8 55 36.2 99 7.33 4 45.5 99 58.2 99 10.7 93 27.2 50 46.3 40 4.97 33 40.5 125 93.3 139 4.12 103 34.4 132 58.3 142 3.42 19
F-TV-L1 [15]66.7 12.0 75 26.5 94 3.56 141 19.2 117 24.7 126 4.83 107 11.7 57 21.5 37 4.00 124 19.3 63 32.7 56 7.68 68 43.1 47 55.3 57 9.83 14 25.1 17 42.8 15 5.07 62 34.8 31 74.0 51 4.16 111 28.5 24 42.7 21 3.56 85
TC/T-Flow [76]67.1 12.4 113 26.4 92 2.83 27 16.5 73 23.1 82 3.83 49 11.0 18 22.4 46 3.00 5 18.9 57 34.5 77 7.33 4 45.5 99 58.1 93 11.4 149 27.3 54 47.6 55 4.93 26 41.1 127 80.4 94 4.20 118 30.9 65 49.7 78 3.37 10
AdaConv-v1 [126]67.4 15.0 150 28.2 111 3.70 145 17.6 94 20.7 31 7.68 155 17.4 131 22.0 42 7.00 148 27.5 141 33.7 71 17.0 156 39.9 12 49.8 12 8.19 3 23.8 12 39.5 11 4.76 9 34.2 21 68.5 14 4.12 103 26.9 13 39.5 13 3.42 19
DPOF [18]67.8 12.3 106 29.4 120 3.11 93 13.3 10 19.1 12 3.56 5 15.7 121 25.2 73 3.70 107 19.4 66 37.5 108 7.59 51 43.1 47 54.6 46 10.0 28 29.1 106 49.7 79 4.90 19 36.6 74 77.0 74 4.08 50 31.5 80 50.5 88 3.51 65
PGM-C [120]69.2 11.8 57 27.3 100 2.83 27 14.4 26 20.7 31 3.70 26 12.3 93 23.0 52 3.00 5 20.6 91 42.3 134 7.62 58 45.8 107 59.5 120 11.2 119 27.2 50 47.4 52 4.97 33 37.1 80 79.2 84 4.04 17 32.4 105 55.0 130 3.51 65
PMF [73]69.4 12.2 97 25.9 85 2.71 5 15.4 44 21.8 48 3.56 5 12.7 100 35.7 141 3.00 5 20.2 84 35.9 92 7.51 30 44.4 73 54.9 52 10.1 40 28.4 84 50.5 98 5.32 113 37.9 91 81.1 99 4.04 17 34.2 129 54.1 124 3.37 10
Ramp [62]69.5 12.0 75 24.6 65 2.94 62 14.8 34 21.3 38 3.70 26 11.7 57 29.4 110 3.00 5 16.9 13 30.3 28 7.39 16 45.4 96 58.5 102 11.0 104 30.2 132 50.9 110 5.23 97 39.8 117 89.6 126 4.04 17 32.4 105 52.5 114 3.42 19
TF+OM [100]69.9 11.6 41 30.1 127 3.11 93 15.0 36 21.6 44 4.04 63 11.7 57 24.0 62 3.00 5 21.3 101 39.0 121 7.68 68 44.3 69 56.7 71 10.3 65 28.8 96 50.4 95 5.07 62 37.7 87 83.5 110 4.08 50 29.2 29 46.0 41 3.56 85
ProFlow_ROB [146]70.8 11.8 57 27.5 104 2.83 27 15.8 55 22.6 66 3.79 44 11.4 53 20.3 24 3.00 5 18.9 57 37.0 104 7.35 9 47.3 142 61.8 148 11.2 119 25.5 21 44.2 22 4.83 15 40.0 122 81.4 101 4.08 50 34.3 131 56.5 137 3.56 85
Ad-TV-NDC [36]70.8 12.2 97 22.5 31 4.32 154 20.6 147 24.8 129 5.80 133 11.7 57 21.6 38 3.37 81 21.6 106 31.8 47 8.04 105 42.5 32 53.4 31 9.97 20 26.4 36 47.6 55 5.16 84 36.8 76 70.9 23 4.08 50 28.3 20 41.8 17 3.70 131
AggregFlow [97]71.0 13.7 138 37.1 145 3.11 93 16.2 65 22.6 66 4.04 63 11.0 18 23.3 57 3.00 5 21.8 108 40.7 130 7.66 66 43.2 50 53.5 32 10.3 65 27.0 45 46.0 37 5.00 55 38.0 92 82.4 107 4.08 50 31.9 90 51.9 109 3.42 19
ComplOF-FED-GPU [35]71.1 12.0 75 27.9 108 2.94 62 15.7 53 22.2 60 3.79 44 16.0 122 21.4 35 3.70 107 18.4 44 33.6 66 7.48 26 44.9 85 57.7 83 10.7 93 27.4 55 45.9 36 5.00 55 36.6 74 78.7 83 4.08 50 32.6 113 52.3 112 3.51 65
OFLAF [77]71.1 11.7 49 24.5 62 2.71 5 13.6 12 20.3 22 3.56 5 11.0 18 23.0 52 3.00 5 17.6 23 31.3 37 7.39 16 47.3 142 61.7 145 11.2 119 29.6 118 51.9 123 5.32 113 41.8 134 95.6 144 4.16 111 33.6 121 52.1 111 3.42 19
S2F-IF [123]71.4 12.1 89 29.8 124 2.71 5 14.2 22 20.6 28 3.56 5 11.3 37 26.3 82 3.00 5 20.2 84 40.1 126 7.53 36 45.9 112 58.7 109 11.3 138 28.4 84 50.7 104 5.20 89 35.7 52 76.0 62 4.08 50 32.3 103 53.1 118 3.46 50
Classic+NL [31]72.0 12.1 89 24.3 53 3.00 77 15.3 43 21.8 48 3.70 26 11.7 57 29.4 110 3.00 5 17.4 17 31.4 39 7.53 36 45.7 103 59.4 116 10.8 96 29.0 101 49.8 82 5.10 79 39.6 114 90.4 131 4.08 50 32.2 100 51.8 106 3.46 50
