Optical flow evaluation results Statistics:     Average   SD   R2.5   R5.0   R10.0   A50   A75   A95  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
R2.5
angle
error
avg. Army
(Hidden texture)
GT   im0   im1
Mequon
(Hidden texture)
GT   im0   im1
Schefflera
(Hidden texture)
GT   im0   im1
Wooden
(Hidden texture)
GT   im0   im1
Grove
(Synthetic)
GT   im0   im1
Urban
(Synthetic)
GT   im0   im1
Yosemite
(Synthetic)
GT   im0   im1
Teddy
(Stereo)
GT   im0   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
NNF-Local [87]13.7 20.0 3 43.3 3 13.0 3 15.9 10 45.3 25 16.1 14 12.5 4 34.1 9 12.8 9 9.68 19 32.0 11 7.01 23 23.3 4 30.0 4 16.2 4 22.0 32 45.4 9 23.8 61 25.8 19 44.8 6 17.6 17 4.37 10 14.4 28 0.48 1
NN-field [71]14.5 22.1 7 44.0 5 14.6 4 18.4 23 47.3 38 19.2 28 12.5 4 32.9 6 14.0 14 6.57 2 28.2 4 3.57 2 23.4 5 30.1 5 15.9 3 17.9 15 36.8 1 15.8 4 35.9 50 51.5 32 27.4 49 4.58 13 15.3 31 0.55 2
TC/T-Flow [76]19.4 19.9 2 46.9 10 10.2 1 16.0 11 47.8 40 13.9 5 13.0 8 36.6 20 11.1 4 8.90 12 35.0 35 6.10 12 27.2 17 35.7 22 21.0 14 15.7 4 47.2 17 15.8 4 21.0 7 39.2 2 42.1 76 7.86 42 19.5 45 10.9 55
ALD-Flow [66]19.7 21.6 6 46.0 7 15.9 6 15.5 8 41.3 9 15.6 10 13.1 9 35.2 12 12.2 5 8.17 10 33.4 21 5.35 9 28.1 24 37.3 34 20.3 10 16.4 6 47.4 19 16.0 6 26.5 22 45.4 8 41.8 74 8.39 46 22.3 55 11.3 57
ComponentFusion [96]19.9 20.0 3 46.3 8 14.8 5 16.6 14 40.3 6 18.5 25 11.7 3 33.6 7 10.9 3 7.09 5 35.2 37 4.45 5 27.6 20 36.0 25 21.4 17 21.5 28 54.1 51 20.2 30 31.8 43 56.8 59 16.2 10 5.46 23 12.8 21 7.47 29
nLayers [57]21.0 22.7 9 40.3 2 18.4 9 27.2 89 45.9 29 30.4 89 15.7 22 35.4 14 21.4 61 8.12 9 26.6 2 6.21 13 22.5 2 29.0 3 15.5 2 19.9 20 40.8 4 17.8 9 31.3 39 52.6 41 16.9 15 4.26 7 11.2 8 5.84 7
OFLAF [77]21.5 29.6 34 47.4 12 24.8 18 17.8 19 40.9 7 18.3 23 11.6 2 26.9 2 13.2 11 11.5 39 29.3 8 8.97 58 23.7 6 30.9 6 16.5 5 22.2 36 41.5 5 19.3 20 30.2 34 50.6 27 32.9 55 5.94 28 13.8 23 8.44 38
RNLOD-Flow [121]21.8 20.7 5 43.8 4 19.4 10 18.1 20 45.9 29 17.0 19 12.7 6 34.1 9 12.3 6 7.38 6 28.7 6 4.87 6 26.5 13 34.9 18 20.9 12 20.3 21 46.2 12 20.2 30 43.1 74 60.3 69 47.5 93 4.98 20 12.7 20 6.55 15
WLIF-Flow [93]22.1 27.0 19 47.0 11 23.1 16 21.7 44 46.6 36 23.3 43 14.8 13 36.2 16 16.3 24 9.33 16 32.2 13 6.64 17 27.7 21 35.1 20 23.4 32 21.6 29 47.7 21 19.2 17 28.7 30 45.3 7 32.0 54 4.50 12 11.2 8 6.43 12
HAST [109]22.2 19.5 1 40.1 1 11.6 2 16.1 12 39.7 4 14.8 8 8.49 1 21.2 1 7.09 1 6.79 3 29.0 7 3.66 3 21.6 1 28.3 2 13.8 1 24.3 55 48.5 25 24.3 63 41.7 71 59.8 68 63.0 118 6.05 30 11.5 14 8.72 41
MDP-Flow2 [68]24.0 35.3 47 55.4 41 30.2 44 14.2 3 39.7 4 14.2 7 13.6 10 31.4 3 12.9 10 12.2 44 34.1 29 8.19 45 27.7 21 35.0 19 22.1 20 22.4 40 45.4 9 21.5 43 27.1 23 54.1 46 16.5 11 5.87 27 14.0 25 4.25 4
OAR-Flow [125]25.0 25.6 12 54.9 38 22.4 14 18.7 24 44.8 22 19.1 26 17.2 35 43.7 45 18.0 30 8.53 11 31.6 10 5.65 10 29.7 35 39.3 39 20.9 12 14.5 2 47.3 18 13.4 2 14.1 2 38.0 1 20.7 30 9.84 60 21.1 51 16.1 71
Layers++ [37]25.4 28.0 31 48.8 15 30.9 47 23.3 59 45.6 28 25.5 67 13.7 11 31.4 3 18.1 31 8.08 8 24.9 1 5.87 11 22.9 3 28.1 1 19.6 8 22.2 36 46.3 14 20.7 34 39.6 66 55.9 55 35.0 57 4.16 4 9.78 2 6.81 17
TC-Flow [46]25.5 24.4 11 52.2 31 22.6 15 11.8 2 38.8 3 11.2 1 12.7 6 35.7 15 9.84 2 9.88 21 34.9 33 7.49 31 28.9 31 38.6 38 21.2 16 20.6 23 52.1 36 21.6 44 22.6 14 47.1 12 36.3 60 9.05 52 21.5 53 12.4 62
LME [70]27.7 31.5 36 51.4 26 21.0 13 14.7 5 36.9 2 15.7 11 16.0 27 35.2 12 19.8 51 11.8 41 36.6 41 8.08 40 28.6 28 36.0 25 25.5 43 21.1 26 49.0 27 19.8 27 29.8 33 50.0 24 21.5 32 6.61 32 15.1 29 7.95 34
AGIF+OF [85]27.8 26.3 13 48.8 15 24.1 17 24.9 69 52.0 68 26.2 69 16.0 27 39.4 30 19.7 48 8.96 13 32.0 11 6.64 17 26.7 15 33.7 12 21.5 19 21.4 27 49.4 28 18.5 13 28.2 27 49.6 21 30.5 53 4.63 16 11.3 13 7.30 26
