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]14.8 20.0 3 43.3 3 13.0 3 15.9 11 45.3 26 16.1 15 12.5 4 34.1 9 12.8 10 9.68 21 32.0 11 7.01 25 23.3 4 30.0 4 16.2 4 22.0 34 45.4 9 23.8 65 25.8 24 44.8 7 17.6 22 4.37 11 14.4 29 0.48 1
NN-field [71]15.6 22.1 7 44.0 5 14.6 4 18.4 24 47.3 39 19.2 29 12.5 4 32.9 6 14.0 15 6.57 2 28.2 4 3.57 2 23.4 5 30.1 5 15.9 3 17.9 16 36.8 1 15.8 4 35.9 59 51.5 34 27.4 59 4.58 14 15.3 32 0.55 2
TC/T-Flow [76]20.8 19.9 2 46.9 11 10.2 1 16.0 12 47.8 41 13.9 5 13.0 8 36.6 21 11.1 4 8.90 14 35.0 37 6.10 14 27.2 18 35.7 23 21.0 15 15.7 4 47.2 17 15.8 4 21.0 9 39.2 2 42.1 88 7.86 45 19.5 47 10.9 58
ComponentFusion [96]21.2 20.0 3 46.3 8 14.8 5 16.6 15 40.3 6 18.5 26 11.7 3 33.6 7 10.9 3 7.09 6 35.2 39 4.45 6 27.6 21 36.0 26 21.4 18 21.5 30 54.1 53 20.2 31 31.8 48 56.8 63 16.2 15 5.46 24 12.8 22 7.47 31
ALD-Flow [66]21.3 21.6 6 46.0 7 15.9 7 15.5 8 41.3 9 15.6 11 13.1 9 35.2 13 12.2 6 8.17 11 33.4 23 5.35 10 28.1 25 37.3 35 20.3 11 16.4 7 47.4 19 16.0 6 26.5 27 45.4 9 41.8 86 8.39 49 22.3 58 11.3 60
ProFlow_ROB [147]21.6 24.2 11 53.3 36 15.8 6 15.6 9 44.5 21 14.8 8 15.5 18 43.0 44 11.8 5 6.94 4 33.1 19 3.97 4 30.0 38 39.9 44 19.6 8 16.2 6 49.1 28 16.1 7 14.9 4 54.0 49 13.9 13 7.47 40 21.2 54 8.63 43
nLayers [57]22.5 22.7 9 40.3 2 18.4 10 27.2 93 45.9 30 30.4 94 15.7 24 35.4 15 21.4 63 8.12 10 26.6 2 6.21 15 22.5 2 29.0 3 15.5 2 19.9 21 40.8 4 17.8 10 31.3 44 52.6 43 16.9 20 4.26 8 11.2 9 5.84 7
OFLAF [77]23.2 29.6 36 47.4 13 24.8 20 17.8 20 40.9 7 18.3 24 11.6 2 26.9 2 13.2 12 11.5 41 29.3 8 8.97 62 23.7 6 30.9 6 16.5 5 22.2 38 41.5 5 19.3 21 30.2 39 50.6 29 32.9 67 5.94 29 13.8 24 8.44 40
RNLOD-Flow [121]23.6 20.7 5 43.8 4 19.4 11 18.1 21 45.9 30 17.0 20 12.7 6 34.1 9 12.3 7 7.38 7 28.7 6 4.87 7 26.5 14 34.9 19 20.9 13 20.3 22 46.2 12 20.2 31 43.1 85 60.3 75 47.5 105 4.98 21 12.7 21 6.55 16
WLIF-Flow [93]23.9 27.0 21 47.0 12 23.1 18 21.7 45 46.6 37 23.3 44 14.8 13 36.2 17 16.3 25 9.33 18 32.2 14 6.64 19 27.7 22 35.1 21 23.4 34 21.6 31 47.7 21 19.2 18 28.7 35 45.3 8 32.0 66 4.50 13 11.2 9 6.43 12
HAST [109]24.0 19.5 1 40.1 1 11.6 2 16.1 13 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 60 48.5 25 24.3 67 41.7 81 59.8 73 63.0 131 6.05 31 11.5 15 8.72 44
MDP-Flow2 [68]25.5 35.3 49 55.4 43 30.2 46 14.2 3 39.7 4 14.2 7 13.6 10 31.4 3 12.9 11 12.2 46 34.1 31 8.19 48 27.7 22 35.0 20 22.1 21 22.4 42 45.4 9 21.5 45 27.1 28 54.1 50 16.5 16 5.87 28 14.0 26 4.25 4
OAR-Flow [125]26.5 25.6 14 54.9 40 22.4 15 18.7 25 44.8 23 19.1 27 17.2 37 43.7 47 18.0 31 8.53 13 31.6 10 5.65 11 29.7 36 39.3 40 20.9 13 14.5 2 47.3 18 13.4 2 14.1 3 38.0 1 20.7 36 9.84 63 21.1 53 16.1 75
Layers++ [37]27.1 28.0 33 48.8 16 30.9 49 23.3 61 45.6 29 25.5 69 13.7 11 31.4 3 18.1 32 8.08 9 24.9 1 5.87 12 22.9 3 28.1 1 19.6 8 22.2 38 46.3 14 20.7 35 39.6 75 55.9 59 35.0 69 4.16 4 9.78 2 6.81 18
TC-Flow [46]27.4 24.4 12 52.2 32 22.6 16 11.8 2 38.8 3 11.2 1 12.7 6 35.7 16 9.84 2 9.88 23 34.9 35 7.49 33 28.9 32 38.6 39 21.2 17 20.6 24 52.1 38 21.6 46 22.6 19 47.1 13 36.3 72 9.05 55 21.5 56 12.4 65
LME [70]29.4 31.5 38 51.4 27 21.0 14 14.7 5 36.9 2 15.7 12 16.0 29 35.2 13 19.8 52 11.8 43 36.6 43 8.08 43 28.6 29 36.0 26 25.5 45 21.1 28 49.0 27 19.8 28 29.8 38 50.0 26 21.5 38 6.61 33 15.1 30 7.95 36
AGIF+OF [85]29.8 26.3 15 48.8 16 24.1 19 24.9 72 52.0 71 26.2 71 16.0 29 39.4 31 19.7 49 8.96 15 32.0 11 6.64 19 26.7 16 33.7 13 21.5 20 21.4 29 49.4 29 18.5 14 28.2 32 49.6 23 30.5 64 4.63 17 11.3 14 7.30 27
PH-Flow [101]30.9 26.7 17 51.6 28 25.6 27 21.7 45 49.4 52 23.8 49 15.5 18 37.6 24 19.5 45 10.2 28 33.8 27 7.44 32 26.4 12 33.7 13 21.0 15 22.0 34 50.3 32 20.4 33 38.8 69 48.4 18 45.4 95 4.26 8 11.2 9 6.38 11
FC-2Layers-FF [74]30.9 26.9 20 48.6 15 28.3 39 22.1 49 48.8 47 23.8 49 14.1 12 32.4 5 19.6 47 9.10 16 28.3 5 6.47 18 25.5 7 31.7 7 23.0 30 23.3 49 47.7 21 21.8 47 44.1 89 56.3 62 46.0 100 3.54 1 9.08 1 5.44 6
NNF-EAC [103]32.0 34.9 44 54.8 38 29.9 45 15.6 9 41.7 11 15.9 13 15.1 17 34.8 12 15.7 19 12.4 50 35.1 38 8.33 51 28.1 25 35.7 23 22.9 28 24.5 63 46.2 12 22.7 58 31.6 47 49.1 20 20.1 34 7.54 42 17.1 40 7.44 30
