Optical flow evaluation results Statistics:     Average   SD   R0.5   R1.0   R2.0   A50   A75   A95  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
R2.0
endpoint
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]5.7 0.19 27 1.11 31 0.00 1 0.73 3 5.01 3 0.12 2 1.08 3 3.84 2 0.00 1 0.54 6 4.91 7 0.02 4 4.35 2 7.43 2 0.89 2 1.53 1 8.39 2 1.54 3 0.00 1 0.00 1 0.00 1 3.65 9 12.4 20 1.32 2
PMMST [114]9.7 0.20 34 1.20 41 0.03 58 0.57 1 4.20 1 0.21 11 1.12 4 3.98 4 0.06 5 0.16 3 1.79 3 0.00 1 6.17 4 10.4 4 2.09 5 2.24 3 10.3 5 3.42 25 0.00 1 0.00 1 0.00 1 3.14 4 10.1 6 3.34 7
NN-field [71]11.7 0.23 60 1.37 62 0.00 1 0.64 2 4.87 2 0.07 1 1.23 7 4.31 5 0.03 3 0.60 8 5.03 8 0.04 5 4.24 1 7.24 1 0.70 1 5.93 55 6.73 1 2.33 10 0.00 1 0.00 1 0.00 1 3.87 12 13.1 32 1.27 1
OFLAF [77]13.2 0.20 34 1.21 42 0.00 1 0.92 9 5.66 7 0.25 16 1.22 5 4.32 6 0.12 10 1.03 21 8.42 24 0.22 31 7.31 10 12.4 10 2.79 9 3.20 13 11.6 7 3.15 21 0.00 1 0.00 1 0.00 1 3.66 10 9.73 5 7.15 24
ComponentFusion [96]19.0 0.17 15 1.02 19 0.03 58 0.93 10 6.31 11 0.23 15 1.48 10 5.26 10 0.22 17 0.68 9 6.90 16 0.05 6 10.5 43 17.2 45 7.34 46 3.34 15 15.8 31 3.80 36 0.00 1 0.00 1 0.00 1 3.81 11 11.2 12 6.45 19
Layers++ [37]19.1 0.15 6 0.90 9 0.00 1 0.88 7 6.28 10 0.29 18 1.61 12 5.50 12 0.95 72 0.92 18 5.94 10 0.24 41 6.07 3 9.99 3 3.95 14 6.14 62 15.3 26 5.23 79 0.00 1 0.00 1 0.00 1 4.11 15 10.5 7 7.50 31
TC/T-Flow [76]19.2 0.11 2 0.67 2 0.00 1 1.63 50 8.48 32 0.45 28 2.21 19 7.45 20 0.16 13 1.20 48 10.2 57 0.16 9 9.34 34 14.9 30 6.04 33 1.76 2 9.86 4 1.36 1 0.00 1 0.00 1 0.00 1 4.64 24 12.6 23 7.19 25
MDP-Flow2 [68]20.0 0.18 21 1.07 24 0.03 58 0.82 4 5.18 4 0.20 10 1.31 8 4.69 8 0.09 8 1.24 55 11.0 64 0.24 41 9.23 31 15.2 34 5.96 32 2.65 6 11.8 9 3.56 30 0.00 1 0.00 1 0.00 1 3.61 8 11.1 10 5.40 13
PWC-Net_ROB [148]23.2 0.15 6 0.89 7 0.01 34 1.39 35 10.0 54 0.40 26 2.59 39 8.97 42 0.71 59 0.59 7 4.66 6 0.16 9 9.75 39 16.4 41 4.25 16 6.09 58 15.2 23 3.22 22 0.00 1 0.00 1 0.00 1 3.57 7 12.1 19 3.32 6
CombBMOF [113]24.0 0.20 34 1.18 36 0.03 58 1.05 14 6.42 12 0.16 4 1.66 13 5.67 13 0.01 2 0.79 12 6.82 15 0.16 9 7.66 13 12.5 12 4.37 18 8.16 97 15.3 26 7.67 124 0.00 1 0.00 1 0.00 1 4.31 17 11.0 9 7.79 35
NNF-EAC [103]24.4 0.17 15 1.03 20 0.01 34 1.01 11 5.78 9 0.38 25 1.81 15 6.09 15 0.13 11 1.27 59 11.4 66 0.24 41 8.50 22 14.2 25 5.00 25 4.85 36 12.2 11 4.55 55 0.00 1 0.00 1 0.00 1 4.77 28 13.1 32 7.37 27
WLIF-Flow [93]24.5 0.20 34 1.21 42 0.01 34 0.91 8 5.77 8 0.26 17 2.30 22 7.50 21 0.38 32 1.10 31 8.71 27 0.25 53 8.40 21 14.0 21 4.94 24 4.91 38 13.0 13 3.79 35 0.00 1 0.00 1 0.00 1 4.98 34 12.6 23 8.37 48
3DFlow [135]25.2 0.26 75 1.57 79 0.00 1 1.31 28 9.13 42 0.31 20 2.56 37 8.87 39 0.25 19 0.11 1 1.19 1 0.00 1 8.69 26 14.2 25 5.21 26 8.16 97 15.8 31 4.22 45 0.00 1 0.00 1 0.00 1 2.86 2 9.33 2 2.36 4
MLDP_OF [89]25.8 0.17 15 1.00 17 0.00 1 0.82 4 5.37 5 0.13 3 2.62 40 8.28 31 0.15 12 1.01 20 8.41 23 0.17 17 8.84 27 14.4 27 5.24 28 2.41 4 11.1 6 1.54 3 0.29 122 0.00 1 1.28 125 5.41 44 12.9 29 5.66 15
nLayers [57]26.2 0.19 27 1.13 33 0.00 1 1.04 13 7.08 20 0.31 20 2.42 29 8.37 34 0.50 38 1.10 31 8.82 29 0.38 70 6.91 8 11.4 8 3.98 15 6.52 68 12.6 12 5.28 81 0.00 1 0.00 1 0.00 1 4.63 23 12.5 22 8.25 44
FC-2Layers-FF [74]26.2 0.19 27 1.10 28 0.00 1 1.53 42 10.0 54 0.68 50 1.47 9 5.05 9 0.37 31 1.07 27 8.29 22 0.22 31 6.46 5 10.5 5 3.24 10 6.93 76 15.2 23 5.43 86 0.00 1 0.00 1 0.00 1 4.89 30 12.6 23 7.93 37
FlowFields+ [130]27.0 0.15 6 0.88 6 0.01 34 1.38 33 8.90 39 0.68 50 2.23 21 7.99 24 0.44 36 0.70 10 6.60 13 0.20 25 12.0 54 19.4 57 7.65 50 2.62 5 16.5 46 1.82 7 0.00 1 0.00 1 0.00 1 5.64 50 18.0 62 5.92 16
IIOF-NLDP [131]27.1 0.32 96 1.90 99 0.00 1 1.27 26 8.57 33 0.16 4 3.02 53 9.58 49 0.20 14 0.48 5 3.49 5 0.13 8 9.15 29 14.9 30 4.86 22 6.07 57 14.8 22 4.05 43 0.00 1 0.00 1 0.00 1 4.43 20 12.0 17 5.52 14
Correlation Flow [75]27.3 0.25 71 1.46 72 0.00 1 1.10 18 7.16 21 0.22 13 4.18 72 12.3 68 0.35 28 0.74 11 5.14 9 0.22 31 11.5 49 17.7 47 9.04 64 4.12 28 13.1 14 2.69 14 0.00 1 0.00 1 0.00 1 3.48 5 10.9 8 3.71 9
PH-Flow [101]29.3 0.20 34 1.16 34 0.00 1 1.36 30 7.94 26 0.53 38 1.69 14 5.76 14 0.64 53 1.10 31 8.60 26 0.24 41 6.59 6 11.1 6 3.26 11 3.52 19 11.6 7 3.39 23 0.13 112 0.00 1 0.44 107 4.21 16 11.4 14 7.94 39
IROF++ [58]30.2 0.23 60 1.37 62 0.00 1 1.37 32 8.26 29 0.45 28 2.40 27 7.86 22 0.51 41 1.16 44 9.50 48 0.24 41 8.06 17 13.2 16 4.86 22 5.64 51 16.4 41 4.51 53 0.00 1 0.00 1 0.00 1 4.62 21 12.7 28 7.93 37
AGIF+OF [85]30.2 0.21 46 1.25 51 0.00 1 1.48 40 8.75 36 0.37 23 2.50 34 8.15 28 0.38 32 1.14 37 8.88 30 0.23 35 7.56 12 12.5 12 4.30 17 6.71 71 15.2 23 4.99 70 0.00 1 0.00 1 0.00 1 5.07 37 13.0 31 8.68 56