PH-Flow [101]28.8 26.7 15 51.6 27 25.6 25 21.7 44 49.4 50 23.8 48 15.5 17 37.6 23 19.5 44 10.2 26 33.8 25 7.44 30 26.4 11 33.7 12 21.0 14 22.0 32 50.3 30 20.4 32 38.8 60 48.4 17 45.4 83 4.26 7 11.2 8 6.38 11
FC-2Layers-FF [74]28.9 26.9 18 48.6 14 28.3 37 22.1 48 48.8 45 23.8 48 14.1 12 32.4 5 19.6 46 9.10 14 28.3 5 6.47 16 25.5 7 31.7 7 23.0 28 23.3 45 47.7 21 21.8 45 44.1 78 56.3 58 46.0 88 3.54 1 9.08 1 5.44 6
Classic+CPF [83]30.0 27.1 23 51.2 25 25.5 24 23.9 63 51.4 64 25.1 62 15.9 24 39.3 29 19.4 42 9.17 15 32.8 16 6.69 19 27.3 18 34.5 16 23.9 33 21.0 25 48.7 26 18.0 11 35.6 49 49.9 23 45.7 85 4.25 6 10.7 5 6.61 16
NNF-EAC [103]30.1 34.9 42 54.8 36 29.9 43 15.6 9 41.7 11 15.9 12 15.1 16 34.8 11 15.7 18 12.4 48 35.1 36 8.33 48 28.1 24 35.7 22 22.9 26 24.5 58 46.2 12 22.7 55 31.6 42 49.1 19 20.1 28 7.54 40 17.1 39 7.44 28
COFM [59]30.4 22.1 7 49.1 17 16.6 7 18.2 21 43.5 16 19.2 28 15.9 24 38.3 26 21.5 62 7.02 4 32.6 14 4.40 4 31.4 44 37.9 35 35.0 80 22.1 34 46.4 15 18.3 12 28.7 30 45.9 10 45.5 84 9.25 53 15.5 33 15.7 70
IROF++ [58]30.8 27.4 25 50.7 21 26.7 31 22.1 48 50.1 59 24.1 52 16.3 30 40.0 34 19.6 46 10.6 33 34.3 30 7.72 36 27.9 23 35.7 22 22.5 22 22.3 38 54.1 51 19.9 28 25.5 18 49.6 21 11.5 6 5.49 24 14.1 26 6.54 14
Sparse-NonSparse [56]31.0 26.8 17 51.9 30 26.8 32 22.2 53 49.0 48 24.6 58 15.6 19 39.4 30 19.0 37 9.46 18 33.6 23 7.07 25 29.0 32 37.2 33 24.3 38 21.7 31 50.4 31 19.5 25 34.0 45 45.8 9 41.6 72 4.44 11 10.9 6 6.96 21
FESL [72]31.8 27.0 19 46.3 8 31.2 49 26.0 80 51.8 67 26.9 73 15.8 23 37.0 21 19.5 44 7.89 7 30.7 9 5.17 8 26.6 14 33.8 14 22.6 23 20.3 21 45.8 11 19.3 20 39.9 67 61.2 74 35.6 58 5.04 21 12.5 19 6.48 13
Efficient-NL [60]32.2 23.3 10 44.7 6 17.6 8 24.6 68 51.6 66 25.4 66 15.0 15 36.2 16 17.5 28 9.92 22 33.1 18 6.94 21 26.4 11 34.0 15 20.3 10 27.2 67 49.4 28 22.6 50 37.6 55 50.5 26 37.1 61 6.98 37 16.2 35 8.16 35
LSM [39]34.0 26.5 14 50.8 22 27.0 33 22.1 48 49.4 50 24.4 56 15.6 19 38.2 25 19.4 42 10.1 23 33.0 17 7.43 29 28.6 28 36.3 27 24.7 39 22.8 43 50.5 32 20.9 38 40.3 69 49.3 20 45.8 87 4.76 18 12.0 16 6.93 20
PMMST [114]34.4 42.4 72 58.9 46 40.2 68 22.1 48 45.3 25 24.7 61 17.9 41 38.4 27 18.8 34 12.2 44 28.1 3 8.26 46 25.7 8 32.7 10 18.5 7 22.3 38 45.3 8 20.8 36 28.5 29 50.7 28 18.3 19 8.51 49 16.8 36 8.73 42
Classic+NL [31]35.4 27.2 24 47.8 13 28.4 39 22.0 47 49.4 50 24.1 52 15.5 17 37.4 22 19.8 51 10.4 30 33.8 25 7.40 28 28.5 26 36.4 28 24.2 37 23.3 45 52.2 37 21.1 39 43.9 76 52.5 38 44.6 80 4.60 15 11.2 8 7.04 23
Ramp [62]35.4 27.0 19 52.3 32 26.1 29 22.3 55 49.1 49 24.6 58 15.6 19 37.8 24 19.8 51 10.5 32 33.6 23 7.61 33 28.6 28 36.6 29 24.0 34 23.6 48 51.2 33 21.8 45 38.2 56 44.5 4 46.1 89 4.86 19 12.1 17 7.13 24
2DHMM-SAS [92]38.2 26.7 15 51.8 29 25.6 25 22.2 53 51.3 62 23.8 48 17.8 39 42.3 40 20.0 56 10.4 30 34.6 32 7.52 32 28.5 26 36.6 29 24.0 34 22.7 42 54.5 54 20.6 33 39.0 62 47.8 15 45.1 81 5.51 25 13.9 24 7.73 32
FMOF [94]38.5 27.8 30 50.4 20 27.1 35 26.2 82 52.5 72 27.4 76 15.9 24 36.4 19 21.7 63 9.71 20 32.7 15 6.98 22 27.3 18 34.6 17 24.1 36 23.7 50 47.6 20 19.7 26 38.4 57 55.4 52 48.9 96 5.80 26 14.1 26 7.00 22
SVFilterOh [111]39.8 39.6 62 54.6 35 39.8 67 23.8 62 44.7 21 24.0 51 17.3 36 33.8 8 18.8 34 10.2 26 36.4 40 4.93 7 25.9 10 32.1 8 19.6 8 24.7 59 46.7 16 22.9 58 52.0 101 76.3 119 59.2 112 4.23 5 10.9 6 5.01 5
S2D-Matching [84]40.7 27.7 27 50.2 19 28.4 39 22.1 48 48.8 45 24.3 54 16.5 32 40.0 34 19.3 40 10.6 33 33.8 25 7.78 37 29.1 34 36.7 32 25.0 40 24.4 57 53.0 47 22.6 50 47.0 89 53.6 43 50.8 101 4.58 13 11.2 8 7.54 30