Classic+CPF [83]32.2 27.1 25 51.2 26 25.5 26 23.9 65 51.4 67 25.1 64 15.9 26 39.3 30 19.4 43 9.17 17 32.8 17 6.69 21 27.3 19 34.5 17 23.9 35 21.0 27 48.7 26 18.0 12 35.6 58 49.9 25 45.7 97 4.25 7 10.7 5 6.61 17
COFM [59]32.5 22.1 7 49.1 18 16.6 8 18.2 22 43.5 16 19.2 29 15.9 26 38.3 27 21.5 64 7.02 5 32.6 15 4.40 5 31.4 46 37.9 36 35.0 85 22.1 36 46.4 15 18.3 13 28.7 35 45.9 11 45.5 96 9.25 56 15.5 34 15.7 74
IROF++ [58]32.5 27.4 27 50.7 22 26.7 33 22.1 49 50.1 62 24.1 54 16.3 32 40.0 35 19.6 47 10.6 35 34.3 32 7.72 38 27.9 24 35.7 23 22.5 23 22.3 40 54.1 53 19.9 29 25.5 23 49.6 23 11.5 10 5.49 25 14.1 27 6.54 15
Sparse-NonSparse [56]33.1 26.8 19 51.9 31 26.8 34 22.2 54 49.0 50 24.6 60 15.6 21 39.4 31 19.0 38 9.46 20 33.6 25 7.07 27 29.0 33 37.2 34 24.3 40 21.7 33 50.4 33 19.5 26 34.0 51 45.8 10 41.6 84 4.44 12 10.9 6 6.96 22
FESL [72]34.1 27.0 21 46.3 8 31.2 51 26.0 84 51.8 70 26.9 76 15.8 25 37.0 22 19.5 45 7.89 8 30.7 9 5.17 9 26.6 15 33.8 15 22.6 24 20.3 22 45.8 11 19.3 21 39.9 76 61.2 80 35.6 70 5.04 22 12.5 20 6.48 14
Efficient-NL [60]34.6 23.3 10 44.7 6 17.6 9 24.6 71 51.6 69 25.4 68 15.0 16 36.2 17 17.5 29 9.92 24 33.1 19 6.94 23 26.4 12 34.0 16 20.3 11 27.2 73 49.4 29 22.6 53 37.6 64 50.5 28 37.1 73 6.98 38 16.2 36 8.16 37
JOF [141]34.9 25.3 13 46.6 10 23.0 17 24.1 67 49.9 60 26.7 73 14.8 13 34.3 11 21.0 61 8.34 12 32.1 13 5.95 13 26.1 11 32.9 12 22.8 27 22.8 45 49.4 29 22.2 49 41.8 82 60.0 74 56.2 122 4.17 5 10.9 6 6.44 13
LSM [39]36.2 26.5 16 50.8 23 27.0 35 22.1 49 49.4 52 24.4 58 15.6 21 38.2 26 19.4 43 10.1 25 33.0 18 7.43 31 28.6 29 36.3 28 24.7 41 22.8 45 50.5 34 20.9 39 40.3 78 49.3 21 45.8 99 4.76 19 12.0 17 6.93 21
PMMST [114]36.2 42.4 75 58.9 48 40.2 72 22.1 49 45.3 26 24.7 63 17.9 43 38.4 28 18.8 35 12.2 46 28.1 3 8.26 49 25.7 8 32.7 10 18.5 7 22.3 40 45.3 8 20.8 37 28.5 34 50.7 30 18.3 25 8.51 52 16.8 37 8.73 45
Ramp [62]37.8 27.0 21 52.3 33 26.1 31 22.3 56 49.1 51 24.6 60 15.6 21 37.8 25 19.8 52 10.5 34 33.6 25 7.61 35 28.6 29 36.6 30 24.0 36 23.6 52 51.2 35 21.8 47 38.2 65 44.5 5 46.1 101 4.86 20 12.1 18 7.13 25
Classic+NL [31]37.8 27.2 26 47.8 14 28.4 41 22.0 48 49.4 52 24.1 54 15.5 18 37.4 23 19.8 52 10.4 32 33.8 27 7.40 30 28.5 27 36.4 29 24.2 39 23.3 49 52.2 39 21.1 40 43.9 87 52.5 40 44.6 92 4.60 16 11.2 9 7.04 24
2DHMM-SAS [92]40.5 26.7 17 51.8 30 25.6 27 22.2 54 51.3 65 23.8 49 17.8 41 42.3 41 20.0 57 10.4 32 34.6 34 7.52 34 28.5 27 36.6 30 24.0 36 22.7 44 54.5 56 20.6 34 39.0 71 47.8 16 45.1 93 5.51 26 13.9 25 7.73 34
FMOF [94]41.1 27.8 32 50.4 21 27.1 37 26.2 86 52.5 75 27.4 79 15.9 26 36.4 20 21.7 65 9.71 22 32.7 16 6.98 24 27.3 19 34.6 18 24.1 38 23.7 54 47.6 20 19.7 27 38.4 66 55.4 56 48.9 108 5.80 27 14.1 27 7.00 23
SVFilterOh [111]42.6 39.6 65 54.6 37 39.8 71 23.8 64 44.7 22 24.0 52 17.3 38 33.8 8 18.8 35 10.2 28 36.4 42 4.93 8 25.9 10 32.1 8 19.6 8 24.7 64 46.7 16 22.9 61 52.0 113 76.3 130 59.2 125 4.23 6 10.9 6 5.01 5
S2D-Matching [84]43.4 27.7 29 50.2 20 28.4 41 22.1 49 48.8 47 24.3 56 16.5 34 40.0 35 19.3 41 10.6 35 33.8 27 7.78 39 29.1 35 36.7 33 25.0 42 24.4 62 53.0 49 22.6 53 47.0 100 53.6 46 50.8 113 4.58 14 11.2 9 7.54 32
ProbFlowFields [128]43.6 33.9 40 68.5 72 30.9 49 20.3 35 45.3 26 22.1 39 19.2 52 44.8 50 22.9 69 11.7 42 39.3 52 8.91 61 31.0 44 40.1 45 23.3 32 16.8 8 47.8 23 19.2 18 23.7 22 55.9 59 23.9 47 8.39 49 22.4 59 9.82 54
SimpleFlow [49]44.2 28.6 35 51.6 28 29.5 44 25.0 73 51.3 65 28.2 85 18.6 48 43.0 44 23.3 70 10.1 25 33.5 24 7.04 26 29.9 37 37.9 36 26.2 47 27.8 78 52.2 39 24.0 66 35.1 55 47.9 17 29.7 63 4.66 18 12.4 19 6.92 20
PMF [73]45.6 37.7 59 58.3 46 27.3 38 19.4 28 45.0 25 18.3 24 16.2 31 39.9 34 14.0 15 13.6 64 35.7 40 8.03 42 25.8 9 32.5 9 17.1 6 30.2 86 57.0 68 31.6 89 58.9 123 74.7 122 55.9 121 3.95 3 10.3 3 6.15 10
Adaptive [20]46.5 27.0 21 52.6 34 19.8 12 21.9 47 47.8 41 22.6 41 20.5 57 47.8 59 19.7 49 10.3 30 39.9 56 6.31 17 45.6 124 52.6 121 51.3 126 17.4 9 48.2 24 13.9 3 34.8 54 56.9 65 19.8 32 6.04 30 15.2 31 7.54 32
TV-L1-MCT [64]46.5 27.5 28 49.4 19 27.0 35 26.5 87 52.8 80 27.8 84 16.8 35 39.1 29 21.8 66 10.6 35 33.8 27 7.82 41 30.3 40 38.1 38 28.7 63 24.7 64 53.4 51 23.4 63 27.4 29 52.5 40 19.4 29 7.28 39 15.3 32 11.4 62
