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]12.9 35.7 4 30.6 4 47.8 11 25.9 11 30.5 12 36.9 3 28.6 5 29.8 7 38.5 2 51.9 8 46.5 17 80.3 10 71.9 8 66.6 6 87.2 13 68.6 7 53.9 28 82.1 40 28.1 3 43.6 10 42.4 13 36.6 36 55.6 38 50.0 14
PMMST [114]13.8 35.8 6 30.8 5 47.9 21 26.5 34 31.0 22 37.3 37 28.6 5 29.9 8 38.4 1 51.7 4 46.0 7 80.2 5 72.0 13 66.7 12 87.3 21 68.5 3 53.3 10 82.0 14 28.1 3 43.7 15 42.4 13 36.5 26 55.5 33 50.0 14
PH-Flow [101]14.7 36.1 24 32.5 31 47.8 11 25.6 5 29.6 5 36.9 3 28.7 11 30.0 10 38.5 2 51.6 2 45.5 3 80.2 5 71.9 8 66.7 12 87.3 21 68.8 38 54.8 74 81.9 6 28.1 3 43.6 10 42.4 13 36.4 20 55.3 22 50.0 14
NNF-Local [87]14.9 35.7 4 31.4 8 47.6 5 25.5 3 29.6 5 36.9 3 28.6 5 29.9 8 38.5 2 52.4 33 48.0 68 80.3 10 72.0 13 66.6 6 87.4 41 68.7 21 54.4 52 82.0 14 28.1 3 43.5 8 42.4 13 36.2 8 55.0 11 50.0 14
NN-field [71]20.4 36.0 18 32.2 20 47.9 21 25.5 3 29.3 4 36.8 1 29.4 65 29.7 6 39.0 46 52.4 33 48.1 75 80.3 10 72.0 13 66.7 12 87.3 21 68.7 21 54.0 33 82.0 14 28.1 3 43.4 6 42.4 13 36.4 20 55.2 18 50.0 14
ProbFlowFields [128]24.8 35.9 11 32.4 25 48.0 33 25.8 9 30.5 12 37.2 32 28.6 5 30.3 14 38.5 2 52.1 21 46.4 13 80.7 63 72.3 74 67.1 74 87.5 91 68.6 7 53.8 19 82.1 40 28.0 2 42.8 3 42.3 2 36.1 4 54.6 6 50.1 34
IROF++ [58]25.0 36.2 31 33.0 49 47.8 11 26.1 17 30.9 19 36.9 3 29.1 33 31.0 33 38.9 29 51.6 2 45.6 4 80.4 19 72.0 13 66.8 22 87.2 13 68.6 7 53.4 11 82.2 63 28.3 22 44.6 48 42.4 13 36.5 26 55.3 22 50.4 89
Sparse-NonSparse [56]26.6 36.2 31 32.8 42 48.0 33 25.9 11 30.4 10 37.0 11 29.0 25 30.9 30 38.8 13 52.0 14 46.1 9 80.6 44 72.1 28 66.8 22 87.3 21 68.9 49 54.6 64 82.1 40 28.3 22 44.0 26 42.4 13 36.4 20 55.4 27 50.1 34
CombBMOF [113]27.8 35.9 11 31.0 6 47.8 11 25.8 9 30.5 12 36.8 1 29.2 41 30.8 26 39.5 88 52.4 33 47.4 44 80.3 10 72.1 28 66.8 22 87.4 41 68.9 49 54.5 57 82.1 40 28.5 65 44.6 48 42.3 2 36.0 3 54.6 6 50.0 14
nLayers [57]29.6 36.4 58 32.0 15 48.2 65 26.0 14 30.4 10 37.3 37 28.7 11 29.4 3 38.8 13 52.2 28 46.8 25 80.4 19 72.3 74 67.1 74 87.4 41 68.8 38 54.7 68 82.0 14 28.3 22 43.7 15 42.4 13 36.4 20 55.4 27 49.9 7
AGIF+OF [85]29.9 36.2 31 32.8 42 47.9 21 26.1 17 30.8 16 37.1 18 29.0 25 30.7 22 38.9 29 51.8 6 46.2 11 80.1 3 72.3 74 67.2 89 87.3 21 68.9 49 55.2 92 81.9 6 28.3 22 43.6 10 42.4 13 36.6 36 56.0 57 49.9 7
2DHMM-SAS [92]31.8 36.4 58 33.9 88 47.9 21 27.1 61 32.6 47 37.0 11 28.5 4 30.4 17 38.9 29 51.8 6 45.6 4 80.4 19 72.1 28 66.9 34 87.4 41 68.8 38 54.5 57 82.0 14 28.3 22 44.2 34 42.3 2 36.7 49 56.1 66 50.0 14
NNF-EAC [103]32.2 36.3 46 32.4 25 48.0 33 26.6 38 31.7 32 37.1 18 29.3 51 30.2 11 39.0 46 52.4 33 46.9 28 81.1 108 72.0 13 66.7 12 87.4 41 68.7 21 53.7 17 82.1 40 28.2 12 43.9 19 42.4 13 36.7 49 55.9 53 50.0 14
Layers++ [37]33.3 36.3 46 32.4 25 48.2 65 25.7 6 29.2 3 37.3 37 28.9 21 30.6 19 38.9 29 52.0 14 46.4 13 80.4 19 72.2 43 67.0 50 87.5 91 68.9 49 55.2 92 82.0 14 28.3 22 44.0 26 42.4 13 36.6 36 55.5 33 50.1 34
LSM [39]34.7 36.3 46 33.7 77 48.0 33 26.1 17 31.0 22 37.0 11 29.1 33 31.8 50 38.9 29 52.2 28 46.9 28 80.6 44 72.1 28 66.9 34 87.3 21 69.0 64 54.9 78 82.1 40 28.3 22 44.1 31 42.4 13 36.5 26 55.7 43 50.0 14
ComponentFusion [96]35.2 36.0 18 32.2 20 48.0 33 26.1 17 31.1 27 36.9 3 29.1 33 32.3 59 38.8 13 52.0 14 47.0 32 80.3 10 72.2 43 67.1 74 87.3 21 68.7 21 53.9 28 82.1 40 28.5 65 46.1 105 42.4 13 36.7 49 55.8 50 50.2 56
FlowFields [110]35.2 36.0 18 32.7 38 47.9 21 26.4 31 32.0 34 37.3 37 29.0 25 32.6 66 38.7 8 52.5 39 47.9 65 80.7 63 72.3 74 67.0 50 87.5 91 68.6 7 54.4 52 82.0 14 28.2 12 44.0 26 42.4 13 36.3 10 55.2 18 50.1 34
S2F-IF [123]35.9 35.9 11 32.5 31 47.8 11 26.2 24 31.6 31 37.2 32 29.0 25 31.9 55 38.6 7 52.3 30 47.6 49 80.4 19 72.4 100 67.2 89 87.5 91 68.7 21 54.5 57 81.9 6 28.4 44 44.7 53 42.4 13 36.3 10 55.2 18 50.1 34
FlowFields+ [130]36.0 35.9 11 32.6 35 47.9 21 26.4 31 32.2 38 37.4 49 29.0 25 32.6 66 38.7 8 52.3 30 47.7 55 80.6 44 72.3 74 67.1 74 87.5 91 68.7 21 54.6 64 82.0 14 28.2 12 44.0 26 42.4 13 36.3 10 55.2 18 50.1 34
TV-L1-MCT [64]36.6 36.8 94 34.7 113 48.2 65 26.7 39 32.4 44 37.3 37 28.6 5 30.9 30 39.0 46 51.9 8 45.7 6 80.5 37 72.2 43 67.0 50 87.3 21 68.6 7 53.0 6 82.3 83 28.3 22 44.4 39 42.4 13 36.1 4 54.9 10 50.2 56
