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        
R5.0
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]11.0 7.69 2 26.2 5 3.54 2 7.19 14 30.7 27 6.11 21 5.88 5 19.3 8 4.53 16 4.01 10 23.9 17 2.00 12 11.7 1 16.4 3 5.52 3 10.4 15 29.7 9 9.30 10 5.25 17 20.0 23 2.61 7 1.88 8 6.47 28 0.19 1
MDP-Flow2 [68]12.2 10.3 20 30.4 19 6.57 21 5.28 2 23.9 3 4.13 3 5.46 3 17.6 3 3.58 8 4.49 18 25.3 22 2.11 15 15.8 21 21.4 21 10.2 27 10.6 16 29.9 10 9.87 16 4.44 7 19.3 16 2.81 8 1.39 3 4.82 6 1.11 4
OFLAF [77]13.0 8.96 9 27.9 9 4.57 8 7.36 17 26.4 8 6.68 23 4.80 2 14.9 2 3.37 7 4.43 17 21.2 9 2.81 26 13.4 7 19.0 10 7.08 7 11.4 25 28.0 3 9.28 9 5.35 19 19.1 15 3.15 10 2.47 17 5.73 19 5.50 34
NN-field [71]14.2 8.65 5 28.3 10 4.00 4 8.38 27 33.1 42 7.44 29 5.86 4 19.0 7 4.53 16 3.15 2 21.4 11 1.25 3 12.0 4 16.9 5 5.41 2 6.58 2 20.2 1 3.45 1 8.64 47 23.6 52 2.88 9 2.47 17 8.48 40 0.20 2
PMMST [114]20.0 12.9 47 32.6 31 8.45 44 10.2 43 30.5 24 10.7 59 7.39 16 22.2 13 6.31 33 3.87 9 13.5 1 2.73 23 14.0 10 18.7 9 7.52 8 10.9 22 28.9 6 9.95 17 4.99 14 20.8 28 3.18 11 1.52 4 3.87 3 1.12 5
ComponentFusion [96]22.5 8.86 8 28.7 13 5.91 15 6.30 5 24.2 4 5.98 16 6.79 11 21.6 10 4.99 22 4.11 11 24.4 18 2.04 14 16.2 29 22.0 26 11.3 39 13.4 41 40.4 58 12.4 56 7.66 39 21.3 34 5.22 35 2.05 9 5.21 10 3.61 18
ALD-Flow [66]22.9 8.44 4 27.6 8 4.09 5 6.49 7 27.2 12 5.04 9 7.66 21 24.1 23 3.72 10 4.58 20 27.1 33 2.01 13 16.0 24 22.7 34 8.55 12 9.39 8 33.3 21 8.46 8 7.21 36 18.5 10 17.3 86 4.06 49 11.1 54 5.94 42
HAST [109]22.9 7.13 1 21.8 1 3.37 1 7.28 15 26.1 7 6.10 20 3.86 1 12.2 1 0.97 1 3.85 8 21.3 10 1.50 4 11.7 1 16.5 4 4.64 1 15.1 62 35.5 32 14.0 67 19.4 89 36.3 97 39.0 118 1.24 2 3.55 1 1.32 6
nLayers [57]24.0 8.66 6 25.4 3 4.54 6 13.0 81 32.1 35 13.7 88 7.74 23 21.8 11 8.85 62 3.29 4 18.2 2 1.89 9 11.8 3 16.2 2 6.65 6 12.2 30 28.4 4 10.3 20 8.59 46 21.5 38 4.98 31 2.36 15 5.74 20 5.08 30
NNF-EAC [103]24.0 10.9 28 31.8 26 6.97 23 6.64 9 26.4 8 5.65 11 6.61 9 20.7 9 4.44 15 5.48 40 27.1 33 2.97 31 16.5 32 22.3 30 11.1 36 12.1 29 30.7 11 9.97 18 6.42 27 21.4 36 3.94 23 2.95 31 7.51 35 4.63 27
LME [70]24.2 9.71 15 29.0 15 6.46 20 5.49 4 22.8 2 4.79 7 8.62 37 22.4 14 11.2 73 4.73 22 28.3 48 2.35 18 16.5 32 21.9 24 12.6 52 10.7 17 34.0 25 9.81 15 5.57 20 21.3 34 3.87 21 2.40 16 6.32 25 4.52 25
TC/T-Flow [76]25.0 9.15 10 32.1 28 3.69 3 6.89 12 31.2 30 4.32 4 7.32 15 23.1 18 4.08 11 5.14 31 27.2 36 2.80 25 15.6 20 21.9 24 9.71 21 8.63 6 29.2 7 8.40 6 6.72 29 20.2 25 19.7 100 3.86 47 9.43 44 6.28 48
WLIF-Flow [93]26.3 9.40 14 27.1 6 6.06 17 10.0 40 33.0 40 9.71 44 7.26 14 22.4 14 5.90 32 4.53 19 23.7 15 2.56 22 16.1 25 22.3 30 11.3 39 12.8 33 33.2 20 10.4 23 6.85 31 18.8 13 7.36 47 2.80 28 6.48 29 5.62 37
FC-2Layers-FF [74]27.2 9.97 16 28.7 13 7.96 33 10.4 45 35.3 50 9.95 45 6.11 7 18.1 6 6.82 37 4.12 12 20.9 7 2.48 21 13.3 6 17.7 6 9.47 18 13.5 42 32.6 15 11.3 35 14.0 71 26.0 66 12.5 67 1.84 6 4.18 4 4.53 26
RNLOD-Flow [121]27.6 7.93 3 24.8 2 5.41 13 8.33 26 31.7 32 6.84 25 7.47 17 23.3 19 4.60 18 3.62 6 21.1 8 1.66 7 14.4 12 21.0 15 7.80 9 12.7 32 32.9 16 12.2 55 17.4 84 34.4 92 20.7 102 2.55 20 5.57 17 5.30 32
Layers++ [37]28.2 10.2 18 29.1 16 8.58 47 10.8 50 30.6 25 11.0 65 5.90 6 17.7 4 6.34 34 3.40 5 18.2 2 1.66 7 12.2 5 16.0 1 9.69 20 13.9 47 33.6 22 11.9 49 13.9 70 27.9 71 8.74 52 2.33 14 4.94 7 5.70 40
FESL [72]29.5 8.67 7 25.6 4 4.73 9 13.6 86 39.4 86 12.9 83 8.22 31 24.3 27 7.10 41 3.76 7 20.3 6 2.12 16 14.1 11 20.1 12 9.08 15 11.2 24 31.0 12 9.80 14 11.3 56 30.4 80 7.66 49 2.10 10 5.40 13 2.40 9
SVFilterOh [111]29.9 12.7 45 28.4 11 8.58 47 9.41 35 29.1 19 8.31 35 6.39 8 17.7 4 5.05 24 3.23 3 18.8 5 0.95 2 14.9 15 20.9 14 6.51 5 13.2 37 32.1 14 11.6 42 22.0 95 46.5 121 30.5 112 1.61 5 4.97 9 2.45 11