ProbFlowFields [128]41.3 33.9 38 68.5 70 30.9 47 20.3 34 45.3 25 22.1 38 19.2 50 44.8 48 22.9 67 11.7 40 39.3 49 8.91 57 31.0 42 40.1 43 23.3 30 16.8 7 47.8 23 19.2 17 23.7 17 55.9 55 23.9 41 8.39 46 22.4 56 9.82 51
SimpleFlow [49]41.6 28.6 33 51.6 27 29.5 42 25.0 70 51.3 62 28.2 81 18.6 46 43.0 43 23.3 68 10.1 23 33.5 22 7.04 24 29.9 36 37.9 35 26.2 45 27.8 72 52.2 37 24.0 62 35.1 48 47.9 16 29.7 52 4.66 17 12.4 18 6.92 19
PMF [73]42.6 37.7 57 58.3 44 27.3 36 19.4 27 45.0 24 18.3 23 16.2 29 39.9 33 14.0 14 13.6 61 35.7 38 8.03 39 25.8 9 32.5 9 17.1 6 30.2 80 57.0 64 31.6 83 58.9 110 74.7 112 55.9 109 3.95 3 10.3 3 6.15 10
Adaptive [20]43.5 27.0 19 52.6 33 19.8 11 21.9 46 47.8 40 22.6 40 20.5 55 47.8 57 19.7 48 10.3 28 39.9 53 6.31 15 45.6 115 52.6 112 51.3 114 17.4 8 48.2 24 13.9 3 34.8 47 56.9 61 19.8 26 6.04 29 15.2 30 7.54 30
TV-L1-MCT [64]43.9 27.5 26 49.4 18 27.0 33 26.5 83 52.8 77 27.8 80 16.8 33 39.1 28 21.8 64 10.6 33 33.8 25 7.82 38 30.3 38 38.1 37 28.7 60 24.7 59 53.4 49 23.4 59 27.4 24 52.5 38 19.4 23 7.28 38 15.3 31 11.4 59
Correlation Flow [75]44.0 36.6 54 55.3 40 34.4 57 16.6 14 44.4 20 14.8 8 18.3 45 42.9 42 12.7 8 12.4 48 39.7 51 8.46 52 32.2 47 40.6 47 25.2 41 29.0 75 54.2 53 29.7 79 39.1 63 52.1 36 47.4 92 6.53 31 16.1 34 6.88 18
IROF-TV [53]44.8 30.9 35 54.8 36 31.6 51 22.8 58 50.5 60 25.1 62 16.9 34 40.8 36 20.8 58 14.0 64 43.7 67 10.1 64 31.2 43 39.5 40 28.6 58 26.8 66 58.7 74 25.6 66 18.8 4 48.4 17 8.08 5 5.28 22 13.6 22 7.77 33
AggregFlow [97]44.9 36.3 53 52.7 34 35.7 59 26.6 84 52.6 75 26.7 71 23.3 68 48.2 59 28.9 85 12.1 42 34.9 33 8.63 54 30.2 37 40.3 46 21.4 17 15.9 5 38.3 2 16.8 7 26.1 21 47.3 13 16.8 13 12.6 72 20.3 47 20.0 81
Occlusion-TV-L1 [63]45.8 34.3 41 58.5 45 25.1 20 20.0 30 46.5 35 20.8 34 22.3 65 49.9 60 20.6 57 12.6 54 41.7 59 8.41 51 35.2 67 44.9 76 32.3 71 17.7 11 52.6 42 21.1 39 28.2 27 52.5 38 13.0 7 9.66 56 23.7 60 10.6 53
3DFlow [135]47.3 35.7 49 56.6 42 28.3 37 19.1 26 46.2 33 17.4 21 18.8 47 41.7 39 14.5 16 13.9 62 33.3 20 9.85 62 29.0 32 36.6 29 23.0 28 32.9 86 65.1 95 34.7 93 49.9 95 65.5 87 77.7 128 3.87 2 10.3 3 3.02 3
Classic++ [32]49.0 27.7 27 51.0 24 28.7 41 21.5 43 45.9 29 24.3 54 18.1 44 44.3 46 19.9 54 10.3 28 37.7 43 7.14 26 33.4 51 44.1 66 27.9 54 24.0 53 57.9 69 21.4 42 46.3 85 55.6 53 49.7 98 8.45 48 20.7 48 9.69 50
Aniso-Texture [82]49.1 28.5 32 50.9 23 32.7 54 21.2 38 41.7 11 25.3 65 17.6 38 41.2 37 21.1 60 5.72 1 33.2 19 2.54 1 35.1 66 43.7 63 31.3 69 23.6 48 53.6 50 22.6 50 62.2 117 75.8 117 53.5 106 6.89 36 17.4 41 8.20 36
IIOF-NLDP [131]50.0 33.3 37 59.3 47 24.9 19 24.4 67 53.8 84 22.9 42 18.8 47 46.2 52 15.0 17 13.5 58 39.7 51 9.86 63 32.3 48 41.2 51 23.3 30 29.9 79 60.2 83 29.6 78 28.1 26 60.8 71 27.0 47 7.51 39 17.2 40 7.29 25
MDP-Flow [26]50.2 35.5 48 65.0 57 32.4 52 20.6 36 43.8 18 24.4 56 18.0 43 43.4 44 19.9 54 14.9 72 41.8 61 11.5 73 30.8 41 39.6 41 25.3 42 23.8 51 57.4 67 22.2 47 31.0 37 59.3 66 16.8 13 10.8 67 26.5 65 10.9 55
OFH [38]50.7 41.9 71 61.6 51 48.5 82 14.7 5 42.7 14 14.1 6 17.4 37 47.6 55 12.6 7 10.6 33 38.5 45 8.39 50 34.8 64 43.7 63 34.5 78 27.2 67 61.9 88 29.5 77 21.3 10 57.6 62 21.4 31 12.2 71 29.8 78 16.2 72
DeepFlow2 [108]50.8 39.1 60 66.4 61 44.4 76 20.1 32 47.9 42 20.9 35 23.8 71 52.8 67 26.3 77 12.2 44 43.2 66 7.64 34 31.4 44 41.7 55 22.9 26 18.2 17 52.4 39 17.9 10 29.6 32 44.7 5 39.0 65 16.2 86 31.2 86 22.7 88
BriefMatch [124]52.4 34.1 40 59.4 48 30.2 44 17.1 16 43.6 17 16.1 14 14.8 13 36.3 18 13.4 12 9.41 17 34.3 30 6.26 14 33.4 51 41.2 51 31.8 70 40.3 110 63.5 90 42.7 113 47.2 90 61.1 72 59.1 111 12.7 74 23.4 57 21.6 86
CPM-Flow [116]53.0 35.2 43 67.0 63 25.3 21 25.8 77 53.6 81 28.2 81 25.5 74 58.5 87 27.5 78 12.4 48 48.0 80 8.11 43 33.9 56 44.2 67 27.1 48 17.6 9 51.8 34 19.1 15 21.3 10 51.7 33 22.6 37 9.92 61 27.2 70 11.3 57