WLIF-Flow [93]37.1 36.1 24 32.5 31 47.8 11 26.3 29 31.2 28 37.1 18 29.1 33 30.7 22 39.1 54 52.0 14 46.4 13 80.6 44 72.1 28 66.8 22 87.4 41 69.0 64 54.9 78 82.3 83 28.3 22 43.9 19 42.5 69 36.8 56 55.9 53 50.1 34
LME [70]39.8 35.8 6 31.0 6 47.8 11 26.9 50 32.2 38 38.4 92 29.2 41 32.6 66 38.8 13 51.9 8 46.7 22 80.4 19 72.6 129 67.4 117 87.7 138 68.8 38 54.9 78 82.0 14 28.1 3 43.5 8 42.4 13 36.3 10 55.3 22 50.0 14
COFM [59]40.2 36.1 24 32.0 15 48.1 49 26.1 17 30.8 16 37.1 18 28.8 14 30.3 14 38.8 13 51.7 4 46.0 7 80.0 1 72.2 43 67.2 89 87.2 13 68.9 49 56.1 124 81.7 2 28.1 3 42.8 3 43.1 132 37.1 90 56.9 103 50.7 122
FMOF [94]40.7 36.5 70 33.7 77 48.2 65 25.9 11 30.3 8 37.1 18 29.3 51 30.7 22 39.0 46 52.5 39 47.5 45 80.2 5 72.2 43 67.0 50 87.5 91 69.0 64 55.1 88 82.0 14 28.1 3 43.4 6 42.4 13 36.8 56 56.0 57 50.1 34
DeepFlow2 [108]41.1 36.2 31 32.4 25 48.2 65 27.1 61 32.9 52 37.8 77 29.2 41 32.9 74 39.0 46 52.5 39 47.5 45 80.5 37 72.2 43 66.9 34 87.5 91 68.5 3 52.9 5 82.1 40 28.3 22 44.4 39 42.4 13 36.4 20 55.4 27 50.2 56
RNLOD-Flow [121]41.1 36.3 46 33.5 66 48.0 33 26.8 44 32.6 47 37.1 18 29.2 41 31.8 50 38.8 13 52.1 21 46.9 28 80.2 5 72.2 43 67.0 50 87.3 21 69.0 64 55.2 92 82.1 40 28.3 22 44.2 34 42.4 13 37.1 90 56.9 103 49.8 2
OFLAF [77]41.2 35.8 6 31.5 9 47.8 11 25.7 6 29.8 7 37.0 11 29.0 25 31.2 36 38.7 8 52.0 14 46.8 25 80.1 3 72.4 100 67.3 105 87.4 41 68.9 49 55.3 97 82.0 14 28.6 84 45.4 89 42.4 13 37.1 90 57.1 113 50.1 34
FF++_ROB [146]42.0 36.0 18 32.6 35 47.9 21 26.8 44 32.6 47 37.6 65 29.3 51 32.4 62 38.9 29 52.5 39 48.3 89 80.5 37 72.4 100 67.1 74 87.4 41 68.8 38 54.3 47 82.2 63 28.2 12 44.0 26 42.4 13 36.3 10 55.1 13 50.1 34
DeepFlow [86]42.4 36.1 24 31.8 13 48.1 49 27.3 67 32.9 52 38.4 92 29.3 51 33.3 87 39.1 54 52.6 54 47.0 32 80.7 63 72.2 43 66.8 22 87.5 91 68.7 21 52.8 4 82.5 108 28.1 3 43.6 10 42.3 2 36.2 8 55.0 11 50.2 56
FGIK [136]43.1 38.3 126 32.7 38 51.4 136 30.5 124 35.5 115 45.9 141 25.0 1 29.5 4 40.5 121 54.4 129 48.0 68 80.4 19 66.3 1 59.5 1 85.6 1 65.3 1 44.9 1 81.1 1 26.8 1 37.4 1 42.0 1 34.2 1 51.0 1 49.8 2
Ramp [62]43.6 36.5 70 34.0 93 48.2 65 26.0 14 30.8 16 37.1 18 28.9 21 30.8 26 38.8 13 51.9 8 46.1 9 80.4 19 72.2 43 67.0 50 87.4 41 69.1 78 55.4 103 82.2 63 28.4 44 44.7 53 42.4 13 36.8 56 56.2 74 50.2 56
MDP-Flow [26]43.7 35.8 6 31.5 9 48.0 33 26.2 24 31.4 30 37.4 49 29.0 25 31.1 34 38.9 29 52.7 64 47.8 61 80.7 63 72.2 43 66.9 34 87.5 91 68.9 49 55.2 92 82.1 40 28.5 65 45.3 88 42.5 69 36.3 10 55.4 27 50.0 14
IROF-TV [53]45.1 36.3 46 33.6 73 48.2 65 26.2 24 31.0 22 37.0 11 29.3 51 33.6 93 39.1 54 51.9 8 46.5 17 80.8 78 72.3 74 67.0 50 87.6 128 68.5 3 53.9 28 81.9 6 28.3 22 44.9 65 42.3 2 36.6 36 55.6 38 50.4 89
PGM-C [120]45.3 36.2 31 33.3 58 48.1 49 26.5 34 32.2 38 37.5 58 29.2 41 32.9 74 38.8 13 52.5 39 48.3 89 80.7 63 72.3 74 67.0 50 87.5 91 68.6 7 54.0 33 82.0 14 28.3 22 44.6 48 42.4 13 36.5 26 55.5 33 50.4 89
Classic+NL [31]45.5 36.5 70 34.0 93 48.2 65 26.2 24 30.9 19 37.1 18 28.8 14 30.6 19 38.8 13 52.1 21 46.5 17 80.6 44 72.2 43 67.0 50 87.4 41 69.2 89 55.3 97 82.2 63 28.4 44 44.6 48 42.4 13 36.8 56 56.2 74 50.2 56
DF-Auto [115]46.0 36.8 94 31.9 14 48.9 105 28.5 97 33.7 73 40.8 112 28.8 14 30.3 14 38.7 8 52.5 39 47.3 38 80.4 19 72.1 28 66.7 12 87.4 41 68.6 7 53.8 19 82.0 14 28.4 44 44.7 53 42.5 69 36.8 56 56.3 79 50.2 56
FC-2Layers-FF [74]48.3 36.4 58 33.8 83 48.1 49 25.7 6 29.1 2 37.4 49 28.9 21 30.9 30 38.8 13 52.1 21 46.8 25 80.6 44 72.3 74 67.2 89 87.4 41 69.1 78 55.5 106 82.1 40 28.4 44 44.7 53 42.5 69 36.9 71 56.3 79 50.0 14
SuperFlow [81]49.3 36.5 70 32.2 20 48.8 102 28.3 91 33.4 66 40.9 113 29.5 74 32.6 66 39.4 80 52.5 39 46.7 22 80.9 86 72.2 43 66.9 34 87.5 91 68.5 3 53.4 11 82.0 14 28.3 22 44.7 53 42.4 13 36.3 10 55.4 27 50.1 34
HAST [109]49.8 36.1 24 31.7 11 48.1 49 26.1 17 31.0 22 37.0 11 29.3 51 31.7 45 39.2 68 51.9 8 46.5 17 80.3 10 72.3 74 67.3 105 87.2 13 69.3 101 56.4 132 82.0 14 28.4 44 45.0 73 42.5 69 37.3 106 57.3 117 50.0 14
CPM-Flow [116]50.6 36.2 31 33.5 66 48.1 49 26.5 34 32.2 38 37.5 58 29.3 51 32.6 66 38.9 29 52.7 64 48.7 103 80.7 63 72.3 74 67.0 50 87.5 91 68.7 21 53.8 19 82.2 63 28.4 44 44.7 53 42.4 13 36.5 26 55.5 33 50.3 75