Classic++ [32]72.9 11.6 41 23.7 42 3.11 93 17.8 96 24.4 118 4.08 68 11.7 57 20.3 24 3.37 81 20.1 81 33.8 72 7.62 58 44.7 78 57.8 86 10.0 28 28.0 70 49.7 79 5.35 120 37.4 84 81.4 101 4.08 50 30.7 61 49.5 76 3.56 85
DMF_ROB [139]73.1 11.9 68 25.4 78 3.00 77 17.1 83 22.8 72 4.08 68 19.4 139 29.7 113 3.70 107 20.4 87 34.5 77 7.68 68 45.3 93 58.1 93 11.1 110 26.4 36 45.6 35 4.97 33 35.7 52 73.8 48 4.08 50 31.2 69 50.2 80 3.42 19
FC-2Layers-FF [74]73.6 12.1 89 26.0 89 2.83 27 13.0 6 18.7 10 3.56 5 11.4 53 25.7 75 3.00 5 17.8 32 33.5 65 7.48 26 46.5 125 60.3 132 11.2 119 30.4 135 52.3 128 5.32 113 39.8 117 90.0 128 4.08 50 31.8 86 51.6 102 3.46 50
LSM [39]73.8 12.3 106 24.7 69 2.83 27 15.4 44 21.9 54 3.56 5 12.0 73 30.3 120 3.00 5 18.7 52 33.2 62 7.44 22 46.1 117 59.4 116 11.1 110 29.3 110 51.9 123 5.07 62 39.2 108 91.0 134 4.04 17 32.3 103 52.5 114 3.42 19
MLDP_OF [89]75.1 11.9 68 24.7 69 2.83 27 17.4 91 23.8 101 3.87 54 10.7 13 24.6 69 3.00 5 20.5 90 33.6 66 8.35 119 44.1 64 56.5 68 10.1 40 29.3 110 50.5 98 5.57 139 35.8 55 73.4 47 4.20 118 31.2 69 50.6 91 3.70 131
FlowNetS+ft+v [112]75.2 11.5 35 23.7 42 3.46 138 19.9 132 24.6 124 7.87 157 12.0 73 21.1 34 3.37 81 19.5 68 30.6 32 8.91 137 43.7 58 56.6 70 11.2 119 26.0 26 44.5 25 4.97 33 38.6 102 87.8 116 4.08 50 30.0 47 46.0 41 3.51 65
RNLOD-Flow [121]76.2 11.8 57 24.6 65 2.89 58 17.3 90 24.0 106 3.74 40 12.7 100 36.0 143 3.11 75 18.1 38 31.2 36 7.48 26 45.8 107 59.6 121 11.1 110 29.3 110 50.6 100 5.16 84 35.4 42 74.1 54 4.08 50 32.0 96 51.6 102 3.42 19
Fusion [6]76.5 11.6 41 24.3 53 2.89 58 15.6 51 21.9 54 3.83 49 11.0 18 23.7 58 3.37 81 21.0 96 33.4 63 7.62 58 44.1 64 56.3 66 10.1 40 30.3 134 54.1 134 5.45 126 38.0 92 83.7 111 4.08 50 34.0 127 54.7 126 3.56 85
TCOF [69]76.5 12.0 75 24.7 69 2.83 27 20.3 142 26.4 157 5.07 115 11.1 34 29.0 104 3.00 5 17.7 26 32.4 53 7.68 68 43.2 50 55.5 58 9.97 20 28.8 96 46.3 40 5.07 62 41.2 130 94.9 142 4.08 50 31.8 86 51.3 97 3.70 131
CRTflow [80]77.0 11.7 49 24.4 60 3.32 124 19.5 124 24.9 133 4.51 89 12.0 73 22.7 48 4.00 124 18.1 38 30.3 28 7.68 68 45.0 87 58.1 93 11.3 138 26.0 26 45.1 33 4.97 33 37.7 87 87.9 117 4.08 50 30.8 62 50.2 80 3.56 85
RFlow [90]77.0 11.6 41 24.3 53 3.00 77 19.3 119 24.8 129 4.36 83 11.6 56 29.7 113 3.37 81 20.0 79 36.1 95 7.72 81 43.0 42 55.2 56 10.1 40 27.9 67 51.8 122 4.97 33 37.1 80 82.8 109 4.08 50 31.6 82 49.5 76 3.56 85
Sparse Occlusion [54]77.5 11.7 49 25.9 85 3.00 77 18.1 101 24.6 124 3.83 49 11.3 37 22.7 48 3.11 75 18.7 52 34.1 75 7.70 75 45.0 87 58.0 90 11.1 110 28.5 91 44.2 22 5.26 101 39.3 111 83.7 111 3.92 11 31.9 90 51.7 104 3.56 85
S2D-Matching [84]77.7 12.3 106 25.7 82 2.94 62 17.2 88 23.7 99 4.00 60 11.7 57 28.7 101 3.00 5 17.7 26 31.9 49 7.55 43 46.8 135 60.1 127 10.4 74 30.0 125 51.5 116 5.29 107 37.0 78 77.7 80 4.04 17 31.8 86 50.9 92 3.46 50
SVFilterOh [111]78.5 11.9 68 26.1 90 2.94 62 14.3 24 20.9 33 3.70 26 12.0 73 26.7 87 3.00 5 19.9 77 36.1 95 7.62 58 46.7 131 59.8 124 11.4 149 30.7 138 55.1 137 5.07 62 36.0 62 77.2 76 4.04 17 32.4 105 53.2 120 3.51 65