Correlation Flow [75]46.7 36.6 56 55.3 42 34.4 60 16.6 15 44.4 20 14.8 8 18.3 47 42.9 43 12.7 9 12.4 50 39.7 54 8.46 55 32.2 49 40.6 49 25.2 43 29.0 81 54.2 55 29.7 85 39.1 72 52.1 38 47.4 104 6.53 32 16.1 35 6.88 19
IROF-TV [53]47.1 30.9 37 54.8 38 31.6 53 22.8 60 50.5 63 25.1 64 16.9 36 40.8 37 20.8 59 14.0 67 43.7 70 10.1 68 31.2 45 39.5 41 28.6 61 26.8 72 58.7 78 25.6 70 18.8 6 48.4 18 8.08 7 5.28 23 13.6 23 7.77 35
AggregFlow [97]47.4 36.3 55 52.7 35 35.7 62 26.6 88 52.6 78 26.7 73 23.3 70 48.2 61 28.9 88 12.1 44 34.9 35 8.63 57 30.2 39 40.3 48 21.4 18 15.9 5 38.3 2 16.8 8 26.1 26 47.3 14 16.8 18 12.6 76 20.3 49 20.0 89
Occlusion-TV-L1 [63]48.2 34.3 43 58.5 47 25.1 22 20.0 31 46.5 36 20.8 35 22.3 67 49.9 62 20.6 58 12.6 56 41.7 62 8.41 54 35.2 71 44.9 79 32.3 76 17.7 12 52.6 44 21.1 40 28.2 32 52.5 40 13.0 11 9.66 59 23.7 63 10.6 56
3DFlow [135]50.5 35.7 51 56.6 44 28.3 39 19.1 27 46.2 34 17.4 22 18.8 49 41.7 40 14.5 17 13.9 65 33.3 22 9.85 66 29.0 33 36.6 30 23.0 30 32.9 92 65.1 100 34.7 100 49.9 107 65.5 94 77.7 141 3.87 2 10.3 3 3.02 3
Classic++ [32]52.0 27.7 29 51.0 25 28.7 43 21.5 44 45.9 30 24.3 56 18.1 46 44.3 48 19.9 55 10.3 30 37.7 45 7.14 28 33.4 53 44.1 69 27.9 56 24.0 57 57.9 73 21.4 44 46.3 96 55.6 57 49.7 110 8.45 51 20.7 50 9.69 53
Aniso-Texture [82]52.3 28.5 34 50.9 24 32.7 57 21.2 39 41.7 11 25.3 67 17.6 40 41.2 38 21.1 62 5.72 1 33.2 21 2.54 1 35.1 70 43.7 66 31.3 74 23.6 52 53.6 52 22.6 53 62.2 130 75.8 128 53.5 118 6.89 37 17.4 42 8.20 38
MDP-Flow [26]53.0 35.5 50 65.0 59 32.4 54 20.6 37 43.8 18 24.4 58 18.0 45 43.4 46 19.9 55 14.9 75 41.8 64 11.5 77 30.8 43 39.6 42 25.3 44 23.8 55 57.4 71 22.2 49 31.0 42 59.3 71 16.8 18 10.8 71 26.5 69 10.9 58
IIOF-NLDP [131]53.1 33.3 39 59.3 49 24.9 21 24.4 70 53.8 87 22.9 43 18.8 49 46.2 54 15.0 18 13.5 61 39.7 54 9.86 67 32.3 50 41.2 53 23.3 32 29.9 85 60.2 87 29.6 84 28.1 31 60.8 77 27.0 56 7.51 41 17.2 41 7.29 26
DeepFlow2 [108]53.9 39.1 63 66.4 63 44.4 80 20.1 33 47.9 43 20.9 36 23.8 73 52.8 69 26.3 79 12.2 46 43.2 69 7.64 36 31.4 46 41.7 57 22.9 28 18.2 18 52.4 41 17.9 11 29.6 37 44.7 6 39.0 77 16.2 94 31.2 92 22.7 97
OFH [38]54.0 41.9 74 61.6 53 48.5 87 14.7 5 42.7 14 14.1 6 17.4 39 47.6 57 12.6 8 10.6 35 38.5 48 8.39 53 34.8 67 43.7 66 34.5 83 27.2 73 61.9 93 29.5 83 21.3 12 57.6 67 21.4 37 12.2 75 29.8 84 16.2 76
CPM-Flow [116]55.7 35.2 45 67.0 65 25.3 23 25.8 80 53.6 84 28.2 85 25.5 76 58.5 89 27.5 81 12.4 50 48.0 84 8.11 46 33.9 58 44.2 70 27.1 50 17.6 10 51.8 36 19.1 16 21.3 12 51.7 35 22.6 43 9.92 64 27.2 74 11.3 60
S2F-IF [123]56.3 35.7 51 69.0 75 26.6 32 24.1 67 54.0 92 26.0 70 25.6 78 60.9 96 25.9 75 12.4 50 46.6 81 8.38 52 34.3 63 44.2 70 27.7 55 18.0 17 53.2 50 19.2 18 21.2 11 51.7 35 22.9 44 8.97 54 24.9 66 9.11 49
BriefMatch [124]56.4 34.1 42 59.4 50 30.2 46 17.1 17 43.6 17 16.1 15 14.8 13 36.3 19 13.4 13 9.41 19 34.3 32 6.26 16 33.4 53 41.2 53 31.8 75 40.3 120 63.5 95 42.7 123 47.2 101 61.1 78 59.1 124 12.7 78 23.4 60 21.6 95
PGM-C [120]56.5 35.2 45 67.1 67 25.4 25 25.8 80 53.6 84 28.2 85 25.8 79 59.3 94 27.5 81 12.4 50 48.1 85 8.16 47 33.9 58 44.3 73 27.1 50 17.7 12 52.8 48 19.1 16 20.8 8 50.3 27 22.4 41 9.82 62 27.2 74 11.5 64
EpicFlow [102]58.4 35.2 45 67.2 68 25.3 23 25.8 80 53.8 87 28.2 85 26.1 81 60.1 95 27.5 81 12.4 50 48.1 85 8.10 45 34.2 62 44.5 75 28.0 57 17.8 14 52.7 46 19.4 23 21.0 9 52.1 38 22.5 42 10.4 68 27.3 76 12.7 67
FlowFields+ [130]59.0 35.8 54 69.2 77 26.0 30 25.6 78 55.3 100 27.7 82 26.7 82 62.9 101 27.7 85 12.7 57 45.9 79 8.84 60 34.0 61 44.2 70 26.6 48 17.6 10 54.9 58 19.0 15 20.6 7 53.9 48 22.3 40 9.31 58 26.5 69 8.79 46
CostFilter [40]59.2 43.6 82 65.7 61 40.8 73 20.8 38 45.9 30 21.0 37 18.8 49 44.9 51 18.3 34 17.3 86 39.5 53 13.9 88 26.7 16 32.8 11 22.7 26 30.9 89 60.0 85 31.6 89 59.7 124 81.5 140 59.3 126 4.31 10 11.9 16 5.93 8
RFlow [90]59.4 44.4 84 75.2 99 50.5 91 16.5 14 42.1 13 17.2 21 21.4 61 52.2 65 16.0 20 11.3 40 36.2 41 7.25 29 35.2 71 44.3 73 32.3 76 24.3 60 55.6 62 22.6 53 38.6 67 55.3 54 41.6 84 13.4 81 29.9 85 16.9 82