PMF [73]30.5 0.20 34 1.19 38 0.03 58 1.06 17 6.51 13 0.18 7 1.50 11 5.33 11 0.09 8 1.26 58 9.04 36 0.23 35 7.32 11 12.4 10 1.91 3 5.47 45 16.3 38 4.67 59 0.09 106 0.00 1 0.25 102 3.51 6 9.50 3 6.99 22
HAST [109]31.8 0.21 46 1.27 53 0.03 58 1.55 45 6.58 14 0.85 66 1.07 2 3.84 2 0.06 5 1.18 47 9.57 50 0.19 23 6.70 7 11.3 7 2.10 6 5.68 52 14.2 18 5.14 77 0.01 89 0.00 1 0.05 91 2.21 1 7.87 1 2.21 3
ProbFlowFields [128]32.3 0.20 34 1.18 36 0.03 58 1.25 24 7.90 25 0.64 47 2.55 36 8.95 40 1.08 75 0.25 4 2.68 4 0.05 6 12.5 65 19.9 63 8.91 61 2.82 9 15.8 31 2.70 15 0.00 1 0.00 1 0.00 1 5.90 55 18.1 63 6.95 21
SVFilterOh [111]34.1 0.22 53 1.31 55 0.05 78 1.14 20 6.84 17 0.30 19 2.13 17 7.39 18 0.69 58 0.86 14 7.24 17 0.16 9 8.17 18 13.8 19 2.18 7 6.69 69 15.3 26 4.47 52 0.27 121 0.00 1 0.74 112 2.89 3 9.59 4 3.97 11
EPPM w/o HM [88]34.8 0.21 46 1.25 51 0.03 58 1.05 14 6.95 19 0.19 8 2.42 29 8.24 30 0.08 7 1.00 19 7.81 20 0.21 29 7.69 14 13.0 14 2.55 8 6.45 67 18.5 69 4.04 42 0.43 129 0.00 1 0.76 113 3.98 14 11.1 10 7.10 23
TC-Flow [46]34.8 0.13 3 0.77 3 0.00 1 1.38 33 8.10 28 0.47 31 2.97 52 10.0 53 0.34 26 1.36 67 10.5 62 0.25 53 11.2 46 18.1 49 7.49 48 3.36 16 17.1 55 1.78 6 0.00 1 0.00 1 0.00 1 6.35 61 17.8 61 10.0 78
CostFilter [40]34.9 0.22 53 1.32 58 0.03 58 1.16 21 6.61 15 0.22 13 1.22 5 4.37 7 0.21 16 1.29 60 10.2 57 0.21 29 7.77 15 13.2 16 2.07 4 5.43 43 15.9 35 3.96 41 0.07 103 0.00 1 0.12 96 4.75 27 13.5 39 7.19 25
ALD-Flow [66]37.5 0.14 5 0.85 5 0.01 34 1.70 53 8.34 30 0.50 34 2.94 50 9.96 52 0.38 32 1.68 77 13.0 75 0.32 64 11.8 53 18.8 54 8.42 57 2.93 10 16.4 41 1.70 5 0.00 1 0.00 1 0.00 1 5.91 57 17.4 58 8.45 51
FlowFields [110]37.6 0.16 11 0.97 13 0.02 53 1.54 44 9.90 53 0.72 54 2.38 25 8.48 36 0.58 50 1.03 21 9.05 37 0.31 62 12.5 65 20.3 69 8.76 60 3.16 12 18.0 68 3.08 20 0.00 1 0.00 1 0.00 1 6.22 59 19.0 67 6.76 20
COFM [59]38.0 0.28 81 1.64 81 0.06 83 1.31 28 7.81 23 0.57 42 3.57 63 12.0 65 1.10 77 0.91 17 7.78 19 0.16 9 11.7 52 18.5 53 10.3 78 4.05 26 13.7 17 4.28 48 0.00 1 0.00 1 0.00 1 3.96 13 11.5 15 6.40 18
RNLOD-Flow [121]38.6 0.17 15 1.03 20 0.00 1 1.50 41 9.63 48 0.56 41 3.15 56 10.1 55 0.56 49 1.14 37 9.02 35 0.20 25 9.73 38 15.7 38 6.54 39 5.43 43 14.7 20 4.56 57 0.06 101 0.00 1 0.34 103 4.41 18 11.3 13 7.56 32
Sparse-NonSparse [56]39.5 0.22 53 1.31 55 0.00 1 1.87 64 11.4 67 0.80 61 2.47 33 8.05 26 0.52 44 1.15 43 8.89 31 0.24 41 9.37 35 15.3 35 5.94 31 7.18 79 16.3 38 5.47 88 0.00 1 0.00 1 0.00 1 5.08 38 13.1 32 8.42 49
LSM [39]39.6 0.21 46 1.23 46 0.00 1 1.88 66 11.5 68 0.82 63 2.45 31 8.04 25 0.52 44 1.12 34 9.06 38 0.23 35 9.27 33 15.1 33 6.05 34 7.21 81 16.5 46 5.47 88 0.00 1 0.00 1 0.00 1 5.29 42 13.8 41 8.49 53
S2F-IF [123]39.8 0.18 21 1.07 24 0.02 53 1.53 42 10.0 54 0.72 54 2.37 24 8.45 35 0.54 46 1.21 49 9.59 51 0.35 66 12.7 69 20.3 69 9.20 68 3.41 17 17.7 64 3.70 33 0.00 1 0.00 1 0.00 1 5.36 43 16.5 53 6.13 17
LME [70]40.1 0.24 64 1.40 66 0.04 74 0.84 6 5.51 6 0.21 11 3.70 65 8.78 37 5.39 107 1.38 68 11.0 64 0.37 68 9.52 37 15.3 35 7.58 49 3.73 21 16.9 53 4.43 50 0.00 1 0.00 1 0.00 1 4.62 21 12.6 23 7.77 34
HBM-GC [105]40.2 0.29 84 1.72 88 0.03 58 1.36 30 8.81 37 0.71 53 2.92 48 10.0 53 0.79 60 1.21 49 8.97 33 0.37 68 8.90 28 14.6 28 5.72 30 5.58 49 9.50 3 3.51 29 0.00 1 0.00 1 0.00 1 5.23 41 15.1 47 8.28 45
FMOF [94]40.3 0.20 34 1.19 38 0.00 1 1.61 48 9.42 45 0.53 38 2.03 16 6.86 16 0.22 17 1.04 23 8.71 27 0.16 9 8.59 23 14.0 21 4.44 19 7.80 91 16.2 36 5.73 96 0.09 106 0.00 1 0.81 115 5.75 52 14.6 46 8.44 50
MDP-Flow [26]40.8 0.13 3 0.78 4 0.00 1 1.05 14 6.71 16 0.64 47 2.31 23 8.09 27 1.26 83 1.35 65 12.5 74 0.28 57 10.4 42 16.8 44 7.29 44 5.39 42 16.9 53 4.89 66 0.00 1 0.00 1 0.00 1 8.69 93 21.5 86 12.1 93
FESL [72]41.0 0.23 60 1.35 61 0.00 1 1.71 55 9.38 44 0.54 40 2.22 20 7.40 19 0.31 21 1.08 28 9.18 40 0.16 9 7.97 16 13.0 14 4.61 20 7.68 88 16.5 46 5.87 98 0.09 106 0.00 1 0.17 99 4.96 33 12.4 20 8.31 46
NL-TV-NCC [25]41.4 0.24 64 1.43 70 0.01 34 1.43 37 9.86 52 0.16 4 3.10 55 10.1 55 0.20 14 1.13 35 9.56 49 0.16 9 11.5 49 18.3 52 7.31 45 8.51 101 20.7 95 4.68 60 0.00 1 0.00 1 0.00 1 5.59 48 16.1 50 5.10 12
DPOF [18]42.3 0.17 15 0.99 15 0.00 1 2.06 77 10.3 59 0.92 71 0.99 1 3.51 1 0.05 4 1.08 28 9.87 55 0.17 17 8.25 20 13.8 19 3.72 12 9.58 118 18.7 71 5.78 97 1.06 135 0.00 1 2.93 133 4.41 18 13.4 38 3.94 10
Classic+NL [31]42.3 0.23 60 1.34 60 0.01 34 1.93 69 11.7 70 0.80 61 2.57 38 8.35 32 0.58 50 1.22 52 9.29 44 0.24 41 8.66 25 14.1 23 5.48 29 7.52 86 16.3 38 5.42 84 0.00 1 0.00 1 0.00 1 5.06 36 12.9 29 8.47 52
ResPWCR_ROB [145]43.8 0.19 27 1.10 28 0.00 1 1.62 49 9.55 46 0.40 26 3.47 61 11.6 64 1.29 88 1.04 23 8.53 25 0.22 31 11.3 47 18.2 50 7.48 47 6.92 75 17.5 62 5.48 90 0.00 1 0.00 1 0.00 1 6.95 69 20.1 75 8.98 64