TC-Flow [46]78.5 12.0 75 30.3 129 2.89 58 16.8 78 23.4 90 3.92 59 11.7 57 21.4 35 3.00 5 19.5 68 36.1 95 8.12 110 46.5 125 59.8 124 11.3 138 27.0 45 48.4 65 5.26 101 35.5 45 74.6 58 4.04 17 33.3 118 54.5 125 3.51 65
HBM-GC [105]79.7 11.8 57 23.8 45 3.11 93 16.8 78 24.2 113 3.87 54 10.7 13 18.7 12 3.00 5 18.9 57 32.9 58 7.68 68 46.8 135 60.8 136 11.5 156 34.5 156 61.7 150 5.48 134 37.7 87 81.9 106 4.04 17 30.5 60 47.8 58 3.51 65
3DFlow [135]80.1 12.4 113 27.1 99 2.83 27 15.5 48 22.1 58 3.87 54 13.7 108 24.0 62 3.00 5 19.2 62 38.7 118 7.68 68 44.0 63 56.0 62 10.1 40 31.2 142 53.8 133 5.60 141 39.5 112 79.2 84 4.16 111 31.1 68 48.0 59 3.56 85
Classic+CPF [83]80.2 12.2 97 24.6 65 2.83 27 15.6 51 22.1 58 3.74 40 12.0 73 30.7 123 3.00 5 17.7 26 30.9 35 7.44 22 47.2 141 61.3 141 11.2 119 31.2 142 55.9 138 5.26 101 39.9 119 88.8 123 4.04 17 33.6 121 54.0 123 3.42 19
Black & Anandan [4]81.0 12.3 106 24.0 47 3.46 138 21.2 150 25.4 141 5.35 125 18.1 134 25.0 72 5.35 139 24.4 130 34.9 81 7.77 85 42.2 27 53.5 32 10.1 40 26.9 44 46.5 43 4.97 33 39.5 112 77.2 76 4.08 50 29.3 31 42.8 22 3.56 85
FESL [72]81.0 12.2 97 25.1 77 2.83 27 14.9 35 21.6 44 3.70 26 12.1 90 33.7 137 3.00 5 19.7 71 35.0 83 7.72 81 46.2 119 60.2 131 11.3 138 29.3 110 50.4 95 5.32 113 39.6 114 88.6 122 3.92 11 32.4 105 51.2 95 3.42 19
CostFilter [40]81.5 13.1 132 33.1 136 2.71 5 15.2 40 21.3 38 3.56 5 14.0 112 42.7 153 3.00 5 22.0 110 44.4 141 7.26 3 45.8 107 57.2 79 10.4 74 27.2 50 48.1 63 5.45 126 39.9 119 89.4 125 4.08 50 35.6 137 56.1 135 3.37 10
Efficient-NL [60]82.6 11.8 57 23.8 45 2.83 27 16.7 76 23.3 87 3.70 26 18.4 136 29.0 104 3.70 107 19.4 66 34.0 73 7.51 30 45.1 89 58.5 102 11.1 110 30.0 125 51.5 116 5.07 62 40.1 123 88.9 124 4.08 50 33.0 115 52.4 113 3.42 19
EpicFlow [102]82.7 11.9 68 27.6 105 2.83 27 16.0 60 22.2 60 3.79 44 11.8 71 21.7 39 3.00 5 21.3 101 42.9 136 7.85 92 46.3 122 59.4 116 11.2 119 27.4 55 47.5 54 5.16 84 38.2 94 76.6 69 4.12 103 35.2 136 58.0 140 3.56 85
SRR-TVOF-NL [91]83.5 12.9 126 28.7 114 3.00 77 16.9 81 23.1 82 4.69 98 11.5 55 27.0 90 3.00 5 22.2 112 37.3 106 7.59 51 44.8 83 57.9 88 11.0 104 29.1 106 51.9 123 4.90 19 35.7 52 77.7 80 4.08 50 33.0 115 51.5 101 3.56 85
Filter Flow [19]84.5 11.8 57 23.1 36 3.37 128 20.0 134 25.1 135 5.23 122 12.2 92 26.0 79 3.70 107 22.1 111 32.7 56 7.94 97 42.1 25 51.9 22 10.4 74 28.1 74 49.0 73 5.07 62 38.4 97 81.6 103 4.16 111 30.0 47 45.5 39 3.74 147
2D-CLG [1]84.8 11.6 41 24.1 49 3.11 93 19.4 122 23.3 87 6.24 145 18.7 137 24.3 66 4.69 133 22.4 114 31.8 47 8.66 130 43.3 54 56.1 65 10.4 74 26.0 26 44.2 22 5.35 120 40.2 124 91.5 137 4.20 118 29.6 40 44.5 26 3.51 65
Bartels [41]85.0 12.2 97 29.9 125 3.37 128 17.4 91 24.3 115 4.83 107 11.3 37 24.7 70 3.70 107 21.2 98 35.4 86 9.15 143 41.3 18 51.0 17 9.87 15 29.7 120 50.2 88 6.32 157 33.7 16 70.7 21 4.20 118 30.2 53 48.4 62 3.79 150
Steered-L1 [118]85.6 11.2 21 22.6 33 2.89 58 16.2 65 22.6 66 4.55 92 21.7 141 32.4 131 5.00 136 23.4 124 38.3 113 10.7 148 44.7 78 57.4 80 9.88 16 28.0 70 48.5 67 5.32 113 37.1 80 79.2 84 4.12 103 31.4 76 51.1 94 3.51 65
Occlusion-TV-L1 [63]88.2 11.6 41 25.0 76 3.11 93 19.8 130 26.0 151 4.83 107 11.3 37 23.0 52 3.46 101 22.5 117 43.0 138 7.94 97 43.0 42 54.8 51 9.88 16 28.0 70 50.7 104 5.32 113 39.6 114 76.6 69 4.62 145 31.5 80 50.5 88 3.56 85
