Optical flow evaluation results Statistics:     Average   SD   R0.5   R1.0   R2.0   A90   A95   A99  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
R0.5
normalized interpolation
error
avg. Mequon
(Hidden texture)
im0   GT   im1
Schefflera
(Hidden texture)
im0   GT   im1
Urban
(Synthetic)
im0   GT   im1
Teddy
(Stereo)
im0   GT   im1
Backyard
(High-speed camera)
im0   GT   im1
Basketball
(High-speed camera)
im0   GT   im1
Dumptruck
(High-speed camera)
im0   GT   im1
Evergreen
(High-speed camera)
im0   GT   im1
rank all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext
MDP-Flow2 [68]9.7 35.7 2 30.6 2 47.8 8 25.9 10 30.5 10 36.9 3 28.6 3 29.8 5 38.5 2 51.9 7 46.5 15 80.3 10 71.9 4 66.6 3 87.2 8 68.6 5 53.9 23 82.1 34 28.1 2 43.6 8 42.4 10 36.6 26 55.6 27 50.0 6
PMMST [114]10.8 35.8 4 30.8 3 47.9 18 26.5 31 31.0 20 37.3 36 28.6 3 29.9 6 38.4 1 51.7 3 46.0 5 80.2 5 72.0 9 66.7 8 87.3 16 68.5 1 53.3 7 82.0 13 28.1 2 43.7 13 42.4 10 36.5 17 55.5 22 50.0 6
PH-Flow [101]11.4 36.1 20 32.5 29 47.8 8 25.6 4 29.6 4 36.9 3 28.7 9 30.0 8 38.5 2 51.6 1 45.5 1 80.2 5 71.9 4 66.7 8 87.3 16 68.8 33 54.8 64 81.9 5 28.1 2 43.6 8 42.4 10 36.4 11 55.3 13 50.0 6
NNF-Local [87]12.0 35.7 2 31.4 6 47.6 3 25.5 2 29.6 4 36.9 3 28.6 3 29.9 6 38.5 2 52.4 30 48.0 61 80.3 10 72.0 9 66.6 3 87.4 34 68.7 19 54.4 44 82.0 13 28.1 2 43.5 6 42.4 10 36.2 4 55.0 6 50.0 6
NN-field [71]16.9 36.0 15 32.2 18 47.9 18 25.5 2 29.3 3 36.8 1 29.4 59 29.7 4 39.0 42 52.4 30 48.1 67 80.3 10 72.0 9 66.7 8 87.3 16 68.7 19 54.0 28 82.0 13 28.1 2 43.4 4 42.4 10 36.4 11 55.2 10 50.0 6
IROF++ [58]20.4 36.2 27 33.0 42 47.8 8 26.1 15 30.9 17 36.9 3 29.1 29 31.0 29 38.9 27 51.6 1 45.6 2 80.4 19 72.0 9 66.8 17 87.2 8 68.6 5 53.4 8 82.2 55 28.3 16 44.6 38 42.4 10 36.5 17 55.3 13 50.4 74
ProbFlowFields [128]20.8 35.9 9 32.4 23 48.0 27 25.8 8 30.5 10 37.2 31 28.6 3 30.3 11 38.5 2 52.1 20 46.4 11 80.7 54 72.3 64 67.1 65 87.5 77 68.6 5 53.8 15 82.1 34 28.0 1 42.8 1 42.3 1 36.1 2 54.6 2 50.1 24
Sparse-NonSparse [56]22.0 36.2 27 32.8 36 48.0 27 25.9 10 30.4 8 37.0 11 29.0 22 30.9 26 38.8 12 52.0 13 46.1 7 80.6 41 72.1 24 66.8 17 87.3 16 68.9 43 54.6 55 82.1 34 28.3 16 44.0 21 42.4 10 36.4 11 55.4 17 50.1 24
CombBMOF [113]23.4 35.9 9 31.0 4 47.8 8 25.8 8 30.5 10 36.8 1 29.2 36 30.8 23 39.5 78 52.4 30 47.4 41 80.3 10 72.1 24 66.8 17 87.4 34 68.9 43 54.5 48 82.1 34 28.5 56 44.6 38 42.3 1 36.0 1 54.6 2 50.0 6
nLayers [57]25.2 36.4 51 32.0 13 48.2 55 26.0 13 30.4 8 37.3 36 28.7 9 29.4 2 38.8 12 52.2 27 46.8 22 80.4 19 72.3 64 67.1 65 87.4 34 68.8 33 54.7 58 82.0 13 28.3 16 43.7 13 42.4 10 36.4 11 55.4 17 49.9 3
AGIF+OF [85]25.2 36.2 27 32.8 36 47.9 18 26.1 15 30.8 14 37.1 18 29.0 22 30.7 19 38.9 27 51.8 5 46.2 9 80.1 3 72.3 64 67.2 77 87.3 16 68.9 43 55.2 80 81.9 5 28.3 16 43.6 8 42.4 10 36.6 26 56.0 44 49.9 3
2DHMM-SAS [92]26.8 36.4 51 33.9 78 47.9 18 27.1 55 32.6 42 37.0 11 28.5 2 30.4 14 38.9 27 51.8 5 45.6 2 80.4 19 72.1 24 66.9 29 87.4 34 68.8 33 54.5 48 82.0 13 28.3 16 44.2 26 42.3 1 36.7 38 56.1 52 50.0 6
NNF-EAC [103]27.5 36.3 40 32.4 23 48.0 27 26.6 34 31.7 30 37.1 18 29.3 46 30.2 9 39.0 42 52.4 30 46.9 25 81.1 95 72.0 9 66.7 8 87.4 34 68.7 19 53.7 14 82.1 34 28.2 11 43.9 16 42.4 10 36.7 38 55.9 41 50.0 6
Layers++ [37]28.1 36.3 40 32.4 23 48.2 55 25.7 5 29.2 2 37.3 36 28.9 18 30.6 16 38.9 27 52.0 13 46.4 11 80.4 19 72.2 36 67.0 42 87.5 77 68.9 43 55.2 80 82.0 13 28.3 16 44.0 21 42.4 10 36.6 26 55.5 22 50.1 24
LSM [39]29.4 36.3 40 33.7 68 48.0 27 26.1 15 31.0 20 37.0 11 29.1 29 31.8 44 38.9 27 52.2 27 46.9 25 80.6 41 72.1 24 66.9 29 87.3 16 69.0 57 54.9 67 82.1 34 28.3 16 44.1 24 42.4 10 36.5 17 55.7 31 50.0 6