Classic+CPF [83]44.5 0.21 46 1.23 46 0.01 34 1.47 39 8.95 40 0.37 23 2.73 42 8.84 38 0.35 28 1.14 37 9.32 45 0.23 35 8.60 24 14.1 23 5.23 27 8.01 95 16.4 41 5.26 80 0.20 118 0.00 1 0.86 117 4.71 25 12.0 17 8.34 47
JOF [141]44.5 0.31 92 1.77 95 0.07 93 1.97 72 10.7 61 1.00 76 2.14 18 7.04 17 0.60 52 1.13 35 8.98 34 0.24 41 7.05 9 11.9 9 3.77 13 6.22 64 14.7 20 5.04 72 0.01 89 0.00 1 0.00 1 4.83 29 13.1 32 8.17 43
ProFlow_ROB [147]44.8 0.28 81 1.66 82 0.01 34 1.65 52 10.1 58 0.73 56 3.30 57 11.4 61 0.64 53 1.35 65 10.4 61 0.23 35 12.1 55 19.8 61 6.97 43 3.91 24 16.6 50 2.12 8 0.00 1 0.00 1 0.00 1 5.60 49 16.8 56 7.48 30
Efficient-NL [60]45.1 0.22 53 1.29 54 0.00 1 1.25 24 7.99 27 0.48 33 2.92 48 9.31 43 0.31 21 1.23 54 9.67 54 0.31 62 8.23 19 13.5 18 4.72 21 8.45 100 17.1 55 6.06 101 0.12 111 0.00 1 0.54 109 4.71 25 11.6 16 7.75 33
Aniso-Texture [82]46.4 0.16 11 0.94 11 0.02 53 1.16 21 8.46 31 0.50 34 5.29 89 14.6 88 1.10 77 0.87 15 6.69 14 0.17 17 14.2 89 20.8 74 14.7 97 5.50 47 18.6 70 4.62 58 0.00 1 0.00 1 0.00 1 6.99 70 18.1 63 10.3 81
Complementary OF [21]46.7 0.15 6 0.89 7 0.00 1 1.43 37 8.69 35 0.35 22 2.54 35 8.95 40 0.28 20 1.45 69 12.4 71 0.28 57 14.9 97 21.6 92 15.4 102 7.75 89 17.6 63 3.64 31 0.00 1 0.00 1 0.00 1 7.27 76 22.2 94 9.59 73
SRR-TVOF-NL [91]46.8 0.19 27 1.05 22 0.03 58 3.08 101 13.8 96 1.68 99 3.97 69 12.4 69 0.84 61 1.22 52 9.35 47 0.20 25 11.5 49 16.7 43 12.3 87 2.79 7 13.5 15 3.68 32 0.00 1 0.00 1 0.00 1 5.69 51 13.1 32 10.1 79
LiteFlowNet [143]47.0 0.31 92 1.86 97 0.03 58 1.96 71 11.5 68 0.68 50 3.06 54 10.4 57 0.51 41 0.89 16 6.31 12 0.19 23 13.1 71 20.9 76 8.46 58 5.32 41 16.5 46 2.97 19 0.00 1 0.00 1 0.00 1 6.37 62 17.6 60 8.62 54
IROF-TV [53]48.5 0.22 53 1.24 49 0.01 34 1.83 62 11.9 73 0.87 68 2.96 51 9.37 44 0.50 38 1.70 78 14.6 84 0.46 76 9.51 36 15.4 37 6.49 38 4.78 34 22.9 108 4.55 55 0.00 1 0.00 1 0.00 1 5.17 39 14.4 45 8.73 58
Ramp [62]48.6 0.21 46 1.24 49 0.00 1 1.77 57 11.1 64 0.79 59 2.39 26 7.95 23 0.55 48 1.17 46 9.16 39 0.24 41 9.25 32 14.9 30 6.31 36 7.18 79 15.7 30 5.42 84 0.19 117 0.00 1 0.96 119 5.18 40 13.3 37 8.87 63
OFH [38]49.5 0.17 15 1.00 17 0.00 1 1.80 59 9.80 50 0.66 49 4.49 78 13.2 80 0.47 37 1.62 75 13.6 79 0.35 66 13.2 74 20.8 74 10.2 76 3.85 22 20.4 92 2.41 11 0.00 1 0.00 1 0.00 1 7.06 73 21.6 88 9.31 68
ROF-ND [107]50.3 0.29 84 1.73 90 0.01 34 2.75 96 11.0 62 0.73 56 3.45 60 10.7 58 0.51 41 0.13 2 1.44 2 0.00 1 12.2 57 18.8 54 10.5 79 6.28 66 17.1 55 4.80 64 0.00 1 0.00 1 0.00 1 8.30 89 21.5 86 9.38 69
OAR-Flow [125]50.9 0.19 27 1.12 32 0.06 83 2.86 97 12.0 74 1.41 94 4.36 75 13.9 83 1.43 92 1.51 71 11.7 68 0.23 35 12.6 68 20.0 66 8.47 59 2.80 8 16.4 41 1.37 2 0.00 1 0.00 1 0.00 1 5.56 47 16.7 54 8.15 42
FF++_ROB [146]51.5 0.29 84 1.66 82 0.06 83 1.74 56 11.3 66 0.84 65 3.66 64 12.1 67 1.40 91 1.14 37 9.66 53 0.33 65 12.4 60 20.1 68 8.17 54 3.96 25 15.4 29 2.67 13 0.00 1 0.00 1 0.00 1 5.83 54 16.3 51 9.01 65
TCOF [69]52.4 0.18 21 1.06 23 0.00 1 1.56 46 9.24 43 0.60 44 4.63 80 12.8 76 0.89 64 1.34 64 12.4 71 0.20 25 12.4 60 19.6 60 9.52 70 6.02 56 14.3 19 5.03 71 0.34 127 0.00 1 1.23 124 4.94 31 13.6 40 8.00 40
TV-L1-MCT [64]53.0 0.22 53 1.33 59 0.00 1 1.64 51 9.85 51 0.52 36 2.86 47 9.38 45 0.32 24 1.14 37 8.89 31 0.24 41 10.6 44 16.4 41 9.05 65 8.81 108 17.2 59 5.12 76 0.08 105 0.00 1 0.84 116 5.93 58 14.3 44 10.1 79
ACK-Prior [27]54.3 0.15 6 0.91 10 0.00 1 1.21 23 7.63 22 0.19 8 2.41 28 8.36 33 0.35 28 1.25 57 10.5 62 0.18 21 12.4 60 18.0 48 11.2 80 9.00 113 19.4 83 6.39 108 0.17 115 0.00 1 1.01 121 9.72 102 20.1 75 13.3 98
2DHMM-SAS [92]54.5 0.20 34 1.21 42 0.00 1 1.80 59 10.4 60 0.63 46 4.15 70 11.3 60 0.86 62 1.24 55 9.61 52 0.25 53 9.18 30 14.8 29 6.44 37 8.98 112 17.3 60 4.98 68 0.13 112 0.00 1 0.69 111 5.55 46 14.2 43 9.22 66
CRTflow [80]55.0 0.18 21 0.99 15 0.03 58 1.70 53 9.09 41 0.59 43 4.56 79 12.8 76 0.68 55 2.03 94 15.1 89 0.64 85 12.4 60 20.0 66 8.26 55 4.42 29 24.0 113 3.47 27 0.00 1 0.00 1 0.00 1 7.88 82 22.0 93 10.4 83
PGM-C [120]55.1 0.20 34 1.19 38 0.07 93 1.87 64 11.8 72 0.85 66 2.76 43 9.82 51 0.92 68 1.99 91 15.1 89 0.74 94 13.1 71 21.2 78 9.19 67 3.52 19 19.2 79 2.47 12 0.00 1 0.00 1 0.00 1 6.38 63 19.5 72 8.65 55
Sparse Occlusion [54]56.5 0.24 64 1.38 64 0.06 83 1.27 26 7.83 24 0.45 28 3.42 58 11.1 59 0.33 25 1.52 73 11.4 66 0.28 57 10.9 45 17.6 46 6.76 41 4.10 27 16.2 36 4.27 47 0.03 93 0.17 138 0.15 97 5.90 55 15.7 48 8.69 57
SimpleFlow [49]56.8 0.22 53 1.31 55 0.00 1 1.78 58 11.0 62 0.82 63 4.30 74 12.5 72 1.22 82 1.16 44 9.20 41 0.24 41 9.84 41 15.8 39 6.94 42 8.51 101 17.3 60 6.11 104 0.09 106 0.00 1 0.39 105 5.01 35 14.1 42 8.00 40
CPM-Flow [116]57.6 0.21 46 1.23 46 0.07 93 1.92 68 12.1 75 0.89 69 2.64 41 9.39 46 0.92 68 1.96 87 14.8 85 0.72 92 13.1 71 21.2 78 8.92 62 4.84 35 19.1 78 3.40 24 0.00 1 0.00 1 0.00 1 6.92 67 20.5 78 9.43 71
