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        
A95
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]10.5 7.47 3 40.1 11 3.98 3 6.49 14 30.3 3 5.60 18 5.82 4 26.1 3 4.68 18 3.86 10 53.5 7 2.99 20 9.77 1 12.4 1 5.36 3 8.67 5 31.8 3 7.03 3 5.10 25 10.1 60 3.70 13 2.31 10 5.34 11 1.21 2
NN-field [71]14.2 8.38 14 43.1 28 4.19 4 7.34 25 28.7 2 6.26 29 5.82 4 28.9 6 4.68 18 2.94 2 54.1 8 2.16 3 10.4 4 13.2 4 5.24 2 6.12 1 17.5 1 4.46 1 6.24 59 10.6 76 4.10 14 2.35 14 6.44 21 1.14 1
MDP-Flow2 [68]16.9 8.02 8 38.6 6 5.75 22 5.17 2 31.1 4 4.55 3 5.48 3 30.8 9 4.22 10 4.49 20 99.9 66 3.27 28 11.3 14 13.4 6 8.04 22 10.8 14 54.4 38 10.5 21 4.84 12 9.33 40 4.31 19 2.69 28 4.85 6 2.20 4
OFLAF [77]18.3 7.70 5 39.8 8 4.74 8 6.40 13 32.5 7 5.82 24 4.73 2 25.3 2 3.96 6 4.47 19 99.9 66 3.55 46 10.2 3 13.0 2 6.29 7 13.3 36 42.1 19 9.90 18 5.10 25 8.01 10 4.66 29 2.75 29 5.59 15 6.33 40
PMMST [114]19.1 8.63 17 31.3 1 6.03 28 8.51 39 26.8 1 8.18 64 7.50 12 28.0 5 6.07 38 4.26 17 34.8 5 3.29 29 10.9 8 13.2 4 6.26 6 10.4 12 29.9 2 9.42 13 5.00 20 10.1 60 4.37 20 3.25 40 4.40 5 3.36 13
nLayers [57]27.1 8.19 11 45.3 54 4.62 6 9.65 63 31.7 6 8.88 85 8.87 21 33.6 11 8.22 66 3.62 6 99.9 66 2.93 17 10.5 5 13.6 8 6.52 8 11.3 20 33.4 4 9.45 15 6.02 54 8.56 17 4.99 37 2.31 10 6.80 26 5.53 35
NNF-EAC [103]28.1 8.80 19 40.8 15 6.14 30 6.13 8 39.3 28 5.36 12 6.97 9 35.1 12 4.73 20 5.83 43 87.9 47 3.49 42 12.1 30 14.6 21 8.87 33 12.5 32 41.2 15 11.8 38 5.35 34 10.1 60 4.61 27 3.19 37 7.62 37 3.99 25
ComponentFusion [96]29.9 8.30 13 49.1 76 5.87 25 5.69 6 35.4 15 5.40 13 7.24 10 35.3 13 4.99 24 3.69 7 99.9 66 2.32 6 11.7 20 14.1 14 8.75 31 15.8 68 66.6 64 15.0 80 5.71 43 8.88 26 5.09 43 2.64 25 5.25 10 3.68 19
FC-2Layers-FF [74]31.7 8.26 12 41.4 19 6.27 31 8.85 43 37.9 22 7.81 48 6.02 7 31.8 10 6.25 41 3.91 12 88.8 50 2.86 15 11.0 11 13.7 10 7.20 11 16.5 76 40.4 11 16.3 94 7.14 79 10.7 80 6.61 68 2.15 3 3.87 1 2.77 6
FESL [72]32.2 7.69 4 40.2 12 4.90 9 11.0 86 48.5 59 9.07 88 10.5 30 42.1 27 6.42 43 3.60 5 99.9 66 2.55 9 10.9 8 13.6 8 8.86 32 11.1 18 36.4 6 10.6 22 6.73 73 10.2 64 5.95 56 2.51 22 5.37 13 3.35 12
LME [70]32.8 7.85 7 42.7 26 6.01 27 5.33 4 34.6 10 4.91 8 14.6 52 54.5 55 40.7 116 4.66 22 73.0 15 3.25 25 11.5 17 13.8 12 9.65 58 11.6 22 70.4 74 12.1 43 5.14 27 9.97 58 4.51 26 2.86 30 6.45 22 4.29 30
TC/T-Flow [76]33.5 9.01 23 38.1 4 3.81 1 6.64 16 55.1 80 4.62 4 8.13 16 46.4 41 4.20 9 5.32 36 99.9 66 2.88 16 11.5 17 14.1 14 7.28 13 8.85 6 38.5 9 9.44 14 5.85 50 10.7 80 10.0 111 3.61 48 10.0 54 8.53 75
HAST [109]34.3 6.42 1 43.9 37 3.97 2 7.16 20 33.1 8 5.92 26 3.76 1 23.5 1 2.83 1 3.36 3 99.9 66 2.08 2 10.0 2 13.0 2 4.83 1 16.7 81 59.3 45 19.4 115 11.3 124 12.9 111 17.6 135 2.67 27 4.13 3 2.93 9
WLIF-Flow [93]36.0 8.04 9 40.7 13 5.53 18 7.98 34 34.6 10 7.20 41 8.75 20 40.5 22 5.74 35 4.27 18 96.8 63 2.94 18 13.4 89 16.1 97 9.77 62 13.5 40 41.3 17 11.8 38 5.65 41 9.12 32 5.96 57 2.29 9 7.30 30 6.96 51
PMF [73]36.2 9.38 31 48.9 74 4.67 7 7.10 18 37.5 19 5.58 17 7.91 14 30.0 8 4.06 7 4.89 32 99.9 66 3.29 29 10.6 7 14.0 13 5.76 5 12.4 31 54.8 39 11.5 33 11.2 123 17.9 144 11.1 116 2.06 1 4.95 9 4.00 26
Layers++ [37]36.8 9.07 24 44.4 40 8.41 67 8.47 38 31.5 5 8.03 57 5.85 6 37.9 15 6.02 37 3.76 9 62.6 9 2.79 12 10.5 5 13.5 7 8.22 27 17.6 89 55.0 40 14.5 77 7.44 84 10.9 84 5.70 55 2.27 8 4.86 7 9.14 80
ALD-Flow [66]36.8 8.18 10 41.6 24 4.51 5 6.32 11 54.8 78 5.03 10 10.7 34 61.8 63 4.24 11 4.24 16 99.9 66 2.61 10 11.7 20 14.3 16 7.21 12 10.8 14 61.4 48 9.93 19 5.96 53 9.55 45 9.77 110 3.87 53 15.7 66 9.38 88
3DFlow [135]37.3 9.37 29 41.4 19 5.02 11 7.10 18 38.0 23 5.51 16 7.41 11 53.2 53 3.81 5 4.74 23 14.8 2 4.00 59 12.0 28 15.2 47 8.89 35 19.9 107 60.3 46 18.1 112 8.06 92 9.24 37 10.1 112 2.26 6 4.12 2 2.04 3
Efficient-NL [60]38.2 8.40 15 43.6 34 5.38 16 9.12 47 37.4 18 7.83 50 11.1 38 56.6 57 6.16 39 5.71 40 99.9 66 3.32 32 11.3 14 14.7 25 7.66 14 16.6 80 37.6 7 12.7 52 6.93 77 10.8 82 5.98 60 2.89 32 5.47 14 2.90 8
RNLOD-Flow [121]39.2 7.26 2 38.7 7 5.25 15 7.65 30 43.0 37 6.20 28 12.7 45 75.2 71 4.59 15 3.52 4 99.9 66 2.46 7 11.4 16 14.9 34 7.74 16 16.2 70 40.2 10 16.2 91 8.20 94 12.2 102 7.63 88 2.49 21 5.98 18 7.10 55
SVFilterOh [111]39.3 8.96 22 55.2 108 5.63 19 7.20 21 37.8 21 6.39 32 6.18 8 43.0 30 5.02 25 3.71 8 99.9 66 2.49 8 11.1 13 14.3 16 5.54 4 13.5 40 50.6 34 14.1 70 10.1 115 16.8 139 12.4 127 2.20 4 4.91 8 2.50 5
ProFlow_ROB [146]39.4 10.5 46 51.4 85 5.14 14 7.28 22 50.8 66 5.66 20 17.6 55 65.7 67 5.43 30 3.88 11 98.0 64 2.18 4 12.3 38 15.2 47 7.81 18 12.1 29 52.1 35 12.9 55 4.24 5 9.88 55 3.68 11 3.79 51 19.4 72 6.62 45