TC-Flow [46]31.0 9.24 11 30.9 22 5.24 12 5.48 3 25.7 6 4.01 2 7.25 13 23.3 19 2.66 4 5.52 41 28.4 49 3.26 37 16.7 36 23.9 42 9.52 19 11.7 26 36.8 37 11.5 41 6.69 28 21.4 36 19.0 97 4.21 51 10.6 51 6.91 60
OAR-Flow [125]33.0 10.8 26 34.0 40 6.23 18 8.94 30 31.9 33 7.53 30 10.4 53 30.3 55 7.58 50 5.60 45 25.9 28 3.04 33 17.0 37 24.0 43 9.35 16 8.62 5 33.0 17 7.87 4 3.37 4 14.6 3 5.54 38 4.80 58 10.4 50 9.44 76
Efficient-NL [60]33.6 9.31 12 27.5 7 5.65 14 12.1 73 38.1 71 11.2 67 8.07 30 24.1 23 6.69 36 5.39 37 25.9 28 3.51 48 14.9 15 21.1 17 9.39 17 14.0 50 35.2 30 11.1 32 11.5 57 25.7 64 6.90 44 2.19 12 5.45 15 1.94 8
AGIF+OF [85]33.8 10.4 21 29.4 17 7.42 26 12.4 74 37.5 63 12.4 78 7.91 28 24.3 27 7.24 43 4.84 25 23.8 16 2.91 28 14.8 14 20.6 13 9.72 22 13.2 37 36.5 35 10.5 25 7.06 33 20.8 28 7.54 48 3.02 36 6.27 23 6.37 50
IROF++ [58]34.1 10.2 18 30.9 22 7.02 24 11.1 57 38.1 71 10.7 59 8.32 35 25.1 32 7.61 51 5.83 48 28.0 44 4.08 58 15.4 19 21.3 19 9.83 23 13.6 43 38.0 46 11.3 35 5.83 21 20.8 28 1.97 6 2.32 13 5.71 18 4.87 29
PMF [73]34.7 11.6 37 29.9 18 4.55 7 7.81 20 30.2 21 6.00 17 7.17 12 23.3 19 3.21 6 4.88 27 23.1 13 2.42 19 13.6 8 18.5 7 6.49 4 16.1 70 42.7 69 15.4 76 27.2 110 43.5 117 28.9 109 2.15 11 4.96 8 4.81 28
PH-Flow [101]35.3 10.9 28 32.6 31 7.94 32 10.9 52 37.4 61 10.5 53 7.56 20 22.8 17 7.74 54 5.75 47 27.2 36 4.04 56 14.4 12 19.8 11 8.81 13 13.0 35 33.6 22 11.1 32 12.7 64 23.1 48 17.6 88 1.84 6 4.19 5 4.50 24
Classic+CPF [83]36.4 10.9 28 31.7 25 7.88 31 11.5 63 37.9 68 10.9 63 8.27 33 25.1 32 7.51 49 5.05 29 25.8 27 3.16 35 15.1 17 21.0 15 10.6 28 13.1 36 34.6 28 10.3 20 9.87 51 22.0 43 13.1 73 2.68 23 5.85 21 5.53 35
COFM [59]37.0 10.1 17 32.0 27 7.63 27 8.06 22 30.4 23 7.17 26 8.93 42 25.9 38 8.04 58 4.17 13 24.9 20 1.63 6 18.8 50 24.0 43 18.6 91 14.4 54 33.0 17 11.7 44 8.15 42 20.4 26 14.7 80 3.16 38 5.36 12 8.09 71
3DFlow [135]37.2 12.6 44 34.9 41 5.05 11 8.12 23 31.5 31 5.95 14 6.67 10 21.9 12 2.51 3 4.59 21 18.4 4 3.30 40 16.6 34 23.0 35 10.9 31 19.7 90 46.8 89 19.8 96 18.3 86 24.2 58 33.3 114 1.20 1 3.86 2 0.68 3
Ramp [62]37.7 10.9 28 32.7 35 7.96 33 10.9 52 37.1 58 10.6 55 7.85 24 24.2 25 7.41 47 5.29 34 27.0 32 3.44 43 16.1 25 22.3 30 10.8 29 13.8 46 35.4 31 11.0 31 11.6 58 21.1 32 18.2 92 2.52 19 5.44 14 5.23 31
Sparse-NonSparse [56]38.3 10.7 24 32.5 30 8.38 42 10.9 52 36.8 56 10.7 59 7.95 29 24.5 31 7.30 45 5.42 39 27.6 39 3.49 47 16.1 25 22.1 27 11.0 34 13.3 39 36.0 34 10.6 27 10.6 54 21.1 32 10.9 58 2.91 29 5.93 22 6.18 46
Correlation Flow [75]38.4 11.9 41 35.3 42 6.03 16 6.85 11 28.0 14 4.77 6 8.29 34 25.8 36 2.17 2 4.84 25 27.2 36 2.77 24 18.5 48 25.9 55 11.7 41 16.9 78 39.5 52 16.7 83 12.1 61 24.6 60 17.8 89 2.59 21 7.33 34 3.08 12
LSM [39]38.8 10.4 21 32.6 31 8.24 37 10.8 50 37.4 61 10.4 52 7.85 24 24.3 27 7.05 39 5.32 35 27.6 39 3.41 42 15.8 21 21.5 22 11.1 36 13.7 44 35.6 33 10.9 30 13.0 65 23.2 49 12.5 67 2.99 35 6.43 27 6.14 45
ProbFlowFields [128]40.0 16.2 64 47.8 77 11.7 74 8.96 31 31.0 28 8.86 38 9.73 48 28.4 47 10.1 67 6.09 56 25.5 24 4.53 67 18.2 46 25.5 49 10.9 31 9.76 12 34.2 26 11.7 44 4.63 8 18.8 13 3.79 20 2.95 31 8.94 43 3.52 16
Classic+NL [31]41.3 10.5 23 31.4 24 8.38 42 11.1 57 37.9 68 10.6 55 7.87 26 24.0 22 7.48 48 5.57 43 27.6 39 3.62 50 15.8 21 21.5 22 10.8 29 14.1 51 37.4 41 11.4 38 14.8 74 25.9 65 13.4 76 2.61 22 5.29 11 6.10 44
FMOF [94]42.7 11.0 35 30.4 19 8.33 41 13.0 81 38.5 77 12.6 79 7.51 18 22.6 16 7.34 46 5.06 30 25.2 21 3.44 43 15.3 18 21.3 19 9.87 25 14.9 61 33.1 19 11.4 38 11.7 60 24.3 59 15.0 82 3.92 48 8.59 41 6.28 48
