Optical flow evaluation results Statistics:     Average   SD   R2.5   R5.0   R10.0   A50   A75   A95  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
Average
angle
error
avg. Army
(Hidden texture)
GT   im0   im1
Mequon
(Hidden texture)
GT   im0   im1
Schefflera
(Hidden texture)
GT   im0   im1
Wooden
(Hidden texture)
GT   im0   im1
Grove
(Synthetic)
GT   im0   im1
Urban
(Synthetic)
GT   im0   im1
Yosemite
(Synthetic)
GT   im0   im1
Teddy
(Stereo)
GT   im0   im1
rank all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext
NNF-Local [75]6.8 2.69 3 7.56 4 1.98 3 1.97 5 7.01 7 1.59 5 2.18 2 5.36 3 1.53 4 1.87 5 9.14 9 1.06 5 2.28 2 2.94 1 1.57 2 2.39 7 6.78 4 2.15 11 2.00 30 3.36 19 1.62 25 0.99 1 2.16 3 0.57 2
NN-field [71]12.4 2.89 8 8.13 16 2.11 5 2.10 9 7.15 12 1.77 18 2.27 4 5.59 5 1.61 9 1.58 2 8.52 8 0.79 2 2.35 4 3.05 5 1.60 3 1.89 2 5.20 2 1.37 1 2.43 64 3.70 60 1.95 52 1.01 2 2.25 4 0.53 1
OFLAF [78]15.8 3.04 14 7.80 9 2.40 15 2.14 10 7.02 8 1.72 12 2.25 3 5.32 2 1.56 6 2.62 22 13.7 30 1.37 24 2.35 4 3.13 6 1.62 4 2.98 28 7.73 9 2.57 25 2.08 37 3.27 12 2.05 57 1.33 13 2.43 7 1.40 21
RAFT-TF_RVC [180]16.3 3.89 59 11.3 78 2.11 5 2.21 13 6.86 6 1.88 23 2.82 17 7.00 16 2.47 58 0.96 1 3.49 1 0.64 1 2.75 24 3.60 25 1.89 9 1.78 1 5.10 1 1.60 2 1.44 2 3.27 12 0.98 4 1.33 13 2.96 17 0.81 3
PMMST [112]16.9 3.42 45 7.60 5 2.65 34 2.32 15 6.39 1 2.20 38 2.63 12 6.08 8 2.03 31 2.06 8 6.07 4 1.44 32 2.60 10 3.27 8 1.91 11 2.56 9 6.78 4 2.09 7 2.06 33 3.53 42 1.63 26 1.27 10 2.29 5 1.02 8
nLayers [57]19.7 2.80 6 7.42 3 2.20 9 2.71 34 7.24 13 2.55 64 2.61 10 6.24 9 2.45 57 2.30 14 12.7 16 1.16 9 2.30 3 3.02 3 1.70 5 2.62 13 6.95 6 2.09 7 2.29 56 3.46 29 1.89 48 1.38 18 3.06 21 1.29 19
MDP-Flow2 [68]22.0 3.23 32 7.93 12 2.60 25 1.92 2 6.64 4 1.52 1 2.46 7 5.91 7 1.56 6 3.05 49 15.8 65 1.51 43 2.77 27 3.50 19 2.16 30 2.86 24 8.58 20 2.70 37 2.00 30 3.50 37 1.59 23 1.28 11 2.67 12 0.89 5
ComponentFusion [94]23.0 2.78 5 8.20 18 2.05 4 2.04 7 7.31 14 1.66 11 2.55 8 6.78 15 1.61 9 2.24 13 13.1 19 1.01 3 2.71 21 3.56 23 2.10 25 3.55 60 12.4 69 3.22 65 2.19 50 3.60 52 1.54 22 1.32 12 2.91 16 1.13 11