PGM-C [120]53.8 35.2 43 67.1 65 25.4 23 25.8 77 53.6 81 28.2 81 25.8 77 59.3 91 27.5 78 12.4 48 48.1 81 8.16 44 33.9 56 44.3 70 27.1 48 17.7 11 52.8 46 19.1 15 20.8 6 50.3 25 22.4 35 9.82 59 27.2 70 11.5 61
S2F-IF [123]53.8 35.7 49 69.0 73 26.6 30 24.1 65 54.0 89 26.0 68 25.6 76 60.9 93 25.9 73 12.4 48 46.6 77 8.38 49 34.3 60 44.2 67 27.7 53 18.0 16 53.2 48 19.2 17 21.2 9 51.7 33 22.9 38 8.97 51 24.9 63 9.11 46
CostFilter [40]55.5 43.6 78 65.7 59 40.8 69 20.8 37 45.9 29 21.0 36 18.8 47 44.9 49 18.3 33 17.3 81 39.5 50 13.9 83 26.7 15 32.8 11 22.7 25 30.9 83 60.0 81 31.6 83 59.7 111 81.5 127 59.3 113 4.31 9 11.9 15 5.93 8
RFlow [90]55.6 44.4 80 75.2 94 50.5 86 16.5 13 42.1 13 17.2 20 21.4 59 52.2 63 16.0 19 11.3 38 36.2 39 7.25 27 35.2 67 44.3 70 32.3 71 24.3 55 55.6 59 22.6 50 38.6 58 55.3 50 41.6 72 13.4 76 29.9 79 16.9 76
EpicFlow [102]55.7 35.2 43 67.2 66 25.3 21 25.8 77 53.8 84 28.2 81 26.1 79 60.1 92 27.5 78 12.4 48 48.1 81 8.10 42 34.2 59 44.5 72 28.0 55 17.8 13 52.7 44 19.4 22 21.0 7 52.1 36 22.5 36 10.4 64 27.3 72 12.7 64
FlowFields+ [130]56.0 35.8 52 69.2 75 26.0 28 25.6 75 55.3 95 27.7 78 26.7 80 62.9 97 27.7 82 12.7 55 45.9 75 8.84 56 34.0 58 44.2 67 26.6 46 17.6 9 54.9 56 19.0 14 20.6 5 53.9 45 22.3 34 9.31 55 26.5 65 8.79 43
TV-L1-improved [17]57.5 27.7 27 57.9 43 20.5 12 18.2 21 44.9 23 19.1 26 19.4 51 47.7 56 17.0 27 10.1 23 38.5 45 6.75 20 35.9 74 46.0 82 27.3 50 43.7 116 70.2 113 47.5 117 51.4 98 60.5 70 50.3 100 10.3 63 26.8 69 10.8 54
FlowFields [110]57.9 35.7 49 68.7 71 25.8 27 25.6 75 55.1 94 27.7 78 26.8 83 62.8 96 27.6 81 13.0 56 46.8 78 9.13 59 34.6 63 44.9 76 28.1 56 17.8 13 54.9 56 19.4 22 21.3 10 54.8 48 24.2 42 9.25 53 26.4 64 8.47 39
Steered-L1 [118]59.8 38.7 59 67.9 67 43.1 74 11.6 1 34.7 1 12.3 2 16.3 30 41.3 38 13.9 13 12.1 42 38.6 47 8.30 47 34.5 62 43.4 60 32.5 73 29.4 77 61.1 87 25.9 67 60.6 114 67.0 94 70.1 124 15.9 85 30.6 82 24.0 90
Sparse Occlusion [54]60.7 38.6 58 61.8 52 32.5 53 26.0 80 48.8 45 29.5 88 20.0 53 45.2 50 19.2 39 14.3 68 38.4 44 9.67 61 34.4 61 42.6 57 26.7 47 25.4 62 52.4 39 22.4 49 67.3 122 75.9 118 48.3 94 8.07 44 19.9 46 7.36 27
DeepFlow [86]61.9 47.3 86 71.9 84 64.0 101 21.4 41 48.2 43 22.7 41 27.9 87 58.2 84 31.6 89 15.1 73 42.7 62 10.6 69 31.5 46 42.1 56 22.6 23 19.6 19 56.7 63 19.4 22 27.6 25 46.2 11 39.7 66 20.6 95 35.3 101 28.0 98
MLDP_OF [89]62.0 48.8 89 77.3 97 52.2 88 20.1 32 49.6 55 19.3 30 23.5 70 54.6 71 18.9 36 12.3 47 38.6 47 7.65 35 33.5 54 40.9 48 29.1 64 28.4 73 55.9 60 31.6 83 49.1 94 62.2 78 60.5 115 7.91 43 16.8 36 8.95 44
TF+OM [100]63.1 39.8 63 55.2 39 30.4 46 20.4 35 41.0 8 23.5 45 19.5 52 39.4 30 28.0 83 18.4 84 37.0 42 18.0 89 35.0 65 41.1 49 39.6 92 29.6 78 52.6 42 29.1 76 49.0 93 66.8 93 43.6 79 14.4 78 29.3 75 18.0 78
CombBMOF [113]65.3 42.4 72 71.5 82 31.3 50 25.2 71 52.9 78 25.1 62 17.9 41 45.8 51 16.1 20 14.2 66 41.7 59 11.4 72 33.5 54 40.2 44 29.6 65 34.5 92 59.9 80 37.3 98 55.2 107 69.9 103 46.5 91 6.78 34 16.8 36 8.62 40
EPPM w/o HM [88]65.9 43.1 76 72.4 86 38.1 65 18.7 24 52.5 72 16.9 18 21.3 58 56.2 76 17.5 28 16.2 77 45.3 73 12.7 80 33.4 51 39.6 41 30.0 66 33.5 88 65.4 97 33.8 89 45.5 80 66.1 91 65.5 121 6.88 35 18.1 42 9.16 48
Complementary OF [21]67.2 51.9 97 74.9 93 59.3 97 14.2 3 41.6 10 13.7 3 20.4 54 46.6 53 19.7 48 22.2 91 40.8 55 21.0 94 36.0 76 43.4 60 38.5 90 33.9 91 63.8 91 31.6 83 31.1 38 51.9 35 36.2 59 18.9 92 34.4 99 29.4 100
Aniso. Huber-L1 [22]68.0 33.9 38 65.1 58 32.8 55 34.0 95 54.0 89 40.0 95 27.9 87 55.0 73 38.4 94 15.2 74 49.9 85 12.0 75 35.3 69 44.6 73 28.5 57 23.9 52 55.9 60 20.7 34 50.6 96 62.1 77 39.7 66 8.15 45 20.7 48 8.39 37