ComponentFusion [96]29.9 36.0 15 32.2 18 48.0 27 26.1 15 31.1 25 36.9 3 29.1 29 32.3 52 38.8 12 52.0 13 47.0 29 80.3 10 72.2 36 67.1 65 87.3 16 68.7 19 53.9 23 82.1 34 28.5 56 46.1 90 42.4 10 36.7 38 55.8 38 50.2 44
FlowFields [110]30.2 36.0 15 32.7 33 47.9 18 26.4 29 32.0 32 37.3 36 29.0 22 32.6 58 38.7 8 52.5 35 47.9 58 80.7 54 72.3 64 67.0 42 87.5 77 68.6 5 54.4 44 82.0 13 28.2 11 44.0 21 42.4 10 36.3 6 55.2 10 50.1 24
TV-L1-MCT [64]30.9 36.8 82 34.7 98 48.2 55 26.7 35 32.4 39 37.3 36 28.6 3 30.9 26 39.0 42 51.9 7 45.7 4 80.5 35 72.2 36 67.0 42 87.3 16 68.6 5 53.0 4 82.3 69 28.3 16 44.4 31 42.4 10 36.1 2 54.9 5 50.2 44
S2F-IF [123]31.0 35.9 9 32.5 29 47.8 8 26.2 22 31.6 29 37.2 31 29.0 22 31.9 49 38.6 7 52.3 29 47.6 46 80.4 19 72.4 89 67.2 77 87.5 77 68.7 19 54.5 48 81.9 5 28.4 37 44.7 43 42.4 10 36.3 6 55.2 10 50.1 24
WLIF-Flow [93]31.7 36.1 20 32.5 29 47.8 8 26.3 27 31.2 26 37.1 18 29.1 29 30.7 19 39.1 49 52.0 13 46.4 11 80.6 41 72.1 24 66.8 17 87.4 34 69.0 57 54.9 67 82.3 69 28.3 16 43.9 16 42.5 60 36.8 45 55.9 41 50.1 24
LME [70]33.9 35.8 4 31.0 4 47.8 8 26.9 45 32.2 35 38.4 83 29.2 36 32.6 58 38.8 12 51.9 7 46.7 20 80.4 19 72.6 109 67.4 101 87.7 117 68.8 33 54.9 67 82.0 13 28.1 2 43.5 6 42.4 10 36.3 6 55.3 13 50.0 6
COFM [59]34.1 36.1 20 32.0 13 48.1 41 26.1 15 30.8 14 37.1 18 28.8 12 30.3 11 38.8 12 51.7 3 46.0 5 80.0 1 72.2 36 67.2 77 87.2 8 68.9 43 56.1 106 81.7 1 28.1 2 42.8 1 43.1 114 37.1 76 56.9 85 50.7 104
FMOF [94]34.9 36.5 59 33.7 68 48.2 55 25.9 10 30.3 7 37.1 18 29.3 46 30.7 19 39.0 42 52.5 35 47.5 42 80.2 5 72.2 36 67.0 42 87.5 77 69.0 57 55.1 77 82.0 13 28.1 2 43.4 4 42.4 10 36.8 45 56.0 44 50.1 24
DeepFlow2 [108]34.9 36.2 27 32.4 23 48.2 55 27.1 55 32.9 46 37.8 68 29.2 36 32.9 65 39.0 42 52.5 35 47.5 42 80.5 35 72.2 36 66.9 29 87.5 77 68.5 1 52.9 3 82.1 34 28.3 16 44.4 31 42.4 10 36.4 11 55.4 17 50.2 44
RNLOD-Flow [121]35.2 36.3 40 33.5 58 48.0 27 26.8 40 32.6 42 37.1 18 29.2 36 31.8 44 38.8 12 52.1 20 46.9 25 80.2 5 72.2 36 67.0 42 87.3 16 69.0 57 55.2 80 82.1 34 28.3 16 44.2 26 42.4 10 37.1 76 56.9 85 49.8 1
OFLAF [77]35.4 35.8 4 31.5 7 47.8 8 25.7 5 29.8 6 37.0 11 29.0 22 31.2 32 38.7 8 52.0 13 46.8 22 80.1 3 72.4 89 67.3 91 87.4 34 68.9 43 55.3 85 82.0 13 28.6 73 45.4 76 42.4 10 37.1 76 57.1 95 50.1 24
DeepFlow [86]36.4 36.1 20 31.8 11 48.1 41 27.3 60 32.9 46 38.4 83 29.3 46 33.3 78 39.1 49 52.6 47 47.0 29 80.7 54 72.2 36 66.8 17 87.5 77 68.7 19 52.8 2 82.5 94 28.1 2 43.6 8 42.3 1 36.2 4 55.0 6 50.2 44
Ramp [62]37.2 36.5 59 34.0 83 48.2 55 26.0 13 30.8 14 37.1 18 28.9 18 30.8 23 38.8 12 51.9 7 46.1 7 80.4 19 72.2 36 67.0 42 87.4 34 69.1 67 55.4 91 82.2 55 28.4 37 44.7 43 42.4 10 36.8 45 56.2 60 50.2 44
MDP-Flow [26]37.4 35.8 4 31.5 7 48.0 27 26.2 22 31.4 28 37.4 47 29.0 22 31.1 30 38.9 27 52.7 56 47.8 55 80.7 54 72.2 36 66.9 29 87.5 77 68.9 43 55.2 80 82.1 34 28.5 56 45.3 75 42.5 60 36.3 6 55.4 17 50.0 6
IROF-TV [53]38.4 36.3 40 33.6 64 48.2 55 26.2 22 31.0 20 37.0 11 29.3 46 33.6 84 39.1 49 51.9 7 46.5 15 80.8 67 72.3 64 67.0 42 87.6 108 68.5 1 53.9 23 81.9 5 28.3 16 44.9 55 42.3 1 36.6 26 55.6 27 50.4 74
PGM-C [120]38.6 36.2 27 33.3 51 48.1 41 26.5 31 32.2 35 37.5 54 29.2 36 32.9 65 38.8 12 52.5 35 48.3 80 80.7 54 72.3 64 67.0 42 87.5 77 68.6 5 54.0 28 82.0 13 28.3 16 44.6 38 42.4 10 36.5 17 55.5 22 50.4 74
Classic+NL [31]38.9 36.5 59 34.0 83 48.2 55 26.2 22 30.9 17 37.1 18 28.8 12 30.6 16 38.8 12 52.1 20 46.5 15 80.6 41 72.2 36 67.0 42 87.4 34 69.2 77 55.3 85 82.2 55 28.4 37 44.6 38 42.4 10 36.8 45 56.2 60 50.2 44
DF-Auto [115]39.4 36.8 82 31.9 12 48.9 92 28.5 85 33.7 64 40.8 97 28.8 12 30.3 11 38.7 8 52.5 35 47.3 35 80.4 19 72.1 24 66.7 8 87.4 34 68.6 5 53.8 15 82.0 13 28.4 37 44.7 43 42.5 60 36.8 45 56.3 65 50.2 44
