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]10.6 35.7 3 30.6 3 47.8 10 25.9 10 30.5 10 36.9 3 28.6 3 29.8 5 38.5 2 51.9 7 46.5 16 80.3 10 71.9 5 66.6 4 87.2 9 68.6 5 53.9 24 82.1 36 28.1 2 43.6 9 42.4 11 36.6 28 55.6 30 50.0 9
PMMST [114]11.7 35.8 5 30.8 4 47.9 20 26.5 32 31.0 20 37.3 37 28.6 3 29.9 6 38.4 1 51.7 3 46.0 6 80.2 5 72.0 10 66.7 9 87.3 17 68.5 1 53.3 8 82.0 13 28.1 2 43.7 14 42.4 11 36.5 19 55.5 25 50.0 9
PH-Flow [101]12.3 36.1 22 32.5 30 47.8 10 25.6 4 29.6 4 36.9 3 28.7 9 30.0 8 38.5 2 51.6 1 45.5 2 80.2 5 71.9 5 66.7 9 87.3 17 68.8 34 54.8 66 81.9 5 28.1 2 43.6 9 42.4 11 36.4 13 55.3 15 50.0 9
NNF-Local [87]12.8 35.7 3 31.4 7 47.6 4 25.5 2 29.6 4 36.9 3 28.6 3 29.9 6 38.5 2 52.4 31 48.0 64 80.3 10 72.0 10 66.6 4 87.4 36 68.7 19 54.4 45 82.0 13 28.1 2 43.5 7 42.4 11 36.2 4 55.0 7 50.0 9
NN-field [71]17.8 36.0 17 32.2 19 47.9 20 25.5 2 29.3 3 36.8 1 29.4 60 29.7 4 39.0 43 52.4 31 48.1 70 80.3 10 72.0 10 66.7 9 87.3 17 68.7 19 54.0 29 82.0 13 28.1 2 43.4 5 42.4 11 36.4 13 55.2 11 50.0 9
IROF++ [58]21.6 36.2 29 33.0 44 47.8 10 26.1 15 30.9 17 36.9 3 29.1 30 31.0 30 38.9 28 51.6 1 45.6 3 80.4 19 72.0 10 66.8 18 87.2 9 68.6 5 53.4 9 82.2 57 28.3 17 44.6 40 42.4 11 36.5 19 55.3 15 50.4 79
ProbFlowFields [128]22.0 35.9 10 32.4 24 48.0 31 25.8 8 30.5 10 37.2 32 28.6 3 30.3 11 38.5 2 52.1 20 46.4 12 80.7 57 72.3 66 67.1 67 87.5 80 68.6 5 53.8 16 82.1 36 28.0 1 42.8 2 42.3 1 36.1 2 54.6 3 50.1 28
Sparse-NonSparse [56]23.2 36.2 29 32.8 38 48.0 31 25.9 10 30.4 8 37.0 11 29.0 22 30.9 27 38.8 13 52.0 13 46.1 8 80.6 41 72.1 25 66.8 18 87.3 17 68.9 44 54.6 56 82.1 36 28.3 17 44.0 22 42.4 11 36.4 13 55.4 20 50.1 28
CombBMOF [113]24.6 35.9 10 31.0 5 47.8 10 25.8 8 30.5 10 36.8 1 29.2 37 30.8 23 39.5 83 52.4 31 47.4 42 80.3 10 72.1 25 66.8 18 87.4 36 68.9 44 54.5 49 82.1 36 28.5 58 44.6 40 42.3 1 36.0 1 54.6 3 50.0 9
AGIF+OF [85]26.3 36.2 29 32.8 38 47.9 20 26.1 15 30.8 14 37.1 18 29.0 22 30.7 19 38.9 28 51.8 5 46.2 10 80.1 3 72.3 66 67.2 80 87.3 17 68.9 44 55.2 82 81.9 5 28.3 17 43.6 9 42.4 11 36.6 28 56.0 47 49.9 4
nLayers [57]26.4 36.4 54 32.0 14 48.2 59 26.0 13 30.4 8 37.3 37 28.7 9 29.4 2 38.8 13 52.2 27 46.8 23 80.4 19 72.3 66 67.1 67 87.4 36 68.8 34 54.7 60 82.0 13 28.3 17 43.7 14 42.4 11 36.4 13 55.4 20 49.9 4
2DHMM-SAS [92]28.2 36.4 54 33.9 82 47.9 20 27.1 57 32.6 45 37.0 11 28.5 2 30.4 14 38.9 28 51.8 5 45.6 3 80.4 19 72.1 25 66.9 30 87.4 36 68.8 34 54.5 49 82.0 13 28.3 17 44.2 28 42.3 1 36.7 40 56.1 55 50.0 9
NNF-EAC [103]28.8 36.3 42 32.4 24 48.0 31 26.6 36 31.7 30 37.1 18 29.3 47 30.2 9 39.0 43 52.4 31 46.9 26 81.1 98 72.0 10 66.7 9 87.4 36 68.7 19 53.7 15 82.1 36 28.2 11 43.9 17 42.4 11 36.7 40 55.9 44 50.0 9
Layers++ [37]29.4 36.3 42 32.4 24 48.2 59 25.7 5 29.2 2 37.3 37 28.9 18 30.6 16 38.9 28 52.0 13 46.4 12 80.4 19 72.2 37 67.0 43 87.5 80 68.9 44 55.2 82 82.0 13 28.3 17 44.0 22 42.4 11 36.6 28 55.5 25 50.1 28
LSM [39]30.8 36.3 42 33.7 71 48.0 31 26.1 15 31.0 20 37.0 11 29.1 30 31.8 47 38.9 28 52.2 27 46.9 26 80.6 41 72.1 25 66.9 30 87.3 17 69.0 58 54.9 69 82.1 36 28.3 17 44.1 26 42.4 11 36.5 19 55.7 34 50.0 9
ComponentFusion [96]31.4 36.0 17 32.2 19 48.0 31 26.1 15 31.1 25 36.9 3 29.1 30 32.3 55 38.8 13 52.0 13 47.0 30 80.3 10 72.2 37 67.1 67 87.3 17 68.7 19 53.9 24 82.1 36 28.5 58 46.1 93 42.4 11 36.7 40 55.8 41 50.2 49
FlowFields [110]31.5 36.0 17 32.7 35 47.9 20 26.4 29 32.0 32 37.3 37 29.0 22 32.6 61 38.7 8 52.5 36 47.9 61 80.7 57 72.3 66 67.0 43 87.5 80 68.6 5 54.4 45 82.0 13 28.2 11 44.0 22 42.4 11 36.3 6 55.2 11 50.1 28
S2F-IF [123]32.2 35.9 10 32.5 30 47.8 10 26.2 22 31.6 29 37.2 32 29.0 22 31.9 52 38.6 7 52.3 29 47.6 47 80.4 19 72.4 92 67.2 80 87.5 80 68.7 19 54.5 49 81.9 5 28.4 38 44.7 45 42.4 11 36.3 6 55.2 11 50.1 28