ComplOF-FED-GPU [35]70.1 49.5 91 75.7 96 55.3 91 15.3 7 47.0 37 13.8 4 21.1 57 52.7 66 16.1 20 17.1 80 40.6 54 14.2 84 35.7 73 45.1 79 32.5 73 35.3 95 67.5 106 34.4 91 46.5 87 59.0 65 50.8 101 12.8 75 29.6 76 16.6 75
TCOF [69]70.2 45.0 81 70.0 76 51.5 87 25.5 74 53.7 83 26.7 71 26.7 80 56.2 76 32.0 90 21.9 90 43.1 65 22.2 96 37.8 86 48.9 98 25.7 44 18.8 18 44.7 7 20.0 29 52.1 102 67.5 96 25.8 43 10.7 66 26.7 67 11.4 59
Rannacher [23]70.2 43.1 76 71.0 80 45.2 78 24.1 65 49.4 50 26.4 70 26.0 78 56.9 80 26.0 75 14.2 66 42.7 62 10.5 68 37.1 83 47.9 93 30.7 68 32.3 85 65.2 96 27.0 71 44.0 77 56.0 57 39.7 66 7.83 41 21.2 52 9.19 49
ACK-Prior [27]70.3 55.9 99 72.7 88 59.3 97 17.5 18 43.3 15 16.0 13 17.8 39 42.3 40 16.3 24 17.6 82 41.3 57 12.0 75 35.3 69 41.1 49 35.9 81 37.4 106 59.6 78 34.3 90 59.8 113 61.1 72 74.7 125 17.7 90 29.2 74 27.4 93
F-TV-L1 [15]72.2 66.8 107 84.2 106 77.3 109 27.1 87 52.0 68 29.1 87 27.2 84 57.3 82 24.2 71 24.1 95 52.0 89 19.5 92 39.3 93 47.7 92 39.3 91 24.2 54 56.5 62 24.9 64 33.2 44 53.7 44 20.1 28 6.69 33 18.6 43 5.94 9
LDOF [28]72.7 41.7 70 70.7 77 47.2 81 24.0 64 53.9 88 24.6 58 26.7 80 58.4 86 25.5 72 15.8 75 57.4 100 10.2 66 36.0 76 45.3 80 34.8 79 22.1 34 58.1 71 21.3 41 30.6 35 56.8 59 23.4 39 22.5 104 38.6 109 30.2 101
ROF-ND [107]72.9 49.2 90 71.5 82 49.4 84 22.5 57 46.2 33 20.6 32 21.4 59 50.0 61 18.1 31 23.1 93 53.7 93 16.0 86 35.9 74 46.1 84 28.6 58 33.5 88 58.5 72 30.3 80 60.7 115 70.5 104 60.4 114 9.67 57 20.9 50 10.2 52
SIOF [67]73.6 50.3 94 66.0 60 47.1 80 19.8 29 48.4 44 20.7 33 29.8 94 55.1 74 32.6 92 25.9 97 48.3 83 25.0 98 37.7 84 46.4 86 36.8 84 32.9 86 58.6 73 35.6 96 37.2 54 53.1 42 18.6 20 16.8 88 33.0 91 21.3 85
LocallyOriented [52]74.2 39.4 61 60.5 49 35.7 59 27.9 90 57.8 102 28.5 85 28.1 90 58.3 85 30.6 88 13.9 62 41.3 57 10.1 64 37.8 86 47.3 90 33.0 77 24.8 61 52.5 41 28.1 73 39.4 65 62.4 79 37.5 62 15.7 83 33.0 91 18.2 80
Second-order prior [8]74.8 37.6 56 70.9 79 37.2 63 22.4 56 51.2 61 23.7 47 24.5 73 59.1 90 22.6 65 11.2 37 41.2 56 8.48 53 37.9 88 49.6 105 28.8 61 29.0 75 68.8 110 26.0 68 55.5 108 64.7 85 52.7 105 14.7 80 34.1 97 17.3 77
Brox et al. [5]75.0 43.7 79 74.4 91 56.4 94 27.0 86 52.5 72 30.5 90 23.4 69 54.5 70 23.3 68 13.4 57 50.0 86 8.66 55 39.8 96 46.5 87 47.6 109 21.6 29 59.8 79 22.8 57 30.9 36 59.3 66 7.61 3 23.1 107 37.0 106 33.4 108
FlowNetS+ft+v [112]75.1 36.8 55 67.0 63 39.4 66 25.3 73 52.1 70 27.6 77 27.8 86 57.2 81 35.5 93 13.5 58 50.9 87 9.44 60 40.1 97 49.5 104 36.8 84 20.9 24 57.0 64 20.8 36 46.3 85 66.3 92 41.0 70 17.4 89 34.3 98 24.1 91
CRTflow [80]75.3 40.9 65 72.5 87 36.2 61 21.3 40 49.4 50 21.8 37 22.9 66 57.5 83 19.0 37 14.0 64 44.7 70 10.3 67 35.4 72 45.0 78 30.4 67 46.6 120 73.4 115 53.8 121 38.8 60 65.5 87 38.2 63 19.5 94 38.5 108 27.6 96
NL-TV-NCC [25]75.5 46.1 83 68.3 69 43.4 75 25.2 71 55.3 95 23.5 45 21.8 64 47.2 54 16.9 26 16.9 79 44.1 68 11.9 74 38.5 90 49.1 102 27.3 50 36.5 101 65.7 98 34.9 94 46.2 82 75.7 116 45.7 85 12.6 72 28.8 73 9.10 45
DF-Auto [115]75.6 41.6 69 64.2 55 32.8 55 42.0 101 58.8 105 49.6 102 34.8 101 62.2 95 47.2 102 20.7 88 53.4 92 14.5 85 36.2 79 44.7 74 37.2 87 15.1 3 42.9 6 17.4 8 45.3 79 69.0 100 13.0 7 24.2 110 37.7 107 31.9 104
SRR-TVOF-NL [91]76.1 47.6 87 69.1 74 41.9 72 23.3 59 52.7 76 23.3 43 25.5 74 56.8 79 25.9 73 13.5 58 47.9 79 8.09 41 36.9 82 43.8 65 32.9 76 25.8 63 57.7 68 22.6 50 62.8 119 75.2 114 49.1 97 21.0 97 29.7 77 31.6 103
TriangleFlow [30]76.2 41.5 68 63.2 53 42.6 73 21.4 41 52.4 71 20.2 31 21.7 63 53.6 69 16.2 22 14.8 70 44.4 69 10.9 70 43.2 107 52.9 114 43.4 100 36.8 105 65.9 99 38.8 101 42.2 72 65.4 86 41.8 74 15.8 84 35.2 100 22.5 87
DPOF [18]77.0 45.3 82 68.9 72 37.6 64 26.7 85 56.9 98 26.9 73 24.3 72 54.6 71 26.2 76 18.6 85 54.6 96 13.6 82 33.3 50 43.1 58 28.9 62 27.6 71 60.8 84 26.3 69 47.2 90 55.3 50 76.0 127 14.3 77 31.0 85 15.3 69