FC-2Layers-FF [74]41.5 36.4 51 33.8 74 48.1 41 25.7 5 29.1 1 37.4 47 28.9 18 30.9 26 38.8 12 52.1 20 46.8 22 80.6 41 72.3 64 67.2 77 87.4 34 69.1 67 55.5 93 82.1 34 28.4 37 44.7 43 42.5 60 36.9 59 56.3 65 50.0 6
SuperFlow [81]42.1 36.5 59 32.2 18 48.8 89 28.3 80 33.4 59 40.9 98 29.5 68 32.6 58 39.4 71 52.5 35 46.7 20 80.9 75 72.2 36 66.9 29 87.5 77 68.5 1 53.4 8 82.0 13 28.3 16 44.7 43 42.4 10 36.3 6 55.4 17 50.1 24
HAST [109]42.8 36.1 20 31.7 9 48.1 41 26.1 15 31.0 20 37.0 11 29.3 46 31.7 41 39.2 60 51.9 7 46.5 15 80.3 10 72.3 64 67.3 91 87.2 8 69.3 88 56.4 114 82.0 13 28.4 37 45.0 62 42.5 60 37.3 89 57.3 99 50.0 6
CPM-Flow [116]43.4 36.2 27 33.5 58 48.1 41 26.5 31 32.2 35 37.5 54 29.3 46 32.6 58 38.9 27 52.7 56 48.7 93 80.7 54 72.3 64 67.0 42 87.5 77 68.7 19 53.8 15 82.2 55 28.4 37 44.7 43 42.4 10 36.5 17 55.5 22 50.3 61
Second-order prior [8]43.6 36.2 27 32.1 16 48.1 41 27.9 74 34.1 70 37.4 47 29.9 84 34.6 99 39.7 88 52.4 30 47.2 33 80.6 41 71.9 4 66.6 3 87.5 77 68.7 19 54.0 28 82.1 34 28.5 56 45.2 73 42.4 10 36.5 17 55.7 31 50.2 44
Aniso. Huber-L1 [22]44.5 36.7 76 33.5 58 48.6 83 28.5 85 34.3 73 38.2 79 29.3 46 31.8 44 38.9 27 52.5 35 47.5 42 80.6 41 72.0 9 66.7 8 87.4 34 68.6 5 54.3 40 81.9 5 28.5 56 45.0 62 42.4 10 36.8 45 56.0 44 50.3 61
Classic+CPF [83]44.7 36.4 51 33.6 64 47.9 18 26.3 27 31.3 27 37.0 11 28.8 12 31.1 30 38.9 27 52.0 13 46.5 15 80.0 1 72.5 101 67.4 101 87.4 34 69.2 77 56.1 106 82.0 13 28.6 73 45.2 73 42.4 10 37.2 83 57.3 99 50.0 6
RFlow [90]45.8 36.2 27 33.0 42 48.2 55 27.6 66 33.7 64 37.1 18 29.3 46 32.5 57 39.2 60 52.6 47 47.8 55 80.6 41 72.0 9 66.8 17 87.3 16 68.6 5 53.8 15 81.9 5 28.5 56 45.5 81 42.6 88 37.2 83 56.9 85 50.3 61
EpicFlow [102]45.9 36.2 27 33.3 51 48.1 41 26.9 45 33.1 52 37.5 54 29.4 59 33.0 70 39.0 42 52.6 47 48.5 84 80.8 67 72.3 64 67.0 42 87.5 77 68.6 5 54.1 32 82.0 13 28.4 37 44.8 52 42.4 10 36.6 26 55.7 31 50.4 74
Brox et al. [5]46.7 36.3 40 32.4 23 48.2 55 27.8 72 34.1 70 38.0 76 29.8 80 33.9 90 39.6 86 52.5 35 47.0 29 80.4 19 72.2 36 66.9 29 87.5 77 68.7 19 53.8 15 82.1 34 28.4 37 44.9 55 42.5 60 36.5 17 55.5 22 50.2 44
S2D-Matching [84]47.4 36.6 68 34.2 89 48.2 55 26.9 45 32.5 41 37.2 31 28.8 12 30.7 19 38.9 27 52.1 20 46.4 11 80.9 75 72.3 64 67.1 65 87.5 77 69.1 67 55.3 85 82.2 55 28.5 56 44.7 43 42.4 10 36.7 38 55.9 41 50.2 44
FESL [72]48.2 36.6 68 33.9 78 48.0 27 26.4 29 31.7 30 37.3 36 29.1 29 31.3 33 38.9 27 52.6 47 47.6 46 80.3 10 72.4 89 67.3 91 87.4 34 69.3 88 55.9 101 82.1 34 28.4 37 44.9 55 42.3 1 37.0 66 56.6 76 50.1 24
p-harmonic [29]48.2 35.9 9 32.1 16 47.9 18 28.2 77 34.3 73 37.8 68 29.4 59 34.2 94 39.4 71 53.0 78 47.7 51 80.7 54 72.2 36 67.0 42 87.3 16 68.8 33 54.1 32 82.3 69 28.5 56 45.5 81 42.4 10 36.6 26 56.0 44 50.2 44
SepConv-v1 [127]49.0 27.1 1 27.5 1 36.4 1 24.9 1 31.0 20 40.3 92 27.6 1 28.4 1 48.9 126 54.0 102 47.3 35 83.0 117 72.0 9 66.7 8 87.1 3 69.1 67 52.6 1 83.6 122 32.2 128 43.9 16 55.7 128 37.0 66 53.8 1 55.4 128
ComplOF-FED-GPU [35]49.3 36.3 40 33.4 55 48.0 27 26.8 40 33.0 49 37.3 36 30.4 98 34.0 91 39.6 86 52.5 35 48.1 67 80.9 75 72.1 24 66.8 17 87.4 34 68.7 19 54.3 40 82.1 34 28.5 56 45.1 68 42.5 60 36.8 45 56.0 44 50.2 44
TC-Flow [46]50.0 36.2 27 33.2 48 48.2 55 26.9 45 33.5 61 37.5 54 29.5 68 33.6 84 38.9 27 52.1 20 47.1 32 80.6 41 72.3 64 67.2 77 87.5 77 69.0 57 54.8 64 82.3 69 28.4 37 44.4 31 42.5 60 36.6 26 56.1 52 50.1 24
EPPM w/o HM [88]50.5 35.8 4 32.3 22 47.6 3 26.7 35 33.0 49 36.9 3 30.0 87 35.5 109 39.4 71 52.6 47 48.9 98 80.4 19 72.2 36 67.1 65 87.4 34 69.3 88 55.9 101 82.3 69 28.4 37 44.9 55 42.5 60 36.8 45 56.1 52 50.1 24
DPOF [18]51.1 36.7 76 34.5 93 48.6 83 26.1 15 30.6 13 37.6 60 29.8 80 31.4 34 39.3 66 52.8 66 48.6 87 80.8 67 72.0 9 66.8 17 87.3 16 69.1 67 55.3 85 81.9 5 28.5 56 44.5 35 42.5 60 36.9 59 56.5 72 50.0 6
