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]5.8 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 7 4.91 8 0.02 5 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 21 1.32 2
PMMST [114]9.9 0.20 34 1.20 41 0.03 60 0.57 1 4.20 1 0.21 11 1.12 4 3.98 4 0.06 5 0.16 4 1.79 4 0.00 1 6.17 4 10.4 4 2.09 5 2.24 3 10.3 5 3.42 26 0.00 1 0.00 1 0.00 1 3.14 4 10.1 6 3.34 7
NN-field [71]11.9 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 9 5.03 9 0.04 6 4.24 1 7.24 1 0.70 1 5.93 56 6.73 1 2.33 10 0.00 1 0.00 1 0.00 1 3.87 12 13.1 33 1.27 1
OFLAF [77]13.4 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 32 7.31 10 12.4 10 2.79 9 3.20 13 11.6 7 3.15 22 0.00 1 0.00 1 0.00 1 3.66 10 9.73 5 7.15 26
Layers++ [37]19.4 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 73 0.92 18 5.94 11 0.24 42 6.07 3 9.99 3 3.95 14 6.14 62 15.3 26 5.23 80 0.00 1 0.00 1 0.00 1 4.11 15 10.5 7 7.50 33
ComponentFusion [96]19.5 0.17 15 1.02 19 0.03 60 0.93 10 6.31 11 0.23 15 1.48 10 5.26 10 0.22 17 0.68 10 6.90 16 0.05 7 10.5 44 17.2 46 7.34 47 3.34 15 15.8 32 3.80 36 0.00 1 0.00 1 0.00 1 3.81 11 11.2 12 6.45 21
TC/T-Flow [76]19.5 0.11 2 0.67 2 0.00 1 1.63 50 8.48 32 0.45 29 2.21 19 7.45 20 0.16 13 1.20 48 10.2 57 0.16 10 9.34 35 14.9 31 6.04 34 1.76 2 9.86 4 1.36 1 0.00 1 0.00 1 0.00 1 4.64 24 12.6 24 7.19 27
MDP-Flow2 [68]20.4 0.18 21 1.07 24 0.03 60 0.82 4 5.18 4 0.20 10 1.31 8 4.69 8 0.09 8 1.24 55 11.0 65 0.24 42 9.23 32 15.2 35 5.96 33 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 14
PWC-Net_ROB [148]23.6 0.15 6 0.89 7 0.01 35 1.39 35 10.0 54 0.40 26 2.59 39 8.97 42 0.71 60 0.59 8 4.66 7 0.16 10 9.75 40 16.4 42 4.25 16 6.09 59 15.2 23 3.22 23 0.00 1 0.00 1 0.00 1 3.57 7 12.1 19 3.32 6
CombBMOF [113]24.3 0.20 34 1.18 36 0.03 60 1.05 14 6.42 12 0.16 4 1.66 13 5.67 13 0.01 2 0.79 13 6.82 15 0.16 10 7.66 13 12.5 12 4.37 18 8.16 97 15.3 26 7.67 126 0.00 1 0.00 1 0.00 1 4.31 17 11.0 9 7.79 37
NNF-EAC [103]24.7 0.17 15 1.03 20 0.01 35 1.01 11 5.78 9 0.38 25 1.81 15 6.09 15 0.13 11 1.27 59 11.4 67 0.24 42 8.50 22 14.2 25 5.00 25 4.85 37 12.2 11 4.55 55 0.00 1 0.00 1 0.00 1 4.77 28 13.1 33 7.37 29
WLIF-Flow [93]24.8 0.20 34 1.21 42 0.01 35 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 54 8.40 21 14.0 21 4.94 24 4.91 39 13.0 13 3.79 35 0.00 1 0.00 1 0.00 1 4.98 34 12.6 24 8.37 50
3DFlow [135]25.3 0.26 75 1.57 80 0.00 1 1.31 28 9.13 42 0.31 20 2.56 37 8.87 39 0.25 19 0.11 2 1.19 2 0.00 1 8.69 26 14.2 25 5.21 26 8.16 97 15.8 32 4.22 45 0.00 1 0.00 1 0.00 1 2.86 2 9.33 2 2.36 4
MLDP_OF [89]26.2 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 18 8.84 27 14.4 27 5.24 28 2.41 4 11.1 6 1.54 3 0.29 124 0.00 1 1.28 127 5.41 46 12.9 30 5.66 16
nLayers [57]26.4 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 71 6.91 8 11.4 8 3.98 15 6.52 68 12.6 12 5.28 82 0.00 1 0.00 1 0.00 1 4.63 23 12.5 23 8.25 46
FC-2Layers-FF [74]26.5 0.19 27 1.10 28 0.00 1 1.53 42 10.0 54 0.68 51 1.47 9 5.05 9 0.37 31 1.07 27 8.29 22 0.22 32 6.46 5 10.5 5 3.24 10 6.93 76 15.2 23 5.43 87 0.00 1 0.00 1 0.00 1 4.89 30 12.6 24 7.93 39
FlowFields+ [130]27.5 0.15 6 0.88 6 0.01 35 1.38 33 8.90 39 0.68 51 2.23 21 7.99 24 0.44 36 0.70 11 6.60 13 0.20 25 12.0 55 19.4 58 7.65 52 2.62 5 16.5 47 1.82 7 0.00 1 0.00 1 0.00 1 5.64 52 18.0 64 5.92 18
IIOF-NLDP [131]27.5 0.32 98 1.90 101 0.00 1 1.27 26 8.57 33 0.16 4 3.02 53 9.58 49 0.20 14 0.48 6 3.49 6 0.13 9 9.15 30 14.9 31 4.86 22 6.07 58 14.8 22 4.05 43 0.00 1 0.00 1 0.00 1 4.43 20 12.0 17 5.52 15
Correlation Flow [75]27.6 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 12 5.14 10 0.22 32 11.5 50 17.7 48 9.04 65 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]29.7 0.20 34 1.16 34 0.00 1 1.36 30 7.94 26 0.53 39 1.69 14 5.76 14 0.64 54 1.10 31 8.60 26 0.24 42 6.59 6 11.1 6 3.26 11 3.52 19 11.6 7 3.39 24 0.13 114 0.00 1 0.44 109 4.21 16 11.4 14 7.94 41
AGIF+OF [85]30.4 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 36 7.56 12 12.5 12 4.30 17 6.71 71 15.2 23 4.99 71 0.00 1 0.00 1 0.00 1 5.07 37 13.0 32 8.68 58
IROF++ [58]30.5 0.23 60 1.37 62 0.00 1 1.37 32 8.26 29 0.45 29 2.40 27 7.86 22 0.51 41 1.16 44 9.50 48 0.24 42 8.06 17 13.2 16 4.86 22 5.64 52 16.4 42 4.51 53 0.00 1 0.00 1 0.00 1 4.62 21 12.7 29 7.93 39