ComplOF-FED-GPU [35]59.4 0.19 27 1.10 28 0.03 58 2.32 84 12.5 83 0.92 71 2.76 43 9.65 50 0.31 21 1.65 76 13.1 76 0.38 70 13.4 79 21.2 78 10.2 76 8.60 105 22.8 106 4.22 45 0.00 1 0.00 1 0.00 1 7.44 77 22.4 95 9.81 74
EpicFlow [102]62.1 0.20 34 1.17 35 0.07 93 1.91 67 12.1 75 0.90 70 3.70 65 12.7 74 0.89 64 1.96 87 14.8 85 0.74 94 13.4 79 21.3 83 9.97 72 6.71 71 19.3 81 3.90 38 0.00 1 0.00 1 0.00 1 7.03 71 20.1 75 9.91 75
S2D-Matching [84]62.9 0.33 98 1.92 101 0.06 83 2.04 75 12.4 80 0.79 59 4.15 70 13.0 78 1.09 76 1.09 30 8.04 21 0.24 41 9.82 40 15.9 40 6.68 40 7.85 92 16.4 41 5.58 92 0.20 118 0.00 1 0.96 119 4.94 31 12.6 23 8.81 60
AggregFlow [97]63.5 0.53 111 2.62 119 0.12 115 2.72 93 13.2 89 1.45 95 3.90 68 13.0 78 1.85 97 1.06 26 9.26 42 0.18 21 12.1 55 19.4 57 7.83 51 3.05 11 12.1 10 2.29 9 0.04 99 0.00 1 0.44 107 5.82 53 15.9 49 9.26 67
TF+OM [100]63.5 0.16 11 0.98 14 0.01 34 1.85 63 10.0 54 1.15 87 4.71 84 12.6 73 5.84 108 1.79 82 14.0 82 0.69 89 15.4 102 22.1 96 16.5 107 5.62 50 19.8 87 3.95 40 0.00 1 0.00 1 0.00 1 8.18 87 20.6 80 12.0 92
DeepFlow2 [108]63.5 0.26 75 1.53 76 0.08 102 2.56 90 11.7 70 1.30 92 3.73 67 11.5 63 0.90 66 1.99 91 15.1 89 0.65 87 12.3 58 19.5 59 9.07 66 4.57 31 18.7 71 2.81 17 0.00 1 0.00 1 0.00 1 8.01 86 21.0 81 10.8 85
ContFlow_ROB [150]65.0 0.36 102 2.02 103 0.07 93 2.72 93 14.1 97 1.09 80 6.17 100 16.0 103 5.86 110 0.85 13 6.14 11 0.17 17 14.8 95 23.5 115 9.03 63 6.12 60 19.0 77 3.45 26 0.00 1 0.00 1 0.00 1 6.92 67 19.4 70 8.85 62
Adaptive [20]65.1 0.29 84 1.72 88 0.06 83 2.04 75 12.5 83 1.13 85 5.51 93 14.7 89 0.68 55 1.83 83 13.9 81 0.59 84 12.7 69 19.9 63 10.1 73 7.15 77 18.9 75 4.08 44 0.00 1 0.00 1 0.00 1 6.38 63 16.4 52 8.82 61
LFNet_ROB [151]69.2 0.25 71 1.50 74 0.04 74 1.94 70 12.3 79 0.95 74 4.69 82 14.9 91 1.47 93 1.14 37 9.32 45 0.51 80 16.3 111 24.6 121 15.5 103 5.01 39 22.7 104 3.48 28 0.00 1 0.00 1 0.00 1 8.24 88 23.7 105 11.4 89
Steered-L1 [118]70.0 0.10 1 0.59 1 0.01 34 1.01 11 6.84 17 0.52 36 2.76 43 9.44 47 0.91 67 1.78 80 14.9 87 0.51 80 14.0 88 20.5 71 15.2 100 9.02 114 19.9 88 6.57 112 1.07 136 0.00 1 7.19 137 12.1 112 22.9 98 20.6 118
DMF_ROB [140]70.2 0.18 21 1.07 24 0.03 58 2.32 84 12.7 85 1.10 82 4.84 86 15.1 97 1.27 86 2.06 96 15.9 94 0.75 97 13.7 82 21.2 78 12.3 87 7.35 84 21.7 101 5.05 73 0.00 1 0.00 1 0.00 1 8.30 89 21.8 90 11.1 87
RFlow [90]70.3 0.20 34 1.21 42 0.01 34 1.58 47 9.77 49 0.77 58 4.69 82 13.5 81 0.34 26 2.30 107 17.7 107 0.80 100 14.3 90 21.4 85 15.1 99 5.47 45 20.9 97 4.98 68 0.01 89 0.00 1 0.15 97 7.91 84 21.0 81 10.6 84
Aniso. Huber-L1 [22]71.5 0.29 84 1.66 82 0.06 83 2.43 88 13.1 88 1.12 84 5.68 94 14.3 87 1.27 86 1.56 74 12.4 71 0.30 61 12.4 60 19.2 56 10.1 73 4.70 33 17.1 55 4.45 51 0.17 115 0.00 1 0.89 118 6.28 60 16.7 54 8.80 59
TriangleFlow [30]71.7 0.24 64 1.39 65 0.00 1 2.50 89 14.3 98 0.98 75 4.46 77 12.7 74 0.41 35 1.49 70 12.2 70 0.42 74 15.8 106 23.1 105 16.4 106 8.57 103 17.7 64 4.86 65 0.03 93 0.00 1 0.05 91 6.59 65 17.3 57 9.55 72
DeepFlow [86]72.2 0.34 101 1.74 92 0.09 104 2.87 98 12.4 80 1.56 96 4.42 76 12.4 69 2.69 102 2.20 101 16.1 96 0.81 101 12.3 58 19.8 61 8.36 56 4.85 36 20.1 89 2.95 18 0.00 1 0.00 1 0.00 1 9.35 97 23.3 103 12.7 95
Occlusion-TV-L1 [63]72.2 0.27 79 1.55 78 0.06 83 1.99 74 12.1 75 1.14 86 5.42 91 14.9 91 0.93 70 1.83 83 14.0 82 0.49 78 13.6 81 21.2 78 11.5 82 6.13 61 19.6 86 5.37 83 0.00 1 0.00 1 0.00 1 9.19 96 23.4 104 11.5 90
CBF [12]74.0 0.18 21 1.09 27 0.01 34 2.37 86 12.9 86 1.94 102 4.28 73 12.0 65 1.13 80 1.97 90 16.1 96 0.66 88 13.3 78 20.5 71 12.7 91 5.89 54 18.8 74 4.73 61 0.45 131 0.00 1 1.33 127 7.67 79 18.9 66 12.7 95
OFRF [134]75.2 0.54 113 2.51 114 0.12 115 7.58 128 15.8 103 7.13 133 7.71 112 15.0 93 5.91 111 1.78 80 9.27 43 1.09 110 11.3 47 18.2 50 6.18 35 6.74 74 13.5 15 2.79 16 0.00 1 0.00 1 0.00 1 12.7 114 19.0 67 27.9 128
LocallyOriented [52]75.2 0.49 110 2.66 120 0.06 83 3.28 102 15.4 101 1.91 101 6.59 104 16.9 106 1.20 81 1.29 60 10.1 56 0.52 83 14.6 92 21.5 87 12.6 89 7.79 90 16.7 51 4.33 49 0.00 1 0.00 1 0.00 1 7.87 81 19.1 69 11.1 87
TV-L1-improved [17]77.3 0.25 71 1.46 72 0.07 93 1.82 61 11.1 64 1.02 77 5.46 92 15.0 93 1.32 89 2.26 104 16.4 99 0.79 99 13.8 84 21.5 87 11.8 83 9.40 115 23.6 112 6.48 109 0.00 1 0.00 1 0.00 1 7.89 83 21.3 85 10.3 81
FlowNet2 [122]77.7 0.74 124 3.32 127 0.12 115 5.00 117 17.2 109 2.46 109 6.13 99 15.0 93 5.85 109 1.29 60 10.3 60 0.40 73 13.2 74 21.6 92 8.11 52 7.27 82 17.7 64 6.06 101 0.00 1 0.00 1 0.05 91 5.52 45 17.5 59 3.70 8
DF-Auto [115]77.9 0.61 119 2.33 111 0.10 110 4.04 109 15.3 100 2.49 110 6.59 104 14.8 90 6.66 113 1.84 85 15.0 88 0.51 80 14.9 97 21.5 87 16.8 109 3.47 18 16.7 51 3.82 37 0.00 1 0.00 1 0.00 1 7.99 85 19.5 72 11.6 91
