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]15.2 20.0 3 43.3 3 13.0 3 15.9 12 45.3 27 16.1 16 12.5 4 34.1 9 12.8 11 9.68 21 32.0 11 7.01 25 23.3 4 30.0 4 16.2 4 22.0 35 45.4 9 23.8 66 25.8 27 44.8 7 17.6 23 4.37 11 14.4 29 0.48 1
NN-field [71]16.1 22.1 7 44.0 5 14.6 4 18.4 25 47.3 40 19.2 30 12.5 4 32.9 6 14.0 16 6.57 2 28.2 4 3.57 2 23.4 5 30.1 5 15.9 3 17.9 17 36.8 1 15.8 4 35.9 62 51.5 35 27.4 61 4.58 14 15.3 33 0.55 2
TC/T-Flow [76]21.4 19.9 2 46.9 11 10.2 1 16.0 13 47.8 42 13.9 6 13.0 8 36.6 21 11.1 5 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 11 39.2 2 42.1 92 7.86 46 19.5 48 10.9 59
ComponentFusion [96]21.8 20.0 3 46.3 8 14.8 5 16.6 16 40.3 7 18.5 27 11.7 3 33.6 7 10.9 4 7.09 6 35.2 39 4.45 6 27.6 21 36.0 26 21.4 18 21.5 31 54.1 54 20.2 32 31.8 51 56.8 65 16.2 16 5.46 24 12.8 22 7.47 31
ALD-Flow [66]22.0 21.6 6 46.0 7 15.9 7 15.5 9 41.3 10 15.6 12 13.1 10 35.2 13 12.2 7 8.17 11 33.4 23 5.35 10 28.1 25 37.3 36 20.3 11 16.4 7 47.4 19 16.0 6 26.5 30 45.4 9 41.8 90 8.39 50 22.3 59 11.3 62
ProFlow_ROB [146]22.2 24.2 11 53.3 36 15.8 6 15.6 10 44.5 22 14.8 9 15.5 19 43.0 45 11.8 6 6.94 4 33.1 19 3.97 4 30.0 39 39.9 46 19.6 8 16.2 6 49.1 28 16.1 7 14.9 4 54.0 51 13.9 14 7.47 41 21.2 55 8.63 44
nLayers [57]23.1 22.7 9 40.3 2 18.4 10 27.2 95 45.9 31 30.4 96 15.7 25 35.4 15 21.4 64 8.12 10 26.6 2 6.21 15 22.5 2 29.0 3 15.5 2 19.9 22 40.8 4 17.8 10 31.3 47 52.6 45 16.9 21 4.26 8 11.2 9 5.84 7
OFLAF [77]23.8 29.6 36 47.4 13 24.8 20 17.8 21 40.9 8 18.3 25 11.6 2 26.9 2 13.2 13 11.5 41 29.3 8 8.97 63 23.7 6 30.9 6 16.5 5 22.2 39 41.5 5 19.3 22 30.2 42 50.6 30 32.9 69 5.94 29 13.8 24 8.44 41
RNLOD-Flow [121]24.3 20.7 5 43.8 4 19.4 11 18.1 22 45.9 31 17.0 21 12.7 6 34.1 9 12.3 8 7.38 7 28.7 6 4.87 7 26.5 14 34.9 19 20.9 13 20.3 23 46.2 12 20.2 32 43.1 88 60.3 78 47.5 109 4.98 21 12.7 21 6.55 16
WLIF-Flow [93]24.4 27.0 21 47.0 12 23.1 18 21.7 46 46.6 38 23.3 45 14.8 14 36.2 17 16.3 26 9.33 18 32.2 14 6.64 19 27.7 22 35.1 21 23.4 35 21.6 32 47.7 21 19.2 19 28.7 38 45.3 8 32.0 68 4.50 13 11.2 9 6.43 12
HAST [109]24.7 19.5 1 40.1 1 11.6 2 16.1 14 39.7 5 14.8 9 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 61 48.5 25 24.3 68 41.7 84 59.8 76 63.0 135 6.05 31 11.5 15 8.72 45
MDP-Flow2 [68]26.3 35.3 51 55.4 43 30.2 49 14.2 4 39.7 5 14.2 8 13.6 11 31.4 3 12.9 12 12.2 46 34.1 31 8.19 49 27.7 22 35.0 20 22.1 21 22.4 43 45.4 9 21.5 46 27.1 31 54.1 52 16.5 17 5.87 28 14.0 26 4.25 4
OAR-Flow [125]27.2 25.6 14 54.9 40 22.4 15 18.7 26 44.8 24 19.1 28 17.2 38 43.7 48 18.0 32 8.53 13 31.6 10 5.65 11 29.7 37 39.3 42 20.9 13 14.5 2 47.3 18 13.4 2 14.1 3 38.0 1 20.7 37 9.84 65 21.1 54 16.1 79
Layers++ [37]27.8 28.0 33 48.8 16 30.9 52 23.3 62 45.6 30 25.5 70 13.7 12 31.4 3 18.1 33 8.08 9 24.9 1 5.87 12 22.9 3 28.1 1 19.6 8 22.2 39 46.3 14 20.7 36 39.6 78 55.9 61 35.0 71 4.16 4 9.78 2 6.81 18
TC-Flow [46]28.0 24.4 12 52.2 32 22.6 16 11.8 2 38.8 4 11.2 1 12.7 6 35.7 16 9.84 3 9.88 23 34.9 35 7.49 33 28.9 32 38.6 41 21.2 17 20.6 25 52.1 38 21.6 47 22.6 22 47.1 13 36.3 74 9.05 56 21.5 57 12.4 67
LME [70]30.0 31.5 38 51.4 27 21.0 14 14.7 6 36.9 2 15.7 13 16.0 30 35.2 13 19.8 53 11.8 43 36.6 43 8.08 43 28.6 29 36.0 26 25.5 47 21.1 29 49.0 27 19.8 29 29.8 41 50.0 27 21.5 39 6.61 33 15.1 30 7.95 37
AGIF+OF [85]30.4 26.3 15 48.8 16 24.1 19 24.9 73 52.0 72 26.2 72 16.0 30 39.4 32 19.7 50 8.96 15 32.0 11 6.64 19 26.7 16 33.7 13 21.5 20 21.4 30 49.4 29 18.5 14 28.2 35 49.6 24 30.5 66 4.63 17 11.3 14 7.30 27
PH-Flow [101]31.5 26.7 17 51.6 28 25.6 28 21.7 46 49.4 53 23.8 50 15.5 19 37.6 25 19.5 46 10.2 28 33.8 27 7.44 32 26.4 12 33.7 13 21.0 15 22.0 35 50.3 32 20.4 34 38.8 72 48.4 18 45.4 99 4.26 8 11.2 9 6.38 11
FC-2Layers-FF [74]31.7 26.9 20 48.6 15 28.3 42 22.1 50 48.8 48 23.8 50 14.1 13 32.4 5 19.6 48 9.10 16 28.3 5 6.47 18 25.5 7 31.7 7 23.0 30 23.3 50 47.7 21 21.8 48 44.1 92 56.3 64 46.0 104 3.54 1 9.08 1 5.44 6
NNF-EAC [103]32.8 34.9 45 54.8 38 29.9 48 15.6 10 41.7 12 15.9 14 15.1 18 34.8 12 15.7 20 12.4 50 35.1 38 8.33 52 28.1 25 35.7 23 22.9 28 24.5 64 46.2 12 22.7 59 31.6 50 49.1 21 20.1 35 7.54 43 17.1 41 7.44 30
Classic+CPF [83]32.9 27.1 25 51.2 26 25.5 27 23.9 66 51.4 68 25.1 65 15.9 27 39.3 31 19.4 44 9.17 17 32.8 17 6.69 21 27.3 19 34.5 17 23.9 36 21.0 28 48.7 26 18.0 12 35.6 61 49.9 26 45.7 101 4.25 7 10.7 5 6.61 17
IROF++ [58]33.2 27.4 27 50.7 22 26.7 35 22.1 50 50.1 63 24.1 55 16.3 33 40.0 36 19.6 48 10.6 35 34.3 32 7.72 38 27.9 24 35.7 23 22.5 23 22.3 41 54.1 54 19.9 30 25.5 26 49.6 24 11.5 11 5.49 25 14.1 27 6.54 15
COFM [59]33.6 22.1 7 49.1 18 16.6 8 18.2 23 43.5 17 19.2 30 15.9 27 38.3 28 21.5 65 7.02 5 32.6 15 4.40 5 31.4 48 37.9 38 35.0 88 22.1 37 46.4 15 18.3 13 28.7 38 45.9 11 45.5 100 9.25 58 15.5 35 15.7 78
Sparse-NonSparse [56]33.9 26.8 19 51.9 31 26.8 36 22.2 55 49.0 51 24.6 61 15.6 22 39.4 32 19.0 39 9.46 20 33.6 25 7.07 27 29.0 33 37.2 35 24.3 41 21.7 34 50.4 33 19.5 27 34.0 54 45.8 10 41.6 88 4.44 12 10.9 6 6.96 22
FESL [72]34.9 27.0 21 46.3 8 31.2 54 26.0 86 51.8 71 26.9 77 15.8 26 37.0 22 19.5 46 7.89 8 30.7 9 5.17 9 26.6 15 33.8 15 22.6 24 20.3 23 45.8 11 19.3 22 39.9 79 61.2 83 35.6 72 5.04 22 12.5 20 6.48 14