PMF [73]31.0 0.20 34 1.19 38 0.03 60 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 36 7.32 11 12.4 10 1.91 3 5.47 46 16.3 39 4.67 60 0.09 108 0.00 1 0.25 104 3.51 6 9.50 3 6.99 24
HAST [109]32.2 0.21 46 1.27 53 0.03 60 1.55 45 6.58 14 0.85 67 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 53 14.2 18 5.14 78 0.01 91 0.00 1 0.05 93 2.21 1 7.87 1 2.21 3
ProbFlowFields [128]33.0 0.20 34 1.18 36 0.03 60 1.25 24 7.90 25 0.64 48 2.55 36 8.95 40 1.08 76 0.25 5 2.68 5 0.05 7 12.5 66 19.9 64 8.91 63 2.82 9 15.8 32 2.70 15 0.00 1 0.00 1 0.00 1 5.90 57 18.1 65 6.95 23
SVFilterOh [111]34.4 0.22 53 1.31 55 0.05 80 1.14 20 6.84 17 0.30 19 2.13 17 7.39 18 0.69 59 0.86 14 7.24 17 0.16 10 8.17 18 13.8 19 2.18 7 6.69 69 15.3 26 4.47 52 0.27 123 0.00 1 0.74 114 2.89 3 9.59 4 3.97 11
EPPM w/o HM [88]35.2 0.21 46 1.25 51 0.03 60 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 71 4.04 42 0.43 131 0.00 1 0.76 115 3.98 14 11.1 10 7.10 25
TC-Flow [46]35.3 0.13 3 0.77 3 0.00 1 1.38 33 8.10 28 0.47 32 2.97 52 10.0 53 0.34 26 1.36 67 10.5 63 0.25 54 11.2 47 18.1 50 7.49 49 3.36 16 17.1 56 1.78 6 0.00 1 0.00 1 0.00 1 6.35 63 17.8 63 10.0 79
CostFilter [40]35.3 0.22 53 1.32 58 0.03 60 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 44 15.9 36 3.96 41 0.07 105 0.00 1 0.12 98 4.75 27 13.5 40 7.19 27
ALD-Flow [66]38.1 0.14 5 0.85 5 0.01 35 1.70 53 8.34 30 0.50 35 2.94 50 9.96 52 0.38 32 1.68 78 13.0 76 0.32 65 11.8 54 18.8 55 8.42 59 2.93 10 16.4 42 1.70 5 0.00 1 0.00 1 0.00 1 5.91 59 17.4 59 8.45 53
FlowFields [110]38.3 0.16 11 0.97 13 0.02 54 1.54 44 9.90 53 0.72 55 2.38 25 8.48 36 0.58 51 1.03 21 9.05 37 0.31 63 12.5 66 20.3 70 8.76 62 3.16 12 18.0 70 3.08 21 0.00 1 0.00 1 0.00 1 6.22 61 19.0 69 6.76 22
COFM [59]38.5 0.28 83 1.64 83 0.06 85 1.31 28 7.81 23 0.57 43 3.57 63 12.0 65 1.10 78 0.91 17 7.78 19 0.16 10 11.7 53 18.5 54 10.3 79 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 20
RNLOD-Flow [121]39.1 0.17 15 1.03 20 0.00 1 1.50 41 9.63 48 0.56 42 3.15 56 10.1 55 0.56 50 1.14 37 9.02 35 0.20 25 9.73 39 15.7 39 6.54 40 5.43 44 14.7 20 4.56 57 0.06 103 0.00 1 0.34 105 4.41 18 11.3 13 7.56 34
Sparse-NonSparse [56]39.9 0.22 53 1.31 55 0.00 1 1.87 65 11.4 67 0.80 62 2.47 33 8.05 26 0.52 44 1.15 43 8.89 31 0.24 42 9.37 36 15.3 36 5.94 32 7.18 79 16.3 39 5.47 89 0.00 1 0.00 1 0.00 1 5.08 38 13.1 33 8.42 51
LSM [39]40.1 0.21 46 1.23 46 0.00 1 1.88 67 11.5 68 0.82 64 2.45 31 8.04 25 0.52 44 1.12 34 9.06 38 0.23 36 9.27 34 15.1 34 6.05 35 7.21 81 16.5 47 5.47 89 0.00 1 0.00 1 0.00 1 5.29 43 13.8 42 8.49 55
S2F-IF [123]40.3 0.18 21 1.07 24 0.02 54 1.53 42 10.0 54 0.72 55 2.37 24 8.45 35 0.54 47 1.21 49 9.59 51 0.35 67 12.7 70 20.3 70 9.20 69 3.41 17 17.7 65 3.70 33 0.00 1 0.00 1 0.00 1 5.36 45 16.5 54 6.13 19
WRT [151]40.5 0.37 104 2.21 108 0.00 1 1.78 58 11.7 70 0.42 28 5.99 100 14.9 91 0.52 44 0.10 1 1.14 1 0.00 1 9.05 29 14.7 29 5.43 29 8.84 111 15.6 30 4.60 58 0.00 1 0.00 1 0.00 1 5.13 39 12.2 20 5.72 17
LME [70]40.7 0.24 64 1.40 66 0.04 76 0.84 6 5.51 6 0.21 11 3.70 65 8.78 37 5.39 110 1.38 69 11.0 65 0.37 69 9.52 38 15.3 36 7.58 50 3.73 21 16.9 54 4.43 50 0.00 1 0.00 1 0.00 1 4.62 21 12.6 24 7.77 36
HBM-GC [105]40.8 0.29 86 1.72 90 0.03 60 1.36 30 8.81 37 0.71 54 2.92 48 10.0 53 0.79 61 1.21 49 8.97 33 0.37 69 8.90 28 14.6 28 5.72 31 5.58 50 9.50 3 3.51 29 0.00 1 0.00 1 0.00 1 5.23 42 15.1 48 8.28 47
FMOF [94]40.9 0.20 34 1.19 38 0.00 1 1.61 48 9.42 45 0.53 39 2.03 16 6.86 16 0.22 17 1.04 23 8.71 27 0.16 10 8.59 23 14.0 21 4.44 19 7.80 91 16.2 37 5.73 97 0.09 108 0.00 1 0.81 117 5.75 54 14.6 47 8.44 52
MDP-Flow [26]41.5 0.13 3 0.78 4 0.00 1 1.05 14 6.71 16 0.64 48 2.31 23 8.09 27 1.26 84 1.35 65 12.5 75 0.28 58 10.4 43 16.8 45 7.29 45 5.39 43 16.9 54 4.89 67 0.00 1 0.00 1 0.00 1 8.69 95 21.5 88 12.1 95
FESL [72]41.5 0.23 60 1.35 61 0.00 1 1.71 55 9.38 44 0.54 41 2.22 20 7.40 19 0.31 21 1.08 28 9.18 40 0.16 10 7.97 16 13.0 14 4.61 20 7.68 88 16.5 47 5.87 100 0.09 108 0.00 1 0.17 101 4.96 33 12.4 21 8.31 48
NL-TV-NCC [25]41.9 0.24 64 1.43 70 0.01 35 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 10 11.5 50 18.3 53 7.31 46 8.51 102 20.7 97 4.68 61 0.00 1 0.00 1 0.00 1 5.59 50 16.1 51 5.10 13