OFH [38]52.6 36.4 51 33.8 74 48.2 55 27.4 62 33.3 57 37.4 47 29.7 75 35.0 104 39.0 42 52.5 35 48.3 80 80.9 75 72.2 36 67.0 42 87.4 34 68.7 19 54.2 38 82.1 34 28.6 73 45.4 76 42.5 60 36.6 26 56.0 44 50.1 24
Efficient-NL [60]53.0 36.5 59 33.6 64 48.0 27 26.7 35 32.0 32 37.1 18 29.9 84 31.4 34 39.3 66 52.7 56 47.7 51 80.4 19 72.2 36 67.0 42 87.3 16 69.5 99 57.0 118 81.9 5 28.6 73 45.9 87 42.4 10 37.9 105 58.1 112 50.1 24
Local-TV-L1 [65]54.6 37.5 98 33.0 42 49.7 104 29.3 97 34.5 81 40.3 92 29.2 36 31.6 39 39.1 49 53.3 89 47.3 35 83.1 120 72.1 24 66.9 29 87.4 34 69.3 88 53.4 8 83.2 116 28.2 11 43.9 16 42.4 10 36.4 11 55.1 8 50.4 74
PMF [73]54.8 35.9 9 32.0 13 47.7 6 26.9 45 33.5 61 36.9 3 29.6 73 34.5 97 39.1 49 52.5 35 47.8 55 80.4 19 72.5 101 67.5 107 87.4 34 69.2 77 55.0 75 82.4 83 28.5 56 45.0 62 42.5 60 37.3 89 57.3 99 50.0 6
OAR-Flow [125]55.5 36.5 59 33.0 42 48.4 73 27.0 51 33.0 49 37.8 68 29.2 36 33.3 78 38.9 27 52.1 20 47.6 46 80.5 35 72.4 89 67.3 91 87.6 108 68.9 43 54.5 48 82.2 55 28.5 56 44.7 43 42.4 10 36.9 59 56.5 72 50.4 74
TC/T-Flow [76]55.5 36.6 68 33.7 68 47.9 18 26.8 40 32.9 46 37.1 18 29.1 29 31.9 49 38.8 12 52.7 56 48.5 84 80.4 19 72.5 101 67.4 101 87.5 77 69.1 67 55.2 80 82.1 34 28.6 73 45.4 76 42.5 60 37.0 66 56.9 85 50.0 6
Sparse Occlusion [54]55.6 36.5 59 33.7 68 48.2 55 27.6 66 34.1 70 37.3 36 29.3 46 31.8 44 38.8 12 52.8 66 48.1 67 80.5 35 72.3 64 67.1 65 87.4 34 69.2 77 56.1 106 82.0 13 28.5 56 45.4 76 42.3 1 37.2 83 57.0 91 50.2 44
TF+OM [100]56.0 36.3 40 33.0 42 48.5 76 26.9 45 32.2 35 39.2 87 28.6 3 32.4 55 38.9 27 52.8 66 48.2 78 80.7 54 72.3 64 67.1 65 87.4 34 69.0 57 54.5 48 82.3 69 28.4 37 45.1 68 42.5 60 37.0 66 56.4 69 50.6 98
SRR-TVOF-NL [91]56.3 36.6 68 33.5 58 48.2 55 27.7 68 34.3 73 37.9 72 29.5 68 33.2 74 39.1 49 53.1 82 48.1 67 80.2 5 72.2 36 67.1 65 87.3 16 68.9 43 55.7 97 81.8 3 28.5 56 44.9 55 42.4 10 37.5 96 58.0 111 50.1 24
SIOF [67]57.5 36.7 76 34.1 85 48.2 55 29.1 93 35.4 99 39.7 89 29.4 59 32.9 65 39.1 49 52.7 56 47.7 51 80.9 75 71.9 4 66.6 3 87.4 34 69.1 67 54.3 40 82.4 83 28.3 16 44.6 38 42.4 10 37.3 89 56.8 82 50.3 61
CLG-TV [48]57.7 36.6 68 33.4 55 48.5 76 28.2 77 34.4 78 38.2 79 29.7 75 33.6 84 39.4 71 52.8 66 48.0 61 80.9 75 72.2 36 66.9 29 87.5 77 68.7 19 54.0 28 82.1 34 28.4 37 45.1 68 42.4 10 37.0 66 56.5 72 50.2 44
ALD-Flow [66]57.8 36.7 76 33.9 78 48.6 83 27.0 51 33.2 54 37.9 72 29.3 46 33.4 81 38.9 27 52.5 35 48.0 61 80.9 75 72.4 89 67.2 77 87.6 108 68.9 43 54.4 44 82.2 55 28.2 11 43.6 8 42.4 10 37.0 66 56.6 76 50.3 61
SimpleFlow [49]58.5 36.5 59 34.2 89 48.2 55 27.2 58 32.8 45 37.3 36 30.1 93 31.7 41 39.4 71 52.0 13 46.3 10 80.7 54 72.3 64 67.2 77 87.4 34 69.0 57 55.4 91 82.0 13 28.7 84 47.1 101 42.6 88 37.0 66 56.8 82 50.1 24
Complementary OF [21]58.9 36.1 20 33.3 51 47.8 8 26.7 35 33.2 54 37.3 36 30.4 98 32.9 65 39.5 78 52.8 66 48.7 93 81.1 95 72.3 64 67.2 77 87.3 16 68.8 33 54.7 58 82.2 55 28.7 84 45.6 84 42.5 60 36.8 45 56.7 78 50.3 61
AggregFlow [97]59.1 37.1 91 34.8 101 48.5 76 27.3 60 33.2 54 38.1 77 28.7 9 30.2 9 38.5 2 52.9 74 48.6 87 80.3 10 72.4 89 67.2 77 87.6 108 69.3 88 54.5 48 82.6 100 28.3 16 44.2 26 42.5 60 36.7 38 56.0 44 50.4 74
LDOF [28]59.2 37.1 91 33.7 68 48.8 89 29.5 98 35.3 97 40.6 96 30.0 87 34.3 95 39.7 88 52.8 66 47.9 58 80.9 75 72.2 36 66.9 29 87.4 34 68.8 33 53.6 13 82.3 69 28.3 16 44.5 35 42.4 10 36.6 26 55.8 38 50.4 74
F-TV-L1 [15]60.2 37.4 96 34.6 95 49.2 95 28.8 91 34.9 91 38.3 81 29.7 75 34.1 93 39.5 78 52.7 56 47.6 46 81.0 87 71.7 2 66.5 2 87.4 34 68.8 33 53.5 12 82.4 83 28.3 16 44.3 29 42.4 10 37.1 76 56.3 65 50.6 98
MLDP_OF [89]60.2 36.2 27 32.9 40 48.0 27 27.0 51 32.7 44 37.2 31 29.1 29 31.8 44 38.8 12 52.6 47 47.3 35 80.8 67 72.3 64 67.1 65 87.5 77 70.5 121 56.6 115 83.6 122 28.6 73 44.8 52 42.8 104 36.9 59 56.1 52 50.5 88