S2D-Matching [84]42.8 10.7 24 32.2 29 8.71 49 10.7 48 36.6 55 10.2 48 8.94 43 27.2 43 6.96 38 5.17 32 26.0 30 3.36 41 16.3 30 22.1 27 10.9 31 14.4 54 37.0 38 11.7 44 16.4 79 26.0 66 16.5 84 2.79 27 5.49 16 6.49 51
IIOF-NLDP [131]45.0 14.6 52 41.6 61 6.71 22 11.0 56 37.5 63 8.25 34 8.77 40 26.9 41 4.19 12 6.07 55 28.0 44 3.76 52 19.7 62 27.1 68 12.6 52 16.7 75 40.7 60 15.4 76 4.68 11 23.0 46 4.41 27 2.78 26 7.26 33 3.16 13
IROF-TV [53]45.6 11.6 37 35.3 42 9.03 52 11.2 60 38.2 74 10.9 63 8.85 41 26.5 39 7.73 53 6.04 54 33.0 72 3.62 50 17.1 39 23.1 37 13.5 63 16.3 71 44.8 76 13.5 65 3.41 5 16.9 5 1.13 3 2.71 24 6.80 31 5.67 39
TV-L1-MCT [64]45.9 10.9 28 30.5 21 8.56 46 13.8 89 40.9 96 13.2 85 8.68 38 25.8 36 7.98 57 4.83 24 25.7 25 3.26 37 17.4 41 23.5 40 13.7 67 14.8 60 36.7 36 12.7 59 5.84 22 19.4 17 10.1 56 3.53 42 6.42 26 6.63 54
2DHMM-SAS [92]47.3 10.9 28 32.6 31 8.06 35 11.5 63 39.5 87 10.6 55 10.0 51 28.3 46 7.91 56 5.93 50 28.2 47 4.07 57 16.1 25 22.3 30 11.0 34 13.7 44 38.3 48 11.1 32 12.3 63 23.2 49 18.0 91 3.08 37 6.48 29 6.24 47
Aniso-Texture [82]47.5 9.33 13 28.5 12 7.26 25 9.17 33 26.8 11 10.2 48 10.1 52 29.2 50 7.28 44 2.77 1 22.6 12 0.94 1 19.9 65 27.1 68 13.3 61 14.6 57 38.5 49 12.4 56 31.5 116 46.3 120 18.2 92 4.45 54 10.1 47 6.60 53
AggregFlow [97]47.5 13.9 50 33.8 38 11.2 68 13.7 87 39.6 89 12.6 79 12.0 66 31.3 56 13.7 82 5.40 38 23.5 14 3.44 43 17.5 42 25.4 47 7.98 11 8.57 4 25.9 2 8.42 7 7.00 32 24.1 57 4.53 28 5.53 68 9.80 46 11.7 87
SimpleFlow [49]47.6 11.6 37 33.7 37 8.98 51 12.5 77 38.9 80 12.6 79 10.4 53 29.3 51 9.20 63 5.99 51 27.6 39 4.08 58 16.3 30 22.2 29 11.1 36 16.7 75 37.4 41 12.7 59 8.29 43 19.9 21 6.11 42 2.74 25 6.28 24 5.86 41
CostFilter [40]47.8 14.1 51 36.2 48 8.48 45 8.61 29 30.6 25 7.43 28 8.26 32 26.9 41 4.40 14 5.72 46 28.1 46 3.24 36 13.7 9 18.5 7 7.81 10 16.6 74 45.0 81 16.0 80 26.8 108 48.6 124 32.7 113 2.93 30 7.59 36 5.38 33
Adaptive [20]48.4 10.9 28 33.8 38 4.92 10 10.5 46 35.0 49 9.53 43 12.2 67 33.7 60 7.68 52 5.57 43 30.3 58 2.95 30 21.7 88 26.7 63 20.6 97 10.8 19 34.9 29 7.26 3 14.0 71 28.8 75 4.88 29 4.50 56 10.2 49 6.84 58
MDP-Flow [26]48.9 12.2 43 40.6 55 8.88 50 9.32 34 28.3 16 10.5 53 9.09 44 28.1 45 9.37 65 6.03 53 30.6 60 3.99 54 17.2 40 23.1 37 12.4 47 13.9 47 42.7 69 12.5 58 7.10 35 23.6 52 4.09 25 5.35 64 13.2 64 7.09 63
RFlow [90]49.2 14.8 53 43.9 66 11.2 68 6.64 9 26.6 10 5.76 12 11.7 62 35.9 69 5.04 23 4.31 15 27.1 33 1.94 10 19.4 54 26.8 65 13.0 60 14.7 58 42.2 66 11.8 48 13.1 66 22.2 44 13.1 73 5.87 73 14.1 71 8.71 74
Occlusion-TV-L1 [63]50.0 12.9 47 36.1 47 8.26 40 9.51 38 32.7 37 8.99 39 12.3 68 34.4 64 8.27 59 5.53 42 29.8 56 3.04 33 20.5 76 28.5 87 13.8 69 9.95 13 37.9 43 11.6 42 7.64 38 21.8 42 3.47 14 5.69 70 13.9 69 7.59 68
OFH [38]51.2 15.0 55 40.9 57 14.4 85 7.06 13 29.9 20 5.37 10 10.8 56 33.1 59 4.86 21 5.84 49 30.6 60 3.46 46 19.5 57 26.1 56 15.3 75 15.6 66 46.5 88 16.6 82 4.19 6 21.7 40 3.74 19 5.39 66 15.4 80 7.23 64
MLDP_OF [89]54.0 18.8 85 51.3 92 16.0 88 8.16 24 32.0 34 6.76 24 10.7 55 31.9 58 5.45 27 4.81 23 26.1 31 2.44 20 18.7 49 24.3 45 13.7 67 15.6 66 37.9 43 18.6 92 19.2 88 28.5 73 38.7 117 3.53 42 7.25 32 4.27 22
DeepFlow2 [108]55.8 15.0 55 43.6 65 11.0 64 10.1 41 34.2 46 9.29 41 12.9 70 36.8 70 11.1 72 7.47 71 32.1 67 4.75 71 17.8 43 25.4 47 9.97 26 10.7 17 40.2 57 10.3 20 6.78 30 18.7 12 13.3 75 9.05 93 17.3 88 15.3 97
Steered-L1 [118]56.7 11.4 36 37.9 50 7.71 30 4.42 1 21.7 1 3.76 1 7.71 22 25.7 34 4.29 13 4.91 28 29.8 56 2.26 17 20.2 71 26.7 63 16.6 82 18.1 84 46.1 87 14.6 69 32.4 117 37.9 104 51.5 127 8.58 90 15.5 82 15.2 96
S2F-IF [123]57.7 18.0 78 51.9 95 10.9 61 11.1 57 38.6 78 10.6 55 13.9 75 40.6 85 13.4 81 7.68 78 32.6 69 5.18 77 19.7 62 27.2 71 13.3 61 10.8 19 39.5 52 11.9 49 4.99 14 19.9 21 6.26 43 3.26 40 10.1 47 3.57 17