AGIF+OF [85]39.7 8.89 21 44.1 38 6.77 36 10.2 70 44.4 43 8.51 80 10.2 27 43.5 32 6.63 47 4.80 27 99.9 66 3.25 25 11.7 20 14.7 25 9.52 53 13.7 43 40.9 12 12.6 49 5.73 46 8.99 27 5.96 57 2.36 16 7.50 33 7.55 59
TC-Flow [46]40.7 8.59 16 41.0 17 5.12 12 5.47 5 45.6 47 4.31 2 10.2 27 94.7 95 3.49 3 6.08 49 99.9 66 3.50 43 11.9 26 14.5 19 7.90 20 11.9 28 61.7 50 11.5 33 5.72 44 9.85 53 11.5 121 4.02 57 15.0 64 9.14 80
IROF++ [58]42.2 9.29 28 45.0 52 6.30 32 9.55 59 43.0 37 8.20 65 10.8 35 43.1 31 7.57 58 6.28 54 99.9 66 3.90 54 12.2 34 14.8 30 9.41 51 15.2 63 44.1 28 14.5 77 5.27 29 9.48 43 3.69 12 2.62 24 6.48 23 4.14 27
PH-Flow [101]42.2 10.2 40 44.6 44 7.86 49 9.41 54 42.0 34 8.11 60 8.41 19 38.9 17 7.40 57 6.39 56 99.9 66 3.93 56 11.8 24 14.5 19 7.72 15 13.8 44 42.9 23 13.1 57 7.21 80 10.3 67 7.61 87 2.34 13 4.20 4 4.20 28
Classic+CPF [83]43.5 9.64 34 43.4 30 7.93 52 9.43 55 46.1 50 7.82 49 10.6 33 51.0 48 6.68 48 5.09 34 99.9 66 3.22 24 12.0 28 15.2 47 9.15 43 14.7 55 34.4 5 13.4 62 6.42 63 10.1 60 6.89 73 2.26 6 6.77 25 7.08 54
Correlation Flow [75]43.5 9.27 27 38.3 5 5.40 17 6.33 12 36.7 16 4.85 7 18.4 57 99.9 105 3.58 4 4.87 30 35.8 6 3.47 39 12.9 65 15.8 79 9.17 45 16.0 69 68.6 67 16.5 101 6.59 69 9.85 53 7.93 95 2.88 31 7.57 36 3.06 10
PWC-Net_ROB [147]43.9 17.5 99 49.3 79 9.65 91 9.55 59 42.8 35 8.41 70 19.6 59 46.1 40 10.6 73 6.18 53 74.3 16 3.39 35 12.4 41 15.4 60 8.92 36 11.8 25 45.5 29 11.5 33 4.32 7 9.79 49 2.49 4 3.08 34 6.38 20 2.86 7
JOF [140]45.4 8.67 18 45.9 56 6.43 33 10.3 73 48.5 59 8.94 87 8.37 18 39.4 19 7.19 52 4.81 28 99.9 66 2.79 12 11.9 26 14.6 21 8.03 21 13.9 47 43.0 24 10.8 23 9.32 108 11.4 92 11.3 120 2.21 5 7.25 28 7.07 53
CostFilter [40]46.0 10.5 46 46.8 65 6.98 40 7.51 27 38.1 24 6.31 31 9.22 22 29.7 7 4.74 21 5.86 45 99.9 66 3.97 58 10.9 8 14.3 16 6.77 9 13.4 37 56.1 41 12.3 45 11.6 127 20.5 148 14.2 129 2.12 2 8.52 44 6.71 47
ProbFlowFields [128]47.5 16.3 90 53.8 99 10.9 106 7.72 31 40.6 31 7.12 37 14.1 50 45.2 39 10.5 71 6.67 61 62.6 9 4.39 72 12.9 65 15.4 60 9.64 57 10.1 9 63.2 56 10.8 23 4.86 14 8.16 15 4.69 31 3.36 42 9.23 50 3.72 21
HCFN [163]48.4 8.86 20 40.7 13 5.67 20 5.27 3 43.8 41 4.64 5 7.53 13 39.4 19 3.23 2 4.87 30 99.9 66 3.58 47 11.0 11 13.7 10 7.15 10 15.4 65 53.4 37 16.3 94 14.7 141 16.8 139 17.8 136 5.63 77 12.6 58 10.6 104
IIOF-NLDP [131]48.5 12.0 61 43.5 32 5.86 24 9.35 50 35.0 12 6.81 35 11.2 39 88.4 91 4.51 13 6.09 50 28.8 4 4.09 64 14.6 119 18.4 132 9.71 59 14.6 54 66.2 63 14.7 79 4.90 17 9.54 44 4.82 35 3.09 35 7.73 40 3.18 11
OAR-Flow [125]48.6 11.1 54 48.8 72 5.85 23 9.88 65 82.9 130 6.47 33 27.3 79 99.9 105 8.06 62 6.75 62 99.9 66 2.80 14 12.4 41 15.1 45 8.20 26 10.3 10 58.1 43 8.37 9 4.07 2 8.06 12 5.45 52 4.81 67 9.74 53 6.36 41
Sparse-NonSparse [56]49.1 9.96 35 44.2 39 8.85 75 9.39 53 50.6 65 8.08 59 10.1 26 43.7 34 7.21 53 6.10 51 88.2 48 3.41 37 12.5 47 15.5 70 8.96 37 16.3 72 41.9 18 16.2 91 6.48 65 9.05 29 6.27 64 2.33 12 7.33 31 7.76 67
MLDP_OF [89]49.5 11.8 60 41.7 25 8.40 66 6.97 17 35.2 14 5.88 25 11.3 42 65.3 66 5.23 28 4.76 26 99.9 66 3.09 21 12.2 34 14.8 30 8.87 33 13.4 37 48.1 31 17.2 108 10.0 114 10.9 84 18.1 137 3.58 47 8.07 43 4.53 33
Ramp [62]49.8 10.2 40 44.4 40 8.09 61 9.47 56 46.1 50 8.17 63 9.51 24 42.4 29 6.88 51 5.40 37 99.9 66 3.53 44 12.5 47 15.2 47 9.71 59 16.7 81 42.1 19 16.5 101 6.76 74 10.0 59 7.07 77 2.46 20 5.84 17 5.24 34
LSM [39]49.9 10.0 38 42.9 27 8.48 68 9.36 52 49.6 63 7.99 54 10.5 30 43.6 33 6.80 49 5.80 41 88.6 49 3.38 34 12.5 47 15.4 60 9.03 39 16.5 76 42.3 21 16.3 94 6.94 78 9.84 50 6.71 69 2.42 19 7.96 42 7.72 64
WRT [150]50.1 10.9 51 48.8 72 5.12 12 10.2 70 39.2 26 8.48 76 39.5 102 99.9 105 4.62 16 4.75 25 14.6 1 3.39 35 11.7 20 15.0 38 9.93 71 21.2 111 64.7 61 17.5 110 5.35 34 8.80 24 5.37 50 3.22 39 7.63 38 3.38 15
MDP-Flow [26]52.9 11.2 55 43.1 28 9.86 95 8.14 37 35.1 13 8.21 66 11.2 39 42.1 27 9.44 69 6.41 57 99.9 66 4.20 68 12.2 34 14.6 21 10.0 74 11.7 24 63.6 57 9.60 16 5.56 39 10.9 84 4.39 21 5.78 78 99.9 124 8.99 77
Classic+NL [31]53.5 10.1 39 44.9 50 8.90 76 9.49 57 51.6 69 7.87 51 9.93 25 43.9 36 7.31 56 6.07 48 99.9 66 3.78 52 12.5 47 15.3 55 9.06 40 17.1 85 41.0 13 15.8 88 7.32 83 10.8 82 6.80 72 2.35 14 5.62 16 7.69 63
FMOF [94]53.5 9.17 25 43.6 34 8.04 58 10.0 68 48.1 56 8.48 76 8.35 17 38.3 16 6.49 45 5.08 33 99.9 66 3.45 38 12.6 53 15.4 60 9.19 46 18.1 95 41.2 15 15.5 85 6.67 72 10.6 76 7.47 84 3.00 33 16.1 67 7.74 65