FlowFields [110]60.9 35.7 51 68.7 73 25.8 29 25.6 78 55.1 99 27.7 82 26.8 85 62.8 100 27.6 84 13.0 59 46.8 82 9.13 63 34.6 66 44.9 79 28.1 58 17.8 14 54.9 58 19.4 23 21.3 12 54.8 52 24.2 49 9.25 56 26.4 68 8.47 41
TV-L1-improved [17]61.7 27.7 29 57.9 45 20.5 13 18.2 22 44.9 24 19.1 27 19.4 53 47.7 58 17.0 28 10.1 25 38.5 48 6.75 22 35.9 78 46.0 87 27.3 52 43.7 126 70.2 120 47.5 128 51.4 110 60.5 76 50.3 112 10.3 67 26.8 73 10.8 57
DMF_ROB [140]61.9 43.0 79 71.7 87 45.5 83 22.4 57 48.3 45 24.0 52 28.0 93 62.4 99 26.9 80 12.8 58 45.8 78 7.80 40 33.9 58 43.1 60 30.0 70 20.9 25 56.4 65 21.2 42 22.3 18 42.0 3 27.0 56 12.7 78 27.6 77 17.1 83
Steered-L1 [118]64.0 38.7 62 67.9 69 43.1 78 11.6 1 34.7 1 12.3 2 16.3 32 41.3 39 13.9 14 12.1 44 38.6 50 8.30 50 34.5 65 43.4 63 32.5 78 29.4 83 61.1 92 25.9 71 60.6 127 67.0 101 70.1 137 15.9 91 30.6 88 24.0 99
Sparse Occlusion [54]64.5 38.6 61 61.8 54 32.5 56 26.0 84 48.8 47 29.5 93 20.0 55 45.2 52 19.2 40 14.3 71 38.4 46 9.67 65 34.4 64 42.6 59 26.7 49 25.4 67 52.4 41 22.4 52 67.3 135 75.9 129 48.3 106 8.07 47 19.9 48 7.36 28
DeepFlow [86]65.8 47.3 90 71.9 88 64.0 109 21.4 42 48.2 44 22.7 42 27.9 90 58.2 86 31.6 94 15.1 76 42.7 65 10.6 73 31.5 48 42.1 58 22.6 24 19.6 20 56.7 67 19.4 23 27.6 30 46.2 12 39.7 78 20.6 104 35.3 110 28.0 107
MLDP_OF [89]65.8 48.8 93 77.3 102 52.2 93 20.1 33 49.6 57 19.3 31 23.5 72 54.6 73 18.9 37 12.3 49 38.6 50 7.65 37 33.5 56 40.9 50 29.1 68 28.4 79 55.9 63 31.6 89 49.1 105 62.2 85 60.5 128 7.91 46 16.8 37 8.95 47
PWC-Net_ROB [148]66.6 49.3 95 75.1 98 39.6 70 28.7 95 54.0 92 29.4 92 27.2 86 58.7 90 31.5 93 15.6 78 38.4 46 8.76 59 36.5 84 45.6 86 28.3 59 26.2 70 60.3 88 26.4 74 13.0 2 49.3 21 4.98 3 7.79 43 19.4 46 7.36 28
TF+OM [100]67.2 39.8 66 55.2 41 30.4 48 20.4 36 41.0 8 23.5 46 19.5 54 39.4 31 28.0 86 18.4 89 37.0 44 18.0 95 35.0 68 41.1 51 39.6 97 29.6 84 52.6 44 29.1 82 49.0 104 66.8 100 43.6 91 14.4 83 29.3 81 18.0 85
CombBMOF [113]69.2 42.4 75 71.5 85 31.3 52 25.2 74 52.9 81 25.1 64 17.9 43 45.8 53 16.1 21 14.2 69 41.7 62 11.4 76 33.5 56 40.2 46 29.6 69 34.5 98 59.9 84 37.3 106 55.2 120 69.9 110 46.5 103 6.78 35 16.8 37 8.62 42
EPPM w/o HM [88]69.8 43.1 80 72.4 90 38.1 68 18.7 25 52.5 75 16.9 19 21.3 60 56.2 78 17.5 29 16.2 82 45.3 76 12.7 84 33.4 53 39.6 42 30.0 70 33.5 94 65.4 102 33.8 95 45.5 91 66.1 98 65.5 134 6.88 36 18.1 43 9.16 51
FF++_ROB [146]70.1 38.0 60 69.4 78 32.4 54 25.8 80 54.8 98 27.6 80 28.3 97 63.7 102 30.3 89 15.7 79 49.6 89 12.9 85 35.0 68 44.9 79 28.9 65 23.0 47 55.4 61 23.0 62 22.1 17 53.1 44 24.0 48 10.1 65 25.5 67 12.8 68
Complementary OF [21]71.7 51.9 102 74.9 97 59.3 103 14.2 3 41.6 10 13.7 3 20.4 56 46.6 55 19.7 49 22.2 96 40.8 58 21.0 100 36.0 80 43.4 63 38.5 95 33.9 97 63.8 96 31.6 89 31.1 43 51.9 37 36.2 71 18.9 101 34.4 108 29.4 109
Aniso. Huber-L1 [22]72.2 33.9 40 65.1 60 32.8 58 34.0 100 54.0 92 40.0 102 27.9 90 55.0 75 38.4 100 15.2 77 49.9 90 12.0 79 35.3 73 44.6 76 28.5 60 23.9 56 55.9 63 20.7 35 50.6 108 62.1 84 39.7 78 8.15 48 20.7 50 8.39 39
TCOF [69]74.1 45.0 85 70.0 79 51.5 92 25.5 77 53.7 86 26.7 73 26.7 82 56.2 78 32.0 95 21.9 95 43.1 68 22.2 102 37.8 91 48.9 103 25.7 46 18.8 19 44.7 7 20.0 30 52.1 114 67.5 103 25.8 50 10.7 70 26.7 71 11.4 62
Rannacher [23]74.4 43.1 80 71.0 83 45.2 82 24.1 67 49.4 52 26.4 72 26.0 80 56.9 82 26.0 77 14.2 69 42.7 65 10.5 72 37.1 88 47.9 98 30.7 73 32.3 91 65.2 101 27.0 76 44.0 88 56.0 61 39.7 78 7.83 44 21.2 54 9.19 52
ComplOF-FED-GPU [35]74.7 49.5 96 75.7 101 55.3 96 15.3 7 47.0 38 13.8 4 21.1 59 52.7 68 16.1 21 17.1 85 40.6 57 14.2 89 35.7 77 45.1 83 32.5 78 35.3 101 67.5 112 34.4 98 46.5 98 59.0 70 50.8 113 12.8 80 29.6 82 16.6 79
ACK-Prior [27]75.2 55.9 104 72.7 92 59.3 103 17.5 19 43.3 15 16.0 14 17.8 41 42.3 41 16.3 25 17.6 87 41.3 60 12.0 79 35.3 73 41.1 51 35.9 86 37.4 113 59.6 82 34.3 97 59.8 126 61.1 78 74.7 138 17.7 99 29.2 80 27.4 102
F-TV-L1 [15]76.6 66.8 114 84.2 112 77.3 120 27.1 91 52.0 71 29.1 91 27.2 86 57.3 84 24.2 73 24.1 101 52.0 95 19.5 98 39.3 98 47.7 97 39.3 96 24.2 59 56.5 66 24.9 68 33.2 50 53.7 47 20.1 34 6.69 34 18.6 44 5.94 9