Efficient-NL [60]35.3 23.3 10 44.7 6 17.6 9 24.6 72 51.6 70 25.4 69 15.0 17 36.2 17 17.5 30 9.92 24 33.1 19 6.94 23 26.4 12 34.0 16 20.3 11 27.2 75 49.4 29 22.6 54 37.6 67 50.5 29 37.1 75 6.98 38 16.2 37 8.16 38
JOF [140]35.6 25.3 13 46.6 10 23.0 17 24.1 68 49.9 61 26.7 74 14.8 14 34.3 11 21.0 62 8.34 12 32.1 13 5.95 13 26.1 11 32.9 12 22.8 27 22.8 46 49.4 29 22.2 50 41.8 85 60.0 77 56.2 126 4.17 5 10.9 6 6.44 13
LSM [39]37.0 26.5 16 50.8 23 27.0 38 22.1 50 49.4 53 24.4 59 15.6 22 38.2 27 19.4 44 10.1 25 33.0 18 7.43 31 28.6 29 36.3 28 24.7 42 22.8 46 50.5 34 20.9 40 40.3 81 49.3 22 45.8 103 4.76 19 12.0 17 6.93 21
PMMST [114]37.2 42.4 78 58.9 48 40.2 75 22.1 50 45.3 27 24.7 64 17.9 44 38.4 29 18.8 36 12.2 46 28.1 3 8.26 50 25.7 8 32.7 10 18.5 7 22.3 41 45.3 8 20.8 38 28.5 37 50.7 31 18.3 26 8.51 53 16.8 38 8.73 46
Ramp [62]38.5 27.0 21 52.3 33 26.1 32 22.3 57 49.1 52 24.6 61 15.6 22 37.8 26 19.8 53 10.5 34 33.6 25 7.61 35 28.6 29 36.6 30 24.0 37 23.6 53 51.2 35 21.8 48 38.2 68 44.5 5 46.1 105 4.86 20 12.1 18 7.13 25
Classic+NL [31]38.8 27.2 26 47.8 14 28.4 44 22.0 49 49.4 53 24.1 55 15.5 19 37.4 24 19.8 53 10.4 32 33.8 27 7.40 30 28.5 27 36.4 29 24.2 40 23.3 50 52.2 40 21.1 41 43.9 90 52.5 42 44.6 96 4.60 16 11.2 9 7.04 24
2DHMM-SAS [92]41.3 26.7 17 51.8 30 25.6 28 22.2 55 51.3 66 23.8 50 17.8 42 42.3 42 20.0 58 10.4 32 34.6 34 7.52 34 28.5 27 36.6 30 24.0 37 22.7 45 54.5 57 20.6 35 39.0 74 47.8 16 45.1 97 5.51 26 13.9 25 7.73 35
FMOF [94]42.0 27.8 32 50.4 21 27.1 40 26.2 88 52.5 76 27.4 80 15.9 27 36.4 20 21.7 66 9.71 22 32.7 16 6.98 24 27.3 19 34.6 18 24.1 39 23.7 55 47.6 20 19.7 28 38.4 69 55.4 58 48.9 112 5.80 27 14.1 27 7.00 23
SVFilterOh [111]43.6 39.6 68 54.6 37 39.8 74 23.8 65 44.7 23 24.0 53 17.3 39 33.8 8 18.8 36 10.2 28 36.4 42 4.93 8 25.9 10 32.1 8 19.6 8 24.7 65 46.7 16 22.9 62 52.0 116 76.3 135 59.2 129 4.23 6 10.9 6 5.01 5
S2D-Matching [84]44.3 27.7 29 50.2 20 28.4 44 22.1 50 48.8 48 24.3 57 16.5 35 40.0 36 19.3 42 10.6 35 33.8 27 7.78 39 29.1 35 36.7 33 25.0 44 24.4 63 53.0 50 22.6 54 47.0 103 53.6 48 50.8 117 4.58 14 11.2 9 7.54 32
ProbFlowFields [128]44.9 33.9 41 68.5 75 30.9 52 20.3 36 45.3 27 22.1 40 19.2 53 44.8 51 22.9 71 11.7 42 39.3 53 8.91 62 31.0 46 40.1 47 23.3 32 16.8 8 47.8 23 19.2 19 23.7 25 55.9 61 23.9 49 8.39 50 22.4 60 9.82 55
SimpleFlow [49]45.3 28.6 35 51.6 28 29.5 47 25.0 74 51.3 66 28.2 86 18.6 49 43.0 45 23.3 72 10.1 25 33.5 24 7.04 26 29.9 38 37.9 38 26.2 49 27.8 80 52.2 40 24.0 67 35.1 59 47.9 17 29.7 65 4.66 18 12.4 19 6.92 20
PMF [73]46.9 37.7 61 58.3 46 27.3 41 19.4 29 45.0 26 18.3 25 16.2 32 39.9 35 14.0 16 13.6 66 35.7 40 8.03 42 25.8 9 32.5 9 17.1 6 30.2 88 57.0 69 31.6 91 58.9 127 74.7 127 55.9 125 3.95 3 10.3 3 6.15 10
Adaptive [20]47.6 27.0 21 52.6 34 19.8 12 21.9 48 47.8 42 22.6 42 20.5 58 47.8 60 19.7 50 10.3 30 39.9 57 6.31 17 45.6 128 52.6 125 51.3 131 17.4 9 48.2 24 13.9 3 34.8 58 56.9 67 19.8 33 6.04 30 15.2 31 7.54 32
TV-L1-MCT [64]47.8 27.5 28 49.4 19 27.0 38 26.5 89 52.8 81 27.8 85 16.8 36 39.1 30 21.8 68 10.6 35 33.8 27 7.82 41 30.3 41 38.1 40 28.7 66 24.7 65 53.4 52 23.4 64 27.4 32 52.5 42 19.4 30 7.28 40 15.3 33 11.4 64
Correlation Flow [75]48.1 36.6 58 55.3 42 34.4 63 16.6 16 44.4 21 14.8 9 18.3 48 42.9 44 12.7 10 12.4 50 39.7 55 8.46 56 32.2 51 40.6 51 25.2 45 29.0 83 54.2 56 29.7 87 39.1 75 52.1 40 47.4 108 6.53 32 16.1 36 6.88 19
IROF-TV [53]48.4 30.9 37 54.8 38 31.6 56 22.8 61 50.5 64 25.1 65 16.9 37 40.8 38 20.8 60 14.0 69 43.7 72 10.1 71 31.2 47 39.5 43 28.6 64 26.8 74 58.7 79 25.6 71 18.8 7 48.4 18 8.08 9 5.28 23 13.6 23 7.77 36
AggregFlow [97]48.8 36.3 57 52.7 35 35.7 65 26.6 90 52.6 79 26.7 74 23.3 71 48.2 62 28.9 91 12.1 44 34.9 35 8.63 58 30.2 40 40.3 50 21.4 18 15.9 5 38.3 2 16.8 8 26.1 29 47.3 14 16.8 19 12.6 81 20.3 50 20.0 94
Occlusion-TV-L1 [63]49.5 34.3 44 58.5 47 25.1 22 20.0 32 46.5 37 20.8 36 22.3 68 49.9 63 20.6 59 12.6 57 41.7 63 8.41 55 35.2 74 44.9 82 32.3 79 17.7 13 52.6 45 21.1 41 28.2 35 52.5 42 13.0 12 9.66 61 23.7 64 10.6 57
3DFlow [135]52.0 35.7 53 56.6 44 28.3 42 19.1 28 46.2 35 17.4 23 18.8 50 41.7 41 14.5 18 13.9 67 33.3 22 9.85 69 29.0 33 36.6 30 23.0 30 32.9 94 65.1 103 34.7 103 49.9 110 65.5 98 77.7 146 3.87 2 10.3 3 3.02 3
Classic++ [32]53.3 27.7 29 51.0 25 28.7 46 21.5 45 45.9 31 24.3 57 18.1 47 44.3 49 19.9 56 10.3 30 37.7 45 7.14 28 33.4 55 44.1 71 27.9 59 24.0 58 57.9 74 21.4 45 46.3 99 55.6 59 49.7 114 8.45 52 20.7 51 9.69 54
Aniso-Texture [82]53.8 28.5 34 50.9 24 32.7 60 21.2 40 41.7 12 25.3 68 17.6 41 41.2 39 21.1 63 5.72 1 33.2 21 2.54 1 35.1 73 43.7 68 31.3 77 23.6 53 53.6 53 22.6 54 62.2 135 75.8 133 53.5 122 6.89 37 17.4 43 8.20 39
HCFN [163]54.5 31.7 39 61.4 53 26.1 32 12.6 3 37.8 3 12.6 3 13.0 8 37.3 23 8.55 2 12.6 57 38.8 52 9.77 68 29.3 36 37.6 37 23.3 32 26.0 70 59.1 81 26.4 75 60.4 131 73.6 121 63.0 135 12.5 80 26.5 73 19.6 93
IIOF-NLDP [131]54.5 33.3 40 59.3 49 24.9 21 24.4 71 53.8 89 22.9 44 18.8 50 46.2 55 15.0 19 13.5 63 39.7 55 9.86 70 32.3 52 41.2 55 23.3 32 29.9 87 60.2 89 29.6 86 28.1 34 60.8 80 27.0 58 7.51 42 17.2 42 7.29 26