OFH [38]88.3 12.0 75 27.3 100 3.00 77 18.1 101 23.4 90 4.20 75 12.4 98 32.7 132 3.00 5 18.6 50 35.4 86 7.35 9 46.5 125 60.1 127 10.8 96 27.5 58 47.2 48 5.26 101 41.1 127 81.1 99 4.20 118 35.7 138 56.1 135 3.46 50
EPPM w/o HM [88]88.4 12.7 123 30.9 131 2.71 5 16.1 61 23.1 82 3.70 26 17.7 132 42.4 152 3.70 107 21.3 101 42.5 135 7.70 75 43.0 42 53.1 29 10.3 65 30.2 132 57.1 141 4.97 33 38.5 100 89.6 126 4.12 103 32.4 105 51.3 97 3.42 19
Adaptive [20]89.4 11.6 41 26.7 95 3.11 93 20.2 138 25.9 148 5.07 115 12.0 73 23.0 52 3.37 81 20.4 87 36.6 102 7.77 85 44.3 69 58.5 102 9.98 24 28.3 82 49.1 75 5.16 84 42.5 139 90.6 133 4.08 50 31.6 82 48.8 69 3.65 126
LFNet_ROB [149]89.9 13.4 135 37.5 147 2.71 5 16.1 61 21.8 48 4.08 68 12.0 73 36.3 146 3.37 81 20.7 92 36.0 93 7.94 97 45.4 96 57.8 86 11.6 159 30.6 136 57.4 142 5.20 89 34.9 37 71.8 33 4.08 50 31.3 74 49.9 79 3.70 131
FF++_ROB [145]90.1 12.1 89 28.2 111 2.71 5 15.5 48 21.6 44 3.74 40 12.0 73 29.4 110 3.00 5 23.3 123 49.1 147 7.83 91 48.1 147 61.6 144 11.3 138 29.1 106 49.5 78 5.94 152 36.5 73 76.4 68 4.08 50 32.1 98 51.3 97 3.65 126
CNN-flow-warp+ref [117]90.9 11.0 14 22.4 30 3.11 93 17.6 94 22.9 76 5.92 137 16.1 123 28.3 100 4.00 124 23.5 125 30.2 26 10.7 148 44.8 83 58.5 102 11.3 138 26.5 40 46.5 43 5.29 107 41.5 132 91.5 137 4.32 133 30.4 58 47.5 54 3.51 65
TriFlow [95]92.3 12.5 118 36.7 143 3.00 77 18.7 107 24.5 121 4.76 101 11.7 57 28.1 98 3.00 5 21.7 107 41.4 132 7.62 58 46.8 135 60.4 133 11.2 119 29.9 122 51.7 121 4.97 33 37.8 90 76.9 72 4.08 50 31.7 85 48.6 66 3.51 65
Horn & Schunck [3]92.4 12.1 89 23.7 42 3.32 124 21.4 152 25.6 144 5.89 136 17.0 128 28.2 99 5.35 139 27.3 140 37.9 109 8.04 105 42.4 30 54.3 39 10.3 65 26.2 30 44.7 27 5.07 62 40.9 126 81.7 104 4.20 118 30.2 53 44.3 25 3.70 131
PWC-Net_ROB [147]92.5 13.5 137 35.8 141 2.71 5 16.4 68 23.3 87 3.74 40 12.0 73 30.3 120 3.00 5 21.3 101 45.6 142 7.51 30 48.8 154 63.0 150 11.2 119 29.7 120 53.0 129 5.29 107 35.8 55 74.9 60 4.08 50 34.2 129 56.0 134 3.51 65
IAOF [50]92.6 13.0 129 29.2 118 3.37 128 23.7 158 27.4 160 6.45 149 16.4 125 28.7 101 3.46 101 22.7 118 33.1 61 8.37 121 43.4 55 55.6 60 10.0 28 27.6 60 50.1 85 4.97 33 38.3 95 82.7 108 4.08 50 30.0 47 46.8 47 3.56 85
TV-L1-improved [17]93.5 11.5 35 25.4 78 3.11 93 20.1 137 26.0 151 5.26 123 16.8 126 19.7 18 4.04 129 19.5 68 32.3 51 7.79 88 43.8 60 56.5 68 10.0 28 28.9 100 51.1 113 5.07 62 43.2 142 98.9 148 4.43 140 31.4 76 50.2 80 3.70 131
HBpMotionGpu [43]93.8 12.3 106 32.0 134 3.79 149 20.6 147 25.4 141 6.00 140 11.3 37 26.1 81 3.00 5 23.2 121 44.0 140 7.85 92 44.3 69 56.9 72 10.8 96 29.0 101 53.5 132 5.26 101 34.9 37 69.8 17 4.04 17 31.8 86 51.4 100 3.70 131
TVL1_ROB [138]93.9 11.9 68 26.4 92 3.70 145 21.7 153 25.8 145 6.06 141 12.0 73 25.7 75 3.46 101 23.1 120 36.3 101 8.35 119 43.0 42 54.5 41 10.1 40 28.2 78 50.0 84 5.10 79 41.3 131 91.4 136 4.24 129 29.7 44 44.8 31 3.56 85
Nguyen [33]95.2 12.0 75 25.9 85 3.37 128 21.2 150 24.5 121 6.27 146 12.7 100 28.0 96 3.70 107 23.8 126 34.7 79 8.58 127 43.0 42 54.7 48 10.1 40 27.7 65 50.7 104 4.97 33 43.4 144 93.7 140 4.43 140 30.2 53 47.4 51 3.56 85
GraphCuts [14]95.5 13.9 143 30.2 128 3.32 124 16.4 68 22.5 64 4.36 83 33.4 156 24.1 65 5.35 139 22.3 113 34.7 79 7.87 95 44.5 75 57.0 73 9.98 24 28.3 82 50.3 93 4.90 19 38.5 100 88.2 119 4.20 118 33.9 126 53.6 122 3.56 85