Sparse Occlusion [54]57.9 12.7 45 35.8 46 8.24 37 12.4 74 33.4 43 13.4 86 9.67 46 29.1 49 6.55 35 5.99 51 28.5 50 3.56 49 19.4 54 26.4 61 12.4 47 14.7 58 39.4 51 11.7 44 37.7 124 48.6 124 17.8 89 3.66 44 9.43 44 5.64 38
Classic++ [32]58.0 10.8 26 32.7 35 8.25 39 10.5 46 32.9 38 10.7 59 10.8 56 31.6 57 8.46 60 5.25 33 29.7 55 2.99 32 20.0 67 28.0 82 13.9 70 15.2 64 44.1 74 11.9 49 17.3 83 26.2 68 18.3 94 5.82 72 12.7 60 8.14 72
PGM-C [120]58.0 17.7 73 50.5 86 11.0 64 11.9 67 39.1 82 11.6 72 13.9 75 40.4 84 13.3 80 7.52 74 35.8 86 4.62 70 19.6 60 27.5 74 12.4 47 9.48 10 37.9 43 9.36 11 4.63 8 16.9 5 5.02 32 4.83 59 14.2 74 6.69 55
CPM-Flow [116]58.8 17.7 73 50.5 86 11.0 64 11.9 67 39.0 81 11.7 73 13.7 74 39.8 82 13.2 78 7.49 73 35.5 84 4.58 69 19.5 57 27.2 71 12.3 46 9.44 9 37.3 40 9.46 12 5.05 16 19.5 18 5.17 34 5.21 62 14.8 76 7.36 66
FlowFields+ [130]59.2 18.4 80 52.2 98 11.4 71 11.9 67 39.9 91 11.5 69 14.9 81 43.4 93 14.4 85 7.97 81 33.1 73 5.58 81 19.4 54 26.9 67 12.7 55 10.2 14 39.9 55 10.5 25 4.74 12 20.1 24 4.29 26 3.80 45 12.4 59 3.48 15
BriefMatch [124]59.2 11.8 40 35.7 45 6.41 19 7.52 18 30.3 22 5.97 15 7.54 19 24.2 25 4.62 19 4.28 14 25.4 23 1.98 11 20.6 78 26.2 59 20.9 99 26.8 113 49.2 92 28.2 115 22.8 99 35.9 96 39.6 121 9.81 96 15.1 79 18.3 105
ACK-Prior [27]59.6 19.5 89 41.5 59 14.3 84 6.57 8 27.6 13 4.53 5 7.87 26 25.7 34 3.70 9 4.33 16 25.7 25 1.53 5 20.5 76 25.6 52 18.3 88 23.1 104 44.0 73 18.5 91 29.9 112 33.1 87 45.6 125 7.91 87 14.8 76 11.7 87
NL-TV-NCC [25]60.0 16.5 67 40.4 53 9.10 53 10.7 48 37.0 57 8.07 32 8.59 36 26.8 40 3.17 5 6.24 58 33.4 74 3.26 37 21.4 85 29.7 99 12.7 55 21.2 96 48.2 91 17.3 87 13.4 69 35.6 95 13.0 72 4.73 57 12.8 61 3.24 14
EpicFlow [102]60.1 17.7 73 50.6 88 10.9 61 12.0 71 39.3 85 11.7 73 14.5 78 42.2 89 13.2 78 7.47 71 35.5 84 4.57 68 19.8 64 27.6 75 12.8 58 9.73 11 38.1 47 10.1 19 4.63 8 17.2 7 4.88 29 5.31 63 14.3 75 7.47 67
CombBMOF [113]60.7 15.2 57 48.2 79 7.67 28 11.3 61 34.5 47 9.95 45 8.75 39 27.2 43 5.37 26 7.60 77 32.1 67 5.65 84 18.0 45 23.0 35 13.9 70 21.7 99 44.9 78 24.3 107 22.6 97 37.2 99 14.5 79 2.97 34 7.73 38 4.35 23
Complementary OF [21]61.8 20.9 92 51.7 93 21.5 98 6.41 6 28.3 16 4.86 8 9.56 45 30.2 54 5.62 28 8.21 83 31.4 63 6.20 87 19.2 52 25.6 52 15.5 76 21.5 98 49.3 93 17.4 88 6.34 25 19.8 20 11.5 61 6.44 79 16.1 85 10.2 80
FlowFields [110]62.0 18.3 79 51.9 95 11.1 67 11.9 67 39.5 87 11.5 69 14.8 79 43.3 92 14.2 83 7.96 80 33.5 77 5.52 80 19.9 65 27.6 75 13.6 65 11.0 23 40.5 59 12.1 53 4.93 13 19.7 19 5.34 37 3.85 46 12.3 58 3.89 19
TF+OM [100]62.8 14.8 53 35.4 44 7.68 29 9.06 32 28.4 18 9.32 42 11.6 61 28.4 47 16.0 90 6.43 59 29.0 53 4.29 61 20.2 71 25.6 52 18.4 89 17.9 82 38.5 49 16.9 86 16.6 80 33.8 88 14.7 80 6.87 82 15.5 82 9.68 77
ROF-ND [107]63.6 18.4 80 45.8 73 11.5 72 7.31 16 25.4 5 6.02 18 9.70 47 29.4 52 4.66 20 9.09 89 28.7 51 5.98 86 21.6 87 29.5 96 14.5 73 19.9 91 44.8 76 15.3 75 33.3 121 41.0 109 30.1 111 2.95 31 7.63 37 2.41 10
TV-L1-improved [17]64.9 11.9 41 36.8 49 8.23 36 8.49 28 31.0 28 7.83 31 11.9 64 33.7 60 7.19 42 5.35 36 28.9 52 2.91 28 20.3 74 28.0 82 12.0 44 27.2 115 55.4 110 30.4 117 23.1 102 38.0 105 22.9 105 5.61 69 14.0 70 7.74 70
DeepFlow [86]65.0 17.5 72 46.9 75 16.5 89 11.8 65 35.8 51 11.2 67 15.1 82 39.6 80 15.2 88 7.81 79 32.6 69 5.12 76 17.8 43 25.5 49 9.86 24 12.0 28 44.9 78 11.4 38 6.11 24 18.0 8 12.8 70 10.8 102 18.7 96 18.8 107
ComplOF-FED-GPU [35]65.1 17.9 76 52.0 97 15.4 87 7.90 21 33.9 45 5.82 13 10.8 56 34.2 62 5.67 29 6.99 66 31.5 64 4.51 66 19.2 52 26.3 60 12.9 59 18.2 85 50.5 100 18.6 92 15.1 76 23.6 52 22.3 104 5.37 65 15.4 80 6.76 56