FlowFields+ [130]32.5 35.9 10 32.6 34 47.9 20 26.4 29 32.2 36 37.4 48 29.0 22 32.6 61 38.7 8 52.3 29 47.7 52 80.6 41 72.3 66 67.1 67 87.5 80 68.7 19 54.6 56 82.0 13 28.2 11 44.0 22 42.4 11 36.3 6 55.2 11 50.1 28
TV-L1-MCT [64]32.5 36.8 86 34.7 102 48.2 59 26.7 37 32.4 42 37.3 37 28.6 3 30.9 27 39.0 43 51.9 7 45.7 5 80.5 35 72.2 37 67.0 43 87.3 17 68.6 5 53.0 5 82.3 73 28.3 17 44.4 33 42.4 11 36.1 2 54.9 6 50.2 49
WLIF-Flow [93]33.0 36.1 22 32.5 30 47.8 10 26.3 27 31.2 26 37.1 18 29.1 30 30.7 19 39.1 51 52.0 13 46.4 12 80.6 41 72.1 25 66.8 18 87.4 36 69.0 58 54.9 69 82.3 73 28.3 17 43.9 17 42.5 62 36.8 47 55.9 44 50.1 28
COFM [59]35.5 36.1 22 32.0 14 48.1 45 26.1 15 30.8 14 37.1 18 28.8 12 30.3 11 38.8 13 51.7 3 46.0 6 80.0 1 72.2 37 67.2 80 87.2 9 68.9 44 56.1 109 81.7 1 28.1 2 42.8 2 43.1 119 37.1 78 56.9 89 50.7 109
LME [70]35.6 35.8 5 31.0 5 47.8 10 26.9 47 32.2 36 38.4 86 29.2 37 32.6 61 38.8 13 51.9 7 46.7 21 80.4 19 72.6 114 67.4 105 87.7 122 68.8 34 54.9 69 82.0 13 28.1 2 43.5 7 42.4 11 36.3 6 55.3 15 50.0 9
FMOF [94]36.3 36.5 63 33.7 71 48.2 59 25.9 10 30.3 7 37.1 18 29.3 47 30.7 19 39.0 43 52.5 36 47.5 43 80.2 5 72.2 37 67.0 43 87.5 80 69.0 58 55.1 79 82.0 13 28.1 2 43.4 5 42.4 11 36.8 47 56.0 47 50.1 28
OFLAF [77]36.8 35.8 5 31.5 8 47.8 10 25.7 5 29.8 6 37.0 11 29.0 22 31.2 33 38.7 8 52.0 13 46.8 23 80.1 3 72.4 92 67.3 94 87.4 36 68.9 44 55.3 87 82.0 13 28.6 75 45.4 79 42.4 11 37.1 78 57.1 99 50.1 28
DeepFlow2 [108]36.8 36.2 29 32.4 24 48.2 59 27.1 57 32.9 49 37.8 71 29.2 37 32.9 69 39.0 43 52.5 36 47.5 43 80.5 35 72.2 37 66.9 30 87.5 80 68.5 1 52.9 4 82.1 36 28.3 17 44.4 33 42.4 11 36.4 13 55.4 20 50.2 49
RNLOD-Flow [121]36.8 36.3 42 33.5 61 48.0 31 26.8 42 32.6 45 37.1 18 29.2 37 31.8 47 38.8 13 52.1 20 46.9 26 80.2 5 72.2 37 67.0 43 87.3 17 69.0 58 55.2 82 82.1 36 28.3 17 44.2 28 42.4 11 37.1 78 56.9 89 49.8 1
DeepFlow [86]38.3 36.1 22 31.8 12 48.1 45 27.3 62 32.9 49 38.4 86 29.3 47 33.3 82 39.1 51 52.6 49 47.0 30 80.7 57 72.2 37 66.8 18 87.5 80 68.7 19 52.8 3 82.5 98 28.1 2 43.6 9 42.3 1 36.2 4 55.0 7 50.2 49
Ramp [62]38.8 36.5 63 34.0 87 48.2 59 26.0 13 30.8 14 37.1 18 28.9 18 30.8 23 38.8 13 51.9 7 46.1 8 80.4 19 72.2 37 67.0 43 87.4 36 69.1 69 55.4 93 82.2 57 28.4 38 44.7 45 42.4 11 36.8 47 56.2 63 50.2 49
MDP-Flow [26]39.1 35.8 5 31.5 8 48.0 31 26.2 22 31.4 28 37.4 48 29.0 22 31.1 31 38.9 28 52.7 58 47.8 58 80.7 57 72.2 37 66.9 30 87.5 80 68.9 44 55.2 82 82.1 36 28.5 58 45.3 78 42.5 62 36.3 6 55.4 20 50.0 9
IROF-TV [53]40.2 36.3 42 33.6 67 48.2 59 26.2 22 31.0 20 37.0 11 29.3 47 33.6 88 39.1 51 51.9 7 46.5 16 80.8 70 72.3 66 67.0 43 87.6 113 68.5 1 53.9 24 81.9 5 28.3 17 44.9 57 42.3 1 36.6 28 55.6 30 50.4 79
Classic+NL [31]40.5 36.5 63 34.0 87 48.2 59 26.2 22 30.9 17 37.1 18 28.8 12 30.6 16 38.8 13 52.1 20 46.5 16 80.6 41 72.2 37 67.0 43 87.4 36 69.2 79 55.3 87 82.2 57 28.4 38 44.6 40 42.4 11 36.8 47 56.2 63 50.2 49
PGM-C [120]40.6 36.2 29 33.3 53 48.1 45 26.5 32 32.2 36 37.5 57 29.2 37 32.9 69 38.8 13 52.5 36 48.3 83 80.7 57 72.3 66 67.0 43 87.5 80 68.6 5 54.0 29 82.0 13 28.3 17 44.6 40 42.4 11 36.5 19 55.5 25 50.4 79
DF-Auto [115]41.1 36.8 86 31.9 13 48.9 96 28.5 88 33.7 67 40.8 101 28.8 12 30.3 11 38.7 8 52.5 36 47.3 36 80.4 19 72.1 25 66.7 9 87.4 36 68.6 5 53.8 16 82.0 13 28.4 38 44.7 45 42.5 62 36.8 47 56.3 68 50.2 49
FC-2Layers-FF [74]43.2 36.4 54 33.8 77 48.1 45 25.7 5 29.1 1 37.4 48 28.9 18 30.9 27 38.8 13 52.1 20 46.8 23 80.6 41 72.3 66 67.2 80 87.4 36 69.1 69 55.5 95 82.1 36 28.4 38 44.7 45 42.5 62 36.9 61 56.3 68 50.0 9