BriefMatch [124]95.9 12.1 89 29.2 118 3.11 93 16.5 73 22.5 64 6.61 151 18.0 133 22.7 48 5.69 142 26.2 135 35.5 90 18.2 158 43.7 58 54.7 48 10.4 74 29.6 118 50.2 88 5.94 152 35.8 55 72.5 40 4.16 111 32.1 98 50.2 80 3.56 85
FlowNet2 [122]97.0 19.1 154 47.5 155 3.11 93 17.1 83 24.1 110 4.55 92 14.2 115 29.8 116 3.37 81 23.8 126 42.9 136 8.33 117 45.9 112 58.1 93 10.6 88 27.6 60 49.4 77 4.93 26 39.2 108 81.0 97 4.08 50 31.6 82 49.2 72 3.56 85
TI-DOFE [24]98.4 12.7 123 27.6 105 3.87 153 22.2 156 25.3 137 6.66 152 14.1 114 25.3 74 4.36 131 27.7 142 38.7 118 9.06 141 42.7 36 53.6 35 10.1 40 26.8 42 48.8 72 4.97 33 38.3 95 76.0 62 4.24 129 31.9 90 44.7 29 3.87 152
AugFNG_ROB [143]99.0 13.7 138 36.6 142 3.00 77 17.5 93 22.9 76 4.80 104 14.3 117 36.0 143 3.37 81 27.8 143 64.0 155 7.96 104 48.6 153 63.0 150 11.4 149 28.0 70 51.6 120 4.83 15 36.1 67 76.6 69 4.08 50 31.9 90 47.2 50 3.42 19
ROF-ND [107]99.8 12.4 113 24.4 60 2.83 27 17.9 97 23.9 103 4.08 68 12.0 73 26.6 86 3.00 5 29.5 148 48.9 146 8.72 132 45.4 96 58.6 106 11.1 110 31.1 141 53.4 130 5.26 101 38.9 106 74.2 55 4.20 118 38.0 144 60.3 146 3.56 85
NL-TV-NCC [25]101.9 13.7 138 27.3 100 2.94 62 18.5 103 24.7 126 4.04 63 15.0 119 29.0 104 3.70 107 25.6 133 46.4 144 7.94 97 42.0 24 51.9 22 10.4 74 30.6 136 51.9 123 5.29 107 41.9 135 81.7 104 4.40 135 31.3 74 48.6 66 3.79 150
TriangleFlow [30]102.0 12.5 118 25.9 85 3.11 93 18.8 109 24.3 115 4.24 77 13.2 105 29.7 113 3.46 101 21.2 98 35.4 86 7.94 97 44.4 73 57.7 83 9.95 18 29.4 115 48.6 68 5.07 62 43.9 146 99.9 149 4.43 140 42.1 154 69.7 157 3.56 85
Correlation Flow [75]102.0 12.6 122 28.0 109 2.71 5 20.0 134 25.8 145 4.36 83 11.3 37 22.3 45 3.00 5 20.7 92 38.6 117 7.72 81 45.7 103 59.0 112 10.3 65 33.4 150 60.4 149 5.45 126 45.6 150 99.9 149 4.40 135 33.4 119 54.9 129 3.56 85
Complementary OF [21]102.3 12.4 113 34.5 139 2.83 27 16.4 68 23.5 94 3.79 44 30.7 148 32.2 130 7.05 151 19.9 77 43.9 139 7.44 22 46.9 138 60.4 133 10.7 93 28.1 74 47.7 58 5.23 97 41.1 127 80.3 93 4.12 103 42.0 152 62.0 150 3.56 85
LocallyOriented [52]103.2 12.2 97 28.1 110 3.27 122 20.5 145 25.9 148 5.07 115 14.3 117 30.0 118 3.37 81 24.2 129 41.7 133 7.66 66 44.7 78 57.1 77 10.1 40 28.8 96 47.4 52 5.48 134 42.4 137 80.6 95 4.12 103 32.4 105 51.2 95 3.56 85
IAOF2 [51]103.6 12.7 123 28.7 114 3.32 124 20.4 143 25.9 148 4.76 101 12.7 100 31.7 128 3.11 75 22.4 114 35.8 91 8.06 109 45.9 112 59.6 121 10.8 96 29.9 122 51.5 116 5.10 79 39.0 107 79.7 89 4.08 50 31.2 69 49.0 71 3.56 85
ContinualFlow_ROB [152]104.7 14.3 146 37.0 144 2.94 62 17.0 82 23.6 96 4.51 89 13.8 110 33.5 136 3.37 81 23.2 121 53.7 151 7.70 75 49.9 155 66.1 156 11.3 138 27.2 50 49.8 82 4.90 19 38.7 104 86.6 114 4.04 17 42.0 152 61.1 148 3.56 85
EPMNet [133]105.7 19.3 155 47.9 156 3.11 93 16.8 78 23.2 86 4.55 92 14.2 115 29.8 116 3.37 81 33.0 153 78.1 160 8.29 115 45.9 112 58.1 93 10.6 88 30.0 125 51.9 123 4.97 33 39.2 108 81.0 97 4.08 50 33.8 125 53.1 118 3.51 65
Aniso-Texture [82]106.3 11.5 35 24.1 49 2.83 27 20.2 138 26.0 151 4.97 111 20.0 140 24.4 68 3.37 81 26.9 138 50.7 148 9.11 142 46.1 117 60.5 135 11.4 149 32.7 149 62.2 154 5.94 152 37.3 83 80.2 91 4.04 17 34.1 128 55.0 130 3.42 19