TCOF [69]65.3 17.2 71 45.4 72 15.3 86 12.6 78 37.6 65 12.3 76 15.7 84 39.5 78 16.6 91 6.72 62 27.7 43 4.48 65 22.5 94 30.9 109 11.9 42 9.21 7 28.4 4 10.8 29 22.9 100 35.0 94 9.29 53 4.22 52 11.3 55 6.79 57
EPPM w/o HM [88]66.5 19.4 87 53.2 100 11.2 68 8.23 25 34.8 48 6.07 19 11.1 59 35.1 67 5.89 31 7.31 69 33.4 74 4.76 72 18.9 51 23.2 39 17.1 84 21.3 97 50.3 99 20.1 97 20.7 93 30.3 79 40.9 123 3.20 39 8.13 39 5.59 36
HBM-GC [105]66.8 31.9 103 41.2 58 25.6 103 13.2 83 32.9 38 14.2 90 9.93 50 24.4 30 8.75 61 10.1 97 24.7 19 6.95 95 16.6 34 21.1 17 13.6 65 18.5 86 33.7 24 15.5 78 33.9 123 47.5 123 20.1 101 3.38 41 8.62 42 5.97 43
Aniso. Huber-L1 [22]68.8 13.6 49 40.4 53 9.77 54 19.4 95 40.1 92 22.0 95 16.4 87 38.4 72 18.3 93 7.56 75 33.4 74 5.00 75 20.1 70 27.7 80 12.5 50 14.5 56 39.7 54 10.4 23 20.8 94 32.0 83 12.9 71 4.35 53 10.8 52 6.56 52
SIOF [67]69.2 16.5 67 40.1 52 10.8 60 10.3 44 37.1 58 9.10 40 16.4 87 38.3 71 18.4 94 8.56 84 35.1 82 5.87 85 21.3 84 28.5 87 16.5 81 17.6 80 43.6 72 19.7 95 7.08 34 21.6 39 3.65 17 6.65 80 16.1 85 10.9 84
F-TV-L1 [15]69.6 31.8 102 60.6 105 43.6 115 13.7 87 38.4 76 13.1 84 15.6 83 39.4 77 10.1 67 10.9 99 37.3 92 8.78 100 20.0 67 26.5 62 16.0 80 12.9 34 40.7 60 10.7 28 9.68 50 23.7 55 3.52 16 4.49 55 12.0 56 4.19 21
Rannacher [23]69.7 15.5 60 43.5 64 10.7 58 11.4 62 35.8 51 11.5 69 14.2 77 39.0 76 10.8 69 6.59 61 30.8 62 4.20 60 21.0 81 29.6 98 12.6 52 19.1 88 50.8 101 15.2 73 14.7 73 26.8 69 16.7 85 4.86 60 12.9 62 7.03 62
Brox et al. [5]72.3 18.5 82 51.2 90 20.8 97 14.0 90 37.8 67 15.1 92 13.6 73 38.8 74 11.7 74 7.20 68 36.8 89 4.02 55 23.0 98 28.5 87 24.3 107 10.8 19 45.3 83 9.57 13 7.81 40 22.7 45 1.58 4 9.61 95 19.2 99 15.0 95
LocallyOriented [52]72.4 15.8 63 41.5 59 10.9 61 15.0 92 44.5 102 13.7 88 17.6 91 43.4 93 14.2 83 7.16 67 31.5 64 4.82 73 21.0 81 29.0 92 12.5 50 11.7 26 34.5 27 12.9 61 11.6 58 29.6 76 12.0 64 7.94 88 18.4 93 11.1 85
SRR-TVOF-NL [91]72.6 22.3 98 44.7 68 12.5 78 12.0 71 38.1 71 10.2 48 14.8 79 40.6 85 10.9 71 6.13 57 34.1 78 2.81 26 19.6 60 25.5 49 13.5 63 16.4 72 42.4 67 13.0 62 30.5 113 42.5 113 18.3 94 6.41 78 11.0 53 12.0 89
CRTflow [80]73.6 16.5 67 49.5 82 10.6 57 9.63 39 33.8 44 8.65 37 13.1 71 38.8 74 7.80 55 6.86 64 34.3 79 4.44 64 20.0 67 27.8 81 12.2 45 31.4 120 59.0 116 36.7 121 10.3 52 30.4 80 12.0 64 8.56 89 20.4 106 12.9 93
DPOF [18]73.7 20.5 91 50.2 85 10.5 55 12.6 78 41.8 98 11.0 65 11.8 63 34.3 63 10.8 69 8.61 86 38.9 99 5.43 78 19.5 57 26.1 56 15.1 74 16.8 77 41.5 65 15.2 73 23.3 103 23.9 56 50.1 126 5.05 61 14.1 71 4.13 20
Bartels [41]75.6 19.3 86 39.6 51 22.4 100 9.47 37 28.2 15 10.0 47 9.91 49 29.7 53 7.09 40 9.18 91 29.3 54 7.40 97 21.7 88 27.6 75 21.1 100 19.1 88 44.4 75 24.2 106 23.0 101 36.3 97 36.2 115 7.46 86 14.9 78 11.5 86
Dynamic MRF [7]76.5 22.0 96 52.3 99 25.2 102 7.67 19 33.0 40 6.18 22 12.4 69 39.8 82 5.34 25 6.49 60 35.4 83 3.86 53 22.9 96 29.2 94 20.7 98 22.2 101 57.8 113 22.9 103 7.42 37 18.1 9 25.1 106 13.2 108 21.3 110 20.5 110
DF-Auto [115]78.7 19.4 87 46.0 74 10.5 55 26.6 105 46.1 104 31.1 105 23.7 103 46.1 97 37.0 105 9.05 88 36.8 89 5.59 82 21.7 88 29.1 93 17.4 86 7.80 3 31.8 13 7.93 5 19.5 90 37.4 101 3.25 12 10.9 103 19.6 102 16.4 99
CBF [12]78.8 15.2 57 44.8 69 12.1 76 23.7 100 37.7 66 30.9 104 13.2 72 34.6 65 14.5 86 6.86 64 32.8 71 4.32 62 22.6 95 28.4 86 20.2 95 15.6 66 41.0 63 12.1 53 32.9 119 39.7 107 29.8 110 5.49 67 13.2 64 8.30 73
TriangleFlow [30]78.8 18.7 84 43.9 66 18.0 90 10.1 41 37.2 60 8.18 33 11.9 64 35.5 68 5.81 30 6.72 62 34.6 81 4.37 63 26.7 115 34.7 116 23.4 104 23.1 104 49.6 94 23.5 104 16.7 81 37.2 99 16.3 83 6.85 81 17.3 88 10.3 81