UnDAF [184]24.8 3.22 31 8.01 14 2.64 31 1.93 3 6.50 2 1.58 4 2.60 9 6.42 11 1.70 15 3.07 51 16.0 69 1.52 45 2.76 26 3.48 16 2.27 37 2.85 22 8.89 22 2.70 37 2.13 45 3.51 38 1.72 28 1.33 13 2.70 13 1.15 13
TC/T-Flow [77]25.6 2.69 3 7.75 8 1.87 2 2.76 37 10.2 53 1.73 13 3.33 29 9.01 36 1.49 2 2.86 38 16.7 77 1.21 11 2.60 10 3.49 18 1.90 10 2.21 4 7.65 7 2.04 5 1.84 17 3.23 9 3.14 109 2.03 45 4.53 45 1.49 26
CoT-AMFlow [175]27.3 3.23 32 8.15 17 2.70 37 1.97 5 6.55 3 1.65 9 2.68 13 6.72 14 1.81 19 3.09 52 16.3 74 1.54 49 2.79 29 3.52 20 2.38 47 2.82 20 8.98 25 2.69 35 2.12 43 3.53 42 1.73 29 1.33 13 2.71 14 1.20 15
FC-2Layers-FF [74]29.3 3.02 13 7.87 11 2.61 26 2.72 35 9.35 40 2.29 45 2.36 5 5.47 4 2.15 38 2.48 15 12.6 15 1.28 15 2.49 7 3.19 7 2.03 18 3.39 48 8.92 23 2.83 50 2.83 89 3.92 77 2.80 88 1.25 8 2.57 11 1.20 15
WLIF-Flow [91]31.6 2.96 10 7.67 6 2.40 15 2.41 20 7.70 18 2.10 32 2.98 21 7.63 23 1.97 30 2.71 30 13.5 26 1.33 18 3.01 50 4.00 56 2.40 52 3.03 31 8.32 14 2.44 19 2.09 39 3.36 19 2.04 56 2.26 54 4.97 56 2.59 63
Layers++ [37]31.6 3.11 17 8.22 21 2.79 47 2.43 23 7.02 8 2.24 41 2.43 6 5.77 6 2.18 41 2.13 10 9.71 12 1.15 8 2.35 4 3.02 3 1.96 12 3.81 68 11.4 53 3.22 65 2.74 83 4.01 83 2.35 71 1.45 19 3.05 20 1.79 38
HAST [107]31.8 2.58 1 7.12 1 1.81 1 2.41 20 7.05 10 2.10 32 1.83 1 4.19 1 1.17 1 2.84 37 15.5 59 1.08 6 2.23 1 2.97 2 1.40 1 3.72 65 10.0 38 3.92 93 3.40 112 4.90 117 5.66 140 1.20 7 2.09 1 1.24 17
AGIF+OF [84]33.3 3.06 15 8.20 18 2.55 23 3.17 65 10.6 60 2.46 58 3.46 34 8.97 34 2.24 44 2.61 20 13.7 30 1.33 18 2.63 15 3.46 15 2.11 26 2.88 26 8.34 16 2.35 15 2.10 41 3.56 47 2.09 60 1.80 35 3.68 35 2.24 49
FESL [72]33.5 2.96 10 7.70 7 2.54 22 3.26 76 10.4 57 2.56 65 3.25 27 8.39 27 2.17 39 2.56 17 13.2 20 1.31 17 2.57 9 3.40 11 2.12 28 2.60 11 7.65 7 2.30 13 2.64 79 4.22 92 2.47 75 1.75 33 3.49 31 1.71 32
Efficient-NL [60]33.7 2.99 12 8.23 22 2.28 10 2.72 35 8.95 36 2.25 43 3.81 45 9.87 43 2.07 35 2.77 34 14.3 41 1.46 38 2.61 12 3.48 16 1.96 12 3.31 44 8.33 15 2.59 27 2.60 74 3.75 62 2.54 78 1.60 27 3.02 18 1.66 29
LME [70]33.7 3.15 22 8.04 15 2.31 12 1.95 4 6.65 5 1.59 5 4.03 52 9.31 37 4.57 104 2.69 28 13.6 28 1.42 29 2.85 35 3.61 27 2.42 54 3.47 55 12.8 76 3.17 61 2.12 43 3.53 42 1.73 29 1.34 17 2.75 15 1.18 14