Bartels [41]78.2 48.6 88 63.2 53 61.4 100 23.4 61 44.0 19 27.1 75 21.4 59 44.6 47 23.8 70 26.2 98 43.0 64 25.4 99 36.8 80 44.7 74 41.7 97 33.7 90 60.0 81 41.7 110 52.6 103 67.2 95 61.1 116 11.2 68 23.4 57 16.3 73
SuperFlow [81]78.4 35.2 43 61.1 50 34.4 57 35.2 96 53.5 80 42.5 96 27.7 85 52.5 65 43.5 101 27.5 99 60.5 104 27.6 100 36.0 76 43.3 59 42.2 98 22.6 41 59.2 77 22.2 47 46.2 82 62.0 76 23.4 39 21.8 102 36.0 102 32.5 106
Dynamic MRF [7]78.5 49.5 91 78.0 98 55.8 93 17.2 17 47.4 39 16.5 17 21.6 62 56.3 78 16.2 22 14.8 70 46.4 76 12.5 78 41.2 101 49.0 100 45.1 104 35.3 95 70.7 114 38.5 100 37.1 53 57.7 63 55.1 107 21.3 99 36.7 105 31.2 102
CBF [12]79.1 41.4 66 74.0 90 48.5 82 40.2 99 51.5 65 51.7 104 22.9 66 50.8 62 28.5 84 14.3 68 44.7 70 11.2 71 38.3 89 46.1 84 36.1 82 26.3 65 55.1 58 24.9 64 61.5 116 71.0 105 52.0 104 11.6 70 26.7 67 14.8 68
CLG-TV [48]79.3 41.4 66 68.0 68 40.8 69 37.0 97 53.1 79 45.3 97 30.9 95 58.7 88 40.2 96 22.8 92 62.0 105 19.3 91 39.0 92 47.6 91 38.2 89 27.2 67 61.0 86 27.1 72 46.2 82 57.8 64 29.3 51 9.74 58 24.6 62 9.11 46
Local-TV-L1 [65]79.4 56.8 101 79.1 99 74.5 105 39.5 98 53.8 84 46.1 98 38.1 102 66.2 100 43.1 100 23.9 94 52.9 91 21.1 95 32.3 48 41.4 54 27.5 52 23.2 44 54.8 55 22.7 55 25.8 19 47.5 14 33.4 56 26.9 113 40.5 112 40.5 117
CNN-flow-warp+ref [117]79.6 42.6 74 71.2 81 49.8 85 31.6 94 53.8 84 37.3 93 32.7 97 63.8 98 42.7 99 16.0 76 55.1 97 12.1 77 38.6 91 46.0 82 43.8 102 23.3 45 59.1 76 23.6 60 23.5 16 50.9 30 21.9 33 24.2 110 36.2 104 32.9 107
HBM-GC [105]81.7 73.5 115 79.7 100 79.4 112 30.0 91 49.7 57 33.6 91 29.3 93 47.8 57 30.4 86 35.4 103 45.2 72 33.3 103 30.5 39 35.1 20 32.6 75 34.6 93 52.0 35 35.4 95 70.9 125 80.1 122 62.6 117 8.83 50 19.1 44 13.0 65
TriFlow [95]84.9 47.1 85 66.5 62 41.1 71 31.2 93 49.6 55 37.3 93 27.9 87 52.3 64 39.4 95 24.7 96 49.3 84 22.3 97 37.7 84 43.5 62 43.1 99 28.4 73 52.7 44 29.0 75 76.7 129 73.7 109 99.5 132 16.2 86 30.5 81 20.1 82
OFRF [134]85.6 50.4 95 64.5 56 55.4 92 41.2 100 57.5 100 46.2 100 34.5 100 58.9 89 40.6 97 29.6 101 45.6 74 28.8 101 30.7 40 40.2 44 22.3 21 31.1 84 57.9 69 30.4 82 43.5 75 62.5 80 51.9 103 29.8 117 39.3 110 49.1 124
p-harmonic [29]87.2 50.4 95 86.6 116 56.5 96 27.1 87 54.5 91 28.9 86 32.9 98 69.3 106 30.4 86 19.8 86 65.1 108 16.2 87 39.6 95 47.2 89 40.3 94 30.4 81 66.5 101 32.2 87 45.6 81 64.4 83 28.9 50 10.2 62 24.1 61 13.2 66
Learning Flow [11]87.5 42.9 75 70.7 77 44.8 77 30.2 92 54.7 92 34.7 92 28.2 91 55.9 75 32.3 91 17.6 82 57.1 99 12.6 79 44.0 110 52.6 112 47.8 111 30.5 82 64.6 93 30.3 80 46.9 88 63.3 81 42.8 78 14.7 80 31.6 89 16.3 73
Fusion [6]89.1 40.5 64 75.6 95 45.9 79 20.0 30 50.0 58 22.5 39 20.8 56 52.8 67 22.8 66 16.2 77 52.8 90 13.5 81 43.1 106 49.0 100 47.5 106 39.6 109 67.8 108 43.8 115 63.9 120 75.0 113 46.3 90 35.5 123 42.6 118 53.3 128
StereoFlow [44]89.4 95.9 132 96.0 131 97.4 132 88.3 132 96.2 132 86.2 128 82.6 129 94.8 131 73.7 126 91.4 131 96.3 131 90.3 131 53.0 122 61.6 126 52.8 115 11.2 1 39.3 3 11.7 1 10.5 1 42.5 3 1.70 1 11.5 69 23.6 59 18.0 78
Shiralkar [42]91.1 46.1 83 85.6 112 54.3 90 19.7 28 57.7 101 18.2 22 28.2 91 70.8 107 19.3 40 20.5 87 59.0 102 18.4 90 39.5 94 49.7 106 36.3 83 40.4 111 76.1 117 41.2 109 51.9 100 65.8 89 64.2 119 21.0 97 42.4 117 25.3 92
SegOF [10]94.3 56.3 100 71.9 84 37.1 62 57.3 115 62.9 112 68.3 117 46.0 108 69.0 105 57.2 114 41.0 105 59.5 103 37.2 104 43.5 108 48.3 96 56.4 119 38.2 107 69.6 112 39.1 102 17.9 3 64.5 84 3.40 2 22.7 106 33.0 91 32.0 105
StereoOF-V1MT [119]94.9 49.7 93 86.0 113 56.4 94 21.2 38 68.8 115 16.3 16 32.2 96 80.7 115 20.8 58 21.3 89 66.1 110 17.4 88 47.0 117 57.0 117 47.5 106 41.7 114 81.2 121 40.9 106 38.6 58 68.1 98 48.6 95 23.2 108 42.2 116 27.7 97