Classic+NL [31]42.8 0.23 60 1.34 60 0.01 35 1.93 70 11.7 70 0.80 62 2.57 38 8.35 32 0.58 51 1.22 52 9.29 44 0.24 42 8.66 25 14.1 23 5.48 30 7.52 86 16.3 39 5.42 85 0.00 1 0.00 1 0.00 1 5.06 36 12.9 30 8.47 54
DPOF [18]42.9 0.17 15 0.99 15 0.00 1 2.06 78 10.3 59 0.92 72 0.99 1 3.51 1 0.05 4 1.08 28 9.87 55 0.17 18 8.25 20 13.8 19 3.72 12 9.58 120 18.7 73 5.78 98 1.06 137 0.00 1 2.93 135 4.41 18 13.4 39 3.94 10
ResPWCR_ROB [145]44.2 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 89 1.04 23 8.53 25 0.22 32 11.3 48 18.2 51 7.48 48 6.92 75 17.5 63 5.48 91 0.00 1 0.00 1 0.00 1 6.95 70 20.1 77 8.98 65
Classic+CPF [83]44.9 0.21 46 1.23 46 0.01 35 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 36 8.60 24 14.1 23 5.23 27 8.01 95 16.4 42 5.26 81 0.20 120 0.00 1 0.86 119 4.71 25 12.0 17 8.34 49
JOF [141]45.2 0.31 94 1.77 97 0.07 96 1.97 73 10.7 61 1.00 77 2.14 18 7.04 17 0.60 53 1.13 35 8.98 34 0.24 42 7.05 9 11.9 9 3.77 13 6.22 64 14.7 20 5.04 73 0.01 91 0.00 1 0.00 1 4.83 29 13.1 33 8.17 45
ProFlow_ROB [147]45.5 0.28 83 1.66 84 0.01 35 1.65 52 10.1 58 0.73 57 3.30 57 11.4 61 0.64 54 1.35 65 10.4 61 0.23 36 12.1 56 19.8 62 6.97 44 3.91 24 16.6 51 2.12 8 0.00 1 0.00 1 0.00 1 5.60 51 16.8 57 7.48 32
Efficient-NL [60]45.6 0.22 53 1.29 54 0.00 1 1.25 24 7.99 27 0.48 34 2.92 48 9.31 43 0.31 21 1.23 54 9.67 54 0.31 63 8.23 19 13.5 18 4.72 21 8.45 101 17.1 56 6.06 103 0.12 113 0.00 1 0.54 111 4.71 25 11.6 16 7.75 35
Aniso-Texture [82]47.1 0.16 11 0.94 11 0.02 54 1.16 21 8.46 31 0.50 35 5.29 89 14.6 88 1.10 78 0.87 15 6.69 14 0.17 18 14.2 91 20.8 75 14.7 99 5.50 48 18.6 72 4.62 59 0.00 1 0.00 1 0.00 1 6.99 71 18.1 65 10.3 82
Complementary OF [21]47.2 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 70 12.4 72 0.28 58 14.9 98 21.6 93 15.4 104 7.75 89 17.6 64 3.64 31 0.00 1 0.00 1 0.00 1 7.27 78 22.2 96 9.59 74
SRR-TVOF-NL [91]47.4 0.19 27 1.05 22 0.03 60 3.08 102 13.8 97 1.68 100 3.97 69 12.4 69 0.84 62 1.22 52 9.35 47 0.20 25 11.5 50 16.7 44 12.3 89 2.79 7 13.5 15 3.68 32 0.00 1 0.00 1 0.00 1 5.69 53 13.1 33 10.1 80
LiteFlowNet [143]47.9 0.31 94 1.86 99 0.03 60 1.96 72 11.5 68 0.68 51 3.06 54 10.4 57 0.51 41 0.89 16 6.31 12 0.19 23 13.1 72 20.9 77 8.46 60 5.32 42 16.5 47 2.97 20 0.00 1 0.00 1 0.00 1 6.37 64 17.6 62 8.62 56
IROF-TV [53]49.2 0.22 53 1.24 49 0.01 35 1.83 63 11.9 74 0.87 69 2.96 51 9.37 44 0.50 38 1.70 79 14.6 86 0.46 77 9.51 37 15.4 38 6.49 39 4.78 35 22.9 110 4.55 55 0.00 1 0.00 1 0.00 1 5.17 40 14.4 46 8.73 60
Ramp [62]49.2 0.21 46 1.24 49 0.00 1 1.77 57 11.1 64 0.79 60 2.39 26 7.95 23 0.55 49 1.17 46 9.16 39 0.24 42 9.25 33 14.9 31 6.31 37 7.18 79 15.7 31 5.42 85 0.19 119 0.00 1 0.96 121 5.18 41 13.3 38 8.87 64
OFH [38]50.1 0.17 15 1.00 17 0.00 1 1.80 60 9.80 50 0.66 50 4.49 78 13.2 80 0.47 37 1.62 76 13.6 81 0.35 67 13.2 75 20.8 75 10.2 77 3.85 22 20.4 94 2.41 11 0.00 1 0.00 1 0.00 1 7.06 74 21.6 90 9.31 69
ROF-ND [107]51.1 0.29 86 1.73 92 0.01 35 2.75 96 11.0 62 0.73 57 3.45 60 10.7 58 0.51 41 0.13 3 1.44 3 0.00 1 12.2 58 18.8 55 10.5 80 6.28 66 17.1 56 4.80 65 0.00 1 0.00 1 0.00 1 8.30 91 21.5 88 9.38 70
OAR-Flow [125]51.6 0.19 27 1.12 32 0.06 85 2.86 97 12.0 75 1.41 95 4.36 75 13.9 83 1.43 93 1.51 72 11.7 69 0.23 36 12.6 69 20.0 67 8.47 61 2.80 8 16.4 42 1.37 2 0.00 1 0.00 1 0.00 1 5.56 49 16.7 55 8.15 44
FF++_ROB [146]52.2 0.29 86 1.66 84 0.06 85 1.74 56 11.3 66 0.84 66 3.66 64 12.1 67 1.40 92 1.14 37 9.66 53 0.33 66 12.4 61 20.1 69 8.17 56 3.96 25 15.4 29 2.67 13 0.00 1 0.00 1 0.00 1 5.83 56 16.3 52 9.01 66
TCOF [69]53.0 0.18 21 1.06 23 0.00 1 1.56 46 9.24 43 0.60 45 4.63 80 12.8 76 0.89 65 1.34 64 12.4 72 0.20 25 12.4 61 19.6 61 9.52 71 6.02 57 14.3 19 5.03 72 0.34 129 0.00 1 1.23 126 4.94 31 13.6 41 8.00 42
TV-L1-MCT [64]53.7 0.22 53 1.33 59 0.00 1 1.64 51 9.85 51 0.52 37 2.86 47 9.38 45 0.32 24 1.14 37 8.89 31 0.24 42 10.6 45 16.4 42 9.05 66 8.81 109 17.2 60 5.12 77 0.08 107 0.00 1 0.84 118 5.93 60 14.3 45 10.1 80
ACK-Prior [27]55.1 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 63 0.18 21 12.4 61 18.0 49 11.2 82 9.00 115 19.4 84 6.39 110 0.17 117 0.00 1 1.01 123 9.72 104 20.1 77 13.3 100