SuperFlow [81]44.1 36.5 63 32.2 19 48.8 93 28.3 83 33.4 62 40.9 102 29.5 69 32.6 61 39.4 75 52.5 36 46.7 21 80.9 78 72.2 37 66.9 30 87.5 80 68.5 1 53.4 9 82.0 13 28.3 17 44.7 45 42.4 11 36.3 6 55.4 20 50.1 28
HAST [109]44.4 36.1 22 31.7 10 48.1 45 26.1 15 31.0 20 37.0 11 29.3 47 31.7 42 39.2 63 51.9 7 46.5 16 80.3 10 72.3 66 67.3 94 87.2 9 69.3 90 56.4 117 82.0 13 28.4 38 45.0 64 42.5 62 37.3 93 57.3 103 50.0 9
CPM-Flow [116]45.5 36.2 29 33.5 61 48.1 45 26.5 32 32.2 36 37.5 57 29.3 47 32.6 61 38.9 28 52.7 58 48.7 96 80.7 57 72.3 66 67.0 43 87.5 80 68.7 19 53.8 16 82.2 57 28.4 38 44.7 45 42.4 11 36.5 19 55.5 25 50.3 66
Second-order prior [8]45.8 36.2 29 32.1 17 48.1 45 27.9 77 34.1 73 37.4 48 29.9 88 34.6 104 39.7 93 52.4 31 47.2 34 80.6 41 71.9 5 66.6 4 87.5 80 68.7 19 54.0 29 82.1 36 28.5 58 45.2 76 42.4 11 36.5 19 55.7 34 50.2 49
Classic+CPF [83]46.4 36.4 54 33.6 67 47.9 20 26.3 27 31.3 27 37.0 11 28.8 12 31.1 31 38.9 28 52.0 13 46.5 16 80.0 1 72.5 104 67.4 105 87.4 36 69.2 79 56.1 109 82.0 13 28.6 75 45.2 76 42.4 11 37.2 86 57.3 103 50.0 9
Aniso. Huber-L1 [22]46.5 36.7 80 33.5 61 48.6 87 28.5 88 34.3 77 38.2 82 29.3 47 31.8 47 38.9 28 52.5 36 47.5 43 80.6 41 72.0 10 66.7 9 87.4 36 68.6 5 54.3 41 81.9 5 28.5 58 45.0 64 42.4 11 36.8 47 56.0 47 50.3 66
RFlow [90]47.8 36.2 29 33.0 44 48.2 59 27.6 68 33.7 67 37.1 18 29.3 47 32.5 60 39.2 63 52.6 49 47.8 58 80.6 41 72.0 10 66.8 18 87.3 17 68.6 5 53.8 16 81.9 5 28.5 58 45.5 84 42.6 91 37.2 86 56.9 89 50.3 66
EpicFlow [102]48.0 36.2 29 33.3 53 48.1 45 26.9 47 33.1 55 37.5 57 29.4 60 33.0 74 39.0 43 52.6 49 48.5 87 80.8 70 72.3 66 67.0 43 87.5 80 68.6 5 54.1 33 82.0 13 28.4 38 44.8 54 42.4 11 36.6 28 55.7 34 50.4 79
Brox et al. [5]48.8 36.3 42 32.4 24 48.2 59 27.8 75 34.1 73 38.0 79 29.8 82 33.9 94 39.6 91 52.5 36 47.0 30 80.4 19 72.2 37 66.9 30 87.5 80 68.7 19 53.8 16 82.1 36 28.4 38 44.9 57 42.5 62 36.5 19 55.5 25 50.2 49
S2D-Matching [84]49.5 36.6 72 34.2 93 48.2 59 26.9 47 32.5 44 37.2 32 28.8 12 30.7 19 38.9 28 52.1 20 46.4 12 80.9 78 72.3 66 67.1 67 87.5 80 69.1 69 55.3 87 82.2 57 28.5 58 44.7 45 42.4 11 36.7 40 55.9 44 50.2 49
FESL [72]50.1 36.6 72 33.9 82 48.0 31 26.4 29 31.7 30 37.3 37 29.1 30 31.3 34 38.9 28 52.6 49 47.6 47 80.3 10 72.4 92 67.3 94 87.4 36 69.3 90 55.9 104 82.1 36 28.4 38 44.9 57 42.3 1 37.0 68 56.6 79 50.1 28
p-harmonic [29]50.5 35.9 10 32.1 17 47.9 20 28.2 80 34.3 77 37.8 71 29.4 60 34.2 98 39.4 75 53.0 80 47.7 52 80.7 57 72.2 37 67.0 43 87.3 17 68.8 34 54.1 33 82.3 73 28.5 58 45.5 84 42.4 11 36.6 28 56.0 47 50.2 49
SepConv-v1 [127]51.1 27.1 1 27.5 1 36.4 1 24.9 1 31.0 20 40.3 95 27.6 1 28.4 1 48.9 131 54.0 108 47.3 36 83.0 123 72.0 10 66.7 9 87.1 4 69.1 69 52.6 2 83.6 127 32.2 133 43.9 17 55.7 133 37.0 68 53.8 2 55.4 133
ComplOF-FED-GPU [35]51.8 36.3 42 33.4 58 48.0 31 26.8 42 33.0 52 37.3 37 30.4 103 34.0 95 39.6 91 52.5 36 48.1 70 80.9 78 72.1 25 66.8 18 87.4 36 68.7 19 54.3 41 82.1 36 28.5 58 45.1 71 42.5 62 36.8 47 56.0 47 50.2 49
TC-Flow [46]52.2 36.2 29 33.2 50 48.2 59 26.9 47 33.5 64 37.5 57 29.5 69 33.6 88 38.9 28 52.1 20 47.1 33 80.6 41 72.3 66 67.2 80 87.5 80 69.0 58 54.8 66 82.3 73 28.4 38 44.4 33 42.5 62 36.6 28 56.1 55 50.1 28
EPPM w/o HM [88]52.9 35.8 5 32.3 23 47.6 4 26.7 37 33.0 52 36.9 3 30.0 91 35.5 115 39.4 75 52.6 49 48.9 102 80.4 19 72.2 37 67.1 67 87.4 36 69.3 90 55.9 104 82.3 73 28.4 38 44.9 57 42.5 62 36.8 47 56.1 55 50.1 28
DPOF [18]53.2 36.7 80 34.5 97 48.6 87 26.1 15 30.6 13 37.6 63 29.8 82 31.4 35 39.3 70 52.8 68 48.6 90 80.8 70 72.0 10 66.8 18 87.3 17 69.1 69 55.3 87 81.9 5 28.5 58 44.5 37 42.5 62 36.9 61 56.5 75 50.0 9
OFH [38]54.9 36.4 54 33.8 77 48.2 59 27.4 64 33.3 60 37.4 48 29.7 77 35.0 110 39.0 43 52.5 36 48.3 83 80.9 78 72.2 37 67.0 43 87.4 36 68.7 19 54.2 39 82.1 36 28.6 75 45.4 79 42.5 62 36.6 28 56.0 47 50.1 28