Second-order prior [8]50.8 36.2 31 32.1 18 48.1 49 27.9 84 34.1 80 37.4 49 29.9 96 34.6 111 39.7 101 52.4 33 47.2 36 80.6 44 71.9 8 66.6 6 87.5 91 68.7 21 54.0 33 82.1 40 28.5 65 45.2 85 42.4 13 36.5 26 55.7 43 50.2 56
Aniso. Huber-L1 [22]51.7 36.7 88 33.5 66 48.6 95 28.5 97 34.3 84 38.2 88 29.3 51 31.8 50 38.9 29 52.5 39 47.5 45 80.6 44 72.0 13 66.7 12 87.4 41 68.6 7 54.3 47 81.9 6 28.5 65 45.0 73 42.4 13 36.8 56 56.0 57 50.3 75
Classic+CPF [83]51.8 36.4 58 33.6 73 47.9 21 26.3 29 31.3 29 37.0 11 28.8 14 31.1 34 38.9 29 52.0 14 46.5 17 80.0 1 72.5 116 67.4 117 87.4 41 69.2 89 56.1 124 82.0 14 28.6 84 45.2 85 42.4 13 37.2 99 57.3 117 50.0 14
RFlow [90]53.3 36.2 31 33.0 49 48.2 65 27.6 75 33.7 73 37.1 18 29.3 51 32.5 65 39.2 68 52.6 54 47.8 61 80.6 44 72.0 13 66.8 22 87.3 21 68.6 7 53.8 19 81.9 6 28.5 65 45.5 94 42.6 101 37.2 99 56.9 103 50.3 75
EpicFlow [102]53.3 36.2 31 33.3 58 48.1 49 26.9 50 33.1 58 37.5 58 29.4 65 33.0 79 39.0 46 52.6 54 48.5 94 80.8 78 72.3 74 67.0 50 87.5 91 68.6 7 54.1 37 82.0 14 28.4 44 44.8 62 42.4 13 36.6 36 55.7 43 50.4 89
Brox et al. [5]54.2 36.3 46 32.4 25 48.2 65 27.8 82 34.1 80 38.0 85 29.8 90 33.9 99 39.6 98 52.5 39 47.0 32 80.4 19 72.2 43 66.9 34 87.5 91 68.7 21 53.8 19 82.1 40 28.4 44 44.9 65 42.5 69 36.5 26 55.5 33 50.2 56
DMF_ROB [140]54.5 36.2 31 32.6 35 48.1 49 27.4 70 33.5 69 37.7 71 30.2 109 34.4 107 39.6 98 52.7 64 47.6 49 80.6 44 72.1 28 66.7 12 87.6 128 68.3 2 53.2 7 82.0 14 28.6 84 44.1 31 43.0 128 36.3 10 55.1 13 50.2 56
PWC-Net_ROB [148]54.9 36.4 58 34.4 105 48.0 33 27.3 67 33.9 78 37.7 71 29.7 84 34.8 115 39.1 54 52.5 39 48.9 110 80.4 19 72.4 100 67.3 105 87.4 41 69.0 64 54.1 37 82.2 63 28.2 12 43.9 19 42.4 13 36.3 10 55.1 13 49.9 7
S2D-Matching [84]55.1 36.6 79 34.2 100 48.2 65 26.9 50 32.5 46 37.2 32 28.8 14 30.7 22 38.9 29 52.1 21 46.4 13 80.9 86 72.3 74 67.1 74 87.5 91 69.1 78 55.3 97 82.2 63 28.5 65 44.7 53 42.4 13 36.7 49 55.9 53 50.2 56
FESL [72]55.5 36.6 79 33.9 88 48.0 33 26.4 31 31.7 32 37.3 37 29.1 33 31.3 37 38.9 29 52.6 54 47.6 49 80.3 10 72.4 100 67.3 105 87.4 41 69.3 101 55.9 117 82.1 40 28.4 44 44.9 65 42.3 2 37.0 79 56.6 92 50.1 34
p-harmonic [29]56.0 35.9 11 32.1 18 47.9 21 28.2 87 34.3 84 37.8 77 29.4 65 34.2 103 39.4 80 53.0 87 47.7 55 80.7 63 72.2 43 67.0 50 87.3 21 68.8 38 54.1 37 82.3 83 28.5 65 45.5 94 42.4 13 36.6 36 56.0 57 50.2 56
ComplOF-FED-GPU [35]57.1 36.3 46 33.4 63 48.0 33 26.8 44 33.0 55 37.3 37 30.4 113 34.0 100 39.6 98 52.5 39 48.1 75 80.9 86 72.1 28 66.8 22 87.4 41 68.7 21 54.3 47 82.1 40 28.5 65 45.1 80 42.5 69 36.8 56 56.0 57 50.2 56
LiteFlowNet [143]57.2 36.4 58 34.2 100 48.0 33 27.1 61 33.4 66 37.5 58 29.6 79 35.1 123 39.1 54 53.3 99 50.7 134 80.6 44 72.1 28 66.9 34 87.3 21 69.1 78 55.1 88 82.0 14 28.6 84 45.5 94 42.3 2 36.1 4 54.8 9 49.9 7
SepConv-v1 [127]57.4 27.1 2 27.5 2 36.4 2 24.9 2 31.0 22 40.3 105 27.6 3 28.4 2 48.9 146 54.0 119 47.3 38 83.0 138 72.0 13 66.7 12 87.1 6 69.1 78 52.6 3 83.6 140 32.2 147 43.9 19 55.7 148 37.0 79 53.8 4 55.4 147
ProFlow_ROB [147]57.6 36.2 31 32.8 42 48.2 65 26.9 50 33.3 63 37.7 71 29.1 33 32.2 57 38.8 13 52.6 54 48.7 103 80.7 63 72.4 100 67.2 89 87.4 41 68.7 21 53.8 19 82.2 63 28.5 65 45.2 85 42.4 13 37.0 79 56.5 87 50.3 75
TC-Flow [46]57.8 36.2 31 33.2 55 48.2 65 26.9 50 33.5 69 37.5 58 29.5 74 33.6 93 38.9 29 52.1 21 47.1 35 80.6 44 72.3 74 67.2 89 87.5 91 69.0 64 54.8 74 82.3 83 28.4 44 44.4 39 42.5 69 36.6 36 56.1 66 50.1 34
CtxSyn [137]58.4 26.8 1 25.3 1 36.2 1 23.8 1 27.2 1 39.5 100 26.3 2 26.1 1 48.0 145 51.4 1 44.1 1 82.1 129 71.6 4 66.0 4 87.1 6 70.2 135 54.2 44 84.5 147 39.3 150 45.6 98 77.2 150 38.0 128 52.3 3 59.7 149
EPPM w/o HM [88]59.0 35.8 6 32.3 24 47.6 5 26.7 39 33.0 55 36.9 3 30.0 100 35.5 127 39.4 80 52.6 54 48.9 110 80.4 19 72.2 43 67.1 74 87.4 41 69.3 101 55.9 117 82.3 83 28.4 44 44.9 65 42.5 69 36.8 56 56.1 66 50.1 34
DPOF [18]59.5 36.7 88 34.5 108 48.6 95 26.1 17 30.6 15 37.6 65 29.8 90 31.4 38 39.3 75 52.8 75 48.6 97 80.8 78 72.0 13 66.8 22 87.3 21 69.1 78 55.3 97 81.9 6 28.5 65 44.5 45 42.5 69 36.9 71 56.5 87 50.0 14