IAOF [50]60.5 38.0 109 34.2 89 49.8 105 31.7 111 37.9 112 41.1 101 28.9 18 32.6 58 39.4 71 53.7 95 48.1 67 80.8 67 72.0 9 66.7 8 87.5 77 68.9 43 54.1 32 82.2 55 28.3 16 45.1 68 42.3 1 36.8 45 56.1 52 50.2 44
Aniso-Texture [82]60.8 36.1 20 32.4 23 48.2 55 28.0 75 34.4 78 37.6 60 30.0 87 32.8 64 39.3 66 52.7 56 48.1 67 80.7 54 72.4 89 67.3 91 87.3 16 69.2 77 56.2 112 82.3 69 28.4 37 44.5 35 42.4 10 37.2 83 57.0 91 50.2 44
Classic++ [32]61.7 36.4 51 33.5 58 48.4 73 27.4 62 33.7 64 37.6 60 29.6 73 33.6 84 39.2 60 52.7 56 47.3 35 80.9 75 72.2 36 67.0 42 87.5 77 69.1 67 54.5 48 82.5 94 28.5 56 44.9 55 42.6 88 36.8 45 56.2 60 50.3 61
Shiralkar [42]63.0 36.5 59 34.6 95 48.1 41 28.3 80 34.3 73 37.2 31 29.8 80 36.9 116 40.0 96 53.9 99 49.0 99 80.5 35 71.8 3 66.6 3 87.2 8 69.2 77 55.1 77 82.4 83 29.2 106 48.0 110 42.5 60 36.6 26 55.7 31 50.1 24
CostFilter [40]63.6 35.9 9 32.7 33 47.6 3 26.8 40 33.5 61 37.1 18 29.7 75 35.6 111 39.2 60 52.9 74 49.4 106 80.3 10 72.6 109 67.6 109 87.4 34 69.6 104 54.8 64 83.1 115 28.6 73 45.6 84 42.6 88 37.0 66 56.7 78 49.9 3
FlowNetS+ft+v [112]63.8 36.8 82 33.0 42 48.7 86 29.5 98 35.6 100 40.5 94 29.8 80 34.3 95 39.5 78 52.8 66 48.2 78 80.8 67 72.2 36 67.0 42 87.4 34 68.7 19 53.9 23 82.1 34 28.6 73 45.9 87 42.5 60 36.7 38 56.0 44 50.4 74
Fusion [6]63.8 36.0 15 32.7 33 47.8 8 26.8 40 32.1 34 37.5 54 29.5 68 31.5 38 39.5 78 53.5 91 48.6 87 80.7 54 72.6 109 68.0 117 87.1 3 69.3 88 57.6 124 81.8 3 28.7 84 47.1 101 42.5 60 38.2 112 59.9 124 50.0 6
TriFlow [95]64.1 37.0 88 35.3 107 48.8 89 28.7 89 34.5 81 41.0 99 29.2 36 33.4 81 38.8 12 53.0 78 48.8 97 80.4 19 72.3 64 67.3 91 87.4 34 69.2 77 55.5 93 82.1 34 28.5 56 44.8 52 42.4 10 36.9 59 56.4 69 50.1 24
Occlusion-TV-L1 [63]64.2 36.6 68 33.8 74 48.5 76 28.4 83 34.8 88 37.7 65 29.5 68 33.0 70 39.5 78 53.0 78 48.1 67 81.1 95 72.1 24 66.8 17 87.5 77 68.9 43 53.4 8 82.4 83 29.0 102 44.7 43 42.6 88 36.8 45 55.6 27 50.4 74
SVFilterOh [111]64.2 36.3 40 32.2 18 48.1 41 26.2 22 30.9 17 37.4 47 29.2 36 30.6 16 39.3 66 52.6 47 47.5 42 81.0 87 72.6 109 67.6 109 87.6 108 69.3 88 55.9 101 82.3 69 28.5 56 43.7 13 43.3 118 37.3 89 57.1 95 51.0 108
CNN-flow-warp+ref [117]64.9 36.3 40 31.7 9 48.7 86 28.5 85 34.7 84 39.5 88 30.4 98 35.0 104 39.8 91 54.0 102 48.1 67 81.2 99 72.3 64 67.0 42 87.4 34 68.6 5 53.2 5 82.4 83 28.8 92 47.1 101 42.5 60 36.6 26 55.7 31 50.3 61
CRTflow [80]65.0 36.7 76 33.8 74 48.5 76 27.7 68 33.8 67 37.4 47 30.7 104 35.3 106 40.9 113 52.9 74 48.1 67 81.8 109 72.2 36 66.9 29 87.4 34 68.9 43 54.1 32 82.3 69 28.4 37 44.9 55 42.5 60 36.8 45 56.1 52 50.5 88
FlowNet2 [122]67.1 39.4 114 38.2 118 50.4 111 29.2 96 34.8 88 41.9 108 30.0 87 34.6 99 39.4 71 53.3 89 51.0 118 80.6 41 72.5 101 67.4 101 87.4 34 68.8 33 54.3 40 82.0 13 28.4 37 45.0 62 42.3 1 36.5 17 55.7 31 49.8 1
Modified CLG [34]67.5 36.9 87 32.8 36 49.4 99 30.9 108 36.3 106 42.8 110 30.0 87 34.8 102 39.9 92 53.0 78 47.9 58 80.7 54 72.2 36 66.9 29 87.5 77 68.7 19 53.8 15 82.2 55 28.4 37 45.1 68 42.5 60 36.9 59 56.2 60 50.5 88
Adaptive [20]68.2 36.8 82 34.4 92 48.5 76 28.8 91 35.2 96 37.7 65 29.4 59 33.2 74 39.2 60 52.6 47 47.6 46 80.6 41 72.3 64 67.0 42 87.5 77 69.1 67 54.7 58 82.3 69 28.7 84 46.0 89 42.4 10 37.3 89 56.9 85 50.4 74
TCOF [69]68.5 36.6 68 33.9 78 48.1 41 29.1 93 35.7 101 38.3 81 29.0 22 31.4 34 38.7 8 52.8 66 48.7 93 80.6 41 72.2 36 67.1 65 87.4 34 69.3 88 56.0 104 82.1 34 28.7 84 46.2 92 42.5 60 38.2 112 58.7 120 50.5 88
Nguyen [33]70.4 39.6 115 33.9 78 52.6 119 32.5 116 37.9 112 43.3 113 30.0 87 35.5 109 40.2 101 54.1 105 49.0 99 80.9 75 72.0 9 66.8 17 87.4 34 68.6 5 53.8 15 82.0 13 28.8 92 47.8 108 42.4 10 36.8 45 56.1 52 50.3 61