Efficient-NL [60]55.3 36.5 63 33.6 67 48.0 31 26.7 37 32.0 32 37.1 18 29.9 88 31.4 35 39.3 70 52.7 58 47.7 52 80.4 19 72.2 37 67.0 43 87.3 17 69.5 101 57.0 122 81.9 5 28.6 75 45.9 90 42.4 11 37.9 111 58.1 118 50.1 28
Local-TV-L1 [65]57.0 37.5 102 33.0 44 49.7 108 29.3 101 34.5 86 40.3 95 29.2 37 31.6 40 39.1 51 53.3 91 47.3 36 83.1 126 72.1 25 66.9 30 87.4 36 69.3 90 53.4 9 83.2 121 28.2 11 43.9 17 42.4 11 36.4 13 55.1 9 50.4 79
PMF [73]57.0 35.9 10 32.0 14 47.7 7 26.9 47 33.5 64 36.9 3 29.6 74 34.5 102 39.1 51 52.5 36 47.8 58 80.4 19 72.5 104 67.5 112 87.4 36 69.2 79 55.0 77 82.4 87 28.5 58 45.0 64 42.5 62 37.3 93 57.3 103 50.0 9
OAR-Flow [125]57.8 36.5 63 33.0 44 48.4 77 27.0 53 33.0 52 37.8 71 29.2 37 33.3 82 38.9 28 52.1 20 47.6 47 80.5 35 72.4 92 67.3 94 87.6 113 68.9 44 54.5 49 82.2 57 28.5 58 44.7 45 42.4 11 36.9 61 56.5 75 50.4 79
Sparse Occlusion [54]57.9 36.5 63 33.7 71 48.2 59 27.6 68 34.1 73 37.3 37 29.3 47 31.8 47 38.8 13 52.8 68 48.1 70 80.5 35 72.3 66 67.1 67 87.4 36 69.2 79 56.1 109 82.0 13 28.5 58 45.4 79 42.3 1 37.2 86 57.0 95 50.2 49
TC/T-Flow [76]57.9 36.6 72 33.7 71 47.9 20 26.8 42 32.9 49 37.1 18 29.1 30 31.9 52 38.8 13 52.7 58 48.5 87 80.4 19 72.5 104 67.4 105 87.5 80 69.1 69 55.2 82 82.1 36 28.6 75 45.4 79 42.5 62 37.0 68 56.9 89 50.0 9
TF+OM [100]58.2 36.3 42 33.0 44 48.5 80 26.9 47 32.2 36 39.2 90 28.6 3 32.4 58 38.9 28 52.8 68 48.2 81 80.7 57 72.3 66 67.1 67 87.4 36 69.0 58 54.5 49 82.3 73 28.4 38 45.1 71 42.5 62 37.0 68 56.4 72 50.6 103
SRR-TVOF-NL [91]58.8 36.6 72 33.5 61 48.2 59 27.7 71 34.3 77 37.9 75 29.5 69 33.2 78 39.1 51 53.1 84 48.1 70 80.2 5 72.2 37 67.1 67 87.3 17 68.9 44 55.7 100 81.8 3 28.5 58 44.9 57 42.4 11 37.5 102 58.0 116 50.1 28
SIOF [67]60.2 36.7 80 34.1 89 48.2 59 29.1 97 35.4 105 39.7 92 29.4 60 32.9 69 39.1 51 52.7 58 47.7 52 80.9 78 71.9 5 66.6 4 87.4 36 69.1 69 54.3 41 82.4 87 28.3 17 44.6 40 42.4 11 37.3 93 56.8 85 50.3 66
ALD-Flow [66]60.3 36.7 80 33.9 82 48.6 87 27.0 53 33.2 57 37.9 75 29.3 47 33.4 85 38.9 28 52.5 36 48.0 64 80.9 78 72.4 92 67.2 80 87.6 113 68.9 44 54.4 45 82.2 57 28.2 11 43.6 9 42.4 11 37.0 68 56.6 79 50.3 66
CLG-TV [48]60.3 36.6 72 33.4 58 48.5 80 28.2 80 34.4 83 38.2 82 29.7 77 33.6 88 39.4 75 52.8 68 48.0 64 80.9 78 72.2 37 66.9 30 87.5 80 68.7 19 54.0 29 82.1 36 28.4 38 45.1 71 42.4 11 37.0 68 56.5 75 50.2 49
SimpleFlow [49]61.0 36.5 63 34.2 93 48.2 59 27.2 60 32.8 48 37.3 37 30.1 98 31.7 42 39.4 75 52.0 13 46.3 11 80.7 57 72.3 66 67.2 80 87.4 36 69.0 58 55.4 93 82.0 13 28.7 86 47.1 104 42.6 91 37.0 68 56.8 85 50.1 28
Complementary OF [21]61.5 36.1 22 33.3 53 47.8 10 26.7 37 33.2 57 37.3 37 30.4 103 32.9 69 39.5 83 52.8 68 48.7 96 81.1 98 72.3 66 67.2 80 87.3 17 68.8 34 54.7 60 82.2 57 28.7 86 45.6 87 42.5 62 36.8 47 56.7 81 50.3 66
AggregFlow [97]61.5 37.1 95 34.8 105 48.5 80 27.3 62 33.2 57 38.1 80 28.7 9 30.2 9 38.5 2 52.9 76 48.6 90 80.3 10 72.4 92 67.2 80 87.6 113 69.3 90 54.5 49 82.6 105 28.3 17 44.2 28 42.5 62 36.7 40 56.0 47 50.4 79
LDOF [28]62.1 37.1 95 33.7 71 48.8 93 29.5 102 35.3 103 40.6 100 30.0 91 34.3 99 39.7 93 52.8 68 47.9 61 80.9 78 72.2 37 66.9 30 87.4 36 68.8 34 53.6 14 82.3 73 28.3 17 44.5 37 42.4 11 36.6 28 55.8 41 50.4 79
SuperSlomo [132]62.2 32.1 2 27.9 2 42.8 2 29.9 108 32.2 36 48.3 130 31.1 116 30.8 23 49.0 132 53.4 95 45.1 1 82.8 121 70.9 1 65.3 1 86.6 2 69.5 101 51.7 1 84.0 131 32.2 133 42.2 1 55.7 133 37.2 86 52.2 1 57.3 134
F-TV-L1 [15]62.8 37.4 100 34.6 99 49.2 99 28.8 94 34.9 96 38.3 84 29.7 77 34.1 97 39.5 83 52.7 58 47.6 47 81.0 90 71.7 3 66.5 3 87.4 36 68.8 34 53.5 13 82.4 87 28.3 17 44.3 31 42.4 11 37.1 78 56.3 68 50.6 103