JOF [141]59.8 36.9 99 34.2 100 48.7 98 26.0 14 30.3 8 37.3 37 28.8 14 30.2 11 38.9 29 52.3 30 46.7 22 81.0 98 72.4 100 67.2 89 87.5 91 69.2 89 55.5 106 82.2 63 28.2 12 43.8 18 42.5 69 36.9 71 56.3 79 50.4 89
OFH [38]60.8 36.4 58 33.8 83 48.2 65 27.4 70 33.3 63 37.4 49 29.7 84 35.0 119 39.0 46 52.5 39 48.3 89 80.9 86 72.2 43 67.0 50 87.4 41 68.7 21 54.2 44 82.1 40 28.6 84 45.4 89 42.5 69 36.6 36 56.0 57 50.1 34
Efficient-NL [60]61.4 36.5 70 33.6 73 48.0 33 26.7 39 32.0 34 37.1 18 29.9 96 31.4 38 39.3 75 52.7 64 47.7 55 80.4 19 72.2 43 67.0 50 87.3 21 69.5 112 57.0 137 81.9 6 28.6 84 45.9 102 42.4 13 37.9 124 58.1 133 50.1 34
PMF [73]63.1 35.9 11 32.0 15 47.7 8 26.9 50 33.5 69 36.9 3 29.6 79 34.5 109 39.1 54 52.5 39 47.8 61 80.4 19 72.5 116 67.5 124 87.4 41 69.2 89 55.0 86 82.4 97 28.5 65 45.0 73 42.5 69 37.3 106 57.3 117 50.0 14
Local-TV-L1 [65]63.4 37.5 112 33.0 49 49.7 120 29.3 111 34.5 93 40.3 105 29.2 41 31.6 43 39.1 54 53.3 99 47.3 38 83.1 141 72.1 28 66.9 34 87.4 41 69.3 101 53.4 11 83.2 134 28.2 12 43.9 19 42.4 13 36.4 20 55.1 13 50.4 89
OAR-Flow [125]64.0 36.5 70 33.0 49 48.4 84 27.0 57 33.0 55 37.8 77 29.2 41 33.3 87 38.9 29 52.1 21 47.6 49 80.5 37 72.4 100 67.3 105 87.6 128 68.9 49 54.5 57 82.2 63 28.5 65 44.7 53 42.4 13 36.9 71 56.5 87 50.4 89
LFNet_ROB [151]64.0 36.6 79 33.5 66 48.4 84 28.4 94 35.0 105 38.4 92 29.9 96 34.8 115 39.5 88 52.4 33 47.8 61 80.6 44 72.1 28 66.9 34 87.4 41 68.9 49 54.8 74 82.1 40 28.3 22 44.4 39 42.6 101 36.6 36 55.4 27 50.4 89
Sparse Occlusion [54]64.2 36.5 70 33.7 77 48.2 65 27.6 75 34.1 80 37.3 37 29.3 51 31.8 50 38.8 13 52.8 75 48.1 75 80.5 37 72.3 74 67.1 74 87.4 41 69.2 89 56.1 124 82.0 14 28.5 65 45.4 89 42.3 2 37.2 99 57.0 109 50.2 56
TC/T-Flow [76]64.2 36.6 79 33.7 77 47.9 21 26.8 44 32.9 52 37.1 18 29.1 33 31.9 55 38.8 13 52.7 64 48.5 94 80.4 19 72.5 116 67.4 117 87.5 91 69.1 78 55.2 92 82.1 40 28.6 84 45.4 89 42.5 69 37.0 79 56.9 103 50.0 14
TF+OM [100]64.8 36.3 46 33.0 49 48.5 88 26.9 50 32.2 38 39.2 99 28.6 5 32.4 62 38.9 29 52.8 75 48.2 86 80.7 63 72.3 74 67.1 74 87.4 41 69.0 64 54.5 57 82.3 83 28.4 44 45.1 80 42.5 69 37.0 79 56.4 84 50.6 116
SRR-TVOF-NL [91]65.0 36.6 79 33.5 66 48.2 65 27.7 78 34.3 84 37.9 81 29.5 74 33.2 83 39.1 54 53.1 91 48.1 75 80.2 5 72.2 43 67.1 74 87.3 21 68.9 49 55.7 112 81.8 4 28.5 65 44.9 65 42.4 13 37.5 115 58.0 131 50.1 34
ALD-Flow [66]66.4 36.7 88 33.9 88 48.6 95 27.0 57 33.2 60 37.9 81 29.3 51 33.4 90 38.9 29 52.5 39 48.0 68 80.9 86 72.4 100 67.2 89 87.6 128 68.9 49 54.4 52 82.2 63 28.2 12 43.6 10 42.4 13 37.0 79 56.6 92 50.3 75
CLG-TV [48]66.8 36.6 79 33.4 63 48.5 88 28.2 87 34.4 90 38.2 88 29.7 84 33.6 93 39.4 80 52.8 75 48.0 68 80.9 86 72.2 43 66.9 34 87.5 91 68.7 21 54.0 33 82.1 40 28.4 44 45.1 80 42.4 13 37.0 79 56.5 87 50.2 56
SIOF [67]67.1 36.7 88 34.1 96 48.2 65 29.1 107 35.4 114 39.7 102 29.4 65 32.9 74 39.1 54 52.7 64 47.7 55 80.9 86 71.9 8 66.6 6 87.4 41 69.1 78 54.3 47 82.4 97 28.3 22 44.6 48 42.4 13 37.3 106 56.8 99 50.3 75
SimpleFlow [49]67.5 36.5 70 34.2 100 48.2 65 27.2 65 32.8 51 37.3 37 30.1 107 31.7 45 39.4 80 52.0 14 46.3 12 80.7 63 72.3 74 67.2 89 87.4 41 69.0 64 55.4 103 82.0 14 28.7 97 47.1 117 42.6 101 37.0 79 56.8 99 50.1 34
Complementary OF [21]68.0 36.1 24 33.3 58 47.8 11 26.7 39 33.2 60 37.3 37 30.4 113 32.9 74 39.5 88 52.8 75 48.7 103 81.1 108 72.3 74 67.2 89 87.3 21 68.8 38 54.7 68 82.2 63 28.7 97 45.6 98 42.5 69 36.8 56 56.7 95 50.3 75
AggregFlow [97]68.6 37.1 104 34.8 116 48.5 88 27.3 67 33.2 60 38.1 86 28.7 11 30.2 11 38.5 2 52.9 83 48.6 97 80.3 10 72.4 100 67.2 89 87.6 128 69.3 101 54.5 57 82.6 116 28.3 22 44.2 34 42.5 69 36.7 49 56.0 57 50.4 89
LDOF [28]69.1 37.1 104 33.7 77 48.8 102 29.5 112 35.3 112 40.6 111 30.0 100 34.3 104 39.7 101 52.8 75 47.9 65 80.9 86 72.2 43 66.9 34 87.4 41 68.8 38 53.6 16 82.3 83 28.3 22 44.5 45 42.4 13 36.6 36 55.8 50 50.4 89
SuperSlomo [132]69.5 32.1 3 27.9 3 42.8 3 29.9 120 32.2 38 48.3 145 31.1 130 30.8 26 49.0 147 53.4 104 45.1 2 82.8 136 70.9 2 65.3 2 86.6 3 69.5 112 51.7 2 84.0 144 32.2 147 42.2 2 55.7 148 37.2 99 52.2 2 57.3 148