TV-L1-MCT [64]54.2 9.57 32 44.7 46 8.66 71 10.9 85 48.1 56 9.11 89 11.8 43 58.1 59 6.61 46 4.74 23 99.9 66 3.34 33 12.9 65 15.2 47 9.89 67 17.8 93 47.8 30 16.0 90 5.28 30 8.09 13 7.71 89 3.33 41 7.26 29 7.53 58
IROF-TV [53]54.3 10.4 44 44.5 43 8.16 62 9.69 64 51.1 68 8.44 71 12.6 44 46.8 42 7.27 55 6.80 63 87.5 46 3.93 56 13.0 71 15.7 75 10.4 80 18.3 97 86.9 117 13.7 66 4.44 8 7.40 5 3.05 8 2.60 23 7.55 35 7.56 60
CombBMOF [113]54.4 12.5 66 41.3 18 6.50 35 8.58 41 36.9 17 6.88 36 10.9 36 35.9 14 5.21 27 10.4 82 85.0 44 5.90 93 11.6 19 15.2 47 8.15 24 27.3 122 60.9 47 35.6 136 9.20 105 14.7 127 6.75 71 3.17 36 7.53 34 4.20 28
NL-TV-NCC [25]55.3 10.7 49 40.8 15 6.45 34 8.52 40 41.1 32 6.30 30 11.2 39 93.6 94 4.18 8 5.99 47 75.9 20 4.02 60 13.2 78 16.2 103 10.1 76 16.7 81 70.9 76 16.3 94 6.56 68 9.91 57 7.05 76 4.76 65 16.9 68 3.56 17
OFH [38]55.3 12.6 67 43.4 30 9.45 84 7.30 24 64.4 91 5.27 11 27.6 80 99.9 105 4.87 23 6.60 60 99.9 66 3.74 50 12.4 41 14.7 25 9.62 55 15.5 66 74.1 82 15.6 87 4.60 9 9.39 41 4.64 28 5.39 73 26.0 83 6.68 46
COFM [59]55.5 9.37 29 55.5 110 6.86 38 7.28 22 44.2 42 6.17 27 14.3 51 47.6 45 8.22 66 4.15 15 99.9 66 2.23 5 13.2 78 16.2 103 12.2 109 17.6 89 75.4 85 15.5 85 6.20 58 8.77 23 7.35 81 3.62 49 5.35 12 6.43 43
Adaptive [20]56.4 10.2 40 46.1 58 4.95 10 9.63 61 55.4 81 7.80 47 36.7 98 99.9 105 7.64 59 6.15 52 78.7 22 2.96 19 12.1 30 14.8 30 9.09 41 12.3 30 85.8 115 6.06 2 8.72 99 12.5 107 4.97 36 3.55 46 34.8 87 9.13 79
S2F-IF [123]57.3 20.0 103 51.4 85 9.91 96 9.64 62 48.3 58 7.93 52 19.7 60 41.7 25 13.6 86 9.98 79 84.3 40 5.40 86 12.8 61 15.3 55 9.92 70 10.9 17 62.4 54 10.9 27 5.00 20 10.4 71 5.30 49 3.71 50 8.55 46 3.87 23
AggregFlow [97]57.5 13.2 69 62.1 132 6.79 37 14.9 98 73.1 101 10.6 97 26.8 78 55.1 56 20.5 99 5.48 38 99.9 66 3.67 48 12.5 47 15.0 38 7.76 17 8.55 4 38.2 8 8.90 11 5.78 47 10.6 76 4.74 33 5.43 74 8.53 45 7.58 61
FlowFields+ [130]57.6 20.3 104 52.0 89 10.3 102 10.3 73 44.8 45 8.44 71 19.5 58 40.2 21 14.1 87 10.2 81 66.6 12 6.28 98 12.8 61 15.4 60 9.97 72 10.3 10 61.8 51 10.2 20 4.85 13 10.9 84 4.79 34 3.97 55 12.8 60 3.85 22
FlowFields [110]59.1 20.3 104 52.3 91 10.2 98 10.2 70 49.0 61 8.46 74 20.3 61 40.5 22 14.7 88 10.8 87 76.6 21 6.16 96 12.9 65 15.4 60 10.0 74 11.1 18 69.9 71 11.0 29 4.97 19 8.63 20 5.12 45 4.04 59 14.0 61 3.98 24
Sparse Occlusion [54]59.2 9.98 37 41.5 23 7.82 48 9.00 46 40.5 30 8.28 68 13.5 48 85.5 88 5.96 36 5.82 42 99.9 66 3.90 54 13.0 71 15.9 81 9.77 62 13.8 44 49.9 33 12.3 45 13.6 139 15.7 135 7.81 92 3.51 43 9.05 48 6.42 42
S2D-Matching [84]59.2 9.96 35 53.0 95 8.51 69 9.53 58 53.0 71 7.94 53 20.5 62 99.9 105 6.80 49 5.30 35 83.0 24 3.53 44 12.4 41 15.2 47 9.16 44 17.3 86 41.1 14 16.8 106 7.75 88 10.5 74 7.90 94 2.36 16 6.34 19 9.58 93
Complementary OF [21]59.7 13.6 73 46.2 59 9.35 81 6.20 9 50.4 64 4.92 9 12.8 46 58.8 61 5.45 31 7.89 70 99.9 66 5.59 88 12.3 38 14.6 21 9.99 73 18.9 102 69.9 71 14.3 74 5.44 36 7.80 7 7.78 91 6.13 83 26.9 84 9.66 96
HBM-GC [105]60.4 10.9 51 57.5 120 7.03 42 9.35 50 40.2 29 8.80 83 8.09 15 52.3 51 6.42 43 6.91 65 84.3 40 6.17 97 11.8 24 14.7 25 8.40 28 14.7 55 43.2 25 12.6 49 9.81 113 17.8 143 8.50 101 3.54 45 10.1 55 10.1 100
RFlow [90]60.9 11.5 58 45.3 54 8.80 74 6.22 10 49.2 62 5.41 14 26.2 76 99.9 105 5.04 26 4.14 14 99.9 66 3.11 22 12.6 53 15.0 38 9.87 65 16.5 76 83.2 110 13.8 69 6.62 70 8.58 18 6.16 61 6.33 86 99.9 124 12.0 110
2DHMM-SAS [92]61.1 10.3 43 44.8 48 8.03 57 10.5 80 52.4 70 8.21 66 21.6 64 97.4 100 8.20 65 6.88 64 99.9 66 3.86 53 12.4 41 15.0 38 9.87 65 17.7 91 43.3 26 15.9 89 6.81 75 10.2 64 7.15 80 2.65 26 7.68 39 7.29 56
Occlusion-TV-L1 [63]62.3 10.4 44 44.9 50 6.90 39 8.77 42 53.3 73 7.54 43 33.8 93 99.9 105 7.96 60 5.88 46 99.9 66 3.48 41 13.6 98 16.3 106 10.6 84 9.50 7 80.1 92 8.60 10 6.12 56 8.69 21 4.39 21 6.52 89 99.9 124 9.37 85
SimpleFlow [49]62.4 11.3 57 46.6 61 9.79 94 10.7 83 45.0 46 9.15 90 23.1 68 99.9 105 8.38 68 8.00 72 99.9 66 3.72 49 12.7 58 15.5 70 9.36 50 16.3 72 42.6 22 15.3 84 5.91 52 9.61 46 5.39 51 2.39 18 7.08 27 9.41 89
Aniso-Texture [82]62.7 7.75 6 40.0 10 5.87 25 7.36 26 41.5 33 7.19 40 41.3 109 99.9 105 6.22 40 2.73 1 65.4 11 1.92 1 12.9 65 15.3 55 10.1 76 29.2 124 99.9 131 16.5 101 11.8 130 14.9 131 8.22 98 3.80 52 12.6 58 8.58 76
SegFlow [161]63.0 20.5 106 54.3 103 9.56 86 10.3 73 62.6 89 8.50 78 21.9 65 44.1 37 14.7 88 10.6 84 99.9 66 4.05 61 13.2 78 15.3 55 10.1 76 11.8 25 65.3 62 12.3 45 5.03 23 8.62 19 5.06 42 4.18 60 10.1 55 5.68 36
PGM-C [120]63.1 20.6 108 54.2 102 9.59 89 10.1 69 60.8 85 8.47 75 22.3 67 44.3 38 14.8 91 10.7 86 99.9 66 4.15 66 13.1 76 15.4 60 9.90 68 11.8 25 64.6 60 12.0 42 4.86 14 7.96 8 5.01 39 4.78 66 14.4 62 7.01 52