MLDP_OF [89]62.9 36.2 29 32.9 42 48.0 31 27.0 53 32.7 47 37.2 32 29.1 30 31.8 47 38.8 13 52.6 49 47.3 36 80.8 70 72.3 66 67.1 67 87.5 80 70.5 127 56.6 118 83.6 127 28.6 75 44.8 54 42.8 108 36.9 61 56.1 55 50.5 93
IAOF [50]63.4 38.0 113 34.2 93 49.8 109 31.7 117 37.9 118 41.1 105 28.9 18 32.6 61 39.4 75 53.7 100 48.1 70 80.8 70 72.0 10 66.7 9 87.5 80 68.9 44 54.1 33 82.2 57 28.3 17 45.1 71 42.3 1 36.8 47 56.1 55 50.2 49
Aniso-Texture [82]63.7 36.1 22 32.4 24 48.2 59 28.0 78 34.4 83 37.6 63 30.0 91 32.8 68 39.3 70 52.7 58 48.1 70 80.7 57 72.4 92 67.3 94 87.3 17 69.2 79 56.2 115 82.3 73 28.4 38 44.5 37 42.4 11 37.2 86 57.0 95 50.2 49
Classic++ [32]64.2 36.4 54 33.5 61 48.4 77 27.4 64 33.7 67 37.6 63 29.6 74 33.6 88 39.2 63 52.7 58 47.3 36 80.9 78 72.2 37 67.0 43 87.5 80 69.1 69 54.5 49 82.5 98 28.5 58 44.9 57 42.6 91 36.8 47 56.2 63 50.3 66
Shiralkar [42]66.1 36.5 63 34.6 99 48.1 45 28.3 83 34.3 77 37.2 32 29.8 82 36.9 122 40.0 101 53.9 104 49.0 104 80.5 35 71.8 4 66.6 4 87.2 9 69.2 79 55.1 79 82.4 87 29.2 110 48.0 115 42.5 62 36.6 28 55.7 34 50.1 28
CostFilter [40]66.2 35.9 10 32.7 35 47.6 4 26.8 42 33.5 64 37.1 18 29.7 77 35.6 117 39.2 63 52.9 76 49.4 111 80.3 10 72.6 114 67.6 114 87.4 36 69.6 107 54.8 66 83.1 120 28.6 75 45.6 87 42.6 91 37.0 68 56.7 81 49.9 4
FlowNetS+ft+v [112]66.5 36.8 86 33.0 44 48.7 90 29.5 102 35.6 106 40.5 97 29.8 82 34.3 99 39.5 83 52.8 68 48.2 81 80.8 70 72.2 37 67.0 43 87.4 36 68.7 19 53.9 24 82.1 36 28.6 75 45.9 90 42.5 62 36.7 40 56.0 47 50.4 79
Fusion [6]66.7 36.0 17 32.7 35 47.8 10 26.8 42 32.1 34 37.5 57 29.5 69 31.5 39 39.5 83 53.5 96 48.6 90 80.7 57 72.6 114 68.0 123 87.1 4 69.3 90 57.6 129 81.8 3 28.7 86 47.1 104 42.5 62 38.2 118 59.9 130 50.0 9
TriFlow [95]66.8 37.0 92 35.3 111 48.8 93 28.7 92 34.5 86 41.0 103 29.2 37 33.4 85 38.8 13 53.0 80 48.8 101 80.4 19 72.3 66 67.3 94 87.4 36 69.2 79 55.5 95 82.1 36 28.5 58 44.8 54 42.4 11 36.9 61 56.4 72 50.1 28
SVFilterOh [111]66.9 36.3 42 32.2 19 48.1 45 26.2 22 30.9 17 37.4 48 29.2 37 30.6 16 39.3 70 52.6 49 47.5 43 81.0 90 72.6 114 67.6 114 87.6 113 69.3 90 55.9 104 82.3 73 28.5 58 43.7 14 43.3 123 37.3 93 57.1 99 51.0 113
Occlusion-TV-L1 [63]67.0 36.6 72 33.8 77 48.5 80 28.4 86 34.8 93 37.7 68 29.5 69 33.0 74 39.5 83 53.0 80 48.1 70 81.1 98 72.1 25 66.8 18 87.5 80 68.9 44 53.4 9 82.4 87 29.0 104 44.7 45 42.6 91 36.8 47 55.6 30 50.4 79
CRTflow [80]67.9 36.7 80 33.8 77 48.5 80 27.7 71 33.8 70 37.4 48 30.7 109 35.3 112 40.9 118 52.9 76 48.1 70 81.8 114 72.2 37 66.9 30 87.4 36 68.9 44 54.1 33 82.3 73 28.4 38 44.9 57 42.5 62 36.8 47 56.1 55 50.5 93
CNN-flow-warp+ref [117]68.0 36.3 42 31.7 10 48.7 90 28.5 88 34.7 89 39.5 91 30.4 103 35.0 110 39.8 96 54.0 108 48.1 70 81.2 103 72.3 66 67.0 43 87.4 36 68.6 5 53.2 6 82.4 87 28.8 94 47.1 104 42.5 62 36.6 28 55.7 34 50.3 66
3DFlow [135]68.8 36.4 54 33.8 77 47.9 20 26.5 32 32.1 34 37.1 18 29.8 82 31.7 42 39.1 51 52.5 36 47.7 52 80.6 41 72.5 104 67.3 94 88.0 125 70.0 113 57.8 130 82.2 57 29.1 108 47.4 108 42.5 62 37.4 99 57.6 109 49.9 4
FlowNet2 [122]70.0 39.4 120 38.2 123 50.4 116 29.2 100 34.8 93 41.9 113 30.0 91 34.6 104 39.4 75 53.3 91 51.0 123 80.6 41 72.5 104 67.4 105 87.4 36 68.8 34 54.3 41 82.0 13 28.4 38 45.0 64 42.3 1 36.5 19 55.7 34 49.8 1
Modified CLG [34]70.6 36.9 91 32.8 38 49.4 103 30.9 114 36.3 112 42.8 115 30.0 91 34.8 108 39.9 97 53.0 80 47.9 61 80.7 57 72.2 37 66.9 30 87.5 80 68.7 19 53.8 16 82.2 57 28.4 38 45.1 71 42.5 62 36.9 61 56.2 63 50.5 93
Adaptive [20]71.0 36.8 86 34.4 96 48.5 80 28.8 94 35.2 102 37.7 68 29.4 60 33.2 78 39.2 63 52.6 49 47.6 47 80.6 41 72.3 66 67.0 43 87.5 80 69.1 69 54.7 60 82.3 73 28.7 86 46.0 92 42.4 11 37.3 93 56.9 89 50.4 79