F-TV-L1 [15]69.5 37.4 110 34.6 110 49.2 110 28.8 103 34.9 103 38.3 90 29.7 84 34.1 102 39.5 88 52.7 64 47.6 49 81.0 98 71.7 5 66.5 5 87.4 41 68.8 38 53.5 15 82.4 97 28.3 22 44.3 37 42.4 13 37.1 90 56.3 79 50.6 116
MLDP_OF [89]69.9 36.2 31 32.9 47 48.0 33 27.0 57 32.7 50 37.2 32 29.1 33 31.8 50 38.8 13 52.6 54 47.3 38 80.8 78 72.3 74 67.1 74 87.5 91 70.5 141 56.6 133 83.6 140 28.6 84 44.8 62 42.8 120 36.9 71 56.1 66 50.5 105
Aniso-Texture [82]70.8 36.1 24 32.4 25 48.2 65 28.0 85 34.4 90 37.6 65 30.0 100 32.8 73 39.3 75 52.7 64 48.1 75 80.7 63 72.4 100 67.3 105 87.3 21 69.2 89 56.2 130 82.3 83 28.4 44 44.5 45 42.4 13 37.2 99 57.0 109 50.2 56
IAOF [50]70.8 38.0 124 34.2 100 49.8 121 31.7 130 37.9 131 41.1 116 28.9 21 32.6 66 39.4 80 53.7 110 48.1 75 80.8 78 72.0 13 66.7 12 87.5 91 68.9 49 54.1 37 82.2 63 28.3 22 45.1 80 42.3 2 36.8 56 56.1 66 50.2 56
Classic++ [32]71.1 36.4 58 33.5 66 48.4 84 27.4 70 33.7 73 37.6 65 29.6 79 33.6 93 39.2 68 52.7 64 47.3 38 80.9 86 72.2 43 67.0 50 87.5 91 69.1 78 54.5 57 82.5 108 28.5 65 44.9 65 42.6 101 36.8 56 56.2 74 50.3 75
CostFilter [40]73.5 35.9 11 32.7 38 47.6 5 26.8 44 33.5 69 37.1 18 29.7 84 35.6 129 39.2 68 52.9 83 49.4 120 80.3 10 72.6 129 67.6 127 87.4 41 69.6 118 54.8 74 83.1 133 28.6 84 45.6 98 42.6 101 37.0 79 56.7 95 49.9 7
Shiralkar [42]73.7 36.5 70 34.6 110 48.1 49 28.3 91 34.3 84 37.2 32 29.8 90 36.9 135 40.0 112 53.9 115 49.0 113 80.5 37 71.8 6 66.6 6 87.2 13 69.2 89 55.1 88 82.4 97 29.2 122 48.0 128 42.5 69 36.6 36 55.7 43 50.1 34
Fusion [6]73.8 36.0 18 32.7 38 47.8 11 26.8 44 32.1 36 37.5 58 29.5 74 31.5 42 39.5 88 53.5 105 48.6 97 80.7 63 72.6 129 68.0 138 87.1 6 69.3 101 57.6 144 81.8 4 28.7 97 47.1 117 42.5 69 38.2 132 59.9 145 50.0 14
FlowNetS+ft+v [112]73.8 36.8 94 33.0 49 48.7 98 29.5 112 35.6 116 40.5 107 29.8 90 34.3 104 39.5 88 52.8 75 48.2 86 80.8 78 72.2 43 67.0 50 87.4 41 68.7 21 53.9 28 82.1 40 28.6 84 45.9 102 42.5 69 36.7 49 56.0 57 50.4 89
Occlusion-TV-L1 [63]74.0 36.6 79 33.8 83 48.5 88 28.4 94 34.8 100 37.7 71 29.5 74 33.0 79 39.5 88 53.0 87 48.1 75 81.1 108 72.1 28 66.8 22 87.5 91 68.9 49 53.4 11 82.4 97 29.0 116 44.7 53 42.6 101 36.8 56 55.6 38 50.4 89
TriFlow [95]74.0 37.0 101 35.3 123 48.8 102 28.7 101 34.5 93 41.0 114 29.2 41 33.4 90 38.8 13 53.0 87 48.8 109 80.4 19 72.3 74 67.3 105 87.4 41 69.2 89 55.5 106 82.1 40 28.5 65 44.8 62 42.4 13 36.9 71 56.4 84 50.1 34
ContFlow_ROB [150]74.1 37.2 108 34.4 105 49.0 107 28.9 105 35.7 117 40.5 107 30.4 113 35.9 130 39.5 88 53.2 93 49.9 126 80.7 63 72.2 43 67.1 74 87.5 91 69.0 64 55.9 117 82.1 40 28.2 12 43.9 19 42.4 13 36.1 4 55.6 38 49.8 2
SVFilterOh [111]74.4 36.3 46 32.2 20 48.1 49 26.2 24 30.9 19 37.4 49 29.2 41 30.6 19 39.3 75 52.6 54 47.5 45 81.0 98 72.6 129 67.6 127 87.6 128 69.3 101 55.9 117 82.3 83 28.5 65 43.7 15 43.3 137 37.3 106 57.1 113 51.0 126
CNN-flow-warp+ref [117]75.5 36.3 46 31.7 11 48.7 98 28.5 97 34.7 96 39.5 100 30.4 113 35.0 119 39.8 105 54.0 119 48.1 75 81.2 113 72.3 74 67.0 50 87.4 41 68.6 7 53.2 7 82.4 97 28.8 105 47.1 117 42.5 69 36.6 36 55.7 43 50.3 75
CRTflow [80]75.6 36.7 88 33.8 83 48.5 88 27.7 78 33.8 76 37.4 49 30.7 122 35.3 124 40.9 131 52.9 83 48.1 75 81.8 126 72.2 43 66.9 34 87.4 41 68.9 49 54.1 37 82.3 83 28.4 44 44.9 65 42.5 69 36.8 56 56.1 66 50.5 105
3DFlow [135]76.0 36.4 58 33.8 83 47.9 21 26.5 34 32.1 36 37.1 18 29.8 90 31.7 45 39.1 54 52.5 39 47.7 55 80.6 44 72.5 116 67.3 105 88.0 141 70.0 125 57.8 145 82.2 63 29.1 120 47.4 121 42.5 69 37.4 112 57.6 124 49.9 7
FlowNet2 [122]77.8 39.4 133 38.2 137 50.4 128 29.2 110 34.8 100 41.9 125 30.0 100 34.6 111 39.4 80 53.3 99 51.0 137 80.6 44 72.5 116 67.4 117 87.4 41 68.8 38 54.3 47 82.0 14 28.4 44 45.0 73 42.3 2 36.5 26 55.7 43 49.8 2
Modified CLG [34]78.6 36.9 99 32.8 42 49.4 114 30.9 127 36.3 125 42.8 127 30.0 100 34.8 115 39.9 108 53.0 87 47.9 65 80.7 63 72.2 43 66.9 34 87.5 91 68.7 21 53.8 19 82.2 63 28.4 44 45.1 80 42.5 69 36.9 71 56.2 74 50.5 105
ResPWCR_ROB [145]78.6 36.4 58 34.0 93 48.1 49 28.2 87 34.9 103 38.9 96 30.7 122 35.0 119 39.7 101 53.7 110 50.6 131 81.5 120 71.8 6 66.6 6 87.0 5 70.7 143 56.0 121 84.3 145 28.4 44 44.9 65 42.5 69 36.5 26 55.9 53 50.0 14