2DHMM-SAS [92]55.3 0.20 34 1.21 42 0.00 1 1.80 60 10.4 60 0.63 47 4.15 70 11.3 60 0.86 63 1.24 55 9.61 52 0.25 54 9.18 31 14.8 30 6.44 38 8.98 114 17.3 61 4.98 69 0.13 114 0.00 1 0.69 113 5.55 48 14.2 44 9.22 67
CRTflow [80]55.9 0.18 21 0.99 15 0.03 60 1.70 53 9.09 41 0.59 44 4.56 79 12.8 76 0.68 56 2.03 96 15.1 91 0.64 87 12.4 61 20.0 67 8.26 57 4.42 29 24.0 115 3.47 27 0.00 1 0.00 1 0.00 1 7.88 84 22.0 95 10.4 84
PGM-C [120]56.0 0.20 34 1.19 38 0.07 96 1.87 65 11.8 73 0.85 67 2.76 43 9.82 51 0.92 69 1.99 93 15.1 91 0.74 96 13.1 72 21.2 79 9.19 68 3.52 19 19.2 80 2.47 12 0.00 1 0.00 1 0.00 1 6.38 65 19.5 73 8.65 57
Sparse Occlusion [54]57.4 0.24 64 1.38 64 0.06 85 1.27 26 7.83 24 0.45 29 3.42 58 11.1 59 0.33 25 1.52 74 11.4 67 0.28 58 10.9 46 17.6 47 6.76 42 4.10 27 16.2 37 4.27 47 0.03 95 0.17 140 0.15 99 5.90 57 15.7 49 8.69 59
SimpleFlow [49]57.5 0.22 53 1.31 55 0.00 1 1.78 58 11.0 62 0.82 64 4.30 74 12.5 72 1.22 83 1.16 44 9.20 41 0.24 42 9.84 42 15.8 40 6.94 43 8.51 102 17.3 61 6.11 106 0.09 108 0.00 1 0.39 107 5.01 35 14.1 43 8.00 42
CPM-Flow [116]58.7 0.21 46 1.23 46 0.07 96 1.92 69 12.1 76 0.89 70 2.64 41 9.39 46 0.92 69 1.96 89 14.8 87 0.72 94 13.1 72 21.2 79 8.92 64 4.84 36 19.1 79 3.40 25 0.00 1 0.00 1 0.00 1 6.92 69 20.5 80 9.43 72
ComplOF-FED-GPU [35]60.2 0.19 27 1.10 28 0.03 60 2.32 85 12.5 84 0.92 72 2.76 43 9.65 50 0.31 21 1.65 77 13.1 77 0.38 71 13.4 80 21.2 79 10.2 77 8.60 106 22.8 108 4.22 45 0.00 1 0.00 1 0.00 1 7.44 79 22.4 97 9.81 75
EpicFlow [102]63.0 0.20 34 1.17 35 0.07 96 1.91 68 12.1 76 0.90 71 3.70 65 12.7 74 0.89 65 1.96 89 14.8 87 0.74 96 13.4 80 21.3 84 9.97 73 6.71 71 19.3 82 3.90 38 0.00 1 0.00 1 0.00 1 7.03 72 20.1 77 9.91 76
S2D-Matching [84]63.8 0.33 100 1.92 103 0.06 85 2.04 76 12.4 81 0.79 60 4.15 70 13.0 78 1.09 77 1.09 30 8.04 21 0.24 42 9.82 41 15.9 41 6.68 41 7.85 92 16.4 42 5.58 93 0.20 120 0.00 1 0.96 121 4.94 31 12.6 24 8.81 62
AggregFlow [97]64.4 0.53 113 2.62 121 0.12 117 2.72 94 13.2 90 1.45 96 3.90 68 13.0 78 1.85 98 1.06 26 9.26 42 0.18 21 12.1 56 19.4 58 7.83 53 3.05 11 12.1 10 2.29 9 0.04 101 0.00 1 0.44 109 5.82 55 15.9 50 9.26 68
DeepFlow2 [108]64.5 0.26 75 1.53 77 0.08 104 2.56 91 11.7 70 1.30 93 3.73 67 11.5 63 0.90 67 1.99 93 15.1 91 0.65 89 12.3 59 19.5 60 9.07 67 4.57 31 18.7 73 2.81 17 0.00 1 0.00 1 0.00 1 8.01 88 21.0 83 10.8 86
TF+OM [100]64.6 0.16 11 0.98 14 0.01 35 1.85 64 10.0 54 1.15 87 4.71 84 12.6 73 5.84 111 1.79 84 14.0 84 0.69 91 15.4 104 22.1 97 16.5 109 5.62 51 19.8 89 3.95 40 0.00 1 0.00 1 0.00 1 8.18 89 20.6 82 12.0 94
Adaptive [20]66.2 0.29 86 1.72 90 0.06 85 2.04 76 12.5 84 1.13 85 5.51 95 14.7 89 0.68 56 1.83 85 13.9 83 0.59 85 12.7 70 19.9 64 10.1 74 7.15 77 18.9 77 4.08 44 0.00 1 0.00 1 0.00 1 6.38 65 16.4 53 8.82 63
ContinualFlow_ROB [153]66.7 0.26 75 1.50 74 0.02 54 3.07 101 15.6 103 1.24 89 5.35 92 16.3 106 3.58 107 1.36 67 10.4 61 0.21 29 13.9 87 22.7 103 7.58 50 8.27 100 19.4 84 5.84 99 0.00 1 0.00 1 0.00 1 5.35 44 17.5 60 4.42 12
LFNet_ROB [150]70.1 0.25 71 1.50 74 0.04 76 1.94 71 12.3 80 0.95 75 4.69 82 14.9 91 1.47 94 1.14 37 9.32 45 0.51 81 16.3 113 24.6 123 15.5 105 5.01 40 22.7 106 3.48 28 0.00 1 0.00 1 0.00 1 8.24 90 23.7 107 11.4 91
Steered-L1 [118]71.2 0.10 1 0.59 1 0.01 35 1.01 11 6.84 17 0.52 37 2.76 43 9.44 47 0.91 68 1.78 82 14.9 89 0.51 81 14.0 90 20.5 72 15.2 102 9.02 116 19.9 90 6.57 114 1.07 138 0.00 1 7.19 139 12.1 114 22.9 100 20.6 120
DMF_ROB [140]71.2 0.18 21 1.07 24 0.03 60 2.32 85 12.7 86 1.10 82 4.84 86 15.1 98 1.27 87 2.06 98 15.9 96 0.75 99 13.7 83 21.2 79 12.3 89 7.35 84 21.7 103 5.05 74 0.00 1 0.00 1 0.00 1 8.30 91 21.8 92 11.1 88
RFlow [90]71.4 0.20 34 1.21 42 0.01 35 1.58 47 9.77 49 0.77 59 4.69 82 13.5 81 0.34 26 2.30 109 17.7 109 0.80 102 14.3 92 21.4 86 15.1 101 5.47 46 20.9 99 4.98 69 0.01 91 0.00 1 0.15 99 7.91 86 21.0 83 10.6 85
EAI-Flow [152]72.5 0.27 80 1.59 81 0.06 85 3.31 104 15.7 104 1.68 100 5.29 89 15.9 103 2.31 101 1.73 81 13.1 77 0.59 85 14.9 98 23.3 111 11.0 81 4.60 32 17.7 65 2.85 18 0.00 1 0.00 1 0.00 1 7.19 76 19.6 75 11.2 90
TriangleFlow [30]72.6 0.24 64 1.39 65 0.00 1 2.50 90 14.3 98 0.98 76 4.46 77 12.7 74 0.41 35 1.49 71 12.2 71 0.42 75 15.8 108 23.1 107 16.4 108 8.57 104 17.7 65 4.86 66 0.03 95 0.00 1 0.05 93 6.59 67 17.3 58 9.55 73