TriFlow [95]78.1 0.27 79 1.62 80 0.01 34 2.27 83 13.2 89 1.24 89 7.10 109 16.9 106 7.37 116 1.31 63 11.7 68 0.43 75 17.3 117 23.4 112 20.6 119 3.24 14 15.8 31 3.91 39 4.67 143 0.00 1 18.1 143 6.86 66 18.1 63 7.89 36
EPMNet [133]79.6 0.64 122 3.15 124 0.09 104 5.25 118 18.8 115 2.74 115 5.08 88 14.0 84 2.76 103 1.51 71 13.3 77 0.28 57 13.2 74 21.6 92 8.11 52 7.27 82 17.7 64 6.06 101 0.00 1 0.00 1 0.02 90 7.03 71 23.1 99 3.19 5
CLG-TV [48]79.8 0.31 92 1.67 86 0.06 83 2.10 79 13.0 87 0.92 71 5.33 90 14.2 86 1.04 74 1.71 79 13.7 80 0.38 70 13.9 86 21.4 85 12.0 84 5.20 40 22.7 104 5.07 74 0.20 118 0.00 1 1.01 121 7.85 80 19.4 70 9.91 75
Bartels [41]81.4 0.24 64 1.40 66 0.01 34 1.42 36 8.88 38 0.62 45 3.51 62 12.4 69 1.00 73 2.26 104 15.8 93 0.95 105 15.5 103 23.3 109 15.8 105 7.99 94 23.0 109 5.20 78 0.33 124 0.00 1 1.92 130 9.95 104 24.0 106 13.7 101
Brox et al. [5]81.6 0.25 71 1.45 71 0.03 58 2.22 82 13.7 95 1.07 79 3.44 59 11.4 61 0.68 55 2.20 101 16.7 103 0.72 92 17.8 122 23.4 112 24.6 128 8.90 111 24.6 116 6.63 113 0.00 1 0.00 1 0.00 1 10.6 107 25.9 114 14.8 106
Fusion [6]82.2 0.24 64 1.41 68 0.05 78 1.13 19 8.57 33 0.47 31 2.45 31 8.15 28 0.93 70 2.12 100 18.3 113 1.21 111 16.2 110 23.1 105 19.6 117 6.72 73 18.7 71 5.67 94 0.07 103 0.15 136 0.10 95 10.4 106 24.9 111 14.6 105
Classic++ [32]82.8 0.26 75 1.50 74 0.07 93 2.08 78 12.2 78 1.03 78 4.84 86 14.0 84 1.26 83 2.07 98 16.1 96 0.64 85 13.9 86 22.5 99 10.1 73 6.11 59 23.1 110 5.28 81 0.06 101 0.00 1 0.34 103 8.66 92 21.7 89 11.0 86
SegOF [10]82.9 0.24 64 1.41 68 0.05 78 4.72 115 21.4 119 3.68 119 9.28 119 19.5 118 4.83 105 1.05 25 7.42 18 0.78 98 20.7 132 27.1 130 28.6 133 10.4 122 26.0 120 7.80 125 0.00 1 0.00 1 0.00 1 7.25 75 20.0 74 7.44 29
Rannacher [23]85.0 0.33 98 1.95 102 0.07 93 2.21 81 13.4 92 1.29 91 5.78 95 15.6 100 1.48 94 2.51 111 17.8 108 0.95 105 14.5 91 22.5 99 12.2 86 9.72 119 24.8 117 6.66 115 0.00 1 0.00 1 0.00 1 7.50 78 21.1 84 9.97 77
SuperFlow [81]86.1 0.45 106 1.75 93 0.10 110 3.01 100 13.4 92 2.04 103 6.82 108 15.2 98 8.24 119 1.96 87 17.0 105 0.50 79 15.6 105 22.2 97 19.2 116 5.87 53 20.6 93 5.46 87 0.00 1 0.00 1 0.00 1 10.1 105 24.6 109 13.4 99
AugFNG_ROB [144]86.8 0.57 117 2.19 106 0.11 113 4.08 111 16.3 106 2.52 112 8.00 114 19.2 117 8.51 120 1.21 49 10.2 57 0.26 56 16.5 114 25.6 127 13.4 93 7.17 78 24.2 114 5.99 99 0.00 1 0.00 1 0.00 1 8.96 95 25.1 112 9.39 70
BriefMatch [124]87.3 0.16 11 0.94 11 0.01 34 1.97 72 9.60 47 1.10 82 2.79 46 9.56 48 0.54 46 2.11 99 15.6 92 0.70 90 14.6 92 21.5 87 15.2 100 10.4 122 22.0 102 8.36 128 2.52 142 0.62 146 13.7 142 13.6 121 25.5 113 22.0 122
Local-TV-L1 [65]87.4 0.53 111 2.10 104 0.12 115 4.96 116 18.0 113 3.44 118 8.54 117 16.7 105 6.16 112 2.47 110 18.5 115 1.01 109 12.5 65 19.9 63 9.65 71 5.53 48 19.5 84 4.95 67 0.00 1 0.00 1 0.00 1 13.4 118 24.2 107 27.1 127
SIOF [67]87.8 0.42 105 2.28 107 0.08 102 3.55 105 17.7 112 2.05 104 8.15 115 17.9 113 7.78 118 2.41 109 17.9 109 1.00 108 15.5 103 22.7 102 17.8 113 4.67 32 19.5 84 4.77 63 0.00 1 0.00 1 0.00 1 9.35 97 21.8 90 17.7 112
Second-order prior [8]90.8 0.26 75 1.53 76 0.05 78 2.88 99 15.5 102 1.60 97 5.87 96 15.3 99 1.11 79 2.21 103 17.2 106 0.94 104 13.8 84 21.3 83 12.6 89 7.46 85 27.8 126 5.71 95 0.16 114 0.00 1 0.76 113 8.65 91 21.0 81 13.9 103
p-harmonic [29]90.9 0.29 84 1.73 90 0.02 53 2.16 80 13.2 89 1.33 93 5.87 96 15.8 101 1.59 95 2.55 112 17.9 109 1.49 114 17.0 115 22.7 102 23.3 125 4.53 30 21.5 100 4.53 54 0.03 93 0.02 135 0.00 1 9.65 101 23.2 102 15.0 107
Dynamic MRF [7]92.5 0.30 91 1.79 96 0.04 74 2.37 86 14.9 99 1.09 80 4.81 85 15.0 93 0.86 62 2.66 113 18.2 112 1.25 112 17.6 120 25.7 128 18.1 114 10.9 127 30.4 131 7.45 121 0.00 1 0.00 1 0.00 1 15.1 124 29.9 129 21.9 121
Shiralkar [42]92.8 0.28 81 1.66 82 0.02 53 3.80 107 19.8 118 1.78 100 6.50 102 16.1 104 1.26 83 3.17 117 20.8 119 1.56 116 16.3 111 25.1 125 14.5 96 12.4 131 29.4 129 6.20 105 0.00 1 0.00 1 0.00 1 12.6 113 30.1 130 13.8 102
F-TV-L1 [15]93.8 0.46 107 2.58 116 0.07 93 4.05 110 16.2 105 2.21 105 6.59 104 15.9 102 1.39 90 2.35 108 17.9 109 0.88 103 13.7 82 21.5 87 11.4 81 7.53 87 21.1 99 4.75 62 0.03 93 0.17 138 0.05 91 7.15 74 20.5 78 7.39 28
CNN-flow-warp+ref [117]95.0 0.33 98 1.91 100 0.09 104 2.72 93 12.4 80 2.32 107 6.77 107 18.9 116 2.09 98 2.28 106 16.4 99 0.82 102 17.7 121 23.9 117 22.8 124 9.40 115 24.3 115 6.73 116 0.00 1 0.00 1 0.00 1 14.0 122 26.8 120 20.2 117
GraphCuts [14]97.5 0.29 84 1.67 86 0.16 123 6.77 125 22.4 123 3.81 120 7.73 113 17.2 109 9.04 121 1.86 86 16.8 104 0.46 76 15.8 106 24.0 118 14.1 95 20.2 140 22.8 106 12.5 137 0.00 1 0.00 1 0.00 1 13.4 118 27.0 123 23.4 124