LDOF [28]77.0 41.7 73 70.7 80 47.2 86 24.0 66 53.9 91 24.6 60 26.7 82 58.4 88 25.5 74 15.8 80 57.4 106 10.2 70 36.0 80 45.3 84 34.8 84 22.1 36 58.1 75 21.3 43 30.6 40 56.8 63 23.4 45 22.5 113 38.6 119 30.2 110
ROF-ND [107]77.3 49.2 94 71.5 85 49.4 89 22.5 59 46.2 34 20.6 33 21.4 61 50.0 63 18.1 32 23.1 98 53.7 99 16.0 91 35.9 78 46.1 89 28.6 61 33.5 94 58.5 76 30.3 86 60.7 128 70.5 111 60.4 127 9.67 60 20.9 52 10.2 55
SIOF [67]78.6 50.3 99 66.0 62 47.1 85 19.8 30 48.4 46 20.7 34 29.8 99 55.1 76 32.6 97 25.9 104 48.3 87 25.0 105 37.7 89 46.4 91 36.8 89 32.9 92 58.6 77 35.6 103 37.2 63 53.1 44 18.6 26 16.8 97 33.0 97 21.3 94
LocallyOriented [52]79.0 39.4 64 60.5 51 35.7 62 27.9 94 57.8 107 28.5 89 28.1 94 58.3 87 30.6 92 13.9 65 41.3 60 10.1 68 37.8 91 47.3 95 33.0 82 24.8 66 52.5 43 28.1 79 39.4 74 62.4 86 37.5 74 15.7 89 33.0 97 18.2 87
Second-order prior [8]79.4 37.6 58 70.9 82 37.2 66 22.4 57 51.2 64 23.7 48 24.5 75 59.1 93 22.6 67 11.2 39 41.2 59 8.48 56 37.9 93 49.6 111 28.8 64 29.0 81 68.8 116 26.0 72 55.5 121 64.7 92 52.7 117 14.7 86 34.1 105 17.3 84
Brox et al. [5]79.7 43.7 83 74.4 95 56.4 100 27.0 90 52.5 75 30.5 95 23.4 71 54.5 72 23.3 70 13.4 60 50.0 91 8.66 58 39.8 101 46.5 92 47.6 118 21.6 31 59.8 83 22.8 60 30.9 41 59.3 71 7.61 4 23.1 117 37.0 115 33.4 119
FlowNetS+ft+v [112]80.0 36.8 57 67.0 65 39.4 69 25.3 76 52.1 73 27.6 80 27.8 89 57.2 83 35.5 98 13.5 61 50.9 93 9.44 64 40.1 102 49.5 110 36.8 89 20.9 25 57.0 68 20.8 37 46.3 96 66.3 99 41.0 82 17.4 98 34.3 107 24.1 100
NL-TV-NCC [25]80.2 46.1 87 68.3 71 43.4 79 25.2 74 55.3 100 23.5 46 21.8 66 47.2 56 16.9 27 16.9 84 44.1 71 11.9 78 38.5 95 49.1 107 27.3 52 36.5 108 65.7 104 34.9 101 46.2 93 75.7 127 45.7 97 12.6 76 28.8 78 9.10 48
CRTflow [80]80.8 40.9 68 72.5 91 36.2 64 21.3 41 49.4 52 21.8 38 22.9 68 57.5 85 19.0 38 14.0 67 44.7 73 10.3 71 35.4 76 45.0 82 30.4 72 46.6 131 73.4 125 53.8 133 38.8 69 65.5 94 38.2 75 19.5 103 38.5 118 27.6 105
DF-Auto [115]80.9 41.6 72 64.2 57 32.8 58 42.0 109 58.8 110 49.6 111 34.8 106 62.2 98 47.2 110 20.7 93 53.4 98 14.5 90 36.2 83 44.7 77 37.2 92 15.1 3 42.9 6 17.4 9 45.3 90 69.0 107 13.0 11 24.2 121 37.7 116 31.9 114
SRR-TVOF-NL [91]81.0 47.6 91 69.1 76 41.9 76 23.3 61 52.7 79 23.3 44 25.5 76 56.8 81 25.9 75 13.5 61 47.9 83 8.09 44 36.9 87 43.8 68 32.9 81 25.8 68 57.7 72 22.6 53 62.8 132 75.2 124 49.1 109 21.0 106 29.7 83 31.6 113
DPOF [18]81.5 45.3 86 68.9 74 37.6 67 26.7 89 56.9 103 26.9 76 24.3 74 54.6 73 26.2 78 18.6 90 54.6 102 13.6 87 33.3 52 43.1 60 28.9 65 27.6 77 60.8 89 26.3 73 47.2 101 55.3 54 76.0 140 14.3 82 31.0 91 15.3 73
TriangleFlow [30]81.6 41.5 71 63.2 55 42.6 77 21.4 42 52.4 74 20.2 32 21.7 65 53.6 71 16.2 23 14.8 73 44.4 72 10.9 74 43.2 115 52.9 123 43.4 107 36.8 112 65.9 105 38.8 110 42.2 83 65.4 93 41.8 86 15.8 90 35.2 109 22.5 96
Bartels [41]83.2 48.6 92 63.2 55 61.4 108 23.4 63 44.0 19 27.1 78 21.4 61 44.6 49 23.8 72 26.2 105 43.0 67 25.4 106 36.8 85 44.7 77 41.7 103 33.7 96 60.0 85 41.7 120 52.6 115 67.2 102 61.1 129 11.2 72 23.4 60 16.3 77
SuperFlow [81]83.8 35.2 45 61.1 52 34.4 60 35.2 101 53.5 83 42.5 103 27.7 88 52.5 67 43.5 108 27.5 106 60.5 112 27.6 108 36.0 80 43.3 62 42.2 104 22.6 43 59.2 81 22.2 49 46.2 93 62.0 83 23.4 45 21.8 111 36.0 111 32.5 116
Dynamic MRF [7]83.9 49.5 96 78.0 103 55.8 99 17.2 18 47.4 40 16.5 18 21.6 64 56.3 80 16.2 23 14.8 73 46.4 80 12.5 82 41.2 107 49.0 105 45.1 112 35.3 101 70.7 121 38.5 109 37.1 62 57.7 68 55.1 119 21.3 108 36.7 114 31.2 112
CBF [12]84.1 41.4 69 74.0 94 48.5 87 40.2 106 51.5 68 51.7 113 22.9 68 50.8 64 28.5 87 14.3 71 44.7 73 11.2 75 38.3 94 46.1 89 36.1 87 26.3 71 55.1 60 24.9 68 61.5 129 71.0 112 52.0 116 11.6 74 26.7 71 14.8 72
CLG-TV [48]84.6 41.4 69 68.0 70 40.8 73 37.0 104 53.1 82 45.3 105 30.9 100 58.7 90 40.2 102 22.8 97 62.0 114 19.3 97 39.0 97 47.6 96 38.2 94 27.2 73 61.0 91 27.1 77 46.2 93 57.8 69 29.3 62 9.74 61 24.6 65 9.11 49
CNN-flow-warp+ref [117]85.1 42.6 77 71.2 84 49.8 90 31.6 99 53.8 87 37.3 100 32.7 102 63.8 103 42.7 106 16.0 81 55.1 103 12.1 81 38.6 96 46.0 87 43.8 110 23.3 49 59.1 80 23.6 64 23.5 21 50.9 32 21.9 39 24.2 121 36.2 113 32.9 117