Local-TV-L1 [65]79.1 24.6 99 51.2 90 30.0 104 22.5 99 40.6 94 25.2 98 23.5 102 46.1 97 28.3 100 9.73 94 37.4 93 6.92 94 18.3 47 25.2 46 12.7 55 13.9 47 43.2 71 12.0 52 5.25 17 20.6 27 5.15 33 15.8 113 21.0 108 32.1 118
SuperFlow [81]80.4 16.2 64 42.7 63 13.0 80 20.9 96 39.6 89 25.0 97 19.7 96 40.6 85 31.8 102 9.89 96 41.2 102 7.16 96 20.9 80 27.1 68 20.3 96 12.2 30 41.1 64 11.3 35 19.0 87 32.1 85 3.87 21 10.1 98 19.3 100 16.4 99
LDOF [28]80.5 17.1 70 48.0 78 12.9 79 13.3 84 40.6 94 12.2 75 15.8 85 42.4 90 12.7 77 9.70 93 44.0 104 6.27 89 20.7 79 28.0 82 16.8 83 14.3 53 45.9 86 13.8 66 8.36 44 23.3 51 7.98 50 11.2 105 21.2 109 18.3 105
CNN-flow-warp+ref [117]81.5 18.5 82 50.0 83 13.9 83 17.8 94 37.9 68 21.1 94 21.3 100 47.3 101 29.7 101 9.13 90 38.8 96 6.72 92 21.8 91 28.2 85 19.6 92 14.2 52 45.7 85 13.1 63 5.94 23 18.5 10 10.9 58 12.4 107 20.6 107 16.4 99
CLG-TV [48]81.6 15.7 62 42.2 62 11.7 74 20.9 96 39.2 84 24.8 96 16.4 87 39.5 78 18.0 92 9.23 92 37.9 94 6.54 90 22.9 96 30.0 103 17.9 87 16.5 73 47.2 90 14.2 68 19.9 91 30.4 80 11.5 61 5.79 71 14.1 71 6.98 61
TriFlow [95]82.2 21.3 94 44.9 70 13.5 82 16.0 93 36.5 54 18.7 93 18.2 93 38.6 73 27.8 99 7.35 70 30.3 58 5.59 82 21.2 83 27.3 73 18.5 90 15.1 62 37.1 39 15.0 72 49.5 129 41.7 111 95.6 132 6.38 77 13.3 66 9.77 78
p-harmonic [29]82.7 21.2 93 63.8 110 20.6 96 12.4 74 35.9 53 12.7 82 17.7 92 47.5 102 14.9 87 10.9 99 42.1 103 8.85 101 20.4 75 26.1 56 17.1 84 17.9 82 52.5 104 18.4 90 15.6 78 28.6 74 5.86 40 5.89 74 13.5 67 7.67 69
FlowNetS+ft+v [112]83.3 15.2 57 44.9 70 10.7 58 13.4 85 38.2 74 13.4 86 18.8 95 42.8 91 24.4 96 9.01 87 38.8 96 6.24 88 23.2 100 31.5 113 15.9 78 13.3 39 42.6 68 13.1 63 18.2 85 32.6 86 21.9 103 8.73 91 19.1 98 12.8 92
OFRF [134]83.4 20.1 90 40.7 56 18.8 92 25.4 103 43.7 100 27.8 102 20.4 98 39.7 81 25.4 97 12.5 101 34.3 79 11.1 103 17.0 37 23.7 41 8.99 14 17.6 80 40.0 56 16.7 83 15.0 75 28.4 72 28.3 108 16.1 114 19.4 101 34.6 119
Second-order prior [8]85.8 15.6 61 48.2 79 12.1 76 12.6 78 39.1 82 12.3 76 16.2 86 44.6 95 12.2 76 7.57 76 31.6 66 5.45 79 22.2 92 30.6 105 14.3 72 20.8 95 56.8 112 17.7 89 28.0 111 33.8 88 27.1 107 7.43 85 17.4 90 10.4 83
StereoFlow [44]88.0 85.4 132 89.0 132 87.9 131 73.1 132 88.5 132 68.8 127 66.8 131 87.5 131 52.4 124 81.5 131 91.1 131 78.5 131 25.9 114 27.6 75 29.7 119 6.38 1 29.4 8 6.60 2 1.39 1 10.9 1 0.20 1 6.34 76 13.8 68 10.3 81
Fusion [6]89.0 17.9 76 57.7 102 18.6 91 9.42 36 32.3 36 10.2 48 11.4 60 34.8 66 11.7 74 8.57 85 40.2 100 6.89 93 25.0 110 30.8 108 24.9 112 23.9 107 52.3 103 25.0 110 33.3 121 43.4 115 19.3 99 9.01 92 18.8 97 13.4 94
Learning Flow [11]89.3 16.4 66 47.3 76 11.5 72 14.0 90 40.3 93 14.4 91 16.4 87 41.7 88 15.6 89 8.05 82 40.7 101 4.87 74 27.1 117 35.0 118 22.5 103 17.2 79 50.0 98 16.0 80 15.5 77 34.1 91 13.9 78 10.1 98 20.2 105 12.5 91
SegOF [10]91.7 28.8 101 51.1 89 13.2 81 37.3 114 51.8 114 44.6 116 30.0 108 53.0 106 43.3 114 27.0 114 49.6 109 22.4 110 24.0 106 27.6 75 28.4 118 24.9 110 58.5 114 24.4 108 2.04 2 16.2 4 0.47 2 10.0 97 16.5 87 16.7 102
Ad-TV-NDC [36]93.6 44.8 117 63.0 108 69.1 124 40.3 117 48.4 109 48.3 119 34.8 113 58.5 109 39.9 108 26.5 113 47.8 108 27.7 114 20.2 71 28.5 87 11.9 42 15.2 64 40.9 62 14.7 70 8.46 45 21.0 31 5.69 39 23.9 124 28.3 124 41.9 128
StereoOF-V1MT [119]94.1 21.7 95 68.0 115 20.3 95 11.8 65 50.4 112 7.18 27 20.7 99 62.8 113 9.21 64 9.80 95 50.8 110 6.56 91 27.9 119 35.8 119 23.9 105 25.0 111 67.3 121 24.0 105 8.00 41 27.7 70 12.2 66 13.4 109 23.5 114 15.8 98
Shiralkar [42]94.5 22.0 96 69.5 117 19.6 93 10.9 52 42.6 99 8.48 36 18.4 94 54.0 107 9.43 66 10.1 97 45.4 105 7.72 98 21.5 86 28.9 91 15.9 78 26.8 113 60.7 117 25.4 112 24.3 106 29.9 78 39.4 119 11.0 104 23.8 115 12.2 90