Adaptive [20]78.8 36.8 94 34.4 105 48.5 88 28.8 103 35.2 111 37.7 71 29.4 65 33.2 83 39.2 68 52.6 54 47.6 49 80.6 44 72.3 74 67.0 50 87.5 91 69.1 78 54.7 68 82.3 83 28.7 97 46.0 104 42.4 13 37.3 106 56.9 103 50.4 89
TCOF [69]78.9 36.6 79 33.9 88 48.1 49 29.1 107 35.7 117 38.3 90 29.0 25 31.4 38 38.7 8 52.8 75 48.7 103 80.6 44 72.2 43 67.1 74 87.4 41 69.3 101 56.0 121 82.1 40 28.7 97 46.2 107 42.5 69 38.2 132 58.7 141 50.5 105
EPMNet [133]79.3 38.9 130 38.5 140 49.9 124 29.0 106 34.2 83 41.2 117 30.0 100 34.6 111 39.4 80 53.9 115 52.7 143 80.6 44 72.5 116 67.4 117 87.4 41 69.0 64 55.5 106 82.0 14 28.4 44 45.0 73 42.3 2 36.3 10 55.3 22 49.8 2
AugFNG_ROB [144]79.3 37.7 115 35.6 125 49.6 117 29.5 112 36.0 120 41.4 121 30.4 113 37.7 138 40.1 117 53.5 105 50.5 130 81.0 98 72.5 116 67.5 124 87.4 41 68.7 21 54.4 52 82.0 14 28.5 65 44.4 39 42.4 13 35.3 2 54.0 5 49.4 1
IIOF-NLDP [131]80.4 36.3 46 33.3 58 47.7 8 27.6 75 34.3 84 37.4 49 29.8 90 31.7 45 39.2 68 53.3 99 48.7 103 81.2 113 72.2 43 67.0 50 87.5 91 69.8 122 56.8 134 82.2 63 29.4 127 50.8 145 42.8 120 37.1 90 56.8 99 49.9 7
Steered-L1 [118]81.2 36.0 18 32.9 47 47.9 21 27.0 57 33.3 63 37.7 71 30.3 112 32.3 59 39.9 108 53.2 93 48.0 68 81.0 98 72.5 116 67.5 124 87.5 91 68.9 49 55.0 86 82.2 63 28.8 105 46.7 114 42.7 115 37.0 79 57.3 117 50.3 75
Nguyen [33]82.5 39.6 134 33.9 88 52.6 139 32.5 135 37.9 131 43.3 130 30.0 100 35.5 127 40.2 118 54.1 123 49.0 113 80.9 86 72.0 13 66.8 22 87.4 41 68.6 7 53.8 19 82.0 14 28.8 105 47.8 126 42.4 13 36.8 56 56.1 66 50.3 75
BriefMatch [124]83.2 36.3 46 33.3 58 48.0 33 27.2 65 33.4 66 38.5 95 30.6 120 32.6 66 40.6 124 54.0 119 48.6 97 82.8 136 72.4 100 67.3 105 87.3 21 70.2 135 55.6 111 83.9 143 28.3 22 44.3 37 42.7 115 36.6 36 55.7 43 50.5 105
StereoOF-V1MT [119]83.8 36.8 94 35.3 123 48.1 49 28.3 91 35.1 108 36.9 3 31.4 132 36.6 132 40.5 121 54.6 133 48.6 97 81.3 115 72.0 13 66.8 22 87.2 13 69.5 112 54.9 78 82.6 116 29.7 137 48.8 135 42.7 115 36.5 26 55.1 13 50.1 34
SPSA-learn [13]87.2 37.4 110 33.6 73 49.4 114 29.8 119 35.1 108 41.4 121 30.9 126 33.2 83 40.7 125 53.5 105 47.2 36 80.4 19 72.2 43 67.0 50 87.4 41 68.8 38 54.1 37 82.2 63 29.5 132 52.2 149 42.9 126 37.1 90 57.0 109 50.3 75
GraphCuts [14]87.6 38.0 124 35.1 120 49.5 116 28.4 94 33.9 78 41.3 119 31.3 131 30.8 26 40.7 125 53.7 110 48.3 89 81.0 98 72.1 28 67.1 74 87.1 6 68.6 7 54.9 78 81.7 2 28.8 105 46.3 108 42.8 120 37.7 118 58.5 137 50.4 89
HBpMotionGpu [43]88.6 38.8 129 35.9 127 50.9 133 32.1 132 38.2 133 44.4 134 29.2 41 31.7 45 39.3 75 53.9 115 49.6 122 81.5 120 72.1 28 67.0 50 87.1 6 69.5 112 54.9 78 82.4 97 28.3 22 44.4 39 42.5 69 37.3 106 56.5 87 51.1 127
Dynamic MRF [7]88.8 36.2 31 34.1 96 48.0 33 27.5 73 34.6 95 37.4 49 30.9 126 36.8 134 40.4 120 54.5 131 49.3 119 81.9 127 71.9 8 66.8 22 87.2 13 69.4 110 55.5 106 82.5 108 29.0 116 47.8 126 42.5 69 37.5 115 56.8 99 50.5 105
ROF-ND [107]88.8 37.0 101 32.8 42 48.1 49 27.7 78 34.7 96 37.6 65 29.7 84 32.3 59 39.1 54 54.2 125 51.4 138 80.4 19 72.4 100 67.3 105 87.4 41 69.5 112 56.9 135 82.0 14 29.7 137 49.0 138 43.2 134 37.8 122 57.7 128 50.2 56
2D-CLG [1]89.2 37.9 119 33.5 66 50.5 131 32.5 135 37.4 128 45.0 136 30.8 125 34.8 115 40.7 125 53.7 110 48.3 89 80.5 37 72.3 74 67.1 74 87.6 128 68.6 7 53.2 7 82.2 63 28.8 105 46.7 114 42.5 69 36.9 71 55.6 38 50.3 75
Black & Anandan [4]89.5 37.9 119 34.1 96 49.6 117 30.7 125 36.0 120 41.2 117 31.0 128 34.7 114 40.3 119 53.9 115 48.6 97 80.7 63 72.3 74 67.0 50 87.4 41 69.0 64 53.8 19 82.5 108 28.8 105 46.5 109 42.4 13 37.0 79 56.1 66 50.4 89
TV-L1-improved [17]89.8 36.6 79 34.1 96 48.4 84 28.6 100 35.1 108 37.8 77 30.5 118 33.2 83 40.0 112 52.7 64 48.0 68 80.9 86 72.3 74 67.2 89 87.4 41 69.1 78 54.9 78 82.3 83 28.8 105 47.3 120 42.6 101 37.2 99 56.7 95 50.6 116
CBF [12]91.0 36.4 58 32.5 31 48.9 105 27.5 73 33.8 76 37.9 81 29.3 51 31.6 43 39.1 54 53.2 93 48.1 75 82.6 133 72.4 100 67.2 89 87.7 138 69.2 89 55.3 97 82.3 83 28.7 97 46.1 105 42.9 126 37.9 124 57.7 128 51.7 136
Rannacher [23]93.0 36.7 88 34.5 108 48.7 98 28.7 101 35.3 112 38.1 86 30.5 118 34.0 100 39.9 108 52.7 64 48.0 68 80.8 78 72.4 100 67.2 89 87.5 91 69.0 64 54.6 64 82.3 83 28.8 105 47.0 116 42.6 101 37.1 90 56.4 84 50.6 116