ALD-Flow [66]34.2 2.82 7 7.86 10 2.16 7 2.84 44 10.1 50 1.86 21 3.73 43 10.4 47 1.67 13 3.10 53 16.8 78 1.28 15 2.69 20 3.60 25 1.85 8 2.79 17 11.3 52 2.32 14 2.07 35 3.25 11 3.10 106 2.03 45 5.11 58 1.94 41
RNLOD-Flow [119]35.3 2.66 2 7.33 2 2.17 8 2.53 30 9.46 42 1.86 21 3.94 50 10.7 53 1.95 27 2.50 16 13.5 26 1.21 11 2.68 18 3.62 29 2.05 20 2.99 29 8.59 21 2.75 42 3.00 99 4.54 104 3.25 114 1.48 21 3.24 25 1.76 37
IROF++ [58]35.4 3.17 25 8.69 32 2.61 26 2.79 39 9.61 43 2.33 46 3.43 31 8.86 31 2.38 51 2.87 41 14.8 46 1.52 45 2.74 23 3.57 24 2.19 33 3.20 40 9.70 35 2.71 39 1.96 28 3.45 28 1.22 12 1.80 35 4.06 37 2.50 59
PH-Flow [99]35.7 3.19 28 8.87 37 2.71 38 2.84 44 9.33 39 2.37 48 2.85 18 7.20 18 2.36 48 2.92 44 15.4 56 1.51 43 2.63 15 3.42 12 2.04 19 3.03 31 8.52 19 2.49 21 2.69 81 3.60 52 3.13 108 1.25 8 2.53 9 1.34 20
ProFlow_ROB [142]36.3 3.29 34 9.91 58 2.35 14 2.50 28 10.0 48 1.83 19 4.04 53 11.6 61 1.96 29 2.86 38 15.0 49 1.22 13 2.87 38 3.89 47 1.97 15 2.60 11 10.5 43 2.20 12 1.53 6 3.54 45 1.53 21 2.50 61 6.37 74 2.33 54
NNF-EAC [101]36.3 3.31 37 8.21 20 2.68 36 2.19 12 7.49 16 1.76 16 2.73 15 6.62 13 1.70 15 3.18 59 15.8 65 1.64 57 2.87 38 3.66 32 2.24 35 3.02 30 8.07 12 2.59 27 2.19 50 3.48 33 1.74 31 2.85 73 6.52 75 3.12 75
Classic+CPF [82]36.7 3.14 20 8.60 29 2.63 30 3.03 61 10.6 60 2.33 46 3.66 38 9.58 39 2.20 42 2.61 20 14.1 36 1.34 21 2.68 18 3.53 21 2.21 34 2.85 22 7.95 11 2.38 16 2.44 66 3.49 35 2.90 99 1.67 31 3.40 28 2.43 57
PRAFlow_RVC [178]37.4 4.24 78 10.2 62 2.85 49 2.93 53 8.16 23 2.65 77 3.81 45 9.57 38 2.86 73 2.05 7 9.67 11 1.03 4 2.93 45 3.77 41 2.17 32 2.07 3 5.50 3 2.06 6 1.48 4 3.51 38 0.68 1 2.83 72 4.62 49 3.47 84
Sparse-NonSparse [56]38.8 3.14 20 8.75 34 2.76 45 3.02 59 10.6 60 2.43 53 3.45 33 8.96 32 2.36 48 2.66 25 13.7 30 1.42 29 2.85 35 3.75 40 2.33 41 3.28 43 9.40 31 2.73 40 2.42 63 3.31 15 2.69 83 1.47 20 3.07 22 1.66 29
TC-Flow [46]40.4 2.91 9 8.00 13 2.34 13 2.18 11 8.77 31 1.52 1 3.84 48 10.7 53 1.49 2 3.13 54 16.6 76 1.46 38 2.78 28 3.73 39 1.96 12 3.08 35 11.4 53 2.66 31 1.94 26 3.43 25 3.20 113 3.06 78 7.04 80 4.08 101
3DFlow [133]40.5 3.44 46 8.63 31 2.46 18 2.43 23 8.59 30 1.75 15 3.71 41 9.93 45 1.64 11 1.61 4 4.58 2 1.23 14 2.86 37 3.72 37 2.16 30 4.52 94 11.6 59 4.20 101 3.16 107 4.02 84 4.44 132 1.13 5 2.14 2 0.89 5