Aniso. Huber-L1 [22]72.7 0.29 86 1.66 84 0.06 85 2.43 89 13.1 89 1.12 84 5.68 96 14.3 87 1.27 87 1.56 75 12.4 72 0.30 62 12.4 61 19.2 57 10.1 74 4.70 34 17.1 56 4.45 51 0.17 117 0.00 1 0.89 120 6.28 62 16.7 55 8.80 61
Occlusion-TV-L1 [63]73.4 0.27 80 1.55 79 0.06 85 1.99 75 12.1 76 1.14 86 5.42 93 14.9 91 0.93 71 1.83 85 14.0 84 0.49 79 13.6 82 21.2 79 11.5 84 6.13 61 19.6 88 5.37 84 0.00 1 0.00 1 0.00 1 9.19 98 23.4 106 11.5 92
DeepFlow [86]73.4 0.34 103 1.74 94 0.09 106 2.87 98 12.4 81 1.56 97 4.42 76 12.4 69 2.69 104 2.20 103 16.1 98 0.81 103 12.3 59 19.8 62 8.36 58 4.85 37 20.1 91 2.95 19 0.00 1 0.00 1 0.00 1 9.35 99 23.3 105 12.7 97
CBF [12]75.2 0.18 21 1.09 27 0.01 35 2.37 87 12.9 87 1.94 104 4.28 73 12.0 65 1.13 81 1.97 92 16.1 98 0.66 90 13.3 79 20.5 72 12.7 93 5.89 55 18.8 76 4.73 62 0.45 133 0.00 1 1.33 129 7.67 81 18.9 68 12.7 97
LocallyOriented [52]76.3 0.49 112 2.66 122 0.06 85 3.28 103 15.4 101 1.91 103 6.59 106 16.9 108 1.20 82 1.29 60 10.1 56 0.52 84 14.6 94 21.5 88 12.6 91 7.79 90 16.7 52 4.33 49 0.00 1 0.00 1 0.00 1 7.87 83 19.1 71 11.1 88
OFRF [134]76.4 0.54 115 2.51 116 0.12 117 7.58 130 15.8 105 7.13 135 7.71 114 15.0 94 5.91 113 1.78 82 9.27 43 1.09 112 11.3 48 18.2 51 6.18 36 6.74 74 13.5 15 2.79 16 0.00 1 0.00 1 0.00 1 12.7 116 19.0 69 27.9 130
TV-L1-improved [17]78.6 0.25 71 1.46 72 0.07 96 1.82 62 11.1 64 1.02 78 5.46 94 15.0 94 1.32 90 2.26 106 16.4 101 0.79 101 13.8 85 21.5 88 11.8 85 9.40 117 23.6 114 6.48 111 0.00 1 0.00 1 0.00 1 7.89 85 21.3 87 10.3 82
FlowNet2 [122]79.0 0.74 126 3.32 129 0.12 117 5.00 119 17.2 111 2.46 111 6.13 102 15.0 94 5.85 112 1.29 60 10.3 60 0.40 74 13.2 75 21.6 93 8.11 54 7.27 82 17.7 65 6.06 103 0.00 1 0.00 1 0.05 93 5.52 47 17.5 60 3.70 8
DF-Auto [115]79.1 0.61 121 2.33 113 0.10 112 4.04 111 15.3 100 2.49 112 6.59 106 14.8 90 6.66 115 1.84 87 15.0 90 0.51 81 14.9 98 21.5 88 16.8 111 3.47 18 16.7 52 3.82 37 0.00 1 0.00 1 0.00 1 7.99 87 19.5 73 11.6 93
TriFlow [95]79.5 0.27 80 1.62 82 0.01 35 2.27 84 13.2 90 1.24 89 7.10 111 16.9 108 7.37 118 1.31 63 11.7 69 0.43 76 17.3 119 23.4 115 20.6 121 3.24 14 15.8 32 3.91 39 4.67 145 0.00 1 18.1 145 6.86 68 18.1 65 7.89 38
EPMNet [133]80.8 0.64 124 3.15 126 0.09 106 5.25 120 18.8 117 2.74 117 5.08 88 14.0 84 2.76 105 1.51 72 13.3 79 0.28 58 13.2 75 21.6 93 8.11 54 7.27 82 17.7 65 6.06 103 0.00 1 0.00 1 0.02 92 7.03 72 23.1 101 3.19 5
CLG-TV [48]81.1 0.31 94 1.67 88 0.06 85 2.10 80 13.0 88 0.92 72 5.33 91 14.2 86 1.04 75 1.71 80 13.7 82 0.38 71 13.9 87 21.4 86 12.0 86 5.20 41 22.7 106 5.07 75 0.20 120 0.00 1 1.01 123 7.85 82 19.4 72 9.91 76
Bartels [41]82.5 0.24 64 1.40 66 0.01 35 1.42 36 8.88 38 0.62 46 3.51 62 12.4 69 1.00 74 2.26 106 15.8 95 0.95 107 15.5 105 23.3 111 15.8 107 7.99 94 23.0 111 5.20 79 0.33 126 0.00 1 1.92 132 9.95 106 24.0 108 13.7 103
Brox et al. [5]82.9 0.25 71 1.45 71 0.03 60 2.22 83 13.7 96 1.07 80 3.44 59 11.4 61 0.68 56 2.20 103 16.7 105 0.72 94 17.8 124 23.4 115 24.6 130 8.90 113 24.6 118 6.63 115 0.00 1 0.00 1 0.00 1 10.6 109 25.9 116 14.8 108
Fusion [6]83.5 0.24 64 1.41 68 0.05 80 1.13 19 8.57 33 0.47 32 2.45 31 8.15 28 0.93 71 2.12 102 18.3 115 1.21 113 16.2 112 23.1 107 19.6 119 6.72 73 18.7 73 5.67 95 0.07 105 0.15 138 0.10 97 10.4 108 24.9 113 14.6 107
Classic++ [32]84.0 0.26 75 1.50 74 0.07 96 2.08 79 12.2 79 1.03 79 4.84 86 14.0 84 1.26 84 2.07 100 16.1 98 0.64 87 13.9 87 22.5 100 10.1 74 6.11 60 23.1 112 5.28 82 0.06 103 0.00 1 0.34 105 8.66 94 21.7 91 11.0 87
SegOF [10]84.3 0.24 64 1.41 68 0.05 80 4.72 117 21.4 121 3.68 121 9.28 121 19.5 120 4.83 108 1.05 25 7.42 18 0.78 100 20.7 134 27.1 132 28.6 135 10.4 124 26.0 122 7.80 127 0.00 1 0.00 1 0.00 1 7.25 77 20.0 76 7.44 31
Rannacher [23]86.5 0.33 100 1.95 104 0.07 96 2.21 82 13.4 93 1.29 92 5.78 97 15.6 101 1.48 95 2.51 113 17.8 110 0.95 107 14.5 93 22.5 100 12.2 88 9.72 121 24.8 119 6.66 117 0.00 1 0.00 1 0.00 1 7.50 80 21.1 86 9.97 78
SuperFlow [81]87.5 0.45 108 1.75 95 0.10 112 3.01 100 13.4 93 2.04 105 6.82 110 15.2 99 8.24 121 1.96 89 17.0 107 0.50 80 15.6 107 22.2 98 19.2 118 5.87 54 20.6 95 5.46 88 0.00 1 0.00 1 0.00 1 10.1 107 24.6 111 13.4 101