StereoOF-V1MT [119]98.9 0.41 103 2.35 112 0.04 74 4.27 113 21.6 120 1.66 98 6.25 101 17.7 111 0.50 38 3.13 116 23.2 123 1.41 113 19.4 129 27.9 134 20.7 121 11.6 129 32.5 133 7.60 123 0.00 1 0.00 1 0.00 1 16.7 128 32.8 133 21.3 119
Ad-TV-NDC [36]101.1 0.79 125 2.68 121 0.12 115 13.0 136 26.5 129 12.9 136 12.9 127 22.0 122 9.24 122 5.02 122 20.3 118 4.82 122 13.2 74 20.5 71 9.43 69 6.17 63 20.3 91 5.07 74 0.03 93 0.00 1 0.00 1 20.5 133 26.9 121 40.8 140
HBpMotionGpu [43]101.2 0.80 126 2.79 122 0.18 124 5.57 119 23.8 127 4.00 121 13.1 128 27.8 134 11.6 128 2.05 95 16.4 99 0.74 94 17.9 123 25.1 125 22.3 123 6.69 69 21.0 98 6.04 100 0.00 1 0.00 1 0.00 1 14.1 123 27.7 124 25.1 125
WOLF_ROB [149]102.2 0.56 115 3.04 123 0.09 104 6.60 122 23.5 125 3.40 117 8.20 116 18.2 115 2.44 100 2.06 96 13.3 77 0.98 107 16.4 113 23.3 109 18.2 115 9.74 120 19.2 79 6.28 107 0.01 89 0.00 1 0.20 101 9.49 99 23.1 99 14.3 104
Filter Flow [19]102.4 0.58 118 2.59 117 0.11 113 4.48 114 19.7 116 2.66 114 12.1 122 23.7 125 13.5 133 14.5 133 30.4 129 15.0 133 18.7 128 23.7 116 27.5 132 8.11 96 20.7 95 6.48 109 0.00 1 0.00 1 0.00 1 11.0 109 21.9 92 17.2 110
StereoFlow [44]102.8 2.82 144 6.92 143 1.29 143 21.5 142 42.6 145 13.8 137 20.5 143 33.3 144 20.4 139 20.6 140 51.2 143 18.6 138 14.9 97 22.6 101 13.7 94 3.89 23 18.9 75 3.74 34 0.00 1 0.00 1 0.00 1 11.3 111 25.9 114 18.7 115
Modified CLG [34]104.8 0.62 120 2.54 115 0.12 115 3.52 104 18.7 114 2.59 113 12.2 124 23.5 124 12.5 130 3.25 118 20.1 117 2.03 118 18.6 127 25.0 124 25.0 129 8.86 110 26.9 125 7.14 119 0.00 1 0.00 1 0.00 1 13.4 118 29.8 128 21.8 120
2bit-BM-tele [98]105.0 0.54 113 2.59 117 0.20 125 2.58 91 16.3 106 1.26 90 6.04 98 17.8 112 2.26 99 2.77 115 19.7 116 1.50 115 15.8 106 23.3 109 16.5 107 8.58 104 22.4 103 5.62 93 1.37 138 0.00 1 5.84 136 10.7 108 24.8 110 16.5 109
Learning Flow [11]106.2 0.32 96 1.89 98 0.01 34 2.61 92 16.0 104 1.21 88 6.52 103 17.9 113 1.65 96 4.69 121 24.9 126 3.14 121 20.8 133 27.4 133 26.9 131 10.9 127 28.6 128 7.90 126 0.10 110 0.00 1 0.64 110 13.3 117 28.5 127 18.1 113
FlowNetS+ft+v [112]107.2 0.31 92 1.76 94 0.09 104 3.39 103 13.5 94 2.49 110 7.24 110 16.9 106 5.12 106 3.32 119 18.3 113 2.07 119 17.1 116 23.2 108 20.3 118 6.23 65 23.2 111 5.50 91 0.35 128 0.52 143 1.50 129 8.79 94 23.1 99 13.6 100
SPSA-learn [13]108.0 0.86 128 3.30 126 0.28 131 6.02 121 22.0 121 4.09 122 10.6 120 21.3 120 9.82 126 5.83 125 22.9 121 5.66 126 17.9 123 23.4 112 23.4 126 10.2 121 25.0 118 8.09 127 0.00 1 0.00 1 0.00 1 15.9 127 28.1 125 23.3 123
IAOF2 [51]108.6 0.47 109 2.28 107 0.33 132 3.77 106 16.3 106 2.22 106 7.40 111 17.2 109 7.06 115 14.7 134 29.4 128 16.6 135 15.2 101 23.0 104 14.7 97 10.5 124 20.6 93 7.03 118 0.32 123 0.00 1 2.00 132 11.2 110 22.6 97 15.4 108
UnFlow [129]109.6 1.88 138 6.59 140 0.87 139 6.75 124 27.2 130 4.57 124 12.5 126 27.9 135 7.37 116 5.65 124 21.0 120 5.26 124 22.5 136 30.2 137 26.4 130 9.48 117 30.5 132 7.32 120 0.00 1 0.00 1 0.00 1 9.58 100 26.9 121 12.3 94
LDOF [28]109.9 0.41 103 2.31 110 0.09 104 3.85 108 17.3 110 2.32 107 4.68 81 13.5 81 2.59 101 3.97 120 24.8 125 2.14 120 16.1 109 23.1 105 17.6 111 8.24 99 26.0 120 6.50 111 0.33 124 0.34 140 1.95 131 9.77 103 26.7 118 12.9 97
TVL1_ROB [139]111.0 1.04 130 3.71 129 0.27 130 9.06 130 24.8 128 7.75 134 14.6 131 25.5 129 12.5 130 10.6 128 31.0 131 11.6 130 17.4 118 24.5 120 20.6 119 8.67 106 25.1 119 6.64 114 0.00 1 0.00 1 0.00 1 21.9 135 31.3 131 39.9 138
IAOF [50]111.8 0.46 107 2.11 105 0.10 110 6.63 123 19.7 116 4.61 125 13.8 130 23.3 123 9.33 123 9.91 127 23.2 123 11.3 129 14.8 95 22.2 97 15.5 103 10.6 125 26.8 124 6.99 117 0.05 100 0.00 1 0.42 106 18.0 131 24.4 108 35.4 136
Nguyen [33]112.4 0.83 127 3.37 128 0.22 126 7.27 127 22.1 122 6.46 128 15.4 134 26.8 132 12.4 129 17.6 137 30.4 129 20.2 140 18.5 126 24.7 122 24.5 127 8.82 109 28.5 127 8.81 130 0.00 1 0.00 1 0.00 1 18.9 132 31.7 132 29.4 130
BlockOverlap [61]112.9 0.62 120 2.30 109 0.14 122 4.11 112 17.6 111 3.02 116 9.12 118 19.6 119 6.97 114 2.74 114 16.5 102 1.72 117 14.7 94 20.9 76 16.8 109 7.89 93 19.3 81 6.25 106 2.12 139 0.52 143 10.9 141 15.2 125 22.4 95 32.3 134
GroupFlow [9]113.6 0.56 115 3.20 125 0.05 78 9.79 132 32.3 136 7.11 132 11.4 121 24.6 126 9.68 125 2.01 93 16.0 95 0.70 90 19.8 130 29.9 136 12.0 84 15.2 137 32.5 133 15.4 139 0.33 124 0.00 1 1.11 123 13.2 116 28.4 126 17.2 110
2D-CLG [1]115.8 1.77 137 6.22 138 0.51 137 5.91 120 22.4 123 4.54 123 16.4 135 28.6 137 18.1 138 17.9 138 35.8 134 19.9 139 20.4 131 25.8 129 29.3 134 12.0 130 29.6 130 11.4 134 0.00 1 0.00 1 0.00 1 17.7 130 32.8 133 26.2 126
Heeger++ [104]117.0 0.95 129 4.26 132 0.26 129 11.8 135 39.5 143 6.54 129 12.3 125 24.7 128 3.51 104 10.7 129 37.1 136 8.97 127 30.7 142 36.7 142 39.2 140 21.4 143 46.3 144 18.3 142 0.00 1 0.00 1 0.00 1 24.4 137 37.0 136 31.9 132