Ad-TV-NDC [36]95.3 73.7 116 85.4 110 89.5 127 56.9 114 60.4 108 67.5 116 51.0 112 75.9 110 57.6 116 45.7 108 65.7 109 47.9 112 35.3 69 45.3 80 28.9 62 27.3 70 57.2 66 28.2 74 34.6 46 55.0 49 27.3 48 34.0 120 48.7 124 47.5 121
Modified CLG [34]97.4 68.7 110 80.5 101 76.1 107 52.0 111 61.0 109 63.6 113 51.9 113 79.4 112 55.6 112 47.4 111 72.1 115 46.7 110 41.2 101 49.7 106 46.0 105 26.0 64 64.7 94 26.7 70 31.4 41 55.6 53 19.9 27 29.0 116 43.8 120 39.9 116
IAOF2 [51]99.1 54.9 98 73.7 89 53.9 89 42.6 102 58.3 103 50.7 103 33.9 99 61.9 94 42.1 98 64.4 121 75.7 118 74.3 123 41.5 103 49.9 109 37.1 86 36.4 100 64.0 92 34.4 91 59.7 111 69.6 102 41.3 71 19.4 93 33.4 95 23.0 89
Filter Flow [19]101.5 62.9 102 74.4 91 60.8 99 42.8 103 60.1 107 49.4 101 42.5 104 66.0 99 51.2 105 52.1 117 69.5 112 50.2 113 44.8 112 49.7 106 54.4 117 41.9 115 66.7 102 43.6 114 74.3 128 88.9 130 42.6 77 10.6 65 21.6 54 12.6 63
GroupFlow [9]101.9 66.4 105 85.2 109 80.8 115 61.6 118 75.4 122 69.0 118 51.9 113 83.6 118 57.0 113 33.5 102 63.9 106 32.5 102 49.6 118 61.0 121 39.9 93 51.3 125 81.7 122 59.4 125 22.8 15 51.1 31 16.5 11 28.0 115 41.9 115 37.9 114
SPSA-learn [13]102.9 65.1 103 87.4 119 72.7 104 45.7 107 59.3 106 53.4 107 45.2 107 74.7 109 52.2 107 41.6 106 69.9 114 42.5 106 42.7 105 48.9 98 48.7 113 38.8 108 69.0 111 42.5 112 39.1 63 61.9 75 19.3 22 36.0 124 45.6 121 48.3 122
2D-CLG [1]103.0 77.2 119 82.3 104 75.4 106 61.5 117 65.9 114 73.7 122 63.2 123 89.6 125 60.8 121 82.8 129 88.3 126 86.8 129 43.5 108 49.3 103 54.8 118 35.1 94 67.5 106 36.1 97 21.3 10 50.8 29 15.5 9 34.4 122 46.3 123 46.0 119
IAOF [50]103.6 66.3 104 81.3 103 77.8 110 50.1 110 58.4 104 59.7 111 45.0 106 74.1 108 49.6 104 50.8 114 68.2 111 58.0 119 40.2 98 48.7 97 37.8 88 36.7 102 66.9 103 33.5 88 54.9 105 63.5 82 40.8 69 30.1 119 41.3 114 43.5 118
BlockOverlap [61]103.7 77.2 119 86.0 113 82.8 117 48.2 108 55.8 97 57.6 110 46.9 110 66.9 101 51.9 106 49.1 113 54.1 94 51.2 114 36.8 80 41.3 53 47.5 106 40.5 112 59.0 75 39.6 104 68.9 124 80.2 123 65.1 120 20.8 96 30.8 83 34.9 110
HBpMotionGpu [43]104.0 67.0 108 80.7 102 72.3 103 55.3 113 57.3 99 66.7 115 44.7 105 67.2 103 54.1 110 39.5 104 57.8 101 38.4 105 42.0 104 48.2 95 48.3 112 35.9 97 60.9 85 39.2 103 65.1 121 72.0 107 50.1 99 22.6 105 32.5 90 36.9 111
Black & Anandan [4]105.8 70.3 112 88.0 120 84.1 118 45.5 106 61.4 110 52.0 105 47.4 111 77.3 111 52.9 108 42.3 107 77.5 119 42.8 107 44.0 110 51.8 110 45.0 103 35.9 97 75.9 116 38.3 99 50.8 97 71.3 106 17.8 18 29.8 117 42.7 119 37.6 113
GraphCuts [14]106.0 66.6 106 87.0 117 80.0 114 43.1 104 63.0 113 46.1 98 41.8 103 67.0 102 53.4 109 28.5 100 64.0 107 20.8 93 40.2 98 48.1 94 43.5 101 46.5 118 63.4 89 40.5 105 62.7 118 75.4 115 69.5 123 23.8 109 33.3 94 38.5 115
EPMNet [133]107.2 78.2 121 91.5 123 78.0 111 61.6 118 75.7 123 69.6 119 55.3 117 79.5 113 57.3 115 48.1 112 56.6 98 47.7 111 45.3 113 54.0 115 41.1 95 36.7 102 67.3 104 41.0 107 56.4 109 81.4 126 26.3 45 18.6 91 36.0 102 20.7 83
FlowNet2 [122]107.8 78.8 122 86.2 115 79.4 112 63.5 123 70.2 117 72.8 121 57.2 120 82.0 116 59.7 120 46.2 109 51.4 88 45.6 109 45.3 113 54.0 115 41.1 95 36.7 102 67.3 104 41.0 107 67.6 123 80.8 124 55.1 107 14.5 79 30.0 80 13.9 67
Nguyen [33]110.2 75.6 118 85.4 110 85.8 120 67.0 124 61.6 111 83.0 126 57.1 119 80.2 114 64.1 123 70.8 122 80.2 121 77.4 125 45.9 116 52.2 111 56.4 119 36.3 99 68.1 109 42.0 111 41.4 70 66.0 90 19.7 25 34.1 121 45.6 121 46.1 120
2bit-BM-tele [98]110.2 82.4 124 87.2 118 91.8 128 44.4 105 54.7 92 52.9 106 46.0 108 68.3 104 47.4 103 51.5 116 54.4 95 53.4 117 40.5 100 47.1 88 47.7 110 47.9 121 66.4 100 53.1 119 71.7 126 83.6 128 75.1 126 21.9 103 39.3 110 29.2 99