TCOF [69]71.2 36.6 72 33.9 82 48.1 45 29.1 97 35.7 107 38.3 84 29.0 22 31.4 35 38.7 8 52.8 68 48.7 96 80.6 41 72.2 37 67.1 67 87.4 36 69.3 90 56.0 107 82.1 36 28.7 86 46.2 95 42.5 62 38.2 118 58.7 126 50.5 93
EPMNet [133]71.3 38.9 117 38.5 125 49.9 112 29.0 96 34.2 76 41.2 106 30.0 91 34.6 104 39.4 75 53.9 104 52.7 128 80.6 41 72.5 104 67.4 105 87.4 36 69.0 58 55.5 95 82.0 13 28.4 38 45.0 64 42.3 1 36.3 6 55.3 15 49.8 1
IIOF-NLDP [131]72.5 36.3 42 33.3 53 47.7 7 27.6 68 34.3 77 37.4 48 29.8 82 31.7 42 39.2 63 53.3 91 48.7 96 81.2 103 72.2 37 67.0 43 87.5 80 69.8 111 56.8 119 82.2 57 29.4 115 50.8 131 42.8 108 37.1 78 56.8 85 49.9 4
Steered-L1 [118]73.5 36.0 17 32.9 42 47.9 20 27.0 53 33.3 60 37.7 68 30.3 102 32.3 55 39.9 97 53.2 86 48.0 64 81.0 90 72.5 104 67.5 112 87.5 80 68.9 44 55.0 77 82.2 57 28.8 94 46.7 101 42.7 103 37.0 68 57.3 103 50.3 66
Nguyen [33]74.0 39.6 121 33.9 82 52.6 125 32.5 122 37.9 118 43.3 118 30.0 91 35.5 115 40.2 106 54.1 111 49.0 104 80.9 78 72.0 10 66.8 18 87.4 36 68.6 5 53.8 16 82.0 13 28.8 94 47.8 113 42.4 11 36.8 47 56.1 55 50.3 66
BriefMatch [124]74.8 36.3 42 33.3 53 48.0 31 27.2 60 33.4 62 38.5 88 30.6 108 32.6 61 40.6 111 54.0 108 48.6 90 82.8 121 72.4 92 67.3 94 87.3 17 70.2 122 55.6 99 83.9 130 28.3 17 44.3 31 42.7 103 36.6 28 55.7 34 50.5 93
StereoOF-V1MT [119]75.2 36.8 86 35.3 111 48.1 45 28.3 83 35.1 99 36.9 3 31.4 118 36.6 119 40.5 109 54.6 119 48.6 90 81.3 105 72.0 10 66.8 18 87.2 9 69.5 101 54.9 69 82.6 105 29.7 124 48.8 122 42.7 103 36.5 19 55.1 9 50.1 28
SPSA-learn [13]78.5 37.4 100 33.6 67 49.4 103 29.8 107 35.1 99 41.4 110 30.9 112 33.2 78 40.7 112 53.5 96 47.2 34 80.4 19 72.2 37 67.0 43 87.4 36 68.8 34 54.1 33 82.2 57 29.5 119 52.2 134 42.9 114 37.1 78 57.0 95 50.3 66
GraphCuts [14]78.8 38.0 113 35.1 108 49.5 105 28.4 86 33.9 72 41.3 108 31.3 117 30.8 23 40.7 112 53.7 100 48.3 83 81.0 90 72.1 25 67.1 67 87.1 4 68.6 5 54.9 69 81.7 1 28.8 94 46.3 96 42.8 108 37.7 105 58.5 122 50.4 79
HBpMotionGpu [43]79.6 38.8 116 35.9 114 50.9 121 32.1 119 38.2 120 44.4 122 29.2 37 31.7 42 39.3 70 53.9 104 49.6 113 81.5 109 72.1 25 67.0 43 87.1 4 69.5 101 54.9 69 82.4 87 28.3 17 44.4 33 42.5 62 37.3 93 56.5 75 51.1 114
Dynamic MRF [7]79.9 36.2 29 34.1 89 48.0 31 27.5 66 34.6 88 37.4 48 30.9 112 36.8 121 40.4 108 54.5 117 49.3 110 81.9 115 71.9 5 66.8 18 87.2 9 69.4 99 55.5 95 82.5 98 29.0 104 47.8 113 42.5 62 37.5 102 56.8 85 50.5 93
2D-CLG [1]80.2 37.9 108 33.5 61 50.5 119 32.5 122 37.4 115 45.0 123 30.8 111 34.8 108 40.7 112 53.7 100 48.3 83 80.5 35 72.3 66 67.1 67 87.6 113 68.6 5 53.2 6 82.2 57 28.8 94 46.7 101 42.5 62 36.9 61 55.6 30 50.3 66
Black & Anandan [4]80.4 37.9 108 34.1 89 49.6 106 30.7 112 36.0 108 41.2 106 31.0 114 34.7 107 40.3 107 53.9 104 48.6 90 80.7 57 72.3 66 67.0 43 87.4 36 69.0 58 53.8 16 82.5 98 28.8 94 46.5 97 42.4 11 37.0 68 56.1 55 50.4 79
ROF-ND [107]80.6 37.0 92 32.8 38 48.1 45 27.7 71 34.7 89 37.6 63 29.7 77 32.3 55 39.1 51 54.2 113 51.4 124 80.4 19 72.4 92 67.3 94 87.4 36 69.5 101 56.9 120 82.0 13 29.7 124 49.0 125 43.2 121 37.8 109 57.7 113 50.2 49
TV-L1-improved [17]80.8 36.6 72 34.1 89 48.4 77 28.6 91 35.1 99 37.8 71 30.5 106 33.2 78 40.0 101 52.7 58 48.0 64 80.9 78 72.3 66 67.2 80 87.4 36 69.1 69 54.9 69 82.3 73 28.8 94 47.3 107 42.6 91 37.2 86 56.7 81 50.6 103
CBF [12]82.3 36.4 54 32.5 30 48.9 96 27.5 66 33.8 70 37.9 75 29.3 47 31.6 40 39.1 51 53.2 86 48.1 70 82.6 118 72.4 92 67.2 80 87.7 122 69.2 79 55.3 87 82.3 73 28.7 86 46.1 93 42.9 114 37.9 111 57.7 113 51.7 123