Local-TV-L1 [65]85.2 56.8 106 79.1 104 74.5 114 39.5 105 53.8 87 46.1 107 38.1 107 66.2 105 43.1 107 23.9 100 52.9 97 21.1 101 32.3 50 41.4 56 27.5 54 23.2 48 54.8 57 22.7 58 25.8 24 47.5 15 33.4 68 26.9 124 40.5 123 40.5 128
HBM-GC [105]87.5 73.5 124 79.7 105 79.4 123 30.0 96 49.7 59 33.6 96 29.3 98 47.8 59 30.4 90 35.4 112 45.2 75 33.3 113 30.5 41 35.1 21 32.6 80 34.6 99 52.0 37 35.4 102 70.9 138 80.1 135 62.6 130 8.83 53 19.1 45 13.0 69
TriFlow [95]90.6 47.1 89 66.5 64 41.1 75 31.2 98 49.6 57 37.3 100 27.9 90 52.3 66 39.4 101 24.7 102 49.3 88 22.3 103 37.7 89 43.5 65 43.1 106 28.4 79 52.7 46 29.0 81 76.7 142 73.7 117 99.5 145 16.2 94 30.5 87 20.1 90
OFRF [134]91.9 50.4 100 64.5 58 55.4 98 41.2 108 57.5 105 46.2 109 34.5 105 58.9 92 40.6 103 29.6 108 45.6 77 28.8 109 30.7 42 40.2 46 22.3 22 31.1 90 57.9 73 30.4 88 43.5 86 62.5 87 51.9 115 29.8 128 39.3 120 49.1 136
p-harmonic [29]92.8 50.4 100 86.6 122 56.5 102 27.1 91 54.5 95 28.9 90 32.9 103 69.3 111 30.4 90 19.8 91 65.1 117 16.2 92 39.6 100 47.2 94 40.3 99 30.4 87 66.5 107 32.2 93 45.6 92 64.4 90 28.9 61 10.2 66 24.1 64 13.2 70
Learning Flow [11]93.3 42.9 78 70.7 80 44.8 81 30.2 97 54.7 96 34.7 97 28.2 95 55.9 77 32.3 96 17.6 87 57.1 105 12.6 83 44.0 118 52.6 121 47.8 121 30.5 88 64.6 98 30.3 86 46.9 99 63.3 88 42.8 90 14.7 86 31.6 95 16.3 77
Fusion [6]95.6 40.5 67 75.6 100 45.9 84 20.0 31 50.0 61 22.5 40 20.8 58 52.8 69 22.8 68 16.2 82 52.8 96 13.5 86 43.1 113 49.0 105 47.5 115 39.6 119 67.8 114 43.8 125 63.9 133 75.0 123 46.3 102 35.5 134 42.6 129 53.3 140
Shiralkar [42]97.7 46.1 87 85.6 118 54.3 95 19.7 29 57.7 106 18.2 23 28.2 95 70.8 112 19.3 41 20.5 92 59.0 108 18.4 96 39.5 99 49.7 113 36.3 88 40.4 121 76.1 127 41.2 119 51.9 112 65.8 96 64.2 132 21.0 106 42.4 128 25.3 101
StereoFlow [44]97.9 95.9 145 96.0 144 97.4 145 88.3 145 96.2 145 86.2 141 82.6 142 94.8 143 73.7 139 91.4 144 96.3 144 90.3 143 53.0 134 61.6 138 52.8 127 11.2 1 39.3 3 11.7 1 10.5 1 42.5 4 1.70 1 11.5 73 23.6 62 18.0 85
LiteFlowNet [143]99.1 62.6 108 88.2 128 55.3 96 35.7 102 65.1 120 36.9 99 39.6 108 74.5 114 38.1 99 23.4 99 50.3 92 17.4 93 43.1 113 51.4 118 42.2 104 35.7 103 69.3 118 33.9 96 41.2 79 75.2 124 17.8 23 14.4 83 28.9 79 16.7 80
SegOF [10]101.6 56.3 105 71.9 88 37.1 65 57.3 125 62.9 117 68.3 127 46.0 115 69.0 110 57.2 124 41.0 116 59.5 110 37.2 115 43.5 116 48.3 101 56.4 131 38.2 117 69.6 119 39.1 111 17.9 5 64.5 91 3.40 2 22.7 116 33.0 97 32.0 115
StereoOF-V1MT [119]102.4 49.7 98 86.0 119 56.4 100 21.2 39 68.8 124 16.3 17 32.2 101 80.7 123 20.8 59 21.3 94 66.1 120 17.4 93 47.0 126 57.0 126 47.5 115 41.7 124 81.2 133 40.9 116 38.6 67 68.1 105 48.6 107 23.2 118 42.2 127 27.7 106
Ad-TV-NDC [36]103.2 73.7 125 85.4 116 89.5 139 56.9 124 60.4 113 67.5 126 51.0 121 75.9 116 57.6 126 45.7 119 65.7 118 47.9 123 35.3 73 45.3 84 28.9 65 27.3 76 57.2 70 28.2 80 34.6 53 55.0 53 27.3 58 34.0 131 48.7 135 47.5 133
WOLF_ROB [149]105.1 56.9 107 87.9 126 59.5 105 35.9 103 66.0 122 35.7 98 42.5 110 78.3 118 44.7 109 24.7 102 59.5 110 22.9 104 41.2 107 49.1 107 43.4 107 37.7 115 72.0 124 35.9 104 34.3 52 61.3 81 27.4 59 22.5 113 40.1 122 33.0 118
Modified CLG [34]105.3 68.7 117 80.5 107 76.1 118 52.0 120 61.0 114 63.6 123 51.9 122 79.4 119 55.6 121 47.4 122 72.1 126 46.7 121 41.2 107 49.7 113 46.0 113 26.0 69 64.7 99 26.7 75 31.4 46 55.6 57 19.9 33 29.0 127 43.8 131 39.9 127
IAOF2 [51]106.6 54.9 103 73.7 93 53.9 94 42.6 110 58.3 108 50.7 112 33.9 104 61.9 97 42.1 105 64.4 132 75.7 129 74.3 134 41.5 110 49.9 116 37.1 91 36.4 107 64.0 97 34.4 98 59.7 124 69.6 109 41.3 83 19.4 102 33.4 102 23.0 98
AugFNG_ROB [144]108.5 72.6 123 79.9 106 59.6 106 59.5 126 72.0 128 68.5 128 55.6 127 83.3 126 56.1 122 34.1 111 59.3 109 30.3 110 49.8 129 58.3 129 47.4 114 37.9 116 71.3 122 39.6 113 35.5 57 73.9 118 8.00 6 15.9 91 33.2 100 18.4 88
Filter Flow [19]109.7 62.9 109 74.4 95 60.8 107 42.8 111 60.1 112 49.4 110 42.5 110 66.0 104 51.2 114 52.1 128 69.5 123 50.2 124 44.8 121 49.7 113 54.4 129 41.9 125 66.7 108 43.6 124 74.3 141 88.9 143 42.6 89 10.6 69 21.6 57 12.6 66
GroupFlow [9]111.1 66.4 112 85.2 115 80.8 126 61.6 129 75.4 133 69.0 129 51.9 122 83.6 128 57.0 123 33.5 110 63.9 115 32.5 112 49.6 128 61.0 133 39.9 98 51.3 137 81.7 134 59.4 137 22.8 20 51.1 33 16.5 16 28.0 126 41.9 126 37.9 125