AugFNG_ROB [144]88.2 0.57 119 2.19 107 0.11 115 4.08 113 16.3 108 2.52 114 8.00 116 19.2 119 8.51 122 1.21 49 10.2 57 0.26 57 16.5 116 25.6 129 13.4 95 7.17 78 24.2 116 5.99 101 0.00 1 0.00 1 0.00 1 8.96 97 25.1 114 9.39 71
BriefMatch [124]88.6 0.16 11 0.94 11 0.01 35 1.97 73 9.60 47 1.10 82 2.79 46 9.56 48 0.54 47 2.11 101 15.6 94 0.70 92 14.6 94 21.5 88 15.2 102 10.4 124 22.0 104 8.36 130 2.52 144 0.62 148 13.7 144 13.6 123 25.5 115 22.0 124
Local-TV-L1 [65]88.9 0.53 113 2.10 105 0.12 117 4.96 118 18.0 115 3.44 120 8.54 119 16.7 107 6.16 114 2.47 112 18.5 117 1.01 111 12.5 66 19.9 64 9.65 72 5.53 49 19.5 86 4.95 68 0.00 1 0.00 1 0.00 1 13.4 120 24.2 109 27.1 129
SIOF [67]89.4 0.42 107 2.28 109 0.08 104 3.55 107 17.7 114 2.05 106 8.15 117 17.9 115 7.78 120 2.41 111 17.9 111 1.00 110 15.5 105 22.7 103 17.8 115 4.67 33 19.5 86 4.77 64 0.00 1 0.00 1 0.00 1 9.35 99 21.8 92 17.7 114
Second-order prior [8]92.1 0.26 75 1.53 77 0.05 80 2.88 99 15.5 102 1.60 98 5.87 98 15.3 100 1.11 80 2.21 105 17.2 108 0.94 106 13.8 85 21.3 84 12.6 91 7.46 85 27.8 128 5.71 96 0.16 116 0.00 1 0.76 115 8.65 93 21.0 83 13.9 105
p-harmonic [29]92.3 0.29 86 1.73 92 0.02 54 2.16 81 13.2 90 1.33 94 5.87 98 15.8 102 1.59 96 2.55 114 17.9 111 1.49 116 17.0 117 22.7 103 23.3 127 4.53 30 21.5 102 4.53 54 0.03 95 0.02 137 0.00 1 9.65 103 23.2 104 15.0 109
Dynamic MRF [7]94.0 0.30 93 1.79 98 0.04 76 2.37 87 14.9 99 1.09 81 4.81 85 15.0 94 0.86 63 2.66 115 18.2 114 1.25 114 17.6 122 25.7 130 18.1 116 10.9 129 30.4 133 7.45 123 0.00 1 0.00 1 0.00 1 15.1 126 29.9 131 21.9 123
Shiralkar [42]94.4 0.28 83 1.66 84 0.02 54 3.80 109 19.8 120 1.78 102 6.50 104 16.1 105 1.26 84 3.17 119 20.8 121 1.56 118 16.3 113 25.1 127 14.5 98 12.4 133 29.4 131 6.20 107 0.00 1 0.00 1 0.00 1 12.6 115 30.1 132 13.8 104
F-TV-L1 [15]95.5 0.46 109 2.58 118 0.07 96 4.05 112 16.2 107 2.21 107 6.59 106 15.9 103 1.39 91 2.35 110 17.9 111 0.88 105 13.7 83 21.5 88 11.4 83 7.53 87 21.1 101 4.75 63 0.03 95 0.17 140 0.05 93 7.15 75 20.5 80 7.39 30
CNN-flow-warp+ref [117]96.6 0.33 100 1.91 102 0.09 106 2.72 94 12.4 81 2.32 109 6.77 109 18.9 118 2.09 99 2.28 108 16.4 101 0.82 104 17.7 123 23.9 119 22.8 126 9.40 117 24.3 117 6.73 118 0.00 1 0.00 1 0.00 1 14.0 124 26.8 122 20.2 119
GraphCuts [14]99.2 0.29 86 1.67 88 0.16 125 6.77 127 22.4 125 3.81 122 7.73 115 17.2 111 9.04 123 1.86 88 16.8 106 0.46 77 15.8 108 24.0 120 14.1 97 20.2 142 22.8 108 12.5 139 0.00 1 0.00 1 0.00 1 13.4 120 27.0 125 23.4 126
StereoOF-V1MT [119]100.5 0.41 105 2.35 114 0.04 76 4.27 115 21.6 122 1.66 99 6.25 103 17.7 113 0.50 38 3.13 118 23.2 125 1.41 115 19.4 131 27.9 136 20.7 123 11.6 131 32.5 135 7.60 125 0.00 1 0.00 1 0.00 1 16.7 130 32.8 135 21.3 121
Ad-TV-NDC [36]102.7 0.79 127 2.68 123 0.12 117 13.0 138 26.5 131 12.9 138 12.9 129 22.0 124 9.24 124 5.02 124 20.3 120 4.82 124 13.2 75 20.5 72 9.43 70 6.17 63 20.3 93 5.07 75 0.03 95 0.00 1 0.00 1 20.5 135 26.9 123 40.8 142
HBpMotionGpu [43]102.9 0.80 128 2.79 124 0.18 126 5.57 121 23.8 129 4.00 123 13.1 130 27.8 136 11.6 130 2.05 97 16.4 101 0.74 96 17.9 125 25.1 127 22.3 125 6.69 69 21.0 100 6.04 102 0.00 1 0.00 1 0.00 1 14.1 125 27.7 126 25.1 127
Filter Flow [19]104.0 0.58 120 2.59 119 0.11 115 4.48 116 19.7 118 2.66 116 12.1 124 23.7 127 13.5 135 14.5 135 30.4 131 15.0 135 18.7 130 23.7 118 27.5 134 8.11 96 20.7 97 6.48 111 0.00 1 0.00 1 0.00 1 11.0 111 21.9 94 17.2 112
WOLF_ROB [149]104.1 0.56 117 3.04 125 0.09 106 6.60 124 23.5 127 3.40 119 8.20 118 18.2 117 2.44 102 2.06 98 13.3 79 0.98 109 16.4 115 23.3 111 18.2 117 9.74 122 19.2 80 6.28 109 0.01 91 0.00 1 0.20 103 9.49 101 23.1 101 14.3 106
StereoFlow [44]104.3 2.82 146 6.92 145 1.29 145 21.5 144 42.6 147 13.8 139 20.5 145 33.3 146 20.4 141 20.6 142 51.2 145 18.6 140 14.9 98 22.6 102 13.7 96 3.89 23 18.9 77 3.74 34 0.00 1 0.00 1 0.00 1 11.3 113 25.9 116 18.7 117
Modified CLG [34]106.5 0.62 122 2.54 117 0.12 117 3.52 106 18.7 116 2.59 115 12.2 126 23.5 126 12.5 132 3.25 120 20.1 119 2.03 120 18.6 129 25.0 126 25.0 131 8.86 112 26.9 127 7.14 121 0.00 1 0.00 1 0.00 1 13.4 120 29.8 130 21.8 122