Steered-L1 [118]70.5 36.0 15 32.9 40 47.9 18 27.0 51 33.3 57 37.7 65 30.3 97 32.3 52 39.9 92 53.2 84 48.0 61 81.0 87 72.5 101 67.5 107 87.5 77 68.9 43 55.0 75 82.2 55 28.8 92 46.7 98 42.7 99 37.0 66 57.3 99 50.3 61
BriefMatch [124]71.4 36.3 40 33.3 51 48.0 27 27.2 58 33.4 59 38.5 85 30.6 103 32.6 58 40.6 106 54.0 102 48.6 87 82.8 116 72.4 89 67.3 91 87.3 16 70.2 116 55.6 96 83.9 125 28.3 16 44.3 29 42.7 99 36.6 26 55.7 31 50.5 88
StereoOF-V1MT [119]71.6 36.8 82 35.3 107 48.1 41 28.3 80 35.1 93 36.9 3 31.4 112 36.6 113 40.5 104 54.6 113 48.6 87 81.3 100 72.0 9 66.8 17 87.2 8 69.5 99 54.9 67 82.6 100 29.7 119 48.8 117 42.7 99 36.5 17 55.1 8 50.1 24
SPSA-learn [13]75.0 37.4 96 33.6 64 49.4 99 29.8 102 35.1 93 41.4 105 30.9 107 33.2 74 40.7 107 53.5 91 47.2 33 80.4 19 72.2 36 67.0 42 87.4 34 68.8 33 54.1 32 82.2 55 29.5 114 52.2 128 42.9 109 37.1 76 57.0 91 50.3 61
GraphCuts [14]75.6 38.0 109 35.1 104 49.5 101 28.4 83 33.9 69 41.3 103 31.3 111 30.8 23 40.7 107 53.7 95 48.3 80 81.0 87 72.1 24 67.1 65 87.1 3 68.6 5 54.9 67 81.7 1 28.8 92 46.3 93 42.8 104 37.7 99 58.5 116 50.4 74
HBpMotionGpu [43]76.2 38.8 112 35.9 110 50.9 115 32.1 113 38.2 114 44.4 117 29.2 36 31.7 41 39.3 66 53.9 99 49.6 108 81.5 104 72.1 24 67.0 42 87.1 3 69.5 99 54.9 67 82.4 83 28.3 16 44.4 31 42.5 60 37.3 89 56.5 72 51.1 109
Dynamic MRF [7]76.4 36.2 27 34.1 85 48.0 27 27.5 64 34.6 83 37.4 47 30.9 107 36.8 115 40.4 103 54.5 111 49.3 105 81.9 110 71.9 4 66.8 17 87.2 8 69.4 97 55.5 93 82.5 94 29.0 102 47.8 108 42.5 60 37.5 96 56.8 82 50.5 88
2D-CLG [1]76.8 37.9 104 33.5 58 50.5 113 32.5 116 37.4 109 45.0 118 30.8 106 34.8 102 40.7 107 53.7 95 48.3 80 80.5 35 72.3 64 67.1 65 87.6 108 68.6 5 53.2 5 82.2 55 28.8 92 46.7 98 42.5 60 36.9 59 55.6 27 50.3 61
Black & Anandan [4]77.0 37.9 104 34.1 85 49.6 102 30.7 106 36.0 102 41.2 102 31.0 109 34.7 101 40.3 102 53.9 99 48.6 87 80.7 54 72.3 64 67.0 42 87.4 34 69.0 57 53.8 15 82.5 94 28.8 92 46.5 94 42.4 10 37.0 66 56.1 52 50.4 74
ROF-ND [107]77.1 37.0 88 32.8 36 48.1 41 27.7 68 34.7 84 37.6 60 29.7 75 32.3 52 39.1 49 54.2 107 51.4 119 80.4 19 72.4 89 67.3 91 87.4 34 69.5 99 56.9 116 82.0 13 29.7 119 49.0 120 43.2 116 37.8 103 57.7 108 50.2 44
TV-L1-improved [17]77.5 36.6 68 34.1 85 48.4 73 28.6 88 35.1 93 37.8 68 30.5 101 33.2 74 40.0 96 52.7 56 48.0 61 80.9 75 72.3 64 67.2 77 87.4 34 69.1 67 54.9 67 82.3 69 28.8 92 47.3 104 42.6 88 37.2 83 56.7 78 50.6 98
CBF [12]79.2 36.4 51 32.5 29 48.9 92 27.5 64 33.8 67 37.9 72 29.3 46 31.6 39 39.1 49 53.2 84 48.1 67 82.6 113 72.4 89 67.2 77 87.7 117 69.2 77 55.3 85 82.3 69 28.7 84 46.1 90 42.9 109 37.9 105 57.7 108 51.7 118
Rannacher [23]80.5 36.7 76 34.5 93 48.7 86 28.7 89 35.3 97 38.1 77 30.5 101 34.0 91 39.9 92 52.7 56 48.0 61 80.8 67 72.4 89 67.2 77 87.5 77 69.0 57 54.6 55 82.3 69 28.8 92 47.0 100 42.6 88 37.1 76 56.4 69 50.6 98
UnFlow [129]80.9 39.2 113 37.9 116 50.6 114 32.3 114 38.9 119 41.3 103 31.6 117 38.5 121 40.8 112 53.2 84 48.7 93 80.9 75 72.0 9 66.7 8 87.4 34 69.5 99 54.6 55 82.4 83 28.2 11 43.2 3 42.4 10 39.3 125 58.3 114 51.2 110
Correlation Flow [75]81.3 36.2 27 33.4 55 47.7 6 27.7 68 34.3 73 37.3 36 29.4 59 31.4 34 38.8 12 53.1 82 48.5 84 81.3 100 72.8 114 67.6 109 88.6 127 70.1 111 57.1 119 82.6 100 29.4 111 48.8 117 43.0 111 37.7 99 57.9 110 50.5 88
HBM-GC [105]82.4 37.7 101 34.7 98 49.8 105 27.1 55 32.4 39 37.9 72 28.8 12 29.6 3 39.2 60 52.6 47 47.3 35 80.8 67 73.2 120 68.1 118 88.2 122 70.0 109 57.3 121 82.7 104 28.9 101 45.0 62 43.5 119 37.6 98 57.2 97 51.3 112
SegOF [10]82.8 37.6 100 33.2 48 50.0 108 29.1 93 34.7 84 41.0 99 31.4 112 35.3 106 40.7 107 53.6 93 50.7 116 80.6 41 72.3 64 67.2 77 87.5 77 69.0 57 55.3 85 82.2 55 29.0 102 48.6 115 42.7 99 36.7 38 55.8 38 50.4 74