Correlation Flow [75]93.9 36.2 31 33.4 63 47.7 8 27.7 78 34.3 84 37.3 37 29.4 65 31.4 38 38.8 13 53.1 91 48.5 94 81.3 115 72.8 135 67.6 127 88.6 149 70.1 129 57.1 138 82.6 116 29.4 127 48.8 135 43.0 128 37.7 118 57.9 130 50.5 105
UnFlow [129]94.0 39.2 132 37.9 134 50.6 132 32.3 133 38.9 139 41.3 119 31.6 137 38.5 141 40.8 130 53.2 93 48.7 103 80.9 86 72.0 13 66.7 12 87.4 41 69.5 112 54.6 64 82.4 97 28.2 12 43.2 5 42.4 13 39.3 145 58.3 135 51.2 128
HBM-GC [105]95.4 37.7 115 34.7 113 49.8 121 27.1 61 32.4 44 37.9 81 28.8 14 29.6 5 39.2 68 52.6 54 47.3 38 80.8 78 73.2 141 68.1 139 88.2 144 70.0 125 57.3 140 82.7 120 28.9 115 45.0 73 43.5 138 37.6 117 57.2 115 51.3 130
TriangleFlow [30]95.7 37.0 101 34.9 117 48.5 88 28.0 85 34.7 96 37.5 58 30.2 109 33.0 79 39.9 108 53.2 93 49.0 113 81.1 108 72.0 13 66.9 34 87.1 6 69.8 122 56.1 124 82.4 97 29.2 122 48.5 132 42.8 120 38.1 130 58.5 137 50.5 105
TVL1_ROB [139]96.0 40.0 137 35.0 118 52.6 139 33.3 138 38.6 137 45.0 136 29.6 79 34.3 104 39.8 105 54.0 119 48.2 86 81.3 115 72.2 43 66.9 34 87.5 91 69.0 64 53.7 17 82.5 108 28.8 105 46.5 109 42.6 101 36.8 56 56.0 57 50.5 105
SegOF [10]96.2 37.6 114 33.2 55 50.0 125 29.1 107 34.7 96 41.0 114 31.4 132 35.3 124 40.7 125 53.6 108 50.7 134 80.6 44 72.3 74 67.2 89 87.5 91 69.0 64 55.3 97 82.2 63 29.0 116 48.6 133 42.7 115 36.7 49 55.8 50 50.4 89
BlockOverlap [61]97.0 38.5 128 33.2 55 51.3 134 30.0 122 34.4 90 42.8 127 29.4 65 30.4 17 40.0 112 53.2 93 46.9 28 83.0 138 72.9 138 67.6 127 88.3 145 69.7 120 54.1 37 83.3 138 28.7 97 44.1 31 43.5 138 37.1 90 55.3 22 51.8 137
IAOF2 [51]99.1 37.9 119 35.9 127 49.1 109 29.6 116 36.1 123 40.0 104 29.3 51 33.4 90 40.0 112 54.1 123 50.2 129 81.0 98 72.4 100 67.4 117 87.4 41 69.2 89 54.9 78 82.4 97 28.6 84 45.5 94 42.4 13 37.9 124 57.6 124 50.6 116
Ad-TV-NDC [36]99.9 40.4 140 35.1 120 53.1 141 31.9 131 36.7 127 43.8 132 29.4 65 32.9 74 39.1 54 54.5 131 49.2 118 82.1 129 72.5 116 67.3 105 87.5 91 69.3 101 53.9 28 82.7 120 28.6 84 45.4 89 42.4 13 37.2 99 56.2 74 50.6 116
OFRF [134]105.2 38.9 130 36.1 130 50.4 128 29.5 112 35.0 105 40.5 107 29.6 79 34.4 107 39.0 46 53.3 99 48.9 110 81.1 108 72.6 129 67.7 134 87.3 21 70.1 129 57.3 140 82.5 108 29.1 120 47.6 124 42.6 101 37.4 112 58.0 131 50.0 14
AdaConv-v1 [126]107.7 37.2 108 36.6 131 47.5 4 34.3 142 39.1 142 51.1 148 36.1 146 39.4 143 52.9 150 58.2 145 53.1 144 83.8 143 70.9 2 65.4 3 86.6 3 69.7 120 54.7 68 84.4 146 38.6 149 46.5 109 77.4 151 38.2 132 54.6 6 60.3 150
LocallyOriented [52]108.2 37.5 112 35.9 127 49.2 110 29.6 116 36.2 124 39.1 98 30.1 107 33.8 97 39.5 88 53.7 110 50.0 127 81.3 115 72.3 74 67.2 89 87.5 91 70.2 135 56.2 130 82.9 129 28.8 105 45.6 98 42.5 69 37.7 118 57.6 124 50.5 105
ACK-Prior [27]109.2 36.4 58 33.7 77 48.1 49 26.7 39 33.1 58 37.1 18 30.7 122 33.3 87 39.7 101 53.6 108 50.0 127 81.0 98 73.5 145 68.6 142 88.3 145 70.8 144 59.8 148 82.7 120 29.7 137 48.7 134 43.6 141 39.5 146 62.1 148 51.3 130
StereoFlow [44]110.2 46.3 149 45.9 150 54.3 142 38.3 149 45.4 150 45.7 139 29.3 51 33.8 97 39.1 54 52.9 83 47.7 55 81.0 98 74.4 149 70.5 150 87.6 128 72.0 148 66.3 150 82.4 97 28.4 44 45.0 73 42.4 13 38.0 128 59.1 142 50.5 105
Horn & Schunck [3]110.3 37.9 119 35.1 120 49.6 117 31.4 128 37.7 130 41.8 124 31.7 138 37.4 137 41.5 133 55.8 137 50.6 131 81.3 115 72.2 43 67.0 50 87.4 41 69.2 89 54.2 44 82.7 120 29.5 132 48.9 137 42.6 101 37.8 122 57.2 115 50.9 125
WOLF_ROB [149]110.5 38.3 126 38.0 135 49.0 107 29.6 116 35.9 119 39.0 97 30.6 120 35.0 119 39.8 105 54.4 129 52.4 142 82.0 128 72.5 116 67.6 127 87.4 41 69.8 122 55.4 103 82.8 126 29.4 127 49.1 139 42.5 69 37.1 90 56.6 92 50.2 56
Filter Flow [19]111.2 37.8 118 34.6 110 49.8 121 30.8 126 36.0 120 44.3 133 29.4 65 32.4 62 39.5 88 54.2 125 48.1 75 82.2 131 72.7 134 67.7 134 87.6 128 69.2 89 55.1 88 82.5 108 28.7 97 46.5 109 42.6 101 38.3 138 58.4 136 51.4 133
TI-DOFE [24]113.1 42.0 143 37.5 133 54.8 145 35.2 144 41.1 147 46.8 143 31.4 132 37.7 138 41.6 135 56.1 139 50.6 131 81.6 122 72.0 13 66.9 34 87.2 13 69.4 110 54.4 52 82.6 116 29.2 122 47.6 124 42.6 101 38.2 132 57.5 121 50.8 124