SPSA-learn [13]111.4 65.1 110 87.4 125 72.7 113 45.7 116 59.3 111 53.4 116 45.2 114 74.7 115 52.2 116 41.6 117 69.9 125 42.5 117 42.7 112 48.9 103 48.7 123 38.8 118 69.0 117 42.5 122 39.1 72 61.9 82 19.3 28 36.0 135 45.6 132 48.3 134
2D-CLG [1]111.8 77.2 128 82.3 110 75.4 116 61.5 128 65.9 121 73.7 133 63.2 134 89.6 136 60.8 131 82.8 141 88.3 137 86.8 141 43.5 116 49.3 109 54.8 130 35.1 100 67.5 112 36.1 105 21.3 12 50.8 31 15.5 14 34.4 133 46.3 134 46.0 130
IAOF [50]111.9 66.3 111 81.3 109 77.8 121 50.1 119 58.4 109 59.7 120 45.0 113 74.1 113 49.6 113 50.8 125 68.2 121 58.0 130 40.2 103 48.7 102 37.8 93 36.7 109 66.9 109 33.5 94 54.9 118 63.5 89 40.8 81 30.1 130 41.3 125 43.5 129
TVL1_ROB [139]112.1 88.5 140 92.7 135 96.3 143 69.8 137 66.8 123 83.7 139 67.9 135 90.2 138 70.7 137 77.3 137 89.0 139 80.6 137 40.3 105 49.6 111 40.9 100 24.0 57 65.5 103 27.6 78 21.8 16 57.3 66 10.2 9 36.2 136 51.1 137 47.2 132
BlockOverlap [61]112.1 77.2 128 86.0 119 82.8 129 48.2 117 55.8 102 57.6 119 46.9 117 66.9 106 51.9 115 49.1 124 54.1 100 51.2 125 36.8 85 41.3 55 47.5 115 40.5 122 59.0 79 39.6 113 68.9 137 80.2 136 65.1 133 20.8 105 30.8 89 34.9 121
HBpMotionGpu [43]112.3 67.0 115 80.7 108 72.3 112 55.3 122 57.3 104 66.7 125 44.7 112 67.2 108 54.1 119 39.5 115 57.8 107 38.4 116 42.0 111 48.2 100 48.3 122 35.9 104 60.9 90 39.2 112 65.1 134 72.0 115 50.1 111 22.6 115 32.5 96 36.9 122
LFNet_ROB [151]112.7 72.3 120 93.8 139 65.3 110 45.6 115 78.1 138 45.9 106 48.8 120 87.7 133 41.8 104 31.5 109 66.0 119 25.6 107 47.8 127 57.1 127 47.6 118 37.6 114 71.5 123 38.0 107 49.3 106 74.5 121 26.4 55 15.9 91 33.5 103 20.9 92
ContFlow_ROB [150]113.6 81.5 135 92.6 134 75.9 117 56.2 123 73.5 129 61.9 122 61.1 133 83.5 127 62.9 134 36.8 113 61.1 113 31.7 111 51.9 131 60.7 132 49.2 124 47.6 132 77.8 130 49.7 130 35.2 56 71.1 113 8.69 8 16.2 94 34.1 105 16.8 81
GraphCuts [14]114.3 66.6 113 87.0 123 80.0 125 43.1 112 63.0 118 46.1 107 41.8 109 67.0 107 53.4 118 28.5 107 64.0 116 20.8 99 40.2 103 48.1 99 43.5 109 46.5 129 63.4 94 40.5 115 62.7 131 75.4 126 69.5 136 23.8 120 33.3 101 38.5 126
Black & Anandan [4]114.6 70.3 119 88.0 127 84.1 130 45.5 114 61.4 115 52.0 114 47.4 118 77.3 117 52.9 117 42.3 118 77.5 130 42.8 118 44.0 118 51.8 119 45.0 111 35.9 104 75.9 126 38.3 108 50.8 109 71.3 114 17.8 23 29.8 128 42.7 130 37.6 124
EPMNet [133]116.5 78.2 130 91.5 132 78.0 122 61.6 129 75.7 134 69.6 130 55.3 126 79.5 120 57.3 125 48.1 123 56.6 104 47.7 122 45.3 122 54.0 124 41.1 101 36.7 109 67.3 110 41.0 117 56.4 122 81.4 139 26.3 53 18.6 100 36.0 111 20.7 91
FlowNet2 [122]116.8 78.8 131 86.2 121 79.4 123 63.5 134 70.2 126 72.8 132 57.2 130 82.0 124 59.7 130 46.2 120 51.4 94 45.6 120 45.3 122 54.0 124 41.1 101 36.7 109 67.3 110 41.0 117 67.6 136 80.8 137 55.1 119 14.5 85 30.0 86 13.9 71
ResPWCR_ROB [145]117.5 78.9 132 92.8 137 75.1 115 40.4 107 63.5 119 43.5 104 48.1 119 80.2 121 48.8 112 39.2 114 69.2 122 35.6 114 44.0 118 50.5 117 49.2 124 44.6 128 76.7 128 47.0 127 54.6 117 78.7 132 31.4 65 23.4 119 38.0 117 30.8 111
2bit-BM-tele [98]119.3 82.4 136 87.2 124 91.8 140 44.4 113 54.7 96 52.9 115 46.0 115 68.3 109 47.4 111 51.5 127 54.4 101 53.4 128 40.5 106 47.1 93 47.7 120 47.9 133 66.4 106 53.1 131 71.7 139 83.6 141 75.1 139 21.9 112 39.3 120 29.2 108
Nguyen [33]119.6 75.6 127 85.4 116 85.8 132 67.0 135 61.6 116 83.0 138 57.1 129 80.2 121 64.1 135 70.8 133 80.2 132 77.4 136 45.9 125 52.2 120 56.4 131 36.3 106 68.1 115 42.0 121 41.4 80 66.0 97 19.7 31 34.1 132 45.6 132 46.1 131
SILK [79]120.4 72.5 121 85.1 114 88.3 136 61.9 131 71.8 127 73.7 133 54.9 125 85.3 129 58.0 128 53.6 129 69.8 124 54.6 129 52.8 132 57.9 128 61.8 135 46.5 129 77.6 129 48.9 129 31.3 44 54.3 51 38.9 76 37.8 137 50.6 136 49.7 137
UnFlow [129]122.9 89.6 142 94.1 140 86.4 133 72.2 138 83.9 141 77.9 136 71.4 139 93.2 140 69.8 136 54.8 130 74.4 127 51.4 126 62.0 140 66.9 141 69.1 142 50.0 135 80.9 131 57.1 134 53.2 116 69.0 107 7.68 5 15.6 88 30.8 89 21.0 93