LSM [39]41.5 3.12 18 8.62 30 2.75 44 3.00 57 10.5 59 2.44 55 3.43 31 8.85 30 2.35 47 2.66 25 13.6 28 1.44 32 2.82 31 3.68 33 2.36 44 3.38 47 9.41 32 2.81 48 2.69 81 3.52 40 2.84 92 1.59 25 3.38 27 1.80 39
SVFilterOh [109]41.5 3.63 52 8.82 35 2.86 50 2.60 32 8.06 21 2.05 31 2.95 19 7.09 17 2.03 31 2.80 36 13.8 33 1.41 28 2.63 15 3.42 12 1.75 7 3.49 56 10.3 40 3.23 68 3.63 121 5.75 139 4.47 133 1.09 4 2.45 8 0.92 7
Ramp [62]42.2 3.18 27 8.83 36 2.73 41 2.89 49 10.1 50 2.44 55 3.27 28 8.43 28 2.38 51 2.74 32 14.2 37 1.46 38 2.82 31 3.69 36 2.29 39 3.37 46 9.31 29 2.93 53 2.62 77 3.38 23 3.19 112 1.54 23 3.21 24 2.24 49
Correlation Flow [76]42.6 3.38 43 8.40 24 2.64 31 2.23 14 7.54 17 1.56 3 5.14 76 13.1 75 1.60 8 2.09 9 8.15 7 1.35 23 3.12 58 4.09 64 2.34 42 4.01 80 11.5 57 4.00 95 2.59 73 3.61 54 3.00 104 1.49 22 3.04 19 1.42 24
PMF [73]42.7 3.61 50 9.07 40 2.62 28 2.40 18 8.05 20 1.83 19 2.61 10 6.27 10 1.65 12 3.35 69 15.4 56 1.58 52 2.54 8 3.27 8 1.71 6 3.59 61 11.1 50 3.46 76 4.07 131 6.18 146 4.02 128 1.06 3 2.38 6 1.25 18
ProbFlowFields [126]43.4 4.18 72 12.4 88 3.40 80 2.43 23 8.16 23 2.19 37 3.65 37 9.72 41 2.86 73 2.22 11 9.42 10 1.42 29 3.01 50 3.96 53 2.36 44 2.73 16 10.9 45 2.51 22 1.89 24 3.39 24 1.82 37 2.59 64 6.21 72 2.75 66
COFM [59]43.7 3.17 25 9.90 57 2.46 18 2.41 20 8.34 27 1.92 25 3.77 44 10.5 48 2.54 61 2.71 30 14.9 48 1.19 10 3.08 55 3.92 51 3.25 98 3.83 71 10.9 45 3.15 60 2.20 53 3.35 17 2.91 101 1.62 30 2.56 10 2.09 45
JOF [136]44.5 3.08 16 8.56 27 2.51 21 3.27 77 10.2 53 2.81 88 3.02 23 7.55 20 2.42 55 2.64 23 14.2 37 1.34 21 2.62 13 3.42 12 2.08 21 3.26 41 8.96 24 2.56 23 3.12 106 4.26 93 4.09 130 2.11 51 4.58 47 2.18 47
FMOF [92]44.9 3.12 18 8.23 22 2.73 41 3.25 73 10.7 67 2.52 62 3.01 22 7.61 21 2.20 42 2.56 17 13.4 24 1.33 18 2.75 24 3.61 27 2.24 35 3.66 63 8.50 18 2.78 46 2.62 77 3.84 70 3.27 116 2.66 69 5.69 63 1.95 43
OAR-Flow [123]45.8 3.37 41 9.87 56 2.67 35 4.22 99 12.8 95 2.87 90 4.95 72 13.4 78 2.66 64 3.23 61 16.4 75 1.37 24 2.83 33 3.82 44 1.97 15 2.49 8 10.9 45 1.87 4 1.52 5 2.82 1 1.86 43 1.85 38 4.35 42 1.68 31