EPPM w/o HM [88]63.2 15.3 85 41.4 19 8.08 60 7.60 28 33.9 9 5.66 20 13.0 47 47.0 43 5.57 32 8.73 76 99.9 66 4.81 81 12.6 53 15.7 75 10.8 88 18.6 99 62.9 55 16.4 99 11.9 133 12.5 107 17.2 134 3.20 38 7.49 32 6.00 37
ACK-Prior [27]63.2 10.7 49 37.9 3 7.90 51 6.01 7 38.5 25 4.80 6 10.2 27 41.5 24 4.35 12 4.56 21 99.9 66 3.75 51 13.2 78 15.9 81 11.3 96 27.3 122 82.2 95 23.1 123 11.6 127 14.9 131 16.2 133 6.43 87 15.5 65 6.11 38
ROF-ND [107]65.9 12.0 61 39.9 9 8.22 65 6.49 14 45.6 47 5.49 15 13.5 48 92.7 92 4.83 22 8.05 73 23.7 3 5.54 87 14.2 113 17.5 121 11.2 94 20.1 109 72.0 78 15.0 80 13.0 137 13.3 117 10.5 115 3.52 44 6.67 24 3.36 13
ComplOF-FED-GPU [35]67.5 13.2 69 44.7 46 7.95 53 9.18 48 82.6 129 5.63 19 15.3 53 58.5 60 5.67 33 7.59 68 99.9 66 4.68 77 12.3 38 14.8 30 9.20 47 18.2 96 83.8 111 16.4 99 7.54 86 9.84 50 11.1 116 5.44 75 31.6 86 7.74 65
CPM-Flow [116]68.0 20.6 108 54.3 103 9.58 87 10.3 73 62.5 88 8.50 78 21.9 65 43.8 35 14.7 88 10.6 84 99.9 66 4.06 62 13.2 78 15.4 60 9.85 64 12.6 33 68.9 68 13.3 59 5.02 22 9.16 35 5.04 41 5.27 70 19.2 70 9.63 95
EpicFlow [102]69.1 20.6 108 54.1 101 9.59 89 10.3 73 62.9 90 8.55 81 26.3 77 99.4 104 15.1 93 10.4 82 99.9 66 4.07 63 13.1 76 15.4 60 9.90 68 11.6 22 67.3 65 11.9 41 4.86 14 7.97 9 4.99 37 5.34 72 19.2 70 9.74 98
SRR-TVOF-NL [91]69.5 14.4 81 46.7 62 8.18 64 13.1 92 74.0 103 8.44 71 24.1 72 63.2 65 11.9 80 6.51 59 85.1 45 3.25 25 12.1 30 15.0 38 10.3 79 17.5 87 61.6 49 13.4 62 10.4 119 12.3 104 8.92 104 5.52 76 7.83 41 7.58 61
DMF_ROB [139]70.0 16.2 89 49.6 81 9.96 97 9.93 67 75.9 105 7.56 44 30.5 86 99.9 105 11.8 78 16.5 104 99.9 66 4.36 71 12.6 53 14.9 34 9.62 55 12.9 35 76.3 87 11.5 33 4.68 10 8.80 24 5.10 44 7.02 97 91.0 121 9.62 94
Steered-L1 [118]70.5 9.19 26 36.3 2 6.06 29 4.59 1 39.2 26 4.30 1 9.30 23 52.3 51 4.57 14 4.86 29 99.9 66 3.30 31 13.6 98 15.9 81 12.3 110 24.7 121 77.0 88 20.2 116 15.1 143 13.7 122 40.0 145 14.7 122 91.5 122 20.9 124
DeepFlow2 [108]71.0 14.3 78 47.4 68 7.03 42 10.4 78 77.1 108 8.01 55 23.3 69 99.9 105 11.8 78 16.1 100 99.9 66 4.41 73 12.4 41 15.0 38 8.16 25 13.4 37 68.4 66 14.2 71 5.65 41 9.07 31 8.50 101 8.52 105 92.9 123 10.6 104
TCOF [69]71.0 13.6 73 44.8 48 8.02 56 9.90 66 54.6 77 8.02 56 31.3 89 99.9 105 15.4 95 6.49 58 82.4 23 4.76 79 14.9 123 18.0 129 9.50 52 9.71 8 48.3 32 12.6 49 10.1 115 12.7 109 8.96 105 4.29 61 9.21 49 6.80 48
DPOF [18]72.1 17.4 98 49.1 76 7.77 47 12.3 88 45.6 47 8.91 86 10.9 36 26.6 4 8.09 63 7.81 69 99.3 65 5.31 83 13.5 94 16.0 92 11.0 91 17.5 87 61.8 51 12.2 44 13.1 138 10.9 84 18.1 137 5.04 68 9.50 52 4.49 31
Aniso. Huber-L1 [22]73.8 11.7 59 43.8 36 8.16 62 13.6 94 66.3 93 12.0 100 35.9 96 99.9 105 10.5 71 10.0 80 72.9 14 5.00 82 13.4 89 16.3 106 9.61 54 15.1 61 63.7 58 7.96 7 8.96 102 11.6 96 7.95 96 4.02 57 26.9 84 7.97 69
F-TV-L1 [15]74.0 15.6 86 47.4 68 13.4 112 18.8 108 99.1 139 11.6 98 43.1 113 99.9 105 11.3 77 14.7 96 99.9 66 7.03 102 12.2 34 14.9 34 9.00 38 13.5 40 99.9 131 7.56 6 6.41 62 10.5 74 4.23 17 3.91 54 80.3 101 3.38 15
TF+OM [100]74.1 12.1 63 51.3 84 7.13 44 8.92 45 44.4 43 8.13 62 33.8 93 54.4 54 45.8 120 6.28 54 90.1 52 4.63 76 12.7 58 15.2 47 10.6 84 18.9 102 99.9 131 11.3 31 7.81 89 14.2 124 6.33 65 7.09 98 43.5 89 8.22 71
LiteFlowNet [142]74.6 24.0 122 51.5 87 13.3 111 11.7 87 43.1 39 9.98 93 21.5 63 47.6 45 13.0 82 10.9 89 71.9 13 6.87 101 13.3 87 16.2 103 11.5 99 18.7 100 52.2 36 16.7 104 6.18 57 9.32 39 4.21 16 5.83 80 24.4 81 7.46 57
FF++_ROB [145]75.5 21.4 114 55.5 110 10.2 98 10.6 82 54.1 75 8.70 82 24.1 72 59.5 62 16.2 97 11.5 91 74.8 18 7.42 105 13.0 71 15.7 75 10.6 84 14.7 55 70.0 73 13.7 66 5.31 33 8.76 22 7.53 86 4.57 63 14.8 63 13.9 114
TV-L1-improved [17]78.2 10.9 51 45.2 53 7.42 45 8.12 35 54.0 74 6.79 34 36.5 97 99.9 105 7.26 54 5.84 44 99.9 66 3.15 23 13.2 78 15.9 81 9.11 42 22.1 115 99.9 131 20.8 117 9.59 111 13.3 117 9.04 106 6.19 84 88.8 117 9.71 97
SIOF [67]79.2 10.6 48 49.7 82 7.01 41 14.8 97 85.9 132 8.40 69 49.7 122 98.3 101 49.2 123 12.0 92 99.9 66 5.88 91 13.5 94 15.9 81 10.8 88 16.3 72 74.2 83 13.6 65 5.51 38 9.02 28 4.42 24 6.52 89 19.5 75 9.85 99
CompactFlow_ROB [160]80.6 34.2 136 63.6 135 16.6 122 19.0 110 46.3 52 18.4 115 37.1 99 62.7 64 45.3 119 15.6 99 99.9 66 10.6 115 13.6 98 16.3 106 11.1 93 14.1 49 64.2 59 12.8 53 4.96 18 8.13 14 2.28 3 5.98 82 22.2 78 6.91 49
DeepFlow [86]80.7 14.7 82 49.0 75 9.78 93 12.9 90 79.3 112 9.80 92 30.1 83 96.1 98 24.4 105 21.4 112 99.9 66 5.36 85 12.5 47 15.1 45 8.59 29 14.0 48 71.9 77 15.1 83 5.46 37 8.01 10 8.73 103 14.2 120 99.9 124 15.7 120