SILK [79]110.3 72.5 113 85.1 108 88.3 124 61.9 120 71.8 118 73.7 122 54.9 116 85.3 119 58.0 118 53.6 118 69.8 113 54.6 118 52.8 120 57.9 118 61.8 123 46.5 118 77.6 118 48.9 118 31.3 39 54.3 47 38.9 64 37.8 125 50.6 125 49.7 125
UnFlow [129]112.1 89.6 129 94.1 127 86.4 121 72.2 126 83.9 129 77.9 125 71.4 126 93.2 128 69.8 124 54.8 119 74.4 116 51.4 115 62.0 127 66.9 128 69.1 130 50.0 123 80.9 119 57.1 122 53.2 104 69.0 100 7.68 4 15.6 82 30.8 83 21.0 84
Periodicity [78]113.2 68.9 111 83.5 105 65.5 102 52.2 112 69.8 116 57.0 109 78.4 128 82.5 117 87.2 130 47.2 110 74.7 117 45.5 108 69.7 132 81.9 132 65.6 127 59.5 127 84.9 129 60.7 126 36.3 52 79.8 121 19.2 21 40.7 127 66.5 131 53.1 127
Horn & Schunck [3]113.7 74.1 117 93.2 126 86.9 122 49.1 109 73.8 119 53.9 108 53.1 115 89.0 124 54.6 111 50.9 115 81.4 122 52.4 116 51.3 119 58.8 119 54.3 116 41.2 113 82.3 123 44.6 116 55.0 106 74.3 111 19.6 24 40.7 127 56.8 127 48.8 123
Heeger++ [104]115.8 86.1 126 91.0 122 77.1 108 67.6 125 91.6 131 65.1 114 85.6 131 94.6 130 83.6 129 71.0 123 88.2 125 68.8 121 62.9 128 69.8 130 67.3 128 69.4 131 91.0 131 70.8 129 40.2 68 80.9 125 26.3 45 21.7 100 31.2 86 27.4 93
SLK [47]117.0 67.5 109 90.3 121 82.1 116 72.2 126 84.7 130 84.8 127 58.4 121 94.0 129 58.1 119 78.1 126 82.5 123 84.6 128 55.4 125 61.5 124 68.1 129 49.4 122 83.7 127 57.7 123 36.2 51 68.1 98 26.2 44 50.3 130 60.0 128 65.2 131
FFV1MT [106]118.3 85.0 125 92.0 124 84.4 119 60.6 116 83.8 128 60.8 112 85.4 130 92.2 127 88.2 131 71.2 124 89.9 128 69.1 122 64.0 130 69.3 129 78.0 131 69.2 130 91.5 132 73.2 131 51.7 99 73.9 110 45.3 82 21.7 100 31.2 86 27.4 93
TI-DOFE [24]119.1 90.7 130 94.6 129 97.1 131 76.9 130 79.5 127 89.4 131 73.1 127 96.1 132 74.4 127 84.6 130 93.6 130 88.3 130 52.9 121 59.9 120 63.9 125 44.5 117 83.6 126 53.5 120 42.9 73 68.0 97 17.0 16 50.5 131 65.5 130 62.4 129
FOLKI [16]119.3 72.5 113 84.5 107 87.5 123 62.3 121 74.9 121 74.0 124 56.9 118 87.2 121 57.7 117 59.8 120 78.1 120 65.4 120 53.3 123 61.2 123 62.7 124 50.9 124 81.0 120 62.7 127 47.3 92 73.3 108 56.8 110 49.0 129 62.9 129 64.3 130
PGAM+LK [55]124.9 79.4 123 92.7 125 88.7 125 62.9 122 76.8 126 71.9 120 59.9 122 88.3 123 62.8 122 74.9 125 90.6 129 75.6 124 54.4 124 61.0 121 64.6 126 58.1 126 82.7 124 58.6 124 77.6 130 85.6 129 78.1 129 38.8 126 52.7 126 50.7 126
Adaptive flow [45]125.2 91.3 131 95.7 130 96.2 129 75.8 129 75.9 124 86.2 128 68.9 124 85.6 120 72.4 125 80.6 128 85.2 124 83.9 127 57.3 126 61.5 124 60.2 122 66.7 128 84.1 128 70.4 128 90.2 131 92.7 131 95.0 130 27.7 114 40.5 112 37.0 112
HCIC-L [99]125.9 88.6 128 96.7 132 89.3 126 80.8 131 74.4 120 93.1 132 86.6 132 87.2 121 95.2 132 95.8 132 97.4 132 96.9 132 63.4 129 66.7 127 57.8 121 68.9 129 82.7 124 73.1 130 96.0 132 95.9 132 98.6 131 25.3 112 33.9 96 34.7 109
Pyramid LK [2]128.2 86.7 127 94.5 128 96.2 129 73.1 128 76.5 125 86.4 130 70.8 125 89.6 125 78.5 128 78.1 126 88.6 127 82.7 126 68.8 131 76.4 131 80.4 132 75.7 132 85.1 130 78.1 132 73.1 127 79.6 120 69.3 122 60.8 132 74.5 132 79.9 132
AdaConv-v1 [126]133.0 100.0 133 100.0 133 100.0 133 100.0 133 100.0 133 100.0 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 100.0 133 99.7 133 99.9 133 99.9 133 99.9 133 99.9 133
SepConv-v1 [127]133.0 100.0 133 100.0 133 100.0 133 100.0 133 100.0 133 100.0 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 100.0 133 99.7 133 99.9 133 99.9 133 99.9 133 99.9 133
SuperSlomo [132]133.0 100.0 133 100.0 133 100.0 133 100.0 133 100.0 133 100.0 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 100.0 133 99.7 133 99.9 133 99.9 133 99.9 133 99.9 133
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.