Rannacher [23]83.8 36.7 80 34.5 97 48.7 90 28.7 92 35.3 103 38.1 80 30.5 106 34.0 95 39.9 97 52.7 58 48.0 64 80.8 70 72.4 92 67.2 80 87.5 80 69.0 58 54.6 56 82.3 73 28.8 94 47.0 103 42.6 91 37.1 78 56.4 72 50.6 103
UnFlow [129]84.6 39.2 119 37.9 121 50.6 120 32.3 120 38.9 125 41.3 108 31.6 123 38.5 127 40.8 117 53.2 86 48.7 96 80.9 78 72.0 10 66.7 9 87.4 36 69.5 101 54.6 56 82.4 87 28.2 11 43.2 4 42.4 11 39.3 131 58.3 120 51.2 115
Correlation Flow [75]85.0 36.2 29 33.4 58 47.7 7 27.7 71 34.3 77 37.3 37 29.4 60 31.4 35 38.8 13 53.1 84 48.5 87 81.3 105 72.8 120 67.6 114 88.6 133 70.1 116 57.1 123 82.6 105 29.4 115 48.8 122 43.0 116 37.7 105 57.9 115 50.5 93
HBM-GC [105]85.9 37.7 105 34.7 102 49.8 109 27.1 57 32.4 42 37.9 75 28.8 12 29.6 3 39.2 63 52.6 49 47.3 36 80.8 70 73.2 126 68.1 124 88.2 128 70.0 113 57.3 125 82.7 109 28.9 103 45.0 64 43.5 124 37.6 104 57.2 101 51.3 117
SegOF [10]86.4 37.6 104 33.2 50 50.0 113 29.1 97 34.7 89 41.0 103 31.4 118 35.3 112 40.7 112 53.6 98 50.7 121 80.6 41 72.3 66 67.2 80 87.5 80 69.0 58 55.3 87 82.2 57 29.0 104 48.6 120 42.7 103 36.7 40 55.8 41 50.4 79
TriangleFlow [30]86.7 37.0 92 34.9 106 48.5 80 28.0 78 34.7 89 37.5 57 30.2 100 33.0 74 39.9 97 53.2 86 49.0 104 81.1 98 72.0 10 66.9 30 87.1 4 69.8 111 56.1 109 82.4 87 29.2 110 48.5 119 42.8 108 38.1 116 58.5 122 50.5 93
BlockOverlap [61]87.1 38.5 115 33.2 50 51.3 122 30.0 110 34.4 83 42.8 115 29.4 60 30.4 14 40.0 101 53.2 86 46.9 26 83.0 123 72.9 123 67.6 114 88.3 129 69.7 109 54.1 33 83.3 125 28.7 86 44.1 26 43.5 124 37.1 78 55.3 15 51.8 124
IAOF2 [51]89.2 37.9 108 35.9 114 49.1 98 29.6 105 36.1 110 40.0 94 29.3 47 33.4 85 40.0 101 54.1 111 50.2 118 81.0 90 72.4 92 67.4 105 87.4 36 69.2 79 54.9 69 82.4 87 28.6 75 45.5 84 42.4 11 37.9 111 57.6 109 50.6 103
Ad-TV-NDC [36]89.6 40.4 125 35.1 108 53.1 126 31.9 118 36.7 114 43.8 120 29.4 60 32.9 69 39.1 51 54.5 117 49.2 109 82.1 116 72.5 104 67.3 94 87.5 80 69.3 90 53.9 24 82.7 109 28.6 75 45.4 79 42.4 11 37.2 86 56.2 63 50.6 103
OFRF [134]95.0 38.9 117 36.1 117 50.4 116 29.5 102 35.0 97 40.5 97 29.6 74 34.4 101 39.0 43 53.3 91 48.9 102 81.1 98 72.6 114 67.7 120 87.3 17 70.1 116 57.3 125 82.5 98 29.1 108 47.6 111 42.6 91 37.4 99 58.0 116 50.0 9
AdaConv-v1 [126]96.6 37.2 99 36.6 118 47.5 3 34.3 127 39.1 127 51.1 133 36.1 131 39.4 129 52.9 135 58.2 131 53.1 129 83.8 128 70.9 1 65.4 2 86.6 2 69.7 109 54.7 60 84.4 132 38.6 135 46.5 97 77.4 135 38.2 118 54.6 3 60.3 135
LocallyOriented [52]97.6 37.5 102 35.9 114 49.2 99 29.6 105 36.2 111 39.1 89 30.1 98 33.8 92 39.5 83 53.7 100 50.0 116 81.3 105 72.3 66 67.2 80 87.5 80 70.2 122 56.2 115 82.9 116 28.8 94 45.6 87 42.5 62 37.7 105 57.6 109 50.5 93
ACK-Prior [27]99.1 36.4 54 33.7 71 48.1 45 26.7 37 33.1 55 37.1 18 30.7 109 33.3 82 39.7 93 53.6 98 50.0 116 81.0 90 73.5 130 68.6 127 88.3 129 70.8 129 59.8 133 82.7 109 29.7 124 48.7 121 43.6 127 39.5 132 62.1 133 51.3 117
Horn & Schunck [3]99.2 37.9 108 35.1 108 49.6 106 31.4 115 37.7 117 41.8 112 31.7 124 37.4 124 41.5 120 55.8 123 50.6 119 81.3 105 72.2 37 67.0 43 87.4 36 69.2 79 54.2 39 82.7 109 29.5 119 48.9 124 42.6 91 37.8 109 57.2 101 50.9 112
StereoFlow [44]99.3 46.3 134 45.9 135 54.3 127 38.3 134 45.4 135 45.7 125 29.3 47 33.8 92 39.1 51 52.9 76 47.7 52 81.0 90 74.4 134 70.5 135 87.6 113 72.0 133 66.3 135 82.4 87 28.4 38 45.0 64 42.4 11 38.0 115 59.1 127 50.5 93
Filter Flow [19]100.2 37.8 107 34.6 99 49.8 109 30.8 113 36.0 108 44.3 121 29.4 60 32.4 58 39.5 83 54.2 113 48.1 70 82.2 117 72.7 119 67.7 120 87.6 113 69.2 79 55.1 79 82.5 98 28.7 86 46.5 97 42.6 91 38.3 124 58.4 121 51.4 120
TI-DOFE [24]101.3 42.0 128 37.5 120 54.8 130 35.2 129 41.1 132 46.8 128 31.4 118 37.7 125 41.6 122 56.1 125 50.6 119 81.6 110 72.0 10 66.9 30 87.2 9 69.4 99 54.4 45 82.6 105 29.2 110 47.6 111 42.6 91 38.2 118 57.5 107 50.8 111