FlowNet2 [122]97.4 47.2 119 61.0 106 42.4 112 44.5 120 57.5 116 51.3 121 37.6 116 64.7 115 43.1 113 21.0 107 35.8 86 17.9 106 25.8 111 30.6 105 24.6 109 20.4 92 49.7 96 21.0 98 32.5 118 53.3 128 4.06 24 4.13 50 13.0 63 1.49 7
HBpMotionGpu [43]99.8 32.0 104 50.0 83 22.9 101 36.1 113 47.0 106 43.9 115 29.2 107 51.9 105 38.6 107 13.0 102 37.1 91 10.2 102 23.5 102 29.5 96 24.2 106 18.9 87 44.9 78 15.9 79 33.2 120 41.2 110 12.6 69 11.8 106 18.5 94 22.7 111
IAOF2 [51]100.3 25.3 100 49.2 81 22.2 99 24.6 101 44.3 101 28.6 103 20.0 97 45.4 96 25.5 98 49.8 123 57.5 118 60.5 125 23.2 100 31.0 110 15.7 77 23.2 106 49.6 94 19.3 94 30.5 113 39.0 106 19.0 97 9.25 94 18.6 95 9.82 79
Modified CLG [34]100.4 34.8 108 61.1 107 35.3 106 33.3 111 46.5 105 41.7 114 36.8 115 63.0 114 45.1 118 22.1 108 55.4 114 18.7 108 23.9 104 31.2 111 21.7 102 15.8 69 51.5 102 14.8 71 9.01 48 24.6 60 11.1 60 17.6 118 25.7 120 29.6 116
EPMNet [133]101.7 47.1 118 71.6 121 41.3 111 41.8 118 61.0 120 47.5 118 34.2 112 60.0 111 40.1 109 22.9 111 38.8 96 20.2 109 25.8 111 30.6 105 24.6 109 20.4 92 49.7 96 21.0 98 23.9 105 44.7 118 3.33 13 7.39 84 18.0 91 7.28 65
2D-CLG [1]102.1 44.0 115 63.3 109 36.1 107 44.3 119 52.3 115 55.1 123 49.1 124 75.4 122 50.5 122 64.3 128 76.4 127 67.8 128 24.8 108 29.7 99 27.4 115 20.5 94 53.6 107 22.4 101 2.52 3 13.0 2 3.50 15 22.8 123 27.9 123 36.9 122
Filter Flow [19]102.1 33.3 105 51.7 93 20.1 94 25.0 102 47.2 108 27.7 101 27.7 105 50.0 103 37.9 106 31.7 116 54.1 113 29.9 115 25.8 111 31.2 111 28.3 117 26.4 112 52.9 106 24.7 109 42.3 126 61.5 130 13.6 77 6.09 75 12.1 57 6.88 59
SPSA-learn [13]102.5 35.8 109 71.2 119 43.1 114 28.4 107 47.0 106 32.8 108 31.4 110 57.7 108 42.2 112 22.2 109 51.0 111 22.9 112 23.9 104 29.4 95 24.6 109 24.8 109 56.5 111 25.1 111 10.7 55 25.1 62 3.72 18 21.7 121 24.9 119 35.5 121
BlockOverlap [61]103.2 41.4 111 54.1 101 36.2 108 27.3 106 41.4 97 32.6 107 26.2 104 46.5 99 31.8 102 20.0 105 36.6 88 18.1 107 22.4 93 26.8 65 25.7 113 24.5 108 45.6 84 21.1 100 39.3 125 47.0 122 43.5 124 13.8 110 16.0 84 28.7 115
IAOF [50]104.3 33.8 106 58.3 103 40.6 109 33.0 110 44.5 102 39.5 112 30.6 109 58.7 110 33.8 104 34.1 119 52.4 112 40.8 119 23.1 99 29.9 101 19.7 94 22.5 102 53.7 108 16.8 85 22.3 96 34.0 90 10.0 55 19.5 119 23.9 116 37.1 124
GraphCuts [14]105.5 34.5 107 59.0 104 32.1 105 26.2 104 51.1 113 26.4 100 28.1 106 51.7 104 40.4 111 13.0 102 47.5 107 7.98 99 23.7 103 30.0 103 24.3 107 33.4 121 45.2 82 25.7 113 31.2 115 37.7 103 36.8 116 10.7 101 19.7 103 17.7 104
GroupFlow [9]105.6 42.7 112 67.1 114 53.4 117 44.8 121 63.8 125 50.2 120 36.7 114 69.4 119 43.9 115 17.2 104 46.0 106 16.7 104 27.8 118 34.9 117 21.2 101 36.7 124 67.0 120 43.6 125 6.40 26 21.7 40 7.17 45 16.6 115 25.9 121 25.0 112
Black & Anandan [4]106.0 38.5 110 69.5 117 53.4 117 28.5 108 49.6 111 32.0 106 33.4 111 60.5 112 40.2 110 22.6 110 55.9 115 22.8 111 24.5 107 32.2 115 19.6 92 21.7 99 58.9 115 22.7 102 22.6 97 37.6 102 5.27 36 16.7 116 22.6 113 25.4 113
2bit-BM-tele [98]108.7 55.1 123 64.1 112 69.1 124 21.4 98 38.7 79 25.3 99 23.3 101 46.7 100 21.2 95 26.2 112 38.7 95 25.2 113 24.9 109 29.9 101 27.7 116 31.3 119 52.6 105 34.6 119 43.3 127 51.7 127 54.5 128 10.3 100 20.1 104 16.8 103
Nguyen [33]110.4 43.9 114 66.0 113 42.8 113 54.0 126 49.4 110 70.1 128 42.9 119 67.4 117 47.3 120 55.4 126 65.7 122 64.4 126 27.0 116 31.8 114 31.0 120 22.8 103 54.8 109 27.3 114 13.1 66 25.2 63 6.08 41 22.2 122 26.9 122 38.9 125
SILK [79]112.4 49.5 122 69.2 116 69.3 126 39.9 116 60.6 119 47.0 117 40.4 118 70.7 120 45.6 119 32.0 117 56.5 116 31.2 117 31.4 121 36.9 122 33.3 122 31.1 118 63.2 118 32.3 118 10.3 52 23.0 46 17.3 86 25.0 125 31.9 125 36.9 122