MDP-Flow [26]54.8 35.5 52 65.0 61 32.4 57 20.6 38 43.8 19 24.4 59 18.0 46 43.4 47 19.9 56 14.9 78 41.8 65 11.5 80 30.8 45 39.6 44 25.3 46 23.8 56 57.4 72 22.2 50 31.0 45 59.3 74 16.8 19 10.8 73 26.5 73 10.9 59
DeepFlow2 [108]55.8 39.1 66 66.4 65 44.4 83 20.1 34 47.9 44 20.9 37 23.8 74 52.8 70 26.3 81 12.2 46 43.2 71 7.64 36 31.4 48 41.7 59 22.9 28 18.2 19 52.4 42 17.9 11 29.6 40 44.7 6 39.0 80 16.2 99 31.2 97 22.7 102
OFH [38]55.9 41.9 77 61.6 54 48.5 90 14.7 6 42.7 15 14.1 7 17.4 40 47.6 58 12.6 9 10.6 35 38.5 48 8.39 54 34.8 70 43.7 68 34.5 86 27.2 75 61.9 95 29.5 85 21.3 15 57.6 69 21.4 38 12.2 79 29.8 89 16.2 80
SegFlow [161]57.2 35.2 46 67.0 67 25.4 25 25.7 81 53.3 84 28.2 86 25.4 77 58.1 88 27.5 83 12.5 56 48.9 90 8.15 47 34.1 64 44.4 77 27.8 58 17.6 10 52.1 38 19.0 15 21.1 13 51.8 38 22.5 43 9.21 57 25.0 69 11.1 61
CPM-Flow [116]57.3 35.2 46 67.0 67 25.3 23 25.8 82 53.6 86 28.2 86 25.5 78 58.5 92 27.5 83 12.4 50 48.0 86 8.11 46 33.9 60 44.2 72 27.1 52 17.6 10 51.8 36 19.1 17 21.3 15 51.7 36 22.6 45 9.92 66 27.2 79 11.3 62
S2F-IF [123]58.0 35.7 53 69.0 78 26.6 34 24.1 68 54.0 94 26.0 71 25.6 80 60.9 99 25.9 77 12.4 50 46.6 83 8.38 53 34.3 66 44.2 72 27.7 57 18.0 18 53.2 51 19.2 19 21.2 14 51.7 36 22.9 46 8.97 55 24.9 68 9.11 50
PGM-C [120]58.1 35.2 46 67.1 70 25.4 25 25.8 82 53.6 86 28.2 86 25.8 81 59.3 97 27.5 83 12.4 50 48.1 87 8.16 48 33.9 60 44.3 75 27.1 52 17.7 13 52.8 49 19.1 17 20.8 9 50.3 28 22.4 42 9.82 64 27.2 79 11.5 66
BriefMatch [124]58.5 34.1 43 59.4 50 30.2 49 17.1 18 43.6 18 16.1 16 14.8 14 36.3 19 13.4 14 9.41 19 34.3 32 6.26 16 33.4 55 41.2 55 31.8 78 40.3 125 63.5 98 42.7 128 47.2 104 61.1 81 59.1 128 12.7 83 23.4 61 21.6 100
EpicFlow [102]60.2 35.2 46 67.2 71 25.3 23 25.8 82 53.8 89 28.2 86 26.1 83 60.1 98 27.5 83 12.4 50 48.1 87 8.10 45 34.2 65 44.5 78 28.0 60 17.8 15 52.7 47 19.4 24 21.0 11 52.1 40 22.5 43 10.4 70 27.3 81 12.7 69
FlowFields+ [130]60.7 35.8 56 69.2 80 26.0 31 25.6 79 55.3 102 27.7 83 26.7 84 62.9 104 27.7 88 12.7 59 45.9 81 8.84 61 34.0 63 44.2 72 26.6 50 17.6 10 54.9 59 19.0 15 20.6 8 53.9 50 22.3 41 9.31 60 26.5 73 8.79 47
CostFilter [40]60.9 43.6 85 65.7 63 40.8 76 20.8 39 45.9 31 21.0 38 18.8 50 44.9 52 18.3 35 17.3 89 39.5 54 13.9 91 26.7 16 32.8 11 22.7 26 30.9 91 60.0 87 31.6 91 59.7 128 81.5 145 59.3 130 4.31 10 11.9 16 5.93 8
RFlow [90]61.5 44.4 87 75.2 102 50.5 94 16.5 15 42.1 14 17.2 22 21.4 62 52.2 66 16.0 21 11.3 40 36.2 41 7.25 29 35.2 74 44.3 75 32.3 79 24.3 61 55.6 63 22.6 54 38.6 70 55.3 56 41.6 88 13.4 86 29.9 90 16.9 86
FlowFields [110]63.0 35.7 53 68.7 76 25.8 30 25.6 79 55.1 101 27.7 83 26.8 87 62.8 103 27.6 87 13.0 61 46.8 84 9.13 65 34.6 69 44.9 82 28.1 61 17.8 15 54.9 59 19.4 24 21.3 15 54.8 54 24.2 51 9.25 58 26.4 72 8.47 42
TV-L1-improved [17]63.7 27.7 29 57.9 45 20.5 13 18.2 23 44.9 25 19.1 28 19.4 54 47.7 59 17.0 29 10.1 25 38.5 48 6.75 22 35.9 81 46.0 90 27.3 54 43.7 132 70.2 125 47.5 133 51.4 113 60.5 79 50.3 116 10.3 69 26.8 78 10.8 58
DMF_ROB [139]64.1 43.0 82 71.7 90 45.5 86 22.4 58 48.3 46 24.0 53 28.0 95 62.4 102 26.9 82 12.8 60 45.8 80 7.80 40 33.9 60 43.1 62 30.0 73 20.9 26 56.4 66 21.2 43 22.3 21 42.0 3 27.0 58 12.7 83 27.6 82 17.1 87
Steered-L1 [118]66.3 38.7 65 67.9 72 43.1 81 11.6 1 34.7 1 12.3 2 16.3 33 41.3 40 13.9 15 12.1 44 38.6 50 8.30 51 34.5 68 43.4 65 32.5 81 29.4 85 61.1 94 25.9 72 60.6 132 67.0 105 70.1 142 15.9 96 30.6 93 24.0 104
Sparse Occlusion [54]66.5 38.6 64 61.8 56 32.5 59 26.0 86 48.8 48 29.5 95 20.0 56 45.2 53 19.2 41 14.3 73 38.4 46 9.67 67 34.4 67 42.6 61 26.7 51 25.4 68 52.4 42 22.4 53 67.3 140 75.9 134 48.3 110 8.07 48 19.9 49 7.36 28
MLDP_OF [89]67.5 48.8 96 77.3 105 52.2 96 20.1 34 49.6 58 19.3 32 23.5 73 54.6 74 18.9 38 12.3 49 38.6 50 7.65 37 33.5 58 40.9 52 29.1 71 28.4 81 55.9 64 31.6 91 49.1 108 62.2 88 60.5 132 7.91 47 16.8 38 8.95 48
DeepFlow [86]68.3 47.3 93 71.9 91 64.0 114 21.4 43 48.2 45 22.7 43 27.9 92 58.2 89 31.6 97 15.1 79 42.7 67 10.6 76 31.5 50 42.1 60 22.6 24 19.6 21 56.7 68 19.4 24 27.6 33 46.2 12 39.7 82 20.6 109 35.3 115 28.0 112
PWC-Net_ROB [147]68.5 49.3 98 75.1 101 39.6 73 28.7 97 54.0 94 29.4 94 27.2 88 58.7 93 31.5 96 15.6 81 38.4 46 8.76 60 36.5 87 45.6 89 28.3 62 26.2 72 60.3 90 26.4 75 13.0 2 49.3 22 4.98 4 7.79 44 19.4 47 7.36 28
WRT [150]68.7 38.4 63 61.6 54 26.8 36 31.9 102 58.0 110 32.7 98 28.0 95 56.1 79 21.7 66 14.6 75 41.9 66 9.03 64 30.7 43 37.0 34 24.9 43 35.7 105 62.5 96 31.8 95 34.3 55 63.2 91 37.1 75 7.23 39 15.2 31 7.62 34
TF+OM [100]69.7 39.8 69 55.2 41 30.4 51 20.4 37 41.0 9 23.5 47 19.5 55 39.4 32 28.0 89 18.4 92 37.0 44 18.0 98 35.0 71 41.1 53 39.6 101 29.6 86 52.6 45 29.1 84 49.0 107 66.8 104 43.6 95 14.4 88 29.3 86 18.0 89
CombBMOF [113]71.2 42.4 78 71.5 88 31.3 55 25.2 75 52.9 82 25.1 65 17.9 44 45.8 54 16.1 22 14.2 71 41.7 63 11.4 79 33.5 58 40.2 48 29.6 72 34.5 100 59.9 86 37.3 109 55.2 123 69.9 114 46.5 107 6.78 35 16.8 38 8.62 43
EPPM w/o HM [88]72.0 43.1 83 72.4 93 38.1 71 18.7 26 52.5 76 16.9 20 21.3 61 56.2 80 17.5 30 16.2 85 45.3 78 12.7 87 33.4 55 39.6 44 30.0 73 33.5 96 65.4 105 33.8 98 45.5 94 66.1 102 65.5 139 6.88 36 18.1 44 9.16 52
FF++_ROB [145]72.5 38.0 62 69.4 81 32.4 57 25.8 82 54.8 100 27.6 81 28.3 100 63.7 105 30.3 92 15.7 82 49.6 92 12.9 88 35.0 71 44.9 82 28.9 68 23.0 48 55.4 62 23.0 63 22.1 20 53.1 46 24.0 50 10.1 67 25.5 70 12.8 71