CRTflow [80]80.7 15.0 83 46.3 60 7.89 50 8.87 44 54.9 79 7.15 38 30.1 83 99.9 105 8.03 61 9.30 78 99.9 66 4.50 75 13.0 71 15.7 75 8.05 23 32.5 128 99.9 131 34.3 135 6.62 70 9.72 48 7.52 85 9.30 109 99.9 124 14.7 116
Brox et al. [5]80.8 16.0 87 49.2 78 12.0 108 12.3 88 80.4 113 10.3 95 23.7 71 73.1 70 13.2 83 24.2 114 99.9 66 4.23 69 14.7 120 16.8 114 15.4 133 10.7 13 96.7 124 9.71 17 5.88 51 9.05 29 3.01 7 8.78 106 67.7 97 9.37 85
LocallyOriented [52]81.8 17.0 97 55.7 112 8.00 55 17.0 105 82.3 128 12.1 101 42.4 112 99.9 105 14.8 91 9.13 77 89.2 51 4.79 80 13.4 89 16.1 97 9.20 47 10.8 14 58.1 43 11.8 38 6.89 76 10.6 76 7.14 79 7.78 103 74.9 98 9.42 90
BriefMatch [124]83.5 9.63 33 44.4 40 5.74 21 7.64 29 51.0 67 5.70 22 10.5 30 39.2 18 4.63 17 3.95 13 99.9 66 2.72 11 16.2 134 17.6 125 33.0 146 41.4 140 99.4 130 43.4 142 12.7 136 13.2 115 67.6 149 79.5 140 99.9 124 99.9 155
Dynamic MRF [7]84.8 14.0 77 50.7 83 9.58 87 7.75 32 85.7 131 5.76 23 31.5 90 99.9 105 5.23 28 7.97 71 99.9 66 4.10 65 13.0 71 15.6 73 10.7 87 30.4 127 99.9 131 29.5 132 5.64 40 7.52 6 9.61 109 67.3 138 99.9 124 66.7 138
Classic++ [32]85.0 11.2 55 49.4 80 9.13 77 9.34 49 68.4 96 8.11 60 30.7 87 95.1 97 10.2 70 5.59 39 99.9 66 3.47 39 13.5 94 16.1 97 10.4 80 19.7 106 99.9 131 17.6 111 8.38 95 11.5 95 8.30 100 7.20 101 99.9 124 9.54 92
ContinualFlow_ROB [152]85.8 30.9 130 63.0 134 13.9 114 22.3 114 47.9 55 20.9 117 34.2 95 99.9 105 31.9 110 13.3 93 99.9 66 7.83 108 13.7 104 16.5 111 11.4 97 21.5 112 70.6 75 21.3 120 4.20 4 10.3 67 2.80 5 4.01 56 8.59 47 3.70 20
ResPWCR_ROB [144]86.4 23.4 120 46.7 62 16.7 124 14.7 96 42.9 36 13.2 103 23.4 70 48.7 47 22.0 102 16.4 103 84.5 42 11.3 119 13.2 78 15.8 79 12.6 115 15.2 63 72.1 79 16.3 94 9.13 104 12.3 104 7.37 82 7.09 98 17.6 69 9.31 84
Rannacher [23]87.1 13.8 76 47.5 70 10.8 105 10.5 80 62.0 87 8.84 84 41.1 108 99.9 105 11.0 75 8.49 74 99.9 66 4.28 70 13.5 94 16.1 97 9.72 61 22.5 117 99.9 131 17.0 107 7.66 87 9.88 55 7.82 93 4.72 64 75.1 99 9.37 85
SuperFlow [81]87.5 14.3 78 47.0 67 9.26 79 19.5 112 58.7 84 17.9 112 45.9 116 99.9 105 56.1 126 19.0 110 99.9 66 5.88 91 13.3 87 16.1 97 12.6 115 11.5 21 74.0 81 8.27 8 9.24 106 12.9 111 4.70 32 8.27 104 89.2 119 8.28 72
CBF [12]87.7 12.2 65 41.4 19 8.65 70 16.5 102 47.1 54 16.6 110 24.7 74 88.1 90 12.9 81 11.0 90 99.9 66 4.18 67 14.9 123 17.5 121 14.0 128 15.0 60 79.8 91 8.97 12 14.9 142 15.1 133 15.9 132 5.78 78 63.0 96 10.1 100
AugFNG_ROB [143]88.3 34.3 137 65.6 139 20.9 130 25.8 118 66.4 94 24.3 121 40.9 106 99.9 105 40.6 115 15.2 98 96.0 60 9.61 111 13.4 89 15.6 73 12.3 110 15.1 61 73.5 80 14.2 71 5.29 31 11.2 90 2.87 6 5.30 71 19.4 72 4.51 32
p-harmonic [29]89.3 15.1 84 48.5 71 14.1 115 10.4 78 53.1 72 9.31 91 41.9 110 99.9 105 15.1 93 19.4 111 99.9 66 10.6 115 12.7 58 14.9 34 11.8 101 18.0 94 85.6 114 18.4 114 7.85 90 10.4 71 5.46 53 6.98 96 99.9 124 9.28 83
CLG-TV [48]90.0 12.1 63 43.5 32 9.42 83 14.1 95 60.9 86 13.2 103 33.2 92 99.9 105 11.2 76 10.8 87 84.7 43 5.82 90 14.8 122 17.9 127 12.1 107 13.8 44 99.9 131 11.3 31 10.9 121 14.2 124 9.22 107 6.69 93 99.9 124 8.52 74
Local-TV-L1 [65]90.1 16.5 92 52.3 91 11.7 107 27.7 120 96.9 136 22.5 119 68.8 130 99.9 105 47.5 121 34.6 124 99.9 66 7.04 103 12.6 53 15.0 38 9.25 49 17.7 91 84.7 112 13.7 66 5.09 24 7.36 4 5.03 40 20.7 125 88.8 117 29.4 130
TriFlow [95]90.2 16.1 88 57.1 118 7.97 54 13.3 93 65.2 92 12.3 102 48.8 119 99.9 105 61.8 130 7.03 66 91.4 54 5.33 84 13.4 89 15.3 55 11.4 97 14.3 53 76.1 86 13.3 59 22.7 148 14.3 126 26.7 141 5.93 81 11.8 57 7.86 68
FlowNet2 [122]90.2 32.0 133 68.0 145 14.9 117 35.2 125 77.9 111 29.8 130 32.9 91 51.2 49 35.4 113 16.3 101 99.9 66 10.5 114 13.2 78 15.9 81 12.0 103 14.1 49 99.9 131 10.8 23 8.84 101 20.1 145 4.66 29 4.49 62 9.46 51 3.65 18
EAI-Flow [151]90.8 25.2 123 57.0 117 16.6 122 19.3 111 76.7 106 14.1 107 29.6 82 51.5 50 22.8 103 23.6 113 93.8 57 10.3 113 12.8 61 16.0 92 10.4 80 15.6 67 74.4 84 14.4 76 12.6 135 11.3 91 6.90 74 5.08 69 20.5 77 8.20 70
OFRF [134]91.2 13.1 68 58.6 124 9.77 92 49.6 138 99.9 140 43.7 139 49.2 120 99.9 105 32.0 111 16.3 101 96.4 61 10.0 112 12.1 30 14.7 25 7.87 19 14.9 59 43.6 27 13.3 59 8.66 98 12.0 101 11.8 124 21.9 128 19.7 76 36.6 132
DF-Auto [115]91.5 20.5 106 55.9 114 9.21 78 22.7 115 74.8 104 19.3 116 44.7 115 93.5 93 57.8 128 27.1 118 99.9 66 5.70 89 15.0 126 18.9 139 11.8 101 7.13 2 57.9 42 7.09 4 10.2 118 13.9 123 4.23 17 8.94 107 54.0 94 9.21 82