FFV1MT [106]120.5 1.42 133 6.80 142 0.25 127 10.3 133 35.9 140 6.76 130 18.0 136 30.0 139 16.5 135 17.2 136 51.3 144 16.2 134 31.5 143 37.1 143 43.2 143 20.9 142 44.0 143 17.2 140 0.00 1 0.00 1 0.00 1 24.4 137 37.0 136 31.9 132
TI-DOFE [24]120.6 1.58 135 5.19 135 0.36 134 16.8 138 34.3 137 17.7 139 19.3 142 30.2 141 21.6 141 23.3 141 39.1 138 27.6 141 21.1 134 27.1 130 29.5 135 14.4 135 35.1 137 12.1 136 0.00 1 0.00 1 0.00 1 27.2 141 40.8 140 41.2 141
Black & Anandan [4]122.5 0.68 123 2.46 113 0.13 121 7.01 126 23.6 126 4.65 126 12.1 122 21.6 121 9.40 124 5.45 123 23.1 122 4.84 123 17.5 119 24.3 119 21.6 122 10.6 125 26.6 123 7.49 122 0.43 129 0.15 136 1.31 126 12.7 114 26.7 118 18.8 116
H+S_ROB [138]123.2 2.47 143 6.65 141 0.89 141 10.4 134 34.3 137 6.83 131 18.1 137 31.4 142 16.8 137 30.4 145 41.9 140 34.3 145 29.4 141 35.1 141 44.5 145 20.4 141 43.6 142 21.5 143 0.00 1 0.00 1 0.00 1 38.2 144 44.9 143 45.2 142
Horn & Schunck [3]123.6 1.05 131 4.22 131 0.25 127 7.74 129 29.1 133 5.17 127 13.6 129 24.6 126 10.8 127 12.7 131 36.1 135 12.8 131 21.4 135 27.3 132 30.9 137 13.9 134 35.2 138 11.6 135 0.03 93 0.00 1 0.17 99 22.3 136 37.9 138 31.7 131
SILK [79]127.2 1.05 131 4.27 133 0.44 135 9.69 131 27.9 131 8.93 135 15.2 133 26.9 133 13.1 132 6.14 126 25.9 127 5.57 125 23.0 137 29.2 135 34.1 138 12.6 132 33.9 135 9.78 132 0.81 134 0.00 1 3.50 134 21.5 134 33.3 135 34.5 135
HCIC-L [99]128.7 1.95 139 6.24 139 0.99 142 28.7 144 32.2 135 35.8 144 18.6 140 26.2 130 25.7 144 25.4 144 46.6 142 27.7 142 15.1 100 21.9 95 12.7 91 8.77 107 20.2 90 9.24 131 6.40 145 0.49 142 23.0 145 15.3 126 26.4 117 18.4 114
PGAM+LK [55]132.4 2.98 145 6.17 137 6.36 150 16.8 138 36.2 141 17.8 140 14.7 132 26.5 131 14.5 134 19.1 139 53.9 145 18.3 137 23.1 138 30.6 138 29.9 136 14.4 135 36.8 139 11.1 133 1.07 136 0.00 1 4.16 135 25.9 139 40.1 139 40.3 139
SLK [47]132.5 1.44 134 5.58 136 0.49 136 14.4 137 35.8 139 14.8 138 18.5 138 30.1 140 21.4 140 24.6 142 35.7 133 27.7 142 26.3 140 31.9 139 39.4 141 15.6 138 38.8 140 13.6 138 0.55 133 0.00 1 1.35 128 31.7 142 41.0 141 49.0 143
Adaptive flow [45]132.5 1.75 136 5.07 134 0.34 133 18.4 140 28.3 132 18.5 141 18.5 138 28.6 137 22.9 142 13.3 132 37.4 137 13.9 132 17.9 123 24.7 122 17.7 112 12.9 133 26.2 122 8.68 129 5.20 144 0.61 145 22.8 144 16.7 128 26.0 116 28.2 129
FOLKI [16]134.2 1.98 140 7.18 144 0.87 139 24.5 143 36.3 142 30.3 143 18.7 141 32.4 143 16.5 135 15.2 135 33.2 132 18.1 136 26.0 139 32.3 140 36.0 139 17.7 139 40.6 141 17.9 141 2.33 141 0.00 1 10.6 139 33.9 143 43.6 142 52.7 144
Periodicity [78]135.0 2.36 142 9.12 145 0.79 138 19.1 141 40.7 144 20.6 142 28.2 145 35.2 145 26.8 145 11.2 130 40.6 139 10.3 128 42.3 145 55.4 145 41.1 142 31.7 144 56.3 145 27.7 144 0.54 132 0.00 1 7.78 138 26.1 140 51.0 144 36.2 137
Pyramid LK [2]142.0 2.31 141 4.20 130 3.47 149 31.6 145 32.0 134 40.4 145 21.0 144 28.5 136 24.0 143 24.6 142 43.7 141 28.6 144 37.5 144 46.6 144 43.7 144 33.1 145 34.2 136 31.3 145 2.17 140 0.47 141 10.7 140 46.5 145 57.3 145 67.2 145
AVG_FLOW_ROB [142]143.1 41.6 151 34.9 151 54.2 151 94.7 151 94.6 151 92.2 151 90.3 151 88.2 151 90.3 151 80.5 151 73.8 151 82.4 151 91.3 151 92.4 146 87.0 151 67.7 146 60.9 151 64.7 146 20.2 146 0.00 1 42.1 146 93.8 146 92.8 146 98.2 146
AdaConv-v1 [126]146.3 6.16 146 11.8 146 2.11 144 91.0 146 93.3 146 87.2 146 83.4 146 79.4 146 87.3 146 47.3 146 64.4 146 46.2 146 89.6 146 93.2 147 73.3 146 69.7 147 60.5 146 67.1 147 41.7 147 14.2 147 92.5 147 99.6 147 98.7 147 100.0 147
SepConv-v1 [127]146.3 6.16 146 11.8 146 2.11 144 91.0 146 93.3 146 87.2 146 83.4 146 79.4 146 87.3 146 47.3 146 64.4 146 46.2 146 89.6 146 93.2 147 73.3 146 69.7 147 60.5 146 67.1 147 41.7 147 14.2 147 92.5 147 99.6 147 98.7 147 100.0 147
SuperSlomo [132]146.3 6.16 146 11.8 146 2.11 144 91.0 146 93.3 146 87.2 146 83.4 146 79.4 146 87.3 146 47.3 146 64.4 146 46.2 146 89.6 146 93.2 147 73.3 146 69.7 147 60.5 146 67.1 147 41.7 147 14.2 147 92.5 147 99.6 147 98.7 147 100.0 147
FGIK [136]146.3 6.16 146 11.8 146 2.11 144 91.0 146 93.3 146 87.2 146 83.4 146 79.4 146 87.3 146 47.3 146 64.4 146 46.2 146 89.6 146 93.2 147 73.3 146 69.7 147 60.5 146 67.1 147 41.7 147 14.2 147 92.5 147 99.6 147 98.7 147 100.0 147
CtxSyn [137]146.3 6.16 146 11.8 146 2.11 144 91.0 146 93.3 146 87.2 146 83.4 146 79.4 146 87.3 146 47.3 146 64.4 146 46.2 146 89.6 146 93.2 147 73.3 146 69.7 147 60.5 146 67.1 147 41.7 147 14.2 147 92.5 147 99.6 147 98.7 147 100.0 147
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

Methodtime*framescolor Reference and notes
[1] 2D-CLG 844 2 gray The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences.