ACK-Prior [27]107.8 12.5 118 29.7 123 2.83 27 16.1 61 22.7 70 4.00 60 25.6 144 27.7 92 5.72 144 22.4 114 36.0 93 10.7 148 45.7 103 59.3 114 11.4 149 31.8 146 50.6 100 5.35 120 38.8 105 79.9 90 4.16 111 33.5 120 51.7 104 3.70 131
IIOF-NLDP [131]108.3 12.9 126 29.0 117 2.71 5 18.6 106 24.8 129 4.08 68 13.4 107 26.7 87 3.00 5 21.9 109 39.8 123 8.16 112 45.8 107 59.4 116 10.4 74 31.6 145 59.9 146 6.06 156 54.7 159 99.9 149 6.03 158 35.7 138 57.2 139 3.42 19
Rannacher [23]108.6 11.7 49 28.7 114 3.16 121 20.4 143 26.3 155 5.07 115 19.0 138 26.0 79 4.80 135 19.8 73 38.1 111 7.79 88 44.5 75 57.4 80 10.1 40 29.0 101 50.3 93 5.20 89 42.6 140 97.0 145 4.40 135 33.7 123 55.9 133 3.70 131
LiteFlowNet [142]109.8 14.1 145 39.6 151 2.71 5 15.7 53 21.9 54 4.00 60 14.0 112 43.0 154 3.00 5 36.3 158 70.9 158 9.02 138 48.3 149 63.2 153 11.5 156 30.1 131 57.7 143 5.10 79 42.1 136 87.4 115 4.24 129 32.4 105 50.2 80 3.51 65
Learning Flow [11]110.3 12.1 89 24.6 65 3.27 122 19.7 127 25.2 136 5.00 112 39.7 158 47.7 159 7.68 153 24.6 131 35.0 83 8.19 114 45.2 92 58.6 106 10.5 87 28.4 84 48.0 61 5.45 126 38.4 97 77.8 82 4.40 135 32.6 113 48.4 62 3.92 154
2bit-BM-tele [98]111.2 11.7 49 27.0 98 3.79 149 20.2 138 26.3 155 5.07 115 12.0 73 23.2 56 4.00 124 21.2 98 36.1 95 8.16 112 45.3 93 58.0 90 10.3 65 34.0 154 61.8 151 5.92 149 54.1 158 99.9 149 5.72 156 29.8 45 47.4 51 3.74 147
SimpleFlow [49]112.5 12.0 75 24.0 47 2.94 62 18.5 103 24.4 118 4.24 77 32.7 151 39.0 147 5.69 142 18.0 36 36.2 99 7.55 43 46.9 138 60.8 136 11.1 110 31.4 144 58.1 144 5.35 120 49.4 154 99.9 149 5.16 154 40.0 148 63.0 153 3.46 50
FOLKI [16]112.6 13.0 129 30.9 131 4.97 158 22.2 156 24.9 133 9.00 158 17.3 130 33.0 134 7.00 148 33.4 154 38.7 118 17.0 156 44.3 69 55.8 61 10.4 74 27.6 60 49.7 79 5.48 134 36.2 70 74.2 55 4.80 148 30.4 58 44.9 33 4.08 156
ResPWCR_ROB [144]113.6 12.9 126 34.8 140 2.94 62 17.1 83 24.0 106 4.36 83 16.8 126 31.4 127 3.37 81 25.7 134 57.3 153 8.29 115 46.7 131 60.8 136 11.2 119 29.9 122 58.2 145 5.92 149 35.6 47 74.0 51 4.20 118 36.6 141 60.5 147 3.56 85
SILK [79]113.9 13.3 134 30.7 130 3.83 152 22.0 155 25.3 137 7.16 153 34.7 157 40.0 149 7.77 155 26.6 136 36.6 102 8.60 129 45.1 89 57.9 88 10.0 28 28.4 84 50.9 110 6.03 155 34.8 31 71.8 33 4.51 144 31.4 76 48.0 59 3.74 147
StereoFlow [44]115.2 22.8 160 48.3 157 3.74 148 20.5 145 26.8 158 5.07 115 11.3 37 29.3 109 3.37 81 20.1 81 37.0 104 7.62 58 59.3 158 75.2 158 10.8 96 39.3 160 71.4 159 5.45 126 35.8 55 73.9 50 4.08 50 35.7 138 55.1 132 3.70 131
H+S_ROB [137]115.6 13.7 138 27.7 107 3.11 93 18.8 109 22.6 66 5.80 133 33.0 153 43.0 154 8.00 156 26.7 137 33.6 66 9.04 140 44.2 66 56.3 66 10.4 74 27.8 66 48.6 68 5.35 120 43.7 145 99.9 149 5.10 153 37.1 142 58.3 142 3.70 131
StereoOF-V1MT [119]117.4 13.7 138 32.7 135 3.00 77 18.7 107 23.6 96 4.80 104 21.8 143 28.0 96 5.07 138 31.6 149 40.6 129 9.57 144 46.5 125 58.9 111 11.5 156 29.2 109 50.2 88 6.45 159 42.4 137 94.7 141 4.80 148 31.4 76 48.3 61 3.46 50
OFRF [134]117.5 14.4 147 38.4 149 3.70 145 19.9 132 25.3 137 5.48 128 13.0 104 33.0 134 3.11 75 20.7 92 38.4 114 7.79 88 47.8 146 61.4 142 10.9 102 31.9 147 56.8 140 5.29 107 41.5 132 90.5 132 4.08 50 34.4 132 54.7 126 3.42 19