Complementary OF [21]74.2 51.9 105 74.9 100 59.3 106 14.2 4 41.6 11 13.7 4 20.4 57 46.6 56 19.7 50 22.2 99 40.8 59 21.0 103 36.0 83 43.4 65 38.5 99 33.9 99 63.8 99 31.6 91 31.1 46 51.9 39 36.2 73 18.9 106 34.4 112 29.4 114
Aniso. Huber-L1 [22]74.5 33.9 41 65.1 62 32.8 61 34.0 103 54.0 94 40.0 106 27.9 92 55.0 76 38.4 103 15.2 80 49.9 93 12.0 82 35.3 76 44.6 79 28.5 63 23.9 57 55.9 64 20.7 36 50.6 111 62.1 87 39.7 82 8.15 49 20.7 51 8.39 40
TCOF [69]76.4 45.0 88 70.0 82 51.5 95 25.5 78 53.7 88 26.7 74 26.7 84 56.2 80 32.0 98 21.9 98 43.1 70 22.2 105 37.8 94 48.9 106 25.7 48 18.8 20 44.7 7 20.0 31 52.1 117 67.5 107 25.8 52 10.7 72 26.7 76 11.4 64
Rannacher [23]76.6 43.1 83 71.0 86 45.2 85 24.1 68 49.4 53 26.4 73 26.0 82 56.9 84 26.0 79 14.2 71 42.7 67 10.5 75 37.1 91 47.9 101 30.7 76 32.3 93 65.2 104 27.0 78 44.0 91 56.0 63 39.7 82 7.83 45 21.2 55 9.19 53
ComplOF-FED-GPU [35]77.4 49.5 99 75.7 104 55.3 99 15.3 8 47.0 39 13.8 5 21.1 60 52.7 69 16.1 22 17.1 88 40.6 58 14.2 92 35.7 80 45.1 86 32.5 81 35.3 103 67.5 116 34.4 101 46.5 101 59.0 73 50.8 117 12.8 85 29.6 87 16.6 84
ACK-Prior [27]78.0 55.9 107 72.7 95 59.3 106 17.5 20 43.3 16 16.0 15 17.8 42 42.3 42 16.3 26 17.6 90 41.3 61 12.0 82 35.3 76 41.1 53 35.9 89 37.4 118 59.6 84 34.3 100 59.8 130 61.1 81 74.7 143 17.7 104 29.2 85 27.4 107
F-TV-L1 [15]78.8 66.8 117 84.2 116 77.3 125 27.1 93 52.0 72 29.1 93 27.2 88 57.3 86 24.2 75 24.1 104 52.0 98 19.5 101 39.3 101 47.7 100 39.3 100 24.2 60 56.5 67 24.9 69 33.2 53 53.7 49 20.1 35 6.69 34 18.6 45 5.94 9
ROF-ND [107]79.6 49.2 97 71.5 88 49.4 92 22.5 60 46.2 35 20.6 34 21.4 62 50.0 64 18.1 33 23.1 101 53.7 102 16.0 94 35.9 81 46.1 92 28.6 64 33.5 96 58.5 77 30.3 88 60.7 133 70.5 115 60.4 131 9.67 62 20.9 53 10.2 56
LDOF [28]79.7 41.7 76 70.7 83 47.2 89 24.0 67 53.9 93 24.6 61 26.7 84 58.4 91 25.5 76 15.8 83 57.4 111 10.2 73 36.0 83 45.3 87 34.8 87 22.1 37 58.1 76 21.3 44 30.6 43 56.8 65 23.4 47 22.5 118 38.6 124 30.2 115
SIOF [67]81.1 50.3 102 66.0 64 47.1 88 19.8 31 48.4 47 20.7 35 29.8 102 55.1 77 32.6 100 25.9 107 48.3 89 25.0 108 37.7 92 46.4 94 36.8 92 32.9 94 58.6 78 35.6 106 37.2 66 53.1 46 18.6 27 16.8 101 33.0 102 21.3 99
LocallyOriented [52]81.6 39.4 67 60.5 51 35.7 65 27.9 96 57.8 109 28.5 91 28.1 97 58.3 90 30.6 95 13.9 67 41.3 61 10.1 71 37.8 94 47.3 98 33.0 85 24.8 67 52.5 44 28.1 81 39.4 77 62.4 89 37.5 77 15.7 94 33.0 102 18.2 91
Second-order prior [8]81.9 37.6 60 70.9 85 37.2 69 22.4 58 51.2 65 23.7 49 24.5 76 59.1 96 22.6 69 11.2 39 41.2 60 8.48 57 37.9 96 49.6 114 28.8 67 29.0 83 68.8 120 26.0 73 55.5 124 64.7 96 52.7 121 14.7 91 34.1 110 17.3 88
Brox et al. [5]82.3 43.7 86 74.4 98 56.4 103 27.0 92 52.5 76 30.5 97 23.4 72 54.5 73 23.3 72 13.4 62 50.0 94 8.66 59 39.8 104 46.5 95 47.6 124 21.6 32 59.8 85 22.8 61 30.9 44 59.3 74 7.61 6 23.1 122 37.0 120 33.4 124
FlowNetS+ft+v [112]82.5 36.8 59 67.0 67 39.4 72 25.3 77 52.1 74 27.6 81 27.8 91 57.2 85 35.5 101 13.5 63 50.9 96 9.44 66 40.1 105 49.5 113 36.8 92 20.9 26 57.0 69 20.8 38 46.3 99 66.3 103 41.0 86 17.4 102 34.3 111 24.1 105
NL-TV-NCC [25]82.9 46.1 90 68.3 74 43.4 82 25.2 75 55.3 102 23.5 47 21.8 67 47.2 57 16.9 28 16.9 87 44.1 73 11.9 81 38.5 98 49.1 110 27.3 54 36.5 111 65.7 107 34.9 104 46.2 96 75.7 132 45.7 101 12.6 81 28.8 83 9.10 49
SRR-TVOF-NL [91]83.5 47.6 94 69.1 79 41.9 79 23.3 62 52.7 80 23.3 45 25.5 78 56.8 83 25.9 77 13.5 63 47.9 85 8.09 44 36.9 90 43.8 70 32.9 84 25.8 69 57.7 73 22.6 54 62.8 137 75.2 129 49.1 113 21.0 111 29.7 88 31.6 118
DF-Auto [115]83.8 41.6 75 64.2 59 32.8 61 42.0 113 58.8 113 49.6 115 34.8 109 62.2 101 47.2 114 20.7 96 53.4 101 14.5 93 36.2 86 44.7 80 37.2 96 15.1 3 42.9 6 17.4 9 45.3 93 69.0 111 13.0 12 24.2 126 37.7 121 31.9 119
CRTflow [80]83.9 40.9 71 72.5 94 36.2 67 21.3 42 49.4 53 21.8 39 22.9 69 57.5 87 19.0 39 14.0 69 44.7 75 10.3 74 35.4 79 45.0 85 30.4 75 46.6 137 73.4 131 53.8 138 38.8 72 65.5 98 38.2 78 19.5 108 38.5 123 27.6 110
DPOF [18]84.1 45.3 89 68.9 77 37.6 70 26.7 91 56.9 105 26.9 77 24.3 75 54.6 74 26.2 80 18.6 93 54.6 105 13.6 90 33.3 54 43.1 62 28.9 68 27.6 79 60.8 91 26.3 74 47.2 104 55.3 56 76.0 145 14.3 87 31.0 96 15.3 77
TriangleFlow [30]84.5 41.5 74 63.2 57 42.6 80 21.4 43 52.4 75 20.2 33 21.7 66 53.6 72 16.2 24 14.8 76 44.4 74 10.9 77 43.2 119 52.9 127 43.4 112 36.8 115 65.9 109 38.8 113 42.2 86 65.4 97 41.8 90 15.8 95 35.2 114 22.5 101
Bartels [41]85.8 48.6 95 63.2 57 61.4 112 23.4 64 44.0 20 27.1 79 21.4 62 44.6 50 23.8 74 26.2 108 43.0 69 25.4 109 36.8 88 44.7 80 41.7 108 33.7 98 60.0 87 41.7 125 52.6 118 67.2 106 61.1 133 11.2 75 23.4 61 16.3 81
SuperFlow [81]86.6 35.2 46 61.1 52 34.4 63 35.2 104 53.5 85 42.5 107 27.7 90 52.5 68 43.5 111 27.5 109 60.5 117 27.6 112 36.0 83 43.3 64 42.2 109 22.6 44 59.2 83 22.2 50 46.2 96 62.0 86 23.4 47 21.8 116 36.0 116 32.5 121
Dynamic MRF [7]86.8 49.5 99 78.0 106 55.8 102 17.2 19 47.4 41 16.5 19 21.6 65 56.3 82 16.2 24 14.8 76 46.4 82 12.5 85 41.2 111 49.0 108 45.1 117 35.3 103 70.7 126 38.5 112 37.1 65 57.7 70 55.1 123 21.3 113 36.7 119 31.2 117