SegOF [10]92.0 22.8 119 54.8 105 15.4 119 27.9 121 56.0 82 27.4 125 39.3 101 87.9 89 33.2 112 37.5 125 75.4 19 22.3 125 14.4 117 16.3 106 14.7 131 21.7 113 99.9 131 24.5 125 4.09 3 7.28 2 2.18 2 6.79 94 48.3 92 6.93 50
EPMNet [133]92.4 29.4 129 62.1 132 16.4 121 36.2 126 95.3 135 29.0 129 30.2 85 47.4 44 30.9 109 18.3 107 99.9 66 11.1 117 13.2 78 15.9 81 12.0 103 14.1 49 99.9 131 10.8 23 8.19 93 16.9 141 4.18 15 6.63 92 19.4 72 6.18 39
TriangleFlow [30]92.8 13.2 69 46.8 65 9.41 82 10.8 84 73.2 102 7.30 42 26.1 75 99.9 105 5.70 34 7.23 67 99.9 66 4.46 74 17.0 139 21.3 144 15.2 132 23.0 118 69.8 70 22.9 122 9.71 112 16.1 136 9.40 108 6.89 95 23.8 79 11.5 108
Bartels [41]93.3 13.3 72 55.0 106 10.2 98 8.13 36 43.2 40 7.67 45 18.1 56 69.0 69 6.30 42 8.49 74 99.9 66 6.05 95 13.9 107 16.1 97 13.9 126 21.8 114 99.9 131 21.5 121 10.6 120 13.5 119 20.3 139 12.3 115 99.9 124 26.9 128
Fusion [6]94.0 16.3 90 53.8 99 12.5 109 7.93 33 37.7 20 7.75 46 15.6 54 41.8 26 13.2 83 13.5 94 83.1 25 7.77 107 15.4 128 18.5 133 14.2 130 33.1 129 89.0 118 24.8 127 11.8 130 14.7 127 8.27 99 11.4 113 99.9 124 13.3 112
WOLF_ROB [148]94.6 21.5 115 55.2 108 10.2 98 37.6 128 99.9 140 17.3 111 54.7 125 99.9 105 23.9 104 25.1 115 99.9 66 12.8 120 12.8 61 15.4 60 11.2 94 18.5 98 61.8 51 17.2 108 5.80 49 9.26 38 6.20 63 11.4 113 24.3 80 15.7 120
LFNet_ROB [149]97.7 28.9 128 53.4 97 17.2 125 15.3 100 46.9 53 13.7 106 31.0 88 96.3 99 21.7 101 18.4 108 92.1 55 14.4 122 13.7 104 16.6 112 12.0 103 18.8 101 90.4 120 16.7 104 6.48 65 10.9 84 5.97 59 6.22 85 99.9 124 10.3 102
CNN-flow-warp+ref [117]98.5 21.3 113 57.3 119 15.1 118 16.8 104 54.4 76 15.9 109 41.0 107 99.9 105 28.8 106 28.6 120 99.9 66 7.45 106 14.0 110 15.9 81 14.0 128 16.5 76 84.8 113 10.9 27 5.30 32 8.23 16 8.13 97 99.9 155 99.9 124 99.9 155
StereoFlow [44]99.3 48.0 146 74.6 163 41.1 147 61.0 143 99.9 140 51.6 142 71.4 131 99.9 105 63.9 132 65.6 140 99.9 66 61.2 140 16.2 134 15.9 81 22.6 140 7.22 3 77.8 90 7.39 5 3.38 1 7.35 3 1.99 1 7.18 100 99.9 124 11.4 107
LDOF [28]99.6 17.9 101 53.5 98 8.72 72 18.7 107 92.6 134 11.8 99 29.5 81 67.1 68 20.9 100 29.0 121 99.9 66 8.92 110 14.2 113 16.4 110 13.7 123 18.9 102 97.5 128 15.0 80 6.26 61 10.3 67 10.1 112 10.4 111 99.9 124 10.3 102
FlowNetS+ft+v [112]100.5 16.5 92 52.1 90 8.06 59 17.4 106 76.9 107 13.4 105 46.3 117 99.9 105 30.4 108 29.8 122 99.9 66 13.8 121 15.5 129 18.5 133 13.8 125 12.7 34 89.5 119 11.7 37 9.24 106 13.5 119 12.1 125 7.39 102 57.9 95 9.52 91
Shiralkar [42]101.1 16.8 95 44.6 44 9.46 85 16.5 102 98.8 138 8.05 58 42.0 111 99.9 105 10.8 74 18.4 108 99.9 66 8.02 109 12.9 65 15.5 70 10.4 80 30.2 126 99.9 131 25.1 128 11.4 126 11.8 99 15.8 131 22.2 129 99.9 124 17.5 123
StereoOF-V1MT [119]101.3 16.5 92 46.0 57 9.27 80 18.9 109 99.9 140 7.16 39 40.5 104 99.9 105 8.18 64 14.7 96 96.4 61 6.30 99 14.1 112 16.8 114 12.9 118 29.9 125 91.4 121 27.0 130 5.78 47 10.4 71 10.4 114 99.9 155 99.9 124 99.9 155
Learning Flow [11]102.0 13.7 75 52.8 93 7.67 46 12.9 90 87.1 133 10.0 94 40.5 104 95.0 96 13.4 85 38.1 126 99.9 66 4.74 78 17.1 141 21.7 145 12.5 114 24.2 120 99.9 131 13.5 64 7.95 91 12.7 109 6.98 75 23.9 131 99.9 124 14.9 117
Filter Flow [19]103.1 21.6 117 57.7 121 14.4 116 24.6 117 77.5 110 18.1 113 54.3 124 80.8 72 66.3 136 52.8 133 91.0 53 46.5 134 13.6 98 16.0 92 12.3 110 17.0 84 69.6 69 14.2 71 12.0 134 16.1 136 7.39 83 6.58 91 37.5 88 8.36 73
Ad-TV-NDC [36]103.3 31.0 131 53.3 96 33.1 143 70.2 144 99.9 140 49.0 141 93.2 156 99.9 105 54.0 125 38.9 127 95.0 58 29.4 128 13.8 106 17.3 120 8.71 30 14.7 55 77.1 89 13.0 56 6.24 59 9.84 50 5.19 48 46.4 136 76.4 100 54.0 136
Second-order prior [8]103.7 14.3 78 46.7 62 8.79 73 15.2 99 72.5 100 10.5 96 39.2 100 99.9 105 16.6 98 17.5 105 99.9 66 6.01 94 14.4 117 17.5 121 10.8 88 38.6 138 99.9 131 24.7 126 11.3 124 12.2 102 11.2 118 9.13 108 89.5 120 15.6 119
TVL1_ROB [138]106.2 31.2 132 59.9 129 29.1 139 48.6 137 99.9 140 41.9 137 91.6 155 99.9 105 71.5 139 52.0 132 99.9 66 44.1 133 14.2 113 16.9 116 12.0 103 14.2 52 99.9 131 13.2 58 4.83 11 9.14 34 3.56 10 21.0 126 99.9 124 22.5 126
GraphCuts [14]106.5 21.7 118 52.8 93 10.4 103 39.2 130 99.9 140 23.1 120 39.7 103 58.0 58 49.6 124 25.6 117 74.6 17 7.31 104 13.6 98 15.9 81 13.2 121 37.8 135 97.6 129 16.2 91 9.36 109 11.4 92 11.7 122 10.3 110 99.9 124 15.0 118
IAOF2 [51]108.0 16.8 95 59.5 127 10.5 104 20.1 113 69.0 98 18.1 113 53.3 123 99.9 105 56.8 127 55.3 137 95.0 58 54.7 138 14.2 113 17.2 119 11.0 91 19.2 105 81.1 93 14.3 74 11.8 130 13.2 115 13.0 128 13.5 117 45.0 90 9.00 78