TriangleFlow [30]82.9 37.0 88 34.9 102 48.5 76 28.0 75 34.7 84 37.5 54 30.2 95 33.0 70 39.9 92 53.2 84 49.0 99 81.1 95 72.0 9 66.9 29 87.1 3 69.8 108 56.1 106 82.4 83 29.2 106 48.5 114 42.8 104 38.1 110 58.5 116 50.5 88
BlockOverlap [61]83.5 38.5 111 33.2 48 51.3 116 30.0 104 34.4 78 42.8 110 29.4 59 30.4 14 40.0 96 53.2 84 46.9 25 83.0 117 72.9 117 67.6 109 88.3 123 69.7 106 54.1 32 83.3 120 28.7 84 44.1 24 43.5 119 37.1 76 55.3 13 51.8 119
IAOF2 [51]85.6 37.9 104 35.9 110 49.1 94 29.6 100 36.1 104 40.0 91 29.3 46 33.4 81 40.0 96 54.1 105 50.2 113 81.0 87 72.4 89 67.4 101 87.4 34 69.2 77 54.9 67 82.4 83 28.6 73 45.5 81 42.4 10 37.9 105 57.6 105 50.6 98
Ad-TV-NDC [36]85.9 40.4 119 35.1 104 53.1 120 31.9 112 36.7 108 43.8 115 29.4 59 32.9 65 39.1 49 54.5 111 49.2 104 82.1 111 72.5 101 67.3 91 87.5 77 69.3 88 53.9 23 82.7 104 28.6 73 45.4 76 42.4 10 37.2 83 56.2 60 50.6 98
AdaConv-v1 [126]92.3 37.2 95 36.6 113 47.5 2 34.3 121 39.1 121 51.1 127 36.1 125 39.4 123 52.9 129 58.2 125 53.1 123 83.8 122 70.9 1 65.4 1 86.6 2 69.7 106 54.7 58 84.4 126 38.6 129 46.5 94 77.4 129 38.2 112 54.6 2 60.3 129
LocallyOriented [52]93.5 37.5 98 35.9 110 49.2 95 29.6 100 36.2 105 39.1 86 30.1 93 33.8 88 39.5 78 53.7 95 50.0 111 81.3 100 72.3 64 67.2 77 87.5 77 70.2 116 56.2 112 82.9 111 28.8 92 45.6 84 42.5 60 37.7 99 57.6 105 50.5 88
ACK-Prior [27]94.6 36.4 51 33.7 68 48.1 41 26.7 35 33.1 52 37.1 18 30.7 104 33.3 78 39.7 88 53.6 93 50.0 111 81.0 87 73.5 124 68.6 121 88.3 123 70.8 123 59.8 127 82.7 104 29.7 119 48.7 116 43.6 122 39.5 126 62.1 127 51.3 112
Horn & Schunck [3]94.9 37.9 104 35.1 104 49.6 102 31.4 109 37.7 111 41.8 107 31.7 118 37.4 118 41.5 115 55.8 117 50.6 114 81.3 100 72.2 36 67.0 42 87.4 34 69.2 77 54.2 38 82.7 104 29.5 114 48.9 119 42.6 88 37.8 103 57.2 97 50.9 107
StereoFlow [44]95.0 46.3 128 45.9 129 54.3 121 38.3 128 45.4 129 45.7 120 29.3 46 33.8 88 39.1 49 52.9 74 47.7 51 81.0 87 74.4 128 70.5 129 87.6 108 72.0 127 66.3 129 82.4 83 28.4 37 45.0 62 42.4 10 38.0 109 59.1 121 50.5 88
Filter Flow [19]96.0 37.8 103 34.6 95 49.8 105 30.8 107 36.0 102 44.3 116 29.4 59 32.4 55 39.5 78 54.2 107 48.1 67 82.2 112 72.7 113 67.7 115 87.6 108 69.2 77 55.1 77 82.5 94 28.7 84 46.5 94 42.6 88 38.3 118 58.4 115 51.4 115
TI-DOFE [24]97.0 42.0 122 37.5 115 54.8 124 35.2 123 41.1 126 46.8 123 31.4 112 37.7 119 41.6 117 56.1 119 50.6 114 81.6 105 72.0 9 66.9 29 87.2 8 69.4 97 54.4 44 82.6 100 29.2 106 47.6 107 42.6 88 38.2 112 57.5 103 50.8 106
SILK [79]98.5 39.6 115 38.1 117 51.5 118 32.4 115 38.5 117 43.6 114 32.4 119 37.2 117 41.5 115 55.4 115 49.7 109 83.0 117 72.2 36 67.0 42 87.4 34 70.0 109 54.7 58 83.4 121 29.0 102 46.5 94 42.8 104 37.4 95 56.7 78 50.7 104
Bartels [41]100.1 37.1 91 35.0 103 49.3 98 28.2 77 34.8 88 40.5 94 29.9 84 33.1 73 40.5 104 54.2 107 49.7 109 83.9 123 73.0 118 67.6 109 88.7 128 71.8 126 56.1 106 85.6 128 28.6 73 43.9 16 43.6 122 38.1 110 57.0 91 53.2 125
SLK [47]106.8 41.6 121 38.7 120 54.4 122 33.0 118 38.3 116 45.5 119 33.3 120 38.6 122 42.8 119 57.8 123 51.8 121 83.5 121 72.1 24 67.3 91 86.5 1 70.1 111 55.8 99 82.7 104 30.0 122 51.4 126 43.0 111 38.2 112 57.5 103 51.5 116
NL-TV-NCC [25]107.9 37.1 91 35.7 109 48.0 27 27.8 72 35.0 92 37.6 60 31.0 109 35.4 108 40.0 96 56.0 118 54.2 126 82.6 113 73.8 126 68.6 121 89.1 129 70.6 122 58.4 126 82.5 94 30.4 126 50.0 123 44.0 126 39.8 127 60.2 125 52.4 123
GroupFlow [9]108.7 40.3 118 40.1 122 51.3 116 31.5 110 38.9 119 42.6 109 33.5 122 39.5 124 43.8 121 54.7 114 52.3 122 81.0 87 73.2 120 68.6 121 87.6 108 70.4 120 57.3 121 83.0 113 29.3 109 48.1 111 42.5 60 37.9 105 58.2 113 50.1 24
FFV1MT [106]109.3 39.6 115 40.8 124 50.3 110 34.8 122 38.8 118 46.6 122 36.5 126 45.8 127 44.6 123 56.2 120 49.0 99 81.7 106 72.5 101 67.4 101 87.4 34 70.2 116 54.7 58 83.2 116 30.1 124 49.3 122 42.8 104 38.6 119 57.6 105 51.3 112