CBF [12]87.0 41.4 72 74.0 97 48.5 90 40.2 110 51.5 69 51.7 117 22.9 69 50.8 65 28.5 90 14.3 73 44.7 75 11.2 78 38.3 97 46.1 92 36.1 90 26.3 73 55.1 61 24.9 69 61.5 134 71.0 116 52.0 120 11.6 78 26.7 76 14.8 76
CLG-TV [48]87.3 41.4 72 68.0 73 40.8 76 37.0 108 53.1 83 45.3 109 30.9 103 58.7 93 40.2 105 22.8 100 62.0 119 19.3 100 39.0 100 47.6 99 38.2 98 27.2 75 61.0 93 27.1 79 46.2 96 57.8 71 29.3 64 9.74 63 24.6 67 9.11 50
CNN-flow-warp+ref [117]87.9 42.6 80 71.2 87 49.8 93 31.6 101 53.8 89 37.3 103 32.7 105 63.8 106 42.7 109 16.0 84 55.1 106 12.1 84 38.6 99 46.0 90 43.8 115 23.3 50 59.1 81 23.6 65 23.5 24 50.9 33 21.9 40 24.2 126 36.2 118 32.9 122
Local-TV-L1 [65]88.0 56.8 109 79.1 107 74.5 119 39.5 109 53.8 89 46.1 111 38.1 110 66.2 108 43.1 110 23.9 103 52.9 100 21.1 104 32.3 52 41.4 58 27.5 56 23.2 49 54.8 58 22.7 59 25.8 27 47.5 15 33.4 70 26.9 129 40.5 128 40.5 133
HBM-GC [105]90.3 73.5 129 79.7 108 79.4 128 30.0 98 49.7 60 33.6 99 29.3 101 47.8 60 30.4 93 35.4 118 45.2 77 33.3 118 30.5 42 35.1 21 32.6 83 34.6 101 52.0 37 35.4 105 70.9 143 80.1 140 62.6 134 8.83 54 19.1 46 13.0 73
TriFlow [95]93.7 47.1 92 66.5 66 41.1 78 31.2 100 49.6 58 37.3 103 27.9 92 52.3 67 39.4 104 24.7 105 49.3 91 22.3 106 37.7 92 43.5 67 43.1 111 28.4 81 52.7 47 29.0 83 76.7 147 73.7 122 99.5 150 16.2 99 30.5 92 20.1 95
OFRF [134]94.8 50.4 103 64.5 60 55.4 101 41.2 112 57.5 107 46.2 113 34.5 108 58.9 95 40.6 106 29.6 111 45.6 79 28.8 113 30.7 43 40.2 48 22.3 22 31.1 92 57.9 74 30.4 90 43.5 89 62.5 90 51.9 119 29.8 133 39.3 125 49.1 141
p-harmonic [29]95.8 50.4 103 86.6 126 56.5 105 27.1 93 54.5 97 28.9 92 32.9 106 69.3 114 30.4 93 19.8 94 65.1 122 16.2 95 39.6 103 47.2 97 40.3 103 30.4 89 66.5 111 32.2 96 45.6 95 64.4 94 28.9 63 10.2 68 24.1 66 13.2 74
Learning Flow [11]96.6 42.9 81 70.7 83 44.8 84 30.2 99 54.7 98 34.7 100 28.2 98 55.9 78 32.3 99 17.6 90 57.1 110 12.6 86 44.0 122 52.6 125 47.8 127 30.5 90 64.6 101 30.3 88 46.9 102 63.3 92 42.8 94 14.7 91 31.6 100 16.3 81
Fusion [6]99.0 40.5 70 75.6 103 45.9 87 20.0 32 50.0 62 22.5 41 20.8 59 52.8 70 22.8 70 16.2 85 52.8 99 13.5 89 43.1 117 49.0 108 47.5 121 39.6 124 67.8 118 43.8 130 63.9 138 75.0 128 46.3 106 35.5 139 42.6 134 53.3 145
Shiralkar [42]101.2 46.1 90 85.6 122 54.3 98 19.7 30 57.7 108 18.2 24 28.2 98 70.8 115 19.3 42 20.5 95 59.0 113 18.4 99 39.5 102 49.7 116 36.3 91 40.4 126 76.1 133 41.2 124 51.9 115 65.8 100 64.2 137 21.0 111 42.4 133 25.3 106
StereoFlow [44]101.4 95.9 150 96.0 149 97.4 150 88.3 150 96.2 150 86.2 146 82.6 147 94.8 148 73.7 144 91.4 149 96.3 149 90.3 148 53.0 139 61.6 143 52.8 132 11.2 1 39.3 3 11.7 1 10.5 1 42.5 4 1.70 1 11.5 76 23.6 63 18.0 89
ContinualFlow_ROB [152]102.5 67.9 120 87.6 130 62.0 113 54.1 126 68.0 128 60.3 125 52.2 128 80.5 127 54.5 124 32.5 113 61.0 118 26.1 111 47.3 131 57.0 131 40.4 104 43.1 131 69.7 124 48.7 134 18.7 6 49.0 20 6.92 5 11.5 76 23.8 65 12.8 71
LiteFlowNet [142]102.7 62.6 111 88.2 133 55.3 99 35.7 105 65.1 124 36.9 102 39.6 111 74.5 118 38.1 102 23.4 102 50.3 95 17.4 96 43.1 117 51.4 122 42.2 109 35.7 105 69.3 122 33.9 99 41.2 82 75.2 129 17.8 24 14.4 88 28.9 84 16.7 85
SegOF [10]105.5 56.3 108 71.9 91 37.1 68 57.3 130 62.9 121 68.3 132 46.0 119 69.0 113 57.2 129 41.0 121 59.5 115 37.2 120 43.5 120 48.3 104 56.4 136 38.2 122 69.6 123 39.1 114 17.9 5 64.5 95 3.40 2 22.7 121 33.0 102 32.0 120
StereoOF-V1MT [119]106.2 49.7 101 86.0 123 56.4 103 21.2 40 68.8 129 16.3 18 32.2 104 80.7 128 20.8 60 21.3 97 66.1 125 17.4 96 47.0 130 57.0 131 47.5 121 41.7 129 81.2 138 40.9 121 38.6 70 68.1 109 48.6 111 23.2 123 42.2 132 27.7 111
Ad-TV-NDC [36]107.0 73.7 130 85.4 120 89.5 144 56.9 128 60.4 117 67.5 131 51.0 125 75.9 120 57.6 131 45.7 124 65.7 123 47.9 128 35.3 76 45.3 87 28.9 68 27.3 78 57.2 71 28.2 82 34.6 57 55.0 55 27.3 60 34.0 136 48.7 140 47.5 138
EAI-Flow [151]107.6 71.2 124 88.2 133 74.6 120 35.9 106 59.6 115 38.0 105 40.3 112 74.4 117 44.4 112 33.3 114 55.4 107 31.8 116 40.7 110 49.7 116 36.9 94 37.2 117 65.8 108 39.3 117 57.5 126 72.5 119 39.3 81 11.1 74 25.5 70 12.7 69
CompactFlow_ROB [160]109.0 75.4 132 80.3 110 60.2 110 56.9 128 71.3 132 64.0 128 59.4 137 86.4 135 66.2 140 34.8 117 57.0 109 30.4 115 47.8 132 55.5 130 46.3 119 37.0 116 71.2 127 39.2 115 20.9 10 58.5 72 3.99 3 17.4 102 34.7 113 16.5 83
WOLF_ROB [148]109.0 56.9 110 87.9 131 59.5 108 35.9 106 66.0 126 35.7 101 42.5 114 78.3 122 44.7 113 24.7 105 59.5 115 22.9 107 41.2 111 49.1 110 43.4 112 37.7 120 72.0 130 35.9 107 34.3 55 61.3 84 27.4 61 22.5 118 40.1 127 33.0 123
Modified CLG [34]109.1 68.7 121 80.5 111 76.1 123 52.0 124 61.0 118 63.6 127 51.9 126 79.4 123 55.6 126 47.4 127 72.1 131 46.7 126 41.2 111 49.7 116 46.0 118 26.0 70 64.7 102 26.7 77 31.4 49 55.6 59 19.9 34 29.0 132 43.8 136 39.9 132
IAOF2 [51]110.4 54.9 106 73.7 96 53.9 97 42.6 114 58.3 111 50.7 116 33.9 107 61.9 100 42.1 108 64.4 137 75.7 134 74.3 139 41.5 114 49.9 120 37.1 95 36.4 110 64.0 100 34.4 101 59.7 128 69.6 113 41.3 87 19.4 107 33.4 107 23.0 103
AugFNG_ROB [143]113.3 72.6 128 79.9 109 59.6 109 59.5 131 72.0 134 68.5 133 55.6 132 83.3 131 56.1 127 34.1 116 59.3 114 30.3 114 49.8 135 58.3 135 47.4 120 37.9 121 71.3 128 39.6 118 35.5 60 73.9 123 8.00 8 15.9 96 33.2 105 18.4 92