2D-CLG [1]108.3 46.1 144 67.5 144 28.2 138 39.5 131 77.3 109 38.9 133 93.9 158 99.9 105 74.9 143 53.6 134 99.9 66 51.0 136 13.9 107 15.9 81 13.5 122 24.0 119 99.9 131 21.2 118 4.28 6 7.24 1 4.50 25 12.7 116 99.9 124 11.6 109
HBpMotionGpu [43]108.8 19.5 102 63.6 135 13.5 113 31.0 122 99.9 140 27.4 125 99.9 161 99.9 105 59.3 129 18.2 106 99.9 66 6.69 100 13.6 98 16.0 92 12.4 113 16.2 70 91.5 122 11.1 30 11.1 122 13.0 114 6.73 70 21.3 127 99.9 124 21.6 125
SPSA-learn [13]110.1 23.6 121 55.7 112 20.1 129 32.9 124 99.9 140 25.2 122 91.2 154 99.9 105 64.5 134 49.6 130 99.9 66 31.2 129 14.0 110 16.0 92 13.0 120 19.9 107 99.9 131 23.3 124 6.53 67 9.13 33 4.40 23 15.8 123 99.9 124 16.5 122
Modified CLG [34]111.5 27.9 126 58.6 124 23.4 133 26.5 119 71.1 99 26.2 124 93.4 157 99.9 105 73.1 141 49.2 129 99.9 66 22.6 126 15.2 127 18.1 130 13.7 123 16.3 72 99.9 131 12.8 53 6.43 64 10.2 64 11.7 122 11.3 112 99.9 124 11.3 106
UnFlow [129]113.0 49.8 147 69.9 160 23.3 132 32.8 123 57.8 83 33.0 131 49.4 121 98.6 102 39.8 114 53.6 134 99.9 66 52.1 137 16.2 134 18.5 133 20.6 137 35.3 132 99.9 131 38.4 138 8.81 100 11.4 92 3.08 9 6.46 88 99.9 124 6.47 44
IAOF [50]113.1 20.6 108 55.0 106 17.4 126 36.6 127 99.9 140 27.6 127 99.9 161 99.9 105 75.5 144 32.7 123 93.3 56 25.5 127 13.9 107 16.6 112 12.1 107 36.5 133 92.3 123 12.3 45 9.40 110 11.7 97 7.13 78 26.2 132 47.4 91 28.8 129
GroupFlow [9]115.6 27.3 125 66.8 142 21.6 131 41.1 132 99.9 140 35.1 132 71.4 131 99.9 105 61.8 130 25.1 115 99.9 66 14.4 122 14.7 120 17.9 127 11.7 100 40.6 139 97.2 127 40.6 140 5.72 44 11.7 97 6.48 66 16.4 124 53.8 93 23.0 127
Black & Anandan [4]116.2 21.5 115 51.7 88 19.8 128 38.6 129 99.9 140 25.8 123 81.3 135 99.9 105 65.5 135 50.4 131 99.9 66 31.6 130 15.5 129 19.1 140 12.8 117 22.4 116 96.8 126 18.2 113 10.1 115 12.4 106 5.16 47 13.9 119 99.9 124 12.9 111
Nguyen [33]117.1 27.2 124 56.2 115 18.7 127 46.7 136 99.9 140 44.1 140 97.7 160 99.9 105 74.1 142 45.7 128 99.9 66 38.0 131 16.4 137 17.7 126 21.8 139 20.8 110 99.9 131 21.2 118 7.21 80 9.42 42 5.61 54 14.6 121 99.9 124 14.2 115
2bit-BM-tele [98]119.4 20.8 112 59.0 126 16.3 120 16.4 101 68.5 97 15.3 108 43.9 114 99.9 105 15.4 95 14.6 95 99.9 66 11.2 118 15.6 131 17.5 121 16.8 135 34.9 131 99.9 131 31.1 133 18.8 146 20.4 147 30.8 142 23.7 130 99.9 124 61.9 137
BlockOverlap [61]120.7 17.6 100 56.5 116 13.1 110 24.0 116 66.9 95 21.5 118 67.6 129 99.9 105 49.0 122 28.2 119 99.9 66 15.2 124 17.6 143 18.3 131 32.7 145 38.1 136 81.6 94 26.6 129 14.5 140 15.5 134 67.6 149 39.8 134 82.5 102 84.7 139
Heeger++ [104]124.7 33.0 134 58.3 123 23.6 134 60.7 141 99.9 140 39.4 134 59.1 126 99.9 105 30.1 107 86.5 161 99.9 66 70.5 142 14.9 123 17.1 117 12.9 118 76.5 147 99.9 131 79.8 147 7.49 85 12.9 111 6.59 67 99.9 155 99.9 124 99.9 155
Horn & Schunck [3]125.8 28.8 127 57.7 121 25.3 135 41.1 132 99.9 140 28.2 128 80.0 134 99.9 105 75.9 145 75.5 141 99.9 66 66.3 141 15.7 132 18.5 133 13.9 126 41.9 141 99.9 131 41.4 141 11.6 127 13.6 121 6.16 61 45.4 135 99.9 124 39.5 133
SILK [79]126.0 33.3 135 64.6 137 29.2 141 46.3 134 99.9 140 39.4 134 95.0 159 99.9 105 66.5 137 56.7 138 99.9 66 50.2 135 16.1 133 18.7 137 17.2 136 48.7 142 99.9 131 37.3 137 7.26 82 9.22 36 14.5 130 70.9 139 99.9 124 51.7 135
H+S_ROB [137]127.0 50.3 148 65.4 138 33.8 144 46.6 135 99.9 140 43.6 138 78.1 133 99.9 105 71.7 140 95.5 162 99.9 66 91.4 162 24.6 148 28.4 148 32.4 144 80.6 148 99.9 131 83.7 163 5.16 28 9.70 47 5.15 46 99.9 155 99.9 124 95.7 154
TI-DOFE [24]129.1 40.2 140 61.2 131 38.6 146 60.2 140 99.9 140 53.7 143 90.4 153 99.9 105 78.2 147 83.9 159 99.9 66 82.8 160 16.6 138 19.4 142 16.4 134 38.1 136 99.9 131 38.7 139 8.51 97 10.3 67 7.75 90 56.3 137 99.9 124 49.7 134
HCIC-L [99]130.8 44.4 143 66.7 141 29.1 139 99.9 162 99.9 140 99.9 162 47.8 118 99.9 105 44.6 118 58.5 139 99.9 66 55.7 139 20.3 145 20.6 143 24.0 142 33.9 130 86.5 116 33.6 134 38.0 150 49.5 150 36.0 143 13.7 118 25.8 82 13.7 113
AdaConv-v1 [126]133.6 66.7 151 69.5 146 54.6 149 80.0 146 82.0 114 79.5 147 81.7 136 82.0 73 80.9 148 82.3 144 83.1 25 82.6 146 85.8 149 85.9 149 85.2 149 88.2 150 83.0 96 82.9 149 75.7 152 67.1 152 77.8 152 85.1 141 86.4 103 84.8 140
SepConv-v1 [127]133.6 66.7 151 69.5 146 54.6 149 80.0 146 82.0 114 79.5 147 81.7 136 82.0 73 80.9 148 82.3 144 83.1 25 82.6 146 85.8 149 85.9 149 85.2 149 88.2 150 83.0 96 82.9 149 75.7 152 67.1 152 77.8 152 85.1 141 86.4 103 84.8 140
SuperSlomo [132]133.6 66.7 151 69.5 146 54.6 149 80.0 146 82.0 114 79.5 147 81.7 136 82.0 73 80.9 148 82.3 144 83.1 25 82.6 146 85.8 149 85.9 149 85.2 149 88.2 150 83.0 96 82.9 149 75.7 152 67.1 152 77.8 152 85.1 141 86.4 103 84.8 140