Shiralkar [42]117.5 13.2 133 31.6 133 3.00 77 19.7 127 24.5 121 4.65 97 17.0 128 30.7 123 4.08 130 32.1 151 53.1 150 8.04 105 46.3 122 59.7 123 10.3 65 28.4 84 50.2 88 5.45 126 45.5 149 95.2 143 4.24 129 39.2 147 62.6 151 3.42 19
Dynamic MRF [7]119.7 12.1 89 26.8 96 2.94 62 18.0 100 23.9 103 4.16 74 18.3 135 30.7 123 5.00 136 28.9 145 39.8 123 10.5 147 45.9 112 58.6 106 11.2 119 30.9 139 56.0 139 5.80 148 43.0 141 90.3 130 4.65 146 33.7 123 51.8 106 3.70 131
Adaptive flow [45]120.7 13.4 135 25.8 84 4.51 155 21.8 154 25.4 141 7.26 154 13.7 108 27.5 91 4.69 133 24.1 128 35.2 85 8.76 136 47.3 142 61.5 143 10.2 60 33.8 153 61.9 152 5.45 126 35.9 60 73.2 46 4.20 118 34.7 135 54.7 126 3.70 131
UnFlow [129]123.1 14.9 149 40.2 152 3.11 93 18.5 103 23.4 90 5.48 128 15.3 120 31.3 126 4.36 131 22.8 119 38.0 110 8.45 123 48.3 149 63.0 150 10.9 102 32.4 148 62.0 153 5.72 143 35.4 42 71.2 26 4.32 133 45.5 157 66.0 156 3.87 152
SPSA-learn [13]125.7 12.3 106 33.7 138 3.37 128 19.2 117 23.6 96 5.45 127 30.0 147 39.7 148 7.00 148 26.9 138 41.3 131 8.41 122 46.7 131 60.1 127 10.2 60 29.4 115 50.6 100 5.20 89 53.7 157 99.9 149 8.43 160 51.4 159 72.0 159 3.51 65
SegOF [10]128.1 12.3 106 33.1 136 3.11 93 17.9 97 23.8 101 4.51 89 29.0 146 34.3 139 6.16 145 32.8 152 78.9 161 8.33 117 48.1 147 63.6 154 11.2 119 28.5 91 54.3 135 5.72 143 44.6 147 99.9 149 4.97 151 37.9 143 61.4 149 3.51 65
WRT [150]128.3 13.0 129 29.4 120 2.83 27 18.8 109 23.5 94 4.69 98 32.7 151 30.0 118 6.73 146 24.7 132 39.3 122 9.02 138 47.4 145 61.7 145 10.4 74 34.4 155 63.1 156 5.92 149 57.2 160 99.9 149 7.68 159 49.8 158 72.2 160 3.56 85
HCIC-L [99]128.6 21.0 159 41.8 153 5.07 159 20.2 138 26.1 154 5.80 133 16.3 124 42.3 151 4.00 124 31.7 150 51.0 149 8.50 124 44.7 78 55.5 58 10.4 74 35.2 157 69.8 158 5.07 62 39.9 119 91.2 135 4.16 111 40.4 151 58.0 140 3.65 126
FFV1MT [106]130.5 17.0 152 37.6 148 3.37 128 19.3 119 22.9 76 6.40 148 28.2 145 46.7 158 6.95 147 29.3 146 38.4 114 11.4 152 46.3 122 58.2 99 10.4 74 29.0 101 50.4 95 5.72 143 46.7 151 88.5 121 4.93 150 39.0 146 56.9 138 4.43 158
PGAM+LK [55]130.9 15.5 151 39.4 150 4.55 156 19.8 130 24.0 106 7.68 155 33.1 155 43.4 156 8.00 156 34.5 156 45.7 143 11.2 151 46.6 129 57.7 83 10.6 88 29.3 110 50.8 109 5.74 147 37.4 84 77.2 76 4.43 140 34.4 132 53.3 121 4.24 157
Heeger++ [104]132.0 19.8 156 44.7 154 3.11 93 18.9 113 22.8 72 6.45 149 33.0 153 35.2 140 7.16 152 29.3 146 38.4 114 11.4 152 51.5 156 65.2 155 11.3 138 28.4 84 46.9 45 6.78 160 47.9 153 84.5 113 4.69 147 40.1 149 58.8 144 3.70 131
SLK [47]133.1 13.9 143 29.9 125 3.79 149 20.0 134 22.8 72 6.22 144 32.0 150 33.7 137 7.72 154 33.4 154 46.4 144 16.1 155 48.5 152 61.7 145 10.3 65 28.4 84 47.9 60 5.72 143 43.2 142 97.9 146 4.97 151 38.7 145 59.8 145 4.04 155
WOLF_ROB [148]141.8 19.8 156 50.0 159 3.37 128 21.0 149 25.8 145 5.42 126 21.7 141 43.4 156 3.37 81 28.0 144 54.1 152 8.54 125 48.3 149 62.7 149 11.3 138 33.4 150 60.0 147 5.57 139 49.5 155 99.9 149 4.40 135 40.3 150 64.3 154 3.65 126
Pyramid LK [2]142.8 14.4 147 37.3 146 4.93 157 23.7 158 25.3 137 9.98 160 42.2 159 35.7 141 12.3 159 56.2 160 64.2 156 35.8 160 65.6 159 83.9 159 10.6 88 28.1 74 46.1 39 5.48 134 45.2 148 99.9 149 5.89 157 53.6 160 75.1 161 5.42 159