Learning Flow [11]109.6 37.7 101 37.0 114 49.2 95 29.9 103 37.5 110 39.7 89 31.5 116 36.3 112 40.7 107 55.4 115 51.6 120 82.6 113 72.8 114 67.8 116 87.8 119 69.6 104 55.7 97 82.8 109 29.3 109 48.4 112 42.7 99 39.2 123 59.8 123 51.2 110
Heeger++ [104]109.8 40.6 120 42.5 126 50.4 111 33.5 119 38.2 114 43.0 112 37.6 127 48.1 128 44.9 124 56.2 120 49.0 99 81.7 106 73.4 123 68.9 126 87.5 77 70.1 111 56.0 104 82.8 109 30.3 125 49.1 121 42.6 88 37.7 99 56.9 85 50.3 61
2bit-BM-tele [98]110.6 37.9 104 34.7 98 50.1 109 30.1 105 36.4 107 41.7 106 30.2 95 32.2 51 41.3 114 54.3 110 49.4 106 84.1 125 73.3 122 68.1 118 88.3 123 72.2 128 57.2 120 85.5 127 30.4 126 52.7 129 44.4 127 38.2 112 56.3 65 54.1 127
FOLKI [16]114.4 44.6 126 40.4 123 58.4 127 35.7 124 42.3 127 47.3 124 33.3 120 40.7 125 44.9 124 59.4 128 53.6 124 86.5 128 72.5 101 67.6 109 87.3 16 70.1 111 55.8 99 83.2 116 29.4 111 48.4 112 43.1 114 38.7 120 58.5 116 52.0 120
Pyramid LK [2]118.1 46.1 127 38.9 121 61.0 128 36.7 127 40.4 124 50.9 126 39.9 128 36.6 113 49.4 127 64.1 129 61.2 129 87.7 129 73.1 119 68.6 121 87.4 34 70.1 111 56.1 106 83.0 113 29.6 117 50.7 125 43.2 116 39.2 123 61.2 126 51.5 116
Adaptive flow [45]118.8 43.8 124 38.2 118 56.5 125 35.8 125 40.5 125 50.2 125 31.4 112 34.5 97 42.5 118 56.5 122 50.9 117 83.9 123 73.5 124 68.7 125 88.1 121 70.2 116 57.4 123 82.9 111 29.4 111 47.5 105 43.6 122 39.0 122 59.1 121 52.0 120
PGAM+LK [55]119.5 42.5 123 41.4 125 54.6 123 33.7 120 40.1 123 45.8 121 33.9 123 41.1 126 43.3 120 59.3 127 55.2 127 85.5 127 72.8 114 68.1 118 87.5 77 70.8 123 56.9 116 83.6 122 29.6 117 50.0 123 43.0 111 38.7 120 58.6 119 52.1 122
HCIC-L [99]123.0 49.1 129 42.6 127 63.0 129 35.8 125 39.4 122 52.5 128 34.6 124 37.7 119 43.9 122 58.0 124 53.9 125 81.7 106 74.0 127 69.3 127 88.5 126 71.7 125 60.5 128 83.2 116 29.5 114 47.5 105 43.9 125 40.5 128 62.9 128 52.8 124
Periodicity [78]126.8 44.4 125 43.3 128 56.9 126 42.8 129 43.4 128 56.2 129 40.9 129 49.1 129 49.5 128 58.9 126 58.6 128 84.9 126 74.4 128 70.2 128 88.0 120 73.1 129 57.9 125 86.2 129 30.0 122 51.5 127 43.5 119 41.8 129 63.4 129 53.7 126
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 Anonymous. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015 submission 744.
[111] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[112] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[113] CombBMOF 51 2 color M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.)
[114] PMMST 182 2 color F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015.
[115] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[116] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[117] CNN-flow-warp+ref 1.4 3 color D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016.
[118] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[119] StereoOF-V1MT 343 2 gray Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132.
[120] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[121] RNLOD-Flow 1040 2 gray C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. Submitted to TIP 2016.
[122] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[123] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[124] BriefMatch 0.068 2 gray G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62.
[125] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[126] AdaConv-v1 2.8 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[127] SepConv-v1 0.2 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[128] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[129] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
* 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.