CtxSyn [136]133.6 66.7 151 69.5 146 54.6 149 80.0 146 82.0 114 79.5 147 81.7 136 82.0 73 80.9 148 82.3 144 83.1 25 82.6 146 85.8 149 85.9 149 85.2 149 88.2 150 83.0 96 82.9 149 75.7 152 67.1 152 77.8 152 85.1 141 86.4 103 84.8 140
CyclicGen [153]133.6 66.7 151 69.5 146 54.6 149 80.0 146 82.0 114 79.5 147 81.7 136 82.0 73 80.9 148 82.3 144 83.1 25 82.6 146 85.8 149 85.9 149 85.2 149 88.2 150 83.0 96 82.9 149 75.7 152 67.1 152 77.8 152 85.1 141 86.4 103 84.8 140
TOF-M [154]133.6 66.7 151 69.5 146 54.6 149 80.0 146 82.0 114 79.5 147 81.7 136 82.0 73 80.9 148 82.3 144 83.1 25 82.6 146 85.8 149 85.9 149 85.2 149 88.2 150 83.0 96 82.9 149 75.7 152 67.1 152 77.8 152 85.1 141 86.4 103 84.8 140
MEMC-Net+ [155]133.6 66.7 151 69.5 146 54.6 149 80.0 146 82.0 114 79.5 147 81.7 136 82.0 73 80.9 148 82.3 144 83.1 25 82.6 146 85.8 149 85.9 149 85.2 149 88.2 150 83.0 96 82.9 149 75.7 152 67.1 152 77.8 152 85.1 141 86.4 103 84.8 140
MPRN [156]133.6 66.7 151 69.5 146 54.6 149 80.0 146 82.0 114 79.5 147 81.7 136 82.0 73 80.9 148 82.3 144 83.1 25 82.6 146 85.8 149 85.9 149 85.2 149 88.2 150 83.0 96 82.9 149 75.7 152 67.1 152 77.8 152 85.1 141 86.4 103 84.8 140
DAIN [157]133.6 66.7 151 69.5 146 54.6 149 80.0 146 82.0 114 79.5 147 81.7 136 82.0 73 80.9 148 82.3 144 83.1 25 82.6 146 85.8 149 85.9 149 85.2 149 88.2 150 83.0 96 82.9 149 75.7 152 67.1 152 77.8 152 85.1 141 86.4 103 84.8 140
InterpCNN [158]133.6 66.7 151 69.5 146 54.6 149 80.0 146 82.0 114 79.5 147 81.7 136 82.0 73 80.9 148 82.3 144 83.1 25 82.6 146 85.8 149 85.9 149 85.2 149 88.2 150 83.0 96 82.9 149 75.7 152 67.1 152 77.8 152 85.1 141 86.4 103 84.8 140
OFRI [159]133.6 66.7 151 69.5 146 54.6 149 80.0 146 82.0 114 79.5 147 81.7 136 82.0 73 80.9 148 82.3 144 83.1 25 82.6 146 85.8 149 85.9 149 85.2 149 88.2 150 83.0 96 82.9 149 75.7 152 67.1 152 77.8 152 85.1 141 86.4 103 84.8 140
PyrWarp [162]133.6 66.7 151 69.5 146 54.6 149 80.0 146 82.0 114 79.5 147 81.7 136 82.0 73 80.9 148 82.3 144 83.1 25 82.6 146 85.8 149 85.9 149 85.2 149 88.2 150 83.0 96 82.9 149 75.7 152 67.1 152 77.8 152 85.1 141 86.4 103 84.8 140
FGME [164]133.6 66.7 151 69.5 146 54.6 149 80.0 146 82.0 114 79.5 147 81.7 136 82.0 73 80.9 148 82.3 144 83.1 25 82.6 146 85.8 149 85.9 149 85.2 149 88.2 150 83.0 96 82.9 149 75.7 152 67.1 152 77.8 152 85.1 141 86.4 103 84.8 140
MS-PFT [165]133.6 66.7 151 69.5 146 54.6 149 80.0 146 82.0 114 79.5 147 81.7 136 82.0 73 80.9 148 82.3 144 83.1 25 82.6 146 85.8 149 85.9 149 85.2 149 88.2 150 83.0 96 82.9 149 75.7 152 67.1 152 77.8 152 85.1 141 86.4 103 84.8 140
FFV1MT [106]134.5 36.4 139 71.0 161 25.8 136 50.3 139 99.9 140 39.7 136 65.6 128 99.1 103 41.6 117 99.9 163 99.9 66 97.4 164 20.2 144 19.3 141 33.1 147 62.5 144 99.9 131 71.1 146 9.04 103 14.8 129 11.2 118 99.9 155 99.9 124 99.9 155
PGAM+LK [55]135.3 43.6 141 67.1 143 43.7 148 73.8 145 99.9 140 77.5 145 61.9 127 82.9 87 63.9 132 76.6 142 99.9 66 72.5 143 17.1 141 17.1 117 31.6 143 66.2 145 99.9 131 64.8 145 18.9 147 20.3 146 22.1 140 99.9 155 99.9 124 99.9 155
SLK [47]135.5 53.1 149 66.3 140 59.5 164 60.9 142 98.1 137 58.6 144 89.7 151 99.9 105 67.7 138 99.9 163 99.9 66 95.1 163 17.0 139 18.8 138 23.5 141 56.6 143 99.9 131 51.2 143 8.43 96 11.9 100 12.2 126 99.9 155 99.9 124 99.9 155
Adaptive flow [45]135.8 34.4 138 59.7 128 29.7 142 84.5 160 99.9 140 77.7 146 87.6 150 99.9 105 92.8 163 54.9 136 99.9 66 39.3 132 20.6 146 23.8 147 20.9 138 37.5 134 96.7 124 29.2 131 35.2 149 30.1 149 58.6 148 38.1 133 99.9 124 33.0 131
FOLKI [16]142.2 43.8 142 74.4 162 38.0 145 99.9 162 99.9 140 99.9 162 89.7 151 99.9 105 76.2 146 85.0 160 99.9 66 81.0 145 23.2 147 22.5 146 38.8 148 66.2 145 99.9 131 62.7 144 17.0 145 17.6 142 42.6 146 99.9 155 99.9 124 99.9 155
Periodicity [78]142.4 54.4 150 84.3 164 26.5 137 99.9 162 99.9 140 99.9 162 99.9 161 99.9 105 99.9 164 81.4 143 99.9 66 76.3 144 99.9 164 99.9 163 99.9 164 99.9 164 99.9 131 99.9 164 6.06 55 14.8 129 70.6 151 99.9 155 99.9 124 99.9 155
Pyramid LK [2]145.5 47.7 145 60.7 130 56.1 163 88.6 161 99.9 140 91.9 161 99.9 161 99.9 105 89.4 162 83.0 158 99.9 66 83.2 161 98.4 163 99.9 163 87.9 163 87.4 149 99.9 131 81.4 148 16.9 144 16.6 138 57.0 147 99.9 155 99.9 124 99.9 155
AVG_FLOW_ROB [141]150.5 99.9 165 99.9 165 99.9 165 99.9 162 99.9 140 99.9 162 99.9 161 99.9 105 99.9 164 99.9 163 99.9 66 99.9 165 99.9 164 99.9 163 99.9 164 99.9 164 99.9 131 99.9 164 48.6 151 52.0 151 38.2 144 99.9 155 99.9 124 99.9 155
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.