GroupFlow [9]143.9 19.9 158 49.6 158 3.42 136 19.1 115 24.1 110 5.48 128 31.4 149 40.0 149 8.19 158 36.2 157 61.9 154 12.1 154 55.6 157 71.3 157 11.4 149 36.3 158 67.0 157 5.60 141 46.7 151 98.5 147 4.20 118 43.6 155 62.8 152 3.56 85
Periodicity [78]158.2 17.6 153 55.7 160 5.45 160 26.8 160 27.0 159 9.75 159 49.4 161 51.5 161 17.7 160 51.3 159 70.3 157 27.9 159 66.6 160 86.3 160 11.7 160 38.7 159 82.5 160 6.38 158 51.8 156 99.9 149 5.48 155 44.3 156 65.5 155 5.80 160
AVG_FLOW_ROB [141]160.2 64.1 161 67.2 161 12.2 161 44.0 161 47.3 161 16.5 161 48.3 160 50.5 160 29.0 161 68.4 161 77.2 159 51.4 161 78.9 161 90.3 161 20.4 161 80.7 161 99.9 161 17.7 161 73.1 161 99.9 149 14.0 161 64.2 161 71.2 158 16.7 161
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] CtxSyn 0.07 2 color S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[137] 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.
[138] 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.
[139] 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.
[140] 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.
[141] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[142] 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.
[143] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[144] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[145] 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.
[146] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[147] 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.
[148] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[149] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
[150] WRT 9 2 color L. Mei, J. Lai, X. Xie, J. Zhu, and J. Chen. Illumination-invariance optical flow estimation using weighted regularization transform. Submitted to IEEE TCSVT 2018.
[151] EAI-Flow 2.1 2 color Anonymous. Hierarchical coherency sensitive hashing and interpolation with RANSAC for large displacement optical flow. CVIU 2018 submission 17-678.
[152] ContinualFlow_ROB 0.5 all color M Neoral, J. Sochman, and J. Matas. Continual occlusions and optical flow estimation. ACCV 2018.
[153] CyclicGen 0.088 2 color Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
[154] TOF-M 0.393 2 color T. Xue, B. Chen, J. Wu, D. Wei, and W. Freeman. Video enhancement with task-oriented flow. arXiv 1711.09078, 2017.
[155] MEMC-Net+ 0.16 2 color W. Bao, W.-S. Lai, X. Zhang, Z. Gao, and M.-H. Yang. (Interpolation results only.) MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement. Submitted to TPAMI 2018.
[156] CFRF 0.128 2 color Anonymous. (Interpolation results only.) Coarse-to-fine refinement framework for video frame interpolation. CVPR 2019 submission 1992.
[157] MPRN 0.32 4 color Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[158] DAIN 0.13 2 color Anonymous. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019 submission 1769.
[159] PyrWarp 0.14 2 color Anonymous. (Interpolation results only.) Feature pyramid warping for video frame interpolation. CVPR 2019 submission 868.
[160] InterpCNN 0.65 2 color Anonymous. (Interpolation results only.) Video frame interpolation with a stack of synthesis networks and intermediate optical flows. CVPR 2019 submission 6533.
[161] OFRI 0.31 2 color Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
* 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.