2bit-BM-tele [98]106.8 0.54 115 2.59 119 0.20 127 2.58 92 16.3 108 1.26 91 6.04 101 17.8 114 2.26 100 2.77 117 19.7 118 1.50 117 15.8 108 23.3 111 16.5 109 8.58 105 22.4 105 5.62 94 1.37 140 0.00 1 5.84 138 10.7 110 24.8 112 16.5 111
Learning Flow [11]107.9 0.32 98 1.89 100 0.01 35 2.61 93 16.0 106 1.21 88 6.52 105 17.9 115 1.65 97 4.69 123 24.9 128 3.14 123 20.8 135 27.4 135 26.9 133 10.9 129 28.6 130 7.90 128 0.10 112 0.00 1 0.64 112 13.3 119 28.5 129 18.1 115
FlowNetS+ft+v [112]109.0 0.31 94 1.76 96 0.09 106 3.39 105 13.5 95 2.49 112 7.24 112 16.9 108 5.12 109 3.32 121 18.3 115 2.07 121 17.1 118 23.2 110 20.3 120 6.23 65 23.2 113 5.50 92 0.35 130 0.52 145 1.50 131 8.79 96 23.1 101 13.6 102
SPSA-learn [13]109.8 0.86 130 3.30 128 0.28 133 6.02 123 22.0 123 4.09 124 10.6 122 21.3 122 9.82 128 5.83 127 22.9 123 5.66 128 17.9 125 23.4 115 23.4 128 10.2 123 25.0 120 8.09 129 0.00 1 0.00 1 0.00 1 15.9 129 28.1 127 23.3 125
IAOF2 [51]110.5 0.47 111 2.28 109 0.33 134 3.77 108 16.3 108 2.22 108 7.40 113 17.2 111 7.06 117 14.7 136 29.4 130 16.6 137 15.2 103 23.0 106 14.7 99 10.5 126 20.6 95 7.03 120 0.32 125 0.00 1 2.00 134 11.2 112 22.6 99 15.4 110
UnFlow [129]111.3 1.88 140 6.59 142 0.87 141 6.75 126 27.2 132 4.57 126 12.5 128 27.9 137 7.37 118 5.65 126 21.0 122 5.26 126 22.5 138 30.2 139 26.4 132 9.48 119 30.5 134 7.32 122 0.00 1 0.00 1 0.00 1 9.58 102 26.9 123 12.3 96
LDOF [28]111.7 0.41 105 2.31 112 0.09 106 3.85 110 17.3 112 2.32 109 4.68 81 13.5 81 2.59 103 3.97 122 24.8 127 2.14 122 16.1 111 23.1 107 17.6 113 8.24 99 26.0 122 6.50 113 0.33 126 0.34 142 1.95 133 9.77 105 26.7 120 12.9 99
TVL1_ROB [139]112.7 1.04 132 3.71 131 0.27 132 9.06 132 24.8 130 7.75 136 14.6 133 25.5 131 12.5 132 10.6 130 31.0 133 11.6 132 17.4 120 24.5 122 20.6 121 8.67 107 25.1 121 6.64 116 0.00 1 0.00 1 0.00 1 21.9 137 31.3 133 39.9 140
IAOF [50]113.7 0.46 109 2.11 106 0.10 112 6.63 125 19.7 118 4.61 127 13.8 132 23.3 125 9.33 125 9.91 129 23.2 125 11.3 131 14.8 97 22.2 98 15.5 105 10.6 127 26.8 126 6.99 119 0.05 102 0.00 1 0.42 108 18.0 133 24.4 110 35.4 138
Nguyen [33]114.1 0.83 129 3.37 130 0.22 128 7.27 129 22.1 124 6.46 130 15.4 136 26.8 134 12.4 131 17.6 139 30.4 131 20.2 142 18.5 128 24.7 124 24.5 129 8.82 110 28.5 129 8.81 132 0.00 1 0.00 1 0.00 1 18.9 134 31.7 134 29.4 132
BlockOverlap [61]114.8 0.62 122 2.30 111 0.14 124 4.11 114 17.6 113 3.02 118 9.12 120 19.6 121 6.97 116 2.74 116 16.5 104 1.72 119 14.7 96 20.9 77 16.8 111 7.89 93 19.3 82 6.25 108 2.12 141 0.52 145 10.9 143 15.2 127 22.4 97 32.3 136
GroupFlow [9]115.5 0.56 117 3.20 127 0.05 80 9.79 134 32.3 138 7.11 134 11.4 123 24.6 128 9.68 127 2.01 95 16.0 97 0.70 92 19.8 132 29.9 138 12.0 86 15.2 139 32.5 135 15.4 141 0.33 126 0.00 1 1.11 125 13.2 118 28.4 128 17.2 112
2D-CLG [1]117.5 1.77 139 6.22 140 0.51 139 5.91 122 22.4 125 4.54 125 16.4 137 28.6 139 18.1 140 17.9 140 35.8 136 19.9 141 20.4 133 25.8 131 29.3 136 12.0 132 29.6 132 11.4 136 0.00 1 0.00 1 0.00 1 17.7 132 32.8 135 26.2 128
Heeger++ [104]118.7 0.95 131 4.26 134 0.26 131 11.8 137 39.5 145 6.54 131 12.3 127 24.7 130 3.51 106 10.7 131 37.1 138 8.97 129 30.7 144 36.7 144 39.2 142 21.4 145 46.3 146 18.3 144 0.00 1 0.00 1 0.00 1 24.4 139 37.0 138 31.9 134
FFV1MT [106]122.2 1.42 135 6.80 144 0.25 129 10.3 135 35.9 142 6.76 132 18.0 138 30.0 141 16.5 137 17.2 138 51.3 146 16.2 136 31.5 145 37.1 145 43.2 145 20.9 144 44.0 145 17.2 142 0.00 1 0.00 1 0.00 1 24.4 139 37.0 138 31.9 134
TI-DOFE [24]122.3 1.58 137 5.19 137 0.36 136 16.8 140 34.3 139 17.7 141 19.3 144 30.2 143 21.6 143 23.3 143 39.1 140 27.6 143 21.1 136 27.1 132 29.5 137 14.4 137 35.1 139 12.1 138 0.00 1 0.00 1 0.00 1 27.2 143 40.8 142 41.2 143
Black & Anandan [4]124.5 0.68 125 2.46 115 0.13 123 7.01 128 23.6 128 4.65 128 12.1 124 21.6 123 9.40 126 5.45 125 23.1 124 4.84 125 17.5 121 24.3 121 21.6 124 10.6 127 26.6 125 7.49 124 0.43 131 0.15 138 1.31 128 12.7 116 26.7 120 18.8 118
H+S_ROB [138]125.0 2.47 145 6.65 143 0.89 143 10.4 136 34.3 139 6.83 133 18.1 139 31.4 144 16.8 139 30.4 147 41.9 142 34.3 147 29.4 143 35.1 143 44.5 147 20.4 143 43.6 144 21.5 145 0.00 1 0.00 1 0.00 1 38.2 146 44.9 145 45.2 144