SILK [79]102.9 39.6 121 38.1 122 51.5 124 32.4 121 38.5 123 43.6 119 32.4 125 37.2 123 41.5 120 55.4 121 49.7 114 83.0 123 72.2 37 67.0 43 87.4 36 70.0 113 54.7 60 83.4 126 29.0 104 46.5 97 42.8 108 37.4 99 56.7 81 50.7 109
Bartels [41]104.6 37.1 95 35.0 107 49.3 102 28.2 80 34.8 93 40.5 97 29.9 88 33.1 77 40.5 109 54.2 113 49.7 114 83.9 129 73.0 124 67.6 114 88.7 134 71.8 132 56.1 109 85.6 134 28.6 75 43.9 17 43.6 127 38.1 116 57.0 95 53.2 130
SLK [47]111.6 41.6 127 38.7 126 54.4 128 33.0 124 38.3 122 45.5 124 33.3 126 38.6 128 42.8 124 57.8 129 51.8 126 83.5 127 72.1 25 67.3 94 86.5 1 70.1 116 55.8 102 82.7 109 30.0 127 51.4 132 43.0 116 38.2 118 57.5 107 51.5 121
NL-TV-NCC [25]113.0 37.1 95 35.7 113 48.0 31 27.8 75 35.0 97 37.6 63 31.0 114 35.4 114 40.0 101 56.0 124 54.2 132 82.6 118 73.8 132 68.6 127 89.1 135 70.6 128 58.4 132 82.5 98 30.4 131 50.0 128 44.0 131 39.8 133 60.2 131 52.4 128
GroupFlow [9]113.9 40.3 124 40.1 128 51.3 122 31.5 116 38.9 125 42.6 114 33.5 128 39.5 130 43.8 126 54.7 120 52.3 127 81.0 90 73.2 126 68.6 127 87.6 113 70.4 126 57.3 125 83.0 118 29.3 113 48.1 116 42.5 62 37.9 111 58.2 119 50.1 28
FFV1MT [106]114.2 39.6 121 40.8 130 50.3 115 34.8 128 38.8 124 46.6 127 36.5 132 45.8 133 44.6 128 56.2 126 49.0 104 81.7 111 72.5 104 67.4 105 87.4 36 70.2 122 54.7 60 83.2 121 30.1 129 49.3 127 42.8 108 38.6 125 57.6 109 51.3 117
Learning Flow [11]114.5 37.7 105 37.0 119 49.2 99 29.9 108 37.5 116 39.7 92 31.5 122 36.3 118 40.7 112 55.4 121 51.6 125 82.6 118 72.8 120 67.8 122 87.8 124 69.6 107 55.7 100 82.8 114 29.3 113 48.4 117 42.7 103 39.2 129 59.8 129 51.2 115
Heeger++ [104]114.9 40.6 126 42.5 132 50.4 116 33.5 125 38.2 120 43.0 117 37.6 133 48.1 134 44.9 129 56.2 126 49.0 104 81.7 111 73.4 129 68.9 132 87.5 80 70.1 116 56.0 107 82.8 114 30.3 130 49.1 126 42.6 91 37.7 105 56.9 89 50.3 66
2bit-BM-tele [98]115.8 37.9 108 34.7 102 50.1 114 30.1 111 36.4 113 41.7 111 30.2 100 32.2 54 41.3 119 54.3 116 49.4 111 84.1 131 73.3 128 68.1 124 88.3 129 72.2 134 57.2 124 85.5 133 30.4 131 52.7 135 44.4 132 38.2 118 56.3 68 54.1 132
FOLKI [16]119.5 44.6 132 40.4 129 58.4 133 35.7 130 42.3 133 47.3 129 33.3 126 40.7 131 44.9 129 59.4 134 53.6 130 86.5 134 72.5 104 67.6 114 87.3 17 70.1 116 55.8 102 83.2 121 29.4 115 48.4 117 43.1 119 38.7 126 58.5 122 52.0 125
Pyramid LK [2]123.6 46.1 133 38.9 127 61.0 134 36.7 133 40.4 130 50.9 132 39.9 134 36.6 119 49.4 133 64.1 135 61.2 135 87.7 135 73.1 125 68.6 127 87.4 36 70.1 116 56.1 109 83.0 118 29.6 122 50.7 130 43.2 121 39.2 129 61.2 132 51.5 121
Adaptive flow [45]124.3 43.8 130 38.2 123 56.5 131 35.8 131 40.5 131 50.2 131 31.4 118 34.5 102 42.5 123 56.5 128 50.9 122 83.9 129 73.5 130 68.7 131 88.1 127 70.2 122 57.4 128 82.9 116 29.4 115 47.5 109 43.6 127 39.0 128 59.1 127 52.0 125
PGAM+LK [55]125.0 42.5 129 41.4 131 54.6 129 33.7 126 40.1 129 45.8 126 33.9 129 41.1 132 43.3 125 59.3 133 55.2 133 85.5 133 72.8 120 68.1 124 87.5 80 70.8 129 56.9 120 83.6 127 29.6 122 50.0 128 43.0 116 38.7 126 58.6 125 52.1 127
HCIC-L [99]128.7 49.1 135 42.6 133 63.0 135 35.8 131 39.4 128 52.5 134 34.6 130 37.7 125 43.9 127 58.0 130 53.9 131 81.7 111 74.0 133 69.3 133 88.5 132 71.7 131 60.5 134 83.2 121 29.5 119 47.5 109 43.9 130 40.5 134 62.9 134 52.8 129
Periodicity [78]132.6 44.4 131 43.3 134 56.9 132 42.8 135 43.4 134 56.2 135 40.9 135 49.1 135 49.5 134 58.9 132 58.6 134 84.9 132 74.4 134 70.2 134 88.0 125 73.1 135 57.9 131 86.2 135 30.0 127 51.5 133 43.5 124 41.8 135 63.4 135 53.7 131
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

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