Filter Flow [19]113.5 62.9 112 74.4 98 60.8 111 42.8 115 60.1 116 49.4 114 42.5 114 66.0 107 51.2 118 52.1 133 69.5 128 50.2 129 44.8 125 49.7 116 54.4 134 41.9 130 66.7 112 43.6 129 74.3 146 88.9 148 42.6 93 10.6 71 21.6 58 12.6 68
GroupFlow [9]115.5 66.4 115 85.2 119 80.8 131 61.6 134 75.4 138 69.0 134 51.9 126 83.6 132 57.0 128 33.5 115 63.9 120 32.5 117 49.6 134 61.0 138 39.9 102 51.3 142 81.7 139 59.4 142 22.8 23 51.1 34 16.5 17 28.0 131 41.9 131 37.9 130
SPSA-learn [13]115.5 65.1 113 87.4 129 72.7 118 45.7 120 59.3 114 53.4 120 45.2 118 74.7 119 52.2 120 41.6 122 69.9 130 42.5 122 42.7 116 48.9 106 48.7 129 38.8 123 69.0 121 42.5 127 39.1 75 61.9 85 19.3 29 36.0 140 45.6 137 48.3 139
IAOF [50]115.9 66.3 114 81.3 113 77.8 126 50.1 123 58.4 112 59.7 124 45.0 117 74.1 116 49.6 117 50.8 130 68.2 126 58.0 135 40.2 106 48.7 105 37.8 97 36.7 112 66.9 113 33.5 97 54.9 121 63.5 93 40.8 85 30.1 135 41.3 130 43.5 134
2D-CLG [1]116.0 77.2 134 82.3 114 75.4 122 61.5 133 65.9 125 73.7 138 63.2 139 89.6 141 60.8 136 82.8 146 88.3 142 86.8 146 43.5 120 49.3 112 54.8 135 35.1 102 67.5 116 36.1 108 21.3 15 50.8 32 15.5 15 34.4 138 46.3 139 46.0 135
TVL1_ROB [138]116.1 88.5 145 92.7 140 96.3 148 69.8 142 66.8 127 83.7 144 67.9 140 90.2 143 70.7 142 77.3 142 89.0 144 80.6 142 40.3 108 49.6 114 40.9 105 24.0 58 65.5 106 27.6 80 21.8 19 57.3 68 10.2 10 36.2 141 51.1 142 47.2 137
BlockOverlap [61]116.3 77.2 134 86.0 123 82.8 134 48.2 121 55.8 104 57.6 123 46.9 121 66.9 109 51.9 119 49.1 129 54.1 103 51.2 130 36.8 88 41.3 57 47.5 121 40.5 127 59.0 80 39.6 118 68.9 142 80.2 141 65.1 138 20.8 110 30.8 94 34.9 126
HBpMotionGpu [43]116.4 67.0 118 80.7 112 72.3 117 55.3 127 57.3 106 66.7 130 44.7 116 67.2 111 54.1 123 39.5 120 57.8 112 38.4 121 42.0 115 48.2 103 48.3 128 35.9 107 60.9 92 39.2 115 65.1 139 72.0 118 50.1 115 22.6 120 32.5 101 36.9 127
LFNet_ROB [149]117.1 72.3 125 93.8 144 65.3 115 45.6 119 78.1 143 45.9 110 48.8 124 87.7 138 41.8 107 31.5 112 66.0 124 25.6 110 47.8 132 57.1 133 47.6 124 37.6 119 71.5 129 38.0 110 49.3 109 74.5 126 26.4 57 15.9 96 33.5 108 20.9 97
GraphCuts [14]118.5 66.6 116 87.0 127 80.0 130 43.1 116 63.0 122 46.1 111 41.8 113 67.0 110 53.4 122 28.5 110 64.0 121 20.8 102 40.2 106 48.1 102 43.5 114 46.5 135 63.4 97 40.5 120 62.7 136 75.4 131 69.5 141 23.8 125 33.3 106 38.5 131
Black & Anandan [4]118.8 70.3 123 88.0 132 84.1 135 45.5 118 61.4 119 52.0 118 47.4 122 77.3 121 52.9 121 42.3 123 77.5 135 42.8 123 44.0 122 51.8 123 45.0 116 35.9 107 75.9 132 38.3 111 50.8 112 71.3 117 17.8 24 29.8 133 42.7 135 37.6 129
EPMNet [133]121.1 78.2 136 91.5 138 78.0 127 61.6 134 75.7 139 69.6 135 55.3 131 79.5 124 57.3 130 48.1 128 56.6 108 47.7 127 45.3 126 54.0 128 41.1 106 36.7 112 67.3 114 41.0 122 56.4 125 81.4 144 26.3 55 18.6 105 36.0 116 20.7 96
FlowNet2 [122]121.4 78.8 137 86.2 125 79.4 128 63.5 139 70.2 131 72.8 137 57.2 135 82.0 129 59.7 135 46.2 125 51.4 97 45.6 125 45.3 126 54.0 128 41.1 106 36.7 112 67.3 114 41.0 122 67.6 141 80.8 142 55.1 123 14.5 90 30.0 91 13.9 75
ResPWCR_ROB [144]122.1 78.9 138 92.8 142 75.1 121 40.4 111 63.5 123 43.5 108 48.1 123 80.2 125 48.8 116 39.2 119 69.2 127 35.6 119 44.0 122 50.5 121 49.2 130 44.6 134 76.7 134 47.0 132 54.6 120 78.7 137 31.4 67 23.4 124 38.0 122 30.8 116
2bit-BM-tele [98]123.6 82.4 141 87.2 128 91.8 145 44.4 117 54.7 98 52.9 119 46.0 119 68.3 112 47.4 115 51.5 132 54.4 104 53.4 133 40.5 109 47.1 96 47.7 126 47.9 138 66.4 110 53.1 136 71.7 144 83.6 146 75.1 144 21.9 117 39.3 125 29.2 113
Nguyen [33]124.0 75.6 133 85.4 120 85.8 137 67.0 140 61.6 120 83.0 143 57.1 134 80.2 125 64.1 139 70.8 138 80.2 137 77.4 141 45.9 129 52.2 124 56.4 136 36.3 109 68.1 119 42.0 126 41.4 83 66.0 101 19.7 32 34.1 137 45.6 137 46.1 136
SILK [79]125.2 72.5 126 85.1 118 88.3 141 61.9 136 71.8 133 73.7 138 54.9 130 85.3 133 58.0 133 53.6 134 69.8 129 54.6 134 52.8 137 57.9 134 61.8 140 46.5 135 77.6 135 48.9 135 31.3 47 54.3 53 38.9 79 37.8 142 50.6 141 49.7 142
UnFlow [129]127.6 89.6 147 94.1 145 86.4 138 72.2 143 83.9 146 77.9 141 71.4 144 93.2 145 69.8 141 54.8 135 74.4 132 51.4 131 62.0 145 66.9 146 69.1 147 50.0 140 80.9 136 57.1 139 53.2 119 69.0 111 7.68 7 15.6 93 30.8 94 21.0 98
Periodicity [78]128.5 68.9 122 83.5 115 65.5 116 52.2 125 69.8 130 57.0 122 78.4 146 82.5 130 87.2 148 47.2 126 74.7 133 45.5 124 69.7 150 81.9 150 65.6 144 59.5 145 84.9 146 60.7 143 36.3 64 79.8 139 19.2 28 40.7 144 66.5 149 53.1 144
Horn & Schunck [3]129.0 74.1 131 93.2 143 86.9 139 49.1 122 73.8 135 53.9 121 53.1 129 89.0 140 54.6 125 50.9 131 81.4 138 52.4 132 51.3 136 58.8 136 54.3 133 41.2 128 82.3 140 44.6 131 55.0 122 74.3 125 19.6 31 40.7 144 56.8 144 48.8 140
Heeger++ [104]131.8 86.1 143 91.0 137 77.1 124 67.6 141 91.6 149 65.1 129 85.6 149 94.6 147 83.6 147 71.0 139 88.2 141 68.8 137 62.9 146 69.8 148 67.3 145 69.4 149 91.0 149 70.8 147 40.2 80 80.9 143 26.3 55 21.7 114 31.2 97 27.4 107
SLK [47]132.7 67.5 119 90.3 136 82.1 132 72.2 143 84.7 147 84.8 145 58.4 136 94.0 146 58.1 134 78.1 143 82.5 139 84.6 145 55.4 142 61.5 141 68.1 146 49.4 139 83.7 144 57.7 140 36.2 63 68.1 109 26.2 54 50.3 147 60.0 146 65.2 149