[2] Pyramid LK 12 2 color A modification of Bouguet's pyramidal implementation of Lucas-Kanade.
[3] Horn & Schunck 49 2 gray A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data.
[4] Black & Anandan 328 2 gray A modern Matlab implementation of the Black & Anandan method by Deqing Sun.
[5] Brox et al. 18 2 color T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.)
[6] Fusion 2,666 2 color V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008.
[7] Dynamic MRF 366 2 gray B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.)
[8] Second-order prior 14 2 gray W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[9] GroupFlow 600 2 gray X. Ren. Local Grouping for Optical Flow. CVPR 2008.
[10] SegOF 60 2 color L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available.
[11] Learning Flow 825 2 gray D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008.
[12] CBF 69 2 color W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[13] SPSA-learn 200 2 color Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008.
[14] GraphCuts 1,200 2 color T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008.
[15] F-TV-L1 8 2 gray A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008.
[16] FOLKI 1.4 2 gray G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005.
[17] TV-L1-improved 2.9 2 gray A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision.
[18] DPOF 287 2 color C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.)
[19] Filter Flow 34,000 2 color S. Seitz and S. Baker. Filter flow. ICCV 2009.
[20] Adaptive 9.2 2 gray A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009.
[21] Complementary OF 44 2 color H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[22] Aniso. Huber-L1 2 2 gray M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision.
[23] Rannacher 0.12 2 gray J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009.
[24] TI-DOFE 260 2 gray C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009.
[25] NL-TV-NCC 20 2 color M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010.
[26] MDP-Flow 188 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010.
[27] ACK-Prior 5872 2 color K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010.
[28] LDOF 122 2 color T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011.
[29] p-harmonic 565 2 gray J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010.
[30] TriangleFlow 4200 2 gray B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010.
[31] Classic+NL 972 2 color D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code.
[32] Classic++ 486 2 gray A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010.
[33] Nguyen 33 2 gray D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011.
[34] Modified CLG 133 2 gray R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010.
[35] ComplOF-FED-GPU 0.97 2 color P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010.
[36] Ad-TV-NDC 35 2 gray M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010.
[37] Layers++ 18206 2 color D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010.
[38] OFH 620 3 color H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011.
[39] LSM 1615 2 color K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011.
[40] CostFilter 55 2 color C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011.
[41] Bartels 0.15 2 gray C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU.
[42] Shiralkar 600 2 gray M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242.
[43] HBpMotionGpu 1000 5 gray S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.)
[44] StereoFlow 7200 2 color G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772.
[45] Adaptive flow 121 2 gray T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011.
[46] TC-Flow 2500 5 color S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011.
[47] SLK 300 2 gray T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011.
[48] CLG-TV 29 2 gray M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code.
[49] SimpleFlow 1.7 2 color M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012.
[50] IAOF 57 2 gray D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011.
[51] IAOF2 56 2 gray D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011.
[52] LocallyOriented 9541 2 gray Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012.
[53] IROF-TV 261 2 color H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop.
[54] Sparse Occlusion 2312 2 color A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011.
[55] PGAM+LK 0.37 2 gray A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010.
[56] Sparse-NonSparse 713 2 color L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013.
[57] nLayers 36150 4 color D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012.
[58] IROF++ 187 2 color H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013.
[59] COFM 600 3 color M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013.
[60] Efficient-NL 400 2 color P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012.
[61] BlockOverlap 2 2 gray M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to MMSP 2012.
[62] Ramp 1200 2 color A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012.
[63] Occlusion-TV-L1 538 3 gray C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012.
[64] TV-L1-MCT 90 2 color M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012.
[65] Local-TV-L1 500 2 gray L. Raket. Local smoothness for global optical flow. ICIP 2012.
[66] ALD-Flow 61 2 color M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012.
[67] SIOF 234 2 color L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012.
[68] MDP-Flow2 342 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available.
[69] TCOF 1421 all gray J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013.
[70] LME 476 2 color W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013.
[71] NN-field 362 2 color L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[72] FESL 3310 2 color W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013.
[73] PMF 35 2 color J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013.
[74] FC-2Layers-FF 2662 4 color D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013.
[75] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[76] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[77] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[78] Periodicity 8000 4 color G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013.
[79] SILK 572 2 gray P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP.
[80] CRTflow 13 3 color O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013.
[81] SuperFlow 178 2 color Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507.
[82] Aniso-Texture 300 2 color Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267.
[83] Classic+CPF 640 2 gray Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013.
[84] S2D-Matching 1200 2 color Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479.
[85] AGIF+OF 438 2 gray Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015.
[86] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[87] NNF-Local 673 2 color Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014.
[88] EPPM w/o HM 2.5 2 color L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014.
[89] MLDP_OF 165 2 gray M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014.
[90] RFlow 20 2 gray S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014.
[91] SRR-TVOF-NL 32 all color P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014.
[92] 2DHMM-SAS 157 2 color M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission.
[93] WLIF-Flow 700 2 color Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014.
[94] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[95] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[96] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[97] AggregFlow 1642 2 color D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759.
[98] 2bit-BM-tele 124 2 gray R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013.
[99] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[100] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[101] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[102] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[103] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[104] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[105] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[106] FFV1MT 358 5 gray F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015.
[107] ROF-ND 4 2 color S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015.
[108] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[109] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[110] FlowFields 15 2 color C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015.
[111] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[112] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[113] CombBMOF 51 2 color M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.)
[114] PMMST 182 2 color F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015.
[115] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[116] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[117] CNN-flow-warp+ref 1.4 3 color D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016.
[118] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[119] StereoOF-V1MT 343 2 gray Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132.
[120] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[121] RNLOD-Flow 1040 2 gray C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. IEEE TIP 26(8):4055-4067, 2017.
[122] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[123] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[124] BriefMatch 0.068 2 gray G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62.
[125] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[126] AdaConv-v1 2.8 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[127] SepConv-v1 0.2 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[128] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[129] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[130] FlowFields+ 10.5 2 color C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017.
[131] IIOF-NLDP 150 2 color D.-H. Trinh, W. Blondel, and C. Daul. A general form of illumination-invariant descriptors in variational optical flow estimation. ICIP 2017.
[132] SuperSlomo 0.5 2 color Anonymous. (Interpolation results only.) Super SloMo: High quality estimation of multiple intermediate frames for video interpolation. CVPR 2018 submission 325.
[133] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[134] OFRF 90 2 color T. Mai, M. Gouiffes, and S. Bouchafa. Optical Flow refinement using iterative propagation under color, proximity and flow reliability constraints. Submitted to Signal, Image and Video Processing 2017.
[135] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
[136] FGIK 0.18 2 color Anonymous. (Interpolation results only.) Learning flow-guided interpolation kernels for video frame synthesis. ECCV 2018 submission 433.
[137] CtxSyn 0.07 2 color S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[138] H+S_ROB 5 2 color ROB 2018 baseline submission, based on: E. Meinhardt-Llopis, J. Sanchez, and D. Kondermann. Horn-Schunck optical flow with a multi-scale strategy. Image Processing On Line 3:151–172, 2013.
[139] TVL1_ROB 1 2 color ROB 2018 baseline submission, based on: J. Sanchez, E. Meinhardt-Llopis, and G. Facciolo. TV-L1 optical flow estimation. Image Processing On Line 3:137-150, 2013.
[140] DMF_ROB 10 2 color ROB 2018 baseline submission, based on: P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[141] JOF 657 2 gray C. Zhang, L. Ge, Z. Chen, M. Li, W. Liu, and H. Chen. Refined TV-L1 optical flow estimation using joint filtering. Submitted to IEEE TMM, 2018.
[142] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[143] LiteFlowNet 0.06 2 color T.-W. Hui, X. Tang, and C. C. Loy. LiteFlowNet: A lightweight convolutional neural network for optical flow estimation. CVPR 2018.
[144] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[145] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[146] FF++_ROB 17.43 2 color R. Schuster, C. Bailer, O. Wasenmueller, D. Stricker. FlowFields++: Accurate optical flow correspondences meet robust interpolation. ICIP 2018. Submitted to ROB 2018.
[147] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[148] PWC-Net_ROB 0.069 2 color D. Sun, X. Yang, M.-Y. Liu, and J. Kautz. PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. CVPR 2018.
[149] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[150] ContFlow_ROB 0.45 all color Anonymous. Continual Flow. ROB 2018 submission.
[151] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
* The "time" column lists the reported runtime in seconds on the "Urban" sequence. Note that these runtimes are not normalized by processor speed or type.