Periodicity [78]123.9 68.9 118 83.5 111 65.5 111 52.2 121 69.8 125 57.0 118 78.4 141 82.5 125 87.2 143 47.2 121 74.7 128 45.5 119 69.7 145 81.9 145 65.6 139 59.5 140 84.9 141 60.7 138 36.3 61 79.8 134 19.2 27 40.7 139 66.5 144 53.1 139
Horn & Schunck [3]124.2 74.1 126 93.2 138 86.9 134 49.1 118 73.8 130 53.9 117 53.1 124 89.0 135 54.6 120 50.9 126 81.4 133 52.4 127 51.3 130 58.8 130 54.3 128 41.2 123 82.3 135 44.6 126 55.0 119 74.3 120 19.6 30 40.7 139 56.8 139 48.8 135
Heeger++ [104]127.0 86.1 138 91.0 131 77.1 119 67.6 136 91.6 144 65.1 124 85.6 144 94.6 142 83.6 142 71.0 134 88.2 136 68.8 132 62.9 141 69.8 143 67.3 140 69.4 144 91.0 144 70.8 142 40.2 77 80.9 138 26.3 53 21.7 109 31.2 92 27.4 102
SLK [47]128.0 67.5 116 90.3 130 82.1 127 72.2 138 84.7 142 84.8 140 58.4 131 94.0 141 58.1 129 78.1 138 82.5 134 84.6 140 55.4 137 61.5 136 68.1 141 49.4 134 83.7 139 57.7 135 36.2 60 68.1 105 26.2 52 50.3 142 60.0 141 65.2 144
FFV1MT [106]129.6 85.0 137 92.0 133 84.4 131 60.6 127 83.8 140 60.8 121 85.4 143 92.2 139 88.2 144 71.2 135 89.9 141 69.1 133 64.0 143 69.3 142 78.0 144 69.2 143 91.5 145 73.2 144 51.7 111 73.9 118 45.3 94 21.7 109 31.2 92 27.4 102
FOLKI [16]130.3 72.5 121 84.5 113 87.5 135 62.3 132 74.9 132 74.0 135 56.9 128 87.2 131 57.7 127 59.8 131 78.1 131 65.4 131 53.3 135 61.2 135 62.7 136 50.9 136 81.0 132 62.7 139 47.3 103 73.3 116 56.8 123 49.0 141 62.9 142 64.3 143
TI-DOFE [24]130.8 90.7 143 94.6 142 97.1 144 76.9 143 79.5 139 89.4 144 73.1 140 96.1 144 74.4 140 84.6 142 93.6 143 88.3 142 52.9 133 59.9 131 63.9 137 44.5 127 83.6 138 53.5 132 42.9 84 68.0 104 17.0 21 50.5 143 65.5 143 62.4 141
H+S_ROB [138]131.4 79.9 134 90.1 129 82.1 127 76.2 142 90.8 143 81.2 137 71.3 138 96.3 145 61.1 132 90.5 143 89.3 140 92.5 144 58.3 139 63.2 139 71.1 143 59.0 139 85.7 143 64.1 140 32.5 49 78.0 131 25.8 50 55.9 144 57.0 140 62.6 142
PGAM+LK [55]136.5 79.4 133 92.7 135 88.7 137 62.9 133 76.8 137 71.9 131 59.9 132 88.3 134 62.8 133 74.9 136 90.6 142 75.6 135 54.4 136 61.0 133 64.6 138 58.1 138 82.7 136 58.6 136 77.6 143 85.6 142 78.1 142 38.8 138 52.7 138 50.7 138
Adaptive flow [45]137.3 91.3 144 95.7 143 96.2 141 75.8 141 75.9 135 86.2 141 68.9 136 85.6 130 72.4 138 80.6 140 85.2 135 83.9 139 57.3 138 61.5 136 60.2 134 66.7 141 84.1 140 70.4 141 90.2 144 92.7 144 95.0 143 27.7 125 40.5 123 37.0 123
HCIC-L [99]138.2 88.6 141 96.7 145 89.3 138 80.8 144 74.4 131 93.1 145 86.6 145 87.2 131 95.2 145 95.8 145 97.4 145 96.9 145 63.4 142 66.7 140 57.8 133 68.9 142 82.7 136 73.1 143 96.0 145 95.9 145 98.6 144 25.3 123 33.9 104 34.7 120
Pyramid LK [2]140.7 86.7 139 94.5 141 96.2 141 73.1 140 76.5 136 86.4 143 70.8 137 89.6 136 78.5 141 78.1 138 88.6 138 82.7 138 68.8 144 76.4 144 80.4 145 75.7 145 85.1 142 78.1 145 73.1 140 79.6 133 69.3 135 60.8 145 74.5 145 79.9 145
AdaConv-v1 [126]146.3 100.0 146 100.0 147 100.0 146 100.0 146 100.0 146 100.0 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 147 99.9 147 99.9 147 99.9 147 100.0 147 99.7 147 99.9 147 99.9 146 99.9 146 99.9 146
SepConv-v1 [127]146.3 100.0 146 100.0 147 100.0 146 100.0 146 100.0 146 100.0 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 147 99.9 147 99.9 147 99.9 147 100.0 147 99.7 147 99.9 147 99.9 146 99.9 146 99.9 146
SuperSlomo [132]146.3 100.0 146 100.0 147 100.0 146 100.0 146 100.0 146 100.0 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 147 99.9 147 99.9 147 99.9 147 100.0 147 99.7 147 99.9 147 99.9 146 99.9 146 99.9 146
FGIK [136]146.3 100.0 146 100.0 147 100.0 146 100.0 146 100.0 146 100.0 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 147 99.9 147 99.9 147 99.9 147 100.0 147 99.7 147 99.9 147 99.9 146 99.9 146 99.9 146
CtxSyn [137]146.3 100.0 146 100.0 147 100.0 146 100.0 146 100.0 146 100.0 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 146 99.9 147 99.9 147 99.9 147 99.9 147 100.0 147 99.7 147 99.9 147 99.9 146 99.9 146 99.9 146
AVG_FLOW_ROB [142]146.6 100.0 146 99.9 146 100.0 146 100.0 146 100.0 146 100.0 146 99.9 146 99.9 146 99.9 146 100.0 151 99.9 146 100.0 151 99.9 146 100.0 151 99.8 146 99.2 146 99.5 146 98.3 146 99.6 146 97.0 146 99.7 146 99.9 146 99.9 146 99.9 146
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.