FFV1MT [106]134.5 85.0 142 92.0 139 84.4 136 60.6 132 83.8 145 60.8 126 85.4 148 92.2 144 88.2 149 71.2 140 89.9 146 69.1 138 64.0 148 69.3 147 78.0 149 69.2 148 91.5 150 73.2 149 51.7 114 73.9 123 45.3 98 21.7 114 31.2 97 27.4 107
FOLKI [16]135.1 72.5 126 84.5 117 87.5 140 62.3 137 74.9 137 74.0 140 56.9 133 87.2 136 57.7 132 59.8 136 78.1 136 65.4 136 53.3 140 61.2 140 62.7 141 50.9 141 81.0 137 62.7 144 47.3 106 73.3 120 56.8 127 49.0 146 62.9 147 64.3 148
TI-DOFE [24]135.6 90.7 148 94.6 147 97.1 149 76.9 148 79.5 144 89.4 149 73.1 145 96.1 149 74.4 145 84.6 147 93.6 148 88.3 147 52.9 138 59.9 137 63.9 142 44.5 133 83.6 143 53.5 137 42.9 87 68.0 108 17.0 22 50.5 148 65.5 148 62.4 146
H+S_ROB [137]136.2 79.9 140 90.1 135 82.1 132 76.2 147 90.8 148 81.2 142 71.3 143 96.3 150 61.1 137 90.5 148 89.3 145 92.5 149 58.3 144 63.2 144 71.1 148 59.0 144 85.7 148 64.1 145 32.5 52 78.0 136 25.8 52 55.9 149 57.0 145 62.6 147
PGAM+LK [55]141.6 79.4 139 92.7 140 88.7 142 62.9 138 76.8 142 71.9 136 59.9 138 88.3 139 62.8 138 74.9 141 90.6 147 75.6 140 54.4 141 61.0 138 64.6 143 58.1 143 82.7 141 58.6 141 77.6 148 85.6 147 78.1 147 38.8 143 52.7 143 50.7 143
Adaptive flow [45]142.2 91.3 149 95.7 148 96.2 146 75.8 146 75.9 140 86.2 146 68.9 141 85.6 134 72.4 143 80.6 145 85.2 140 83.9 144 57.3 143 61.5 141 60.2 139 66.7 146 84.1 145 70.4 146 90.2 149 92.7 149 95.0 148 27.7 130 40.5 128 37.0 128
HCIC-L [99]143.2 88.6 146 96.7 150 89.3 143 80.8 149 74.4 136 93.1 150 86.6 150 87.2 136 95.2 150 95.8 150 97.4 150 96.9 150 63.4 147 66.7 145 57.8 138 68.9 147 82.7 141 73.1 148 96.0 150 95.9 150 98.6 149 25.3 128 33.9 109 34.7 125
Pyramid LK [2]145.7 86.7 144 94.5 146 96.2 146 73.1 145 76.5 141 86.4 148 70.8 142 89.6 141 78.5 146 78.1 143 88.6 143 82.7 143 68.8 149 76.4 149 80.4 150 75.7 150 85.1 147 78.1 150 73.1 145 79.6 138 69.3 140 60.8 150 74.5 150 79.9 150
AdaConv-v1 [126]151.3 100.0 151 100.0 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 152 99.9 152 99.9 152 99.9 152 100.0 152 99.7 152 99.9 152 99.9 151 99.9 151 99.9 151
SepConv-v1 [127]151.3 100.0 151 100.0 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 152 99.9 152 99.9 152 99.9 152 100.0 152 99.7 152 99.9 152 99.9 151 99.9 151 99.9 151
SuperSlomo [132]151.3 100.0 151 100.0 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 152 99.9 152 99.9 152 99.9 152 100.0 152 99.7 152 99.9 152 99.9 151 99.9 151 99.9 151
CtxSyn [136]151.3 100.0 151 100.0 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 152 99.9 152 99.9 152 99.9 152 100.0 152 99.7 152 99.9 152 99.9 151 99.9 151 99.9 151
CyclicGen [153]151.3 100.0 151 100.0 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 152 99.9 152 99.9 152 99.9 152 100.0 152 99.7 152 99.9 152 99.9 151 99.9 151 99.9 151
TOF-M [154]151.3 100.0 151 100.0 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 152 99.9 152 99.9 152 99.9 152 100.0 152 99.7 152 99.9 152 99.9 151 99.9 151 99.9 151
MEMC-Net+ [155]151.3 100.0 151 100.0 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 152 99.9 152 99.9 152 99.9 152 100.0 152 99.7 152 99.9 152 99.9 151 99.9 151 99.9 151
MPRN [156]151.3 100.0 151 100.0 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 152 99.9 152 99.9 152 99.9 152 100.0 152 99.7 152 99.9 152 99.9 151 99.9 151 99.9 151
DAIN [157]151.3 100.0 151 100.0 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 152 99.9 152 99.9 152 99.9 152 100.0 152 99.7 152 99.9 152 99.9 151 99.9 151 99.9 151
InterpCNN [158]151.3 100.0 151 100.0 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 152 99.9 152 99.9 152 99.9 152 100.0 152 99.7 152 99.9 152 99.9 151 99.9 151 99.9 151
OFRI [159]151.3 100.0 151 100.0 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 152 99.9 152 99.9 152 99.9 152 100.0 152 99.7 152 99.9 152 99.9 151 99.9 151 99.9 151
PyrWarp [162]151.3 100.0 151 100.0 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 152 99.9 152 99.9 152 99.9 152 100.0 152 99.7 152 99.9 152 99.9 151 99.9 151 99.9 151
FGME [164]151.3 100.0 151 100.0 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 152 99.9 152 99.9 152 99.9 152 100.0 152 99.7 152 99.9 152 99.9 151 99.9 151 99.9 151
MS-PFT [165]151.3 100.0 151 100.0 152 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 151 99.9 152 99.9 152 99.9 152 99.9 152 100.0 152 99.7 152 99.9 152 99.9 151 99.9 151 99.9 151
AVG_FLOW_ROB [141]152.8 100.0 151 99.9 151 100.0 151 100.0 151 100.0 151 100.0 151 99.9 151 99.9 151 99.9 151 100.0 165 99.9 151 100.0 165 99.9 151 100.0 165 99.8 151 99.2 151 99.5 151 98.3 151 99.6 151 97.0 151 99.7 151 99.9 151 99.9 151 99.9 151
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

Methodtime*framescolor Reference and notes
[1] 2D-CLG 844 2 gray The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences.
[2] Pyramid LK 12 2 color A modification of Bouguet's pyramidal implementation of Lucas-Kanade.
[3] Horn & Schunck 49 2 gray A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data.
[4] Black & Anandan 328 2 gray A modern Matlab implementation of the Black & Anandan method by Deqing Sun.