Horn & Schunck [3]125.5 1.05 133 4.22 133 0.25 129 7.74 131 29.1 135 5.17 129 13.6 131 24.6 128 10.8 129 12.7 133 36.1 137 12.8 133 21.4 137 27.3 134 30.9 139 13.9 136 35.2 140 11.6 137 0.03 95 0.00 1 0.17 101 22.3 138 37.9 140 31.7 133
SILK [79]129.2 1.05 133 4.27 135 0.44 137 9.69 133 27.9 133 8.93 137 15.2 135 26.9 135 13.1 134 6.14 128 25.9 129 5.57 127 23.0 139 29.2 137 34.1 140 12.6 134 33.9 137 9.78 134 0.81 136 0.00 1 3.50 136 21.5 136 33.3 137 34.5 137
HCIC-L [99]130.6 1.95 141 6.24 141 0.99 144 28.7 146 32.2 137 35.8 146 18.6 142 26.2 132 25.7 146 25.4 146 46.6 144 27.7 144 15.1 102 21.9 96 12.7 93 8.77 108 20.2 92 9.24 133 6.40 147 0.49 144 23.0 147 15.3 128 26.4 119 18.4 116
PGAM+LK [55]134.3 2.98 147 6.17 139 6.36 153 16.8 140 36.2 143 17.8 142 14.7 134 26.5 133 14.5 136 19.1 141 53.9 147 18.3 139 23.1 140 30.6 140 29.9 138 14.4 137 36.8 141 11.1 135 1.07 138 0.00 1 4.16 137 25.9 141 40.1 141 40.3 141
SLK [47]134.4 1.44 136 5.58 138 0.49 138 14.4 139 35.8 141 14.8 140 18.5 140 30.1 142 21.4 142 24.6 144 35.7 135 27.7 144 26.3 142 31.9 141 39.4 143 15.6 140 38.8 142 13.6 140 0.55 135 0.00 1 1.35 130 31.7 144 41.0 143 49.0 145
Adaptive flow [45]134.5 1.75 138 5.07 136 0.34 135 18.4 142 28.3 134 18.5 143 18.5 140 28.6 139 22.9 144 13.3 134 37.4 139 13.9 134 17.9 125 24.7 124 17.7 114 12.9 135 26.2 124 8.68 131 5.20 146 0.61 147 22.8 146 16.7 130 26.0 118 28.2 131
FOLKI [16]136.2 1.98 142 7.18 146 0.87 141 24.5 145 36.3 144 30.3 145 18.7 143 32.4 145 16.5 137 15.2 137 33.2 134 18.1 138 26.0 141 32.3 142 36.0 141 17.7 141 40.6 143 17.9 143 2.33 143 0.00 1 10.6 141 33.9 145 43.6 144 52.7 146
Periodicity [78]137.0 2.36 144 9.12 147 0.79 140 19.1 143 40.7 146 20.6 144 28.2 147 35.2 147 26.8 147 11.2 132 40.6 141 10.3 130 42.3 147 55.4 147 41.1 144 31.7 146 56.3 147 27.7 146 0.54 134 0.00 1 7.78 140 26.1 142 51.0 146 36.2 139
Pyramid LK [2]144.0 2.31 143 4.20 132 3.47 152 31.6 147 32.0 136 40.4 147 21.0 146 28.5 138 24.0 145 24.6 144 43.7 143 28.6 146 37.5 146 46.6 146 43.7 146 33.1 147 34.2 138 31.3 147 2.17 142 0.47 143 10.7 142 46.5 147 57.3 147 67.2 147
AVG_FLOW_ROB [142]145.6 41.6 154 34.9 154 54.2 154 94.7 154 94.6 154 92.2 154 90.3 154 88.2 154 90.3 154 80.5 154 73.8 154 82.4 154 91.3 154 92.4 148 87.0 154 67.7 148 60.9 154 64.7 148 20.2 148 0.00 1 42.1 148 93.8 148 92.8 148 98.2 148
AdaConv-v1 [126]148.3 6.16 148 11.8 148 2.11 146 91.0 148 93.3 148 87.2 148 83.4 148 79.4 148 87.3 148 47.3 148 64.4 148 46.2 148 89.6 148 93.2 149 73.3 148 69.7 149 60.5 148 67.1 149 41.7 149 14.2 149 92.5 149 99.6 149 98.7 149 100.0 149
SepConv-v1 [127]148.3 6.16 148 11.8 148 2.11 146 91.0 148 93.3 148 87.2 148 83.4 148 79.4 148 87.3 148 47.3 148 64.4 148 46.2 148 89.6 148 93.2 149 73.3 148 69.7 149 60.5 148 67.1 149 41.7 149 14.2 149 92.5 149 99.6 149 98.7 149 100.0 149
SuperSlomo [132]148.3 6.16 148 11.8 148 2.11 146 91.0 148 93.3 148 87.2 148 83.4 148 79.4 148 87.3 148 47.3 148 64.4 148 46.2 148 89.6 148 93.2 149 73.3 148 69.7 149 60.5 148 67.1 149 41.7 149 14.2 149 92.5 149 99.6 149 98.7 149 100.0 149
FGIK [136]148.3 6.16 148 11.8 148 2.11 146 91.0 148 93.3 148 87.2 148 83.4 148 79.4 148 87.3 148 47.3 148 64.4 148 46.2 148 89.6 148 93.2 149 73.3 148 69.7 149 60.5 148 67.1 149 41.7 149 14.2 149 92.5 149 99.6 149 98.7 149 100.0 149
CtxSyn [137]148.3 6.16 148 11.8 148 2.11 146 91.0 148 93.3 148 87.2 148 83.4 148 79.4 148 87.3 148 47.3 148 64.4 148 46.2 148 89.6 148 93.2 149 73.3 148 69.7 149 60.5 148 67.1 149 41.7 149 14.2 149 92.5 149 99.6 149 98.7 149 100.0 149
CyclicGen [154]148.3 6.16 148 11.8 148 2.11 146 91.0 148 93.3 148 87.2 148 83.4 148 79.4 148 87.3 148 47.3 148 64.4 148 46.2 148 89.6 148 93.2 149 73.3 148 69.7 149 60.5 148 67.1 149 41.7 149 14.2 149 92.5 149 99.6 149 98.7 149 100.0 149
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] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
[151] 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.
[152] 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.
[153] ContinualFlow_ROB 0.5 all color Anonymous. Continual Flow. ACCV 2018 submission 273.
[154] CyclicGen 0.088 2 color Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
* 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.