UnFlow [129]112.8 70.9 128 78.9 123 58.5 120 51.3 125 67.4 128 56.9 124 54.4 126 83.6 129 52.8 125 33.4 118 60.2 119 30.1 116 36.7 128 38.4 125 46.2 129 38.2 125 69.6 124 42.8 124 26.2 107 40.3 108 1.60 5 7.20 83 18.3 92 8.75 75
Periodicity [78]114.2 48.9 121 63.9 111 41.0 110 34.5 112 60.0 118 37.5 111 55.4 127 67.4 117 56.6 127 20.4 106 56.9 117 17.5 105 53.2 131 66.7 132 46.5 130 48.3 129 76.0 130 46.4 127 9.14 49 34.4 92 9.98 54 28.3 128 48.2 131 40.6 127
Horn & Schunck [3]114.9 43.3 113 80.7 126 58.6 121 32.5 109 59.7 117 35.1 109 40.2 117 76.3 125 44.7 117 31.5 115 64.8 120 32.6 118 29.3 120 36.4 121 27.0 114 27.5 116 68.7 122 29.7 116 27.0 109 43.3 114 7.32 46 25.9 126 36.5 127 34.6 119
Heeger++ [104]117.4 61.9 126 80.2 125 47.4 116 44.8 121 77.8 131 40.9 113 68.0 132 84.7 130 62.1 130 43.6 122 69.1 123 41.9 120 32.6 123 37.9 123 32.0 121 51.1 130 78.4 131 54.2 130 13.3 68 43.4 115 10.4 57 15.0 111 21.4 111 19.6 108
SLK [47]118.2 44.7 116 78.9 123 59.1 122 58.2 128 71.2 129 70.9 129 47.5 122 83.5 128 50.6 123 65.0 129 69.5 124 73.4 129 34.7 125 38.9 127 42.9 128 34.8 122 70.9 127 39.4 122 12.1 61 29.8 77 11.5 61 34.4 129 40.1 128 48.8 129
TI-DOFE [24]120.4 73.1 129 84.6 130 89.6 132 61.2 130 64.7 127 74.8 131 58.6 128 88.7 132 58.0 128 70.9 130 81.6 129 76.1 130 31.7 122 38.0 124 35.4 123 29.7 117 68.7 122 36.3 120 17.1 82 32.0 83 8.67 51 35.5 130 42.8 129 49.8 130
FFV1MT [106]120.4 59.9 125 77.8 122 53.6 119 37.7 115 72.5 130 37.0 110 63.6 130 82.1 127 62.4 131 42.8 121 73.9 126 42.6 121 41.9 130 45.8 130 52.3 131 52.5 131 81.8 132 56.1 131 20.2 92 42.4 112 18.3 94 15.0 111 21.4 111 19.6 108
FOLKI [16]122.9 48.0 120 71.5 120 68.8 123 48.6 124 63.2 122 59.5 125 43.0 120 75.6 123 44.0 116 40.4 120 65.6 121 45.8 122 35.3 126 40.6 128 41.6 126 36.3 123 71.6 129 44.4 126 23.6 104 44.7 118 40.4 122 36.9 131 43.4 130 54.5 131
PGAM+LK [55]125.0 58.6 124 80.9 127 69.8 127 45.1 123 63.7 124 51.9 122 43.2 121 76.2 124 47.5 121 50.3 124 82.2 130 51.4 123 32.7 124 36.0 120 42.3 127 41.4 126 70.1 125 41.2 123 56.3 130 58.0 129 55.0 129 25.9 126 32.4 126 40.3 126
Adaptive flow [45]125.3 76.7 131 83.7 129 86.4 129 57.9 127 63.6 123 67.3 126 48.7 123 73.2 121 52.9 126 52.7 125 69.9 125 56.0 124 35.4 127 38.4 125 39.4 125 46.1 127 70.6 126 47.6 128 73.1 131 75.2 131 88.1 130 17.2 117 24.6 118 25.6 114
HCIC-L [99]127.2 76.5 130 86.4 131 73.3 128 70.1 131 62.5 121 85.3 132 63.5 129 66.1 116 79.5 132 83.3 132 91.8 132 86.5 132 39.0 129 42.8 129 38.7 124 46.4 128 66.6 119 52.3 129 89.6 132 85.9 132 94.0 131 19.8 120 24.2 117 29.6 116
Pyramid LK [2]128.7 68.1 127 83.5 128 86.8 130 59.4 129 64.5 126 73.1 130 52.8 125 76.3 125 61.4 129 60.2 127 79.0 128 65.9 127 53.8 132 61.8 131 64.5 132 59.4 132 71.1 128 63.0 132 43.9 128 49.4 126 39.5 120 50.2 132 60.2 132 70.8 132
AdaConv-v1 [126]133.0 100.0 133 99.9 133 100.0 133 100.0 133 100.0 133 100.0 133 99.9 133 99.9 133 99.9 133 100.0 133 100.0 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.8 133 100.0 133 99.7 133 97.0 133 99.9 133 99.9 133 99.9 133 99.9 133
SepConv-v1 [127]133.0 100.0 133 99.9 133 100.0 133 100.0 133 100.0 133 100.0 133 99.9 133 99.9 133 99.9 133 100.0 133 100.0 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.8 133 100.0 133 99.7 133 97.0 133 99.9 133 99.9 133 99.9 133 99.9 133
SuperSlomo [132]133.0 100.0 133 99.9 133 100.0 133 100.0 133 100.0 133 100.0 133 99.9 133 99.9 133 99.9 133 100.0 133 100.0 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.8 133 100.0 133 99.7 133 97.0 133 99.9 133 99.9 133 99.9 133 99.9 133
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

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