[5] Brox et al. 18 2 color T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.)
[6] Fusion 2,666 2 color V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008.
[7] Dynamic MRF 366 2 gray B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.)
[8] Second-order prior 14 2 gray W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[9] GroupFlow 600 2 gray X. Ren. Local Grouping for Optical Flow. CVPR 2008.
[10] SegOF 60 2 color L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available.
[11] Learning Flow 825 2 gray D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008.
[12] CBF 69 2 color W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[13] SPSA-learn 200 2 color Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008.
[14] GraphCuts 1,200 2 color T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008.
[15] F-TV-L1 8 2 gray A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008.
[16] FOLKI 1.4 2 gray G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005.
[17] TV-L1-improved 2.9 2 gray A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision.
[18] DPOF 287 2 color C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.)
[19] Filter Flow 34,000 2 color S. Seitz and S. Baker. Filter flow. ICCV 2009.
[20] Adaptive 9.2 2 gray A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009.
[21] Complementary OF 44 2 color H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[22] Aniso. Huber-L1 2 2 gray M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision.
[23] Rannacher 0.12 2 gray J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009.
[24] TI-DOFE 260 2 gray C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009.
[25] NL-TV-NCC 20 2 color M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010.
[26] MDP-Flow 188 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010.
[27] ACK-Prior 5872 2 color K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010.
[28] LDOF 122 2 color T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011.
[29] p-harmonic 565 2 gray J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010.
[30] TriangleFlow 4200 2 gray B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010.
[31] Classic+NL 972 2 color D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code.
[32] Classic++ 486 2 gray A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010.
[33] Nguyen 33 2 gray D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011.
[34] Modified CLG 133 2 gray R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010.
[35] ComplOF-FED-GPU 0.97 2 color P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010.
[36] Ad-TV-NDC 35 2 gray M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010.
[37] Layers++ 18206 2 color D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010.
[38] OFH 620 3 color H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011.
[39] LSM 1615 2 color K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011.
[40] CostFilter 55 2 color C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011.
[41] Bartels 0.15 2 gray C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU.
[42] Shiralkar 600 2 gray M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242.
[43] HBpMotionGpu 1000 5 gray S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.)
[44] StereoFlow 7200 2 color G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772.
[45] Adaptive flow 121 2 gray T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011.
[46] TC-Flow 2500 5 color S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011.
[47] SLK 300 2 gray T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011.
[48] CLG-TV 29 2 gray M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code.
[49] SimpleFlow 1.7 2 color M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012.
[50] IAOF 57 2 gray D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011.
[51] IAOF2 56 2 gray D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011.
[52] LocallyOriented 9541 2 gray Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012.
[53] IROF-TV 261 2 color H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop.
[54] Sparse Occlusion 2312 2 color A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011.
[55] PGAM+LK 0.37 2 gray A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010.
[56] Sparse-NonSparse 713 2 color L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013.
[57] nLayers 36150 4 color D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012.
[58] IROF++ 187 2 color H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013.
[59] COFM 600 3 color M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013.
[60] Efficient-NL 400 2 color P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012.
[61] BlockOverlap 2 2 gray M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to MMSP 2012.
[62] Ramp 1200 2 color A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012.
[63] Occlusion-TV-L1 538 3 gray C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012.
[64] TV-L1-MCT 90 2 color M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012.
[65] Local-TV-L1 500 2 gray L. Raket. Local smoothness for global optical flow. ICIP 2012.
[66] ALD-Flow 61 2 color M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012.
[67] SIOF 234 2 color L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012.
[68] MDP-Flow2 342 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available.
[69] TCOF 1421 all gray J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013.
[70] LME 476 2 color W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013.
[71] NN-field 362 2 color L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[72] FESL 3310 2 color W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013.
[73] PMF 35 2 color J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013.
[74] FC-2Layers-FF 2662 4 color D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013.
[75] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[76] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[77] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[78] Periodicity 8000 4 color G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013.
[79] SILK 572 2 gray P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP.
[80] CRTflow 13 3 color O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013.
[81] SuperFlow 178 2 color Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507.
[82] Aniso-Texture 300 2 color Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267.
[83] Classic+CPF 640 2 gray Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013.
[84] S2D-Matching 1200 2 color Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479.
[85] AGIF+OF 438 2 gray Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015.
[86] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[87] NNF-Local 673 2 color Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014.
[88] EPPM w/o HM 2.5 2 color L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014.
[89] MLDP_OF 165 2 gray M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014.
[90] RFlow 20 2 gray S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014.
[91] SRR-TVOF-NL 32 all color P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014.
[92] 2DHMM-SAS 157 2 color M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission.
[93] WLIF-Flow 700 2 color Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014.
[94] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[95] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[96] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[97] AggregFlow 1642 2 color D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759.
[98] 2bit-BM-tele 124 2 gray R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013.
[99] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[100] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[101] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[102] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[103] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[104] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[105] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[106] FFV1MT 358 5 gray F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015.
[107] ROF-ND 4 2 color S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015.
[108] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[109] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[110] FlowFields 15 2 color C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015.
[111] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[112] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[113] CombBMOF 51 2 color M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.)
[114] PMMST 182 2 color F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015.
[115] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[116] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[117] CNN-flow-warp+ref 1.4 3 color D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016.
[118] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[119] StereoOF-V1MT 343 2 gray Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132.
[120] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[121] RNLOD-Flow 1040 2 gray C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. IEEE TIP 26(8):4055-4067, 2017.
[122] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[123] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[124] BriefMatch 0.068 2 gray G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62.
[125] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[126] AdaConv-v1 2.8 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[127] SepConv-v1 0.2 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[128] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[129] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[130] FlowFields+ 10.5 2 color C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017.
[131] IIOF-NLDP 150 2 color D.-H. Trinh, W. Blondel, and C. Daul. A general form of illumination-invariant descriptors in variational optical flow estimation. ICIP 2017.
[132] SuperSlomo 0.5 2 color Anonymous. (Interpolation results only.) Super SloMo: High quality estimation of multiple intermediate frames for video interpolation. CVPR 2018 submission 325.
[133] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[134] OFRF 90 2 color T. Mai, M. Gouiffes, and S. Bouchafa. Optical Flow refinement using iterative propagation under color, proximity and flow reliability constraints. Submitted to Signal, Image and Video Processing 2017.
[135] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
[136] CtxSyn 0.07 2 color S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[137] 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.
[138] 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.
[139] 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.
[140] 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.
[141] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[142] 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.
[143] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[144] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[145] 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.
[146] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[147] 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.
[148] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[149] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
[150] WRT 9 2 color L. Mei, J. Lai, X. Xie, J. Zhu, and J. Chen. Illumination-invariance optical flow estimation using weighted regularization transform. Submitted to IEEE TCSVT 2018.
[151] EAI-Flow 2.1 2 color Anonymous. Hierarchical coherency sensitive hashing and interpolation with RANSAC for large displacement optical flow. CVIU 2018 submission 17-678.
[152] ContinualFlow_ROB 0.5 all color M Neoral, J. Sochman, and J. Matas. Continual occlusions and optical flow estimation. ACCV 2018.
[153] CyclicGen 0.088 2 color Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
[154] TOF-M 0.393 2 color T. Xue, B. Chen, J. Wu, D. Wei, and W. Freeman. Video enhancement with task-oriented flow. arXiv 1711.09078, 2017.
[155] MEMC-Net+ 0.16 2 color W. Bao, W.-S. Lai, X. Zhang, Z. Gao, and M.-H. Yang. (Interpolation results only.) MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement. Submitted to TPAMI 2018.
[156] MPRN 0.32 4 color Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[157] DAIN 0.13 2 color Anonymous. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019 submission 1769.
[158] InterpCNN 0.65 2 color Anonymous. (Interpolation results only.) Video frame interpolation with a stack of synthesis networks and intermediate optical flows. CVPR 2019 submission 6533.
[159] OFRI 0.31 2 color Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
[160] CompactFlow_ROB 0.05 2 color Anonymous. CompactFlow: spatially shiftable window revisited. CVPR 2019 submission 1387.
[161] SegFlow 3.2 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. Efficient segmentation-based PatchMatch for large displacement optical flow estimation. IEEE TCSVT 2018.
[162] PyrWarp 0.14 2 color Anonymous. (Interpolation results only.) Video frame interpolation using differentiable forward-warping of feature pyramids. ICCV 2019 submission 741.
[163] HCFN 0.18 2 color Anonymous. Practical coarse-to-fine optical flow with deep networks. ICCV 2019 submission 116.
[164] FGME 0.23 2 color Anonymous. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. ICCV 2019 submission 4327.
[165] MS-PFT 0.44 2 color X. Cheng and Z. Chen. (Interpolation results only.) A multi-scale position feature transform network for video frame interpolation. Submitted to TCSVT 2019.
* 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.