SILK [79]114.7 39.6 134 38.1 136 51.5 138 32.4 134 38.5 136 43.6 131 32.4 139 37.2 136 41.5 133 55.4 135 49.7 123 83.0 138 72.2 43 67.0 50 87.4 41 70.0 125 54.7 68 83.4 139 29.0 116 46.5 109 42.8 120 37.4 112 56.7 95 50.7 122
Bartels [41]116.0 37.1 104 35.0 118 49.3 113 28.2 87 34.8 100 40.5 107 29.9 96 33.1 82 40.5 121 54.2 125 49.7 123 83.9 144 73.0 139 67.6 127 88.7 150 71.8 147 56.1 124 85.6 149 28.6 84 43.9 19 43.6 141 38.1 130 57.0 109 53.2 144
SLK [47]124.2 41.6 142 38.7 141 54.4 143 33.0 137 38.3 135 45.5 138 33.3 140 38.6 142 42.8 137 57.8 143 51.8 140 83.5 142 72.1 28 67.3 105 86.5 2 70.1 129 55.8 115 82.7 120 30.0 140 51.4 147 43.0 128 38.2 132 57.5 121 51.5 134
NL-TV-NCC [25]125.1 37.1 104 35.7 126 48.0 33 27.8 82 35.0 105 37.6 65 31.0 128 35.4 126 40.0 112 56.0 138 54.2 147 82.6 133 73.8 147 68.6 142 89.1 151 70.6 142 58.4 147 82.5 108 30.4 144 50.0 142 44.0 145 39.8 148 60.2 146 52.4 142
GroupFlow [9]126.9 40.3 139 40.1 143 51.3 134 31.5 129 38.9 139 42.6 126 33.5 142 39.5 144 43.8 139 54.7 134 52.3 141 81.0 98 73.2 141 68.6 142 87.6 128 70.4 140 57.3 140 83.0 131 29.3 125 48.1 129 42.5 69 37.9 124 58.2 134 50.1 34
FFV1MT [106]127.0 39.6 134 40.8 145 50.3 127 34.8 143 38.8 138 46.6 142 36.5 147 45.8 148 44.6 142 56.2 140 49.0 113 81.7 123 72.5 116 67.4 117 87.4 41 70.2 135 54.7 68 83.2 134 30.1 142 49.3 141 42.8 120 38.6 139 57.6 124 51.3 130
Learning Flow [11]127.5 37.7 115 37.0 132 49.2 110 29.9 120 37.5 129 39.7 102 31.5 136 36.3 131 40.7 125 55.4 135 51.6 139 82.6 133 72.8 135 67.8 137 87.8 140 69.6 118 55.7 112 82.8 126 29.3 125 48.4 130 42.7 115 39.2 143 59.8 144 51.2 128
Heeger++ [104]127.9 40.6 141 42.5 147 50.4 128 33.5 139 38.2 133 43.0 129 37.6 148 48.1 149 44.9 143 56.2 140 49.0 113 81.7 123 73.4 144 68.9 147 87.5 91 70.1 129 56.0 121 82.8 126 30.3 143 49.1 139 42.6 101 37.7 118 56.9 103 50.3 75
2bit-BM-tele [98]128.4 37.9 119 34.7 113 50.1 126 30.1 123 36.4 126 41.7 123 30.2 109 32.2 57 41.3 132 54.3 128 49.4 120 84.1 146 73.3 143 68.1 139 88.3 145 72.2 149 57.2 139 85.5 148 30.4 144 52.7 150 44.4 146 38.2 132 56.3 79 54.1 146
H+S_ROB [138]129.4 40.0 137 38.4 139 51.4 136 34.1 141 38.9 139 44.9 135 35.1 145 42.5 147 44.2 141 59.3 147 49.7 123 82.3 132 72.5 116 67.7 134 87.1 6 70.0 125 55.7 112 82.7 120 30.4 144 50.9 146 43.2 134 39.6 147 57.5 121 51.9 138
FOLKI [16]133.1 44.6 147 40.4 144 58.4 148 35.7 145 42.3 148 47.3 144 33.3 140 40.7 145 44.9 143 59.4 149 53.6 145 86.5 149 72.5 116 67.6 127 87.3 21 70.1 129 55.8 115 83.2 134 29.4 127 48.4 130 43.1 132 38.7 140 58.5 137 52.0 139
Pyramid LK [2]137.6 46.1 148 38.9 142 61.0 149 36.7 148 40.4 145 50.9 147 39.9 149 36.6 132 49.4 148 64.1 150 61.2 150 87.7 150 73.1 140 68.6 142 87.4 41 70.1 129 56.1 124 83.0 131 29.6 135 50.7 144 43.2 134 39.2 143 61.2 147 51.5 134
Adaptive flow [45]138.3 43.8 145 38.2 137 56.5 146 35.8 146 40.5 146 50.2 146 31.4 132 34.5 109 42.5 136 56.5 142 50.9 136 83.9 144 73.5 145 68.7 146 88.1 143 70.2 135 57.4 143 82.9 129 29.4 127 47.5 122 43.6 141 39.0 142 59.1 142 52.0 139
PGAM+LK [55]139.1 42.5 144 41.4 146 54.6 144 33.7 140 40.1 144 45.8 140 33.9 143 41.1 146 43.3 138 59.3 147 55.2 148 85.5 148 72.8 135 68.1 139 87.5 91 70.8 144 56.9 135 83.6 140 29.6 135 50.0 142 43.0 128 38.7 140 58.6 140 52.1 141
HCIC-L [99]143.0 49.1 150 42.6 148 63.0 150 35.8 146 39.4 143 52.5 149 34.6 144 37.7 138 43.9 140 58.0 144 53.9 146 81.7 123 74.0 148 69.3 148 88.5 148 71.7 146 60.5 149 83.2 134 29.5 132 47.5 122 43.9 144 40.5 149 62.9 149 52.8 143
Periodicity [78]147.4 44.4 146 43.3 149 56.9 147 42.8 150 43.4 149 56.2 150 40.9 150 49.1 150 49.5 149 58.9 146 58.6 149 84.9 147 74.4 149 70.2 149 88.0 141 73.1 150 57.9 146 86.2 150 30.0 140 51.5 148 43.5 138 41.8 150 63.4 150 53.7 145
AVG_FLOW_ROB [142]148.3 76.9 151 76.7 151 78.2 151 71.8 151 68.8 151 76.4 151 64.0 151 60.2 151 65.8 151 82.9 151 80.9 151 91.0 151 80.9 151 79.6 151 87.5 91 83.9 151 84.0 151 86.6 151 53.7 151 65.3 151 47.7 147 62.3 151 71.1 151 70.4 151
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

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