Classic+NL [31]46.3 3.20 30 8.72 33 2.81 48 3.02 59 10.6 60 2.44 55 3.46 34 8.84 29 2.38 51 2.78 35 14.3 41 1.46 38 2.83 33 3.68 33 2.31 40 3.40 49 9.09 27 2.76 44 2.87 91 3.82 69 2.86 96 1.67 31 3.53 32 2.26 53
HCFN [157]47.3 3.15 22 8.58 28 2.42 17 2.09 8 8.31 26 1.63 8 2.81 16 7.61 21 1.54 5 2.86 38 15.3 53 1.44 32 2.73 22 3.55 22 2.08 21 3.42 51 10.4 41 3.28 70 4.88 145 6.08 144 5.70 141 2.45 59 5.24 61 3.47 84
TV-L1-MCT [64]47.3 3.16 24 8.48 26 2.71 38 3.28 78 10.8 71 2.60 73 3.95 51 10.5 48 2.38 51 2.69 28 13.9 34 1.45 37 2.94 46 3.79 42 2.63 75 3.50 57 9.75 36 3.06 57 2.08 37 3.35 17 2.29 68 1.95 41 3.89 36 2.71 65
PWC-Net_RVC [143]49.9 4.86 106 12.4 88 3.56 89 3.14 63 10.3 56 2.60 73 4.38 61 11.6 61 3.18 81 2.56 17 10.6 13 1.52 45 3.25 76 4.18 68 2.46 56 3.10 37 10.6 44 2.75 42 1.44 2 3.56 47 1.01 5 1.60 27 3.41 29 1.14 12
IIOF-NLDP [129]51.3 3.65 53 9.81 55 2.56 24 2.79 39 9.36 41 2.00 27 4.28 59 11.3 59 1.69 14 2.02 6 7.52 6 1.38 27 3.36 82 4.52 96 2.40 52 3.82 69 11.2 51 3.67 86 2.07 35 3.79 66 1.88 46 2.91 75 5.30 62 4.17 102
CostFilter [40]51.6 3.84 57 9.64 51 3.06 59 2.55 31 8.09 22 2.03 29 2.69 14 6.47 12 1.88 23 3.66 80 16.8 78 1.88 70 2.62 13 3.34 10 1.99 17 4.05 81 11.0 49 3.65 85 4.16 133 7.18 153 4.66 135 1.16 6 3.36 26 0.87 4
SimpleFlow [49]52.1 3.35 38 9.20 43 2.98 57 3.18 68 10.7 67 2.71 80 5.06 74 12.6 73 2.70 66 2.95 46 15.1 51 1.58 52 2.91 43 3.79 42 2.47 57 3.59 61 9.49 33 2.99 55 2.39 61 3.46 29 2.24 67 1.60 27 3.56 34 1.57 27
VCN_RVC [179]52.2 5.03 108 12.9 97 3.98 100 3.16 64 10.0 48 2.74 83 3.66 38 9.00 35 2.85 72 3.14 55 14.0 35 1.78 66 3.16 59 4.08 63 2.47 57 3.03 31 10.4 41 2.77 45 1.75 10 3.70 60 1.08 6 1.56 24 3.54 33 1.41 22
2DHMM-SAS [90]54.6 3.19 28 8.89 38 2.71 38 3.20 71 11.5 81 2.38 49 5.19 77 12.2 69 2.73 68 2.92 44 15.2 52 1.53 48 2.79 29 3.65 31 2.27 37 3.45 53 9.34 30 2.78 46 2.66 80 3.56 47 3.07 105 2.34 57 5.12 59 2.97 73
S2D-Matching [83]55.5 3.36 39 9.66 52 2.86 50 3.19 70 11.1 75 2.46 58 4.86 71 12.9 74 2.47 58 2.67 27 13.2 20 1.44 32 2.87 38 3.72 37 2.38 47 3.45 53 9.76 37 2.95 54 3.05 100 3.79 66 3.30 118 1.95 41 4.16 40 3.00 74
FlowFields+ [128]55.8 4.57 91 13.7 103 3.35 71 2.94 55 10.1 50 2.58 69 4.05 54 10.6 50 3.26 84 2.90 43 13.2 20 1.81 68 3.18 63 4.20 72 2.54 64 2.68 15 11.4 53 2.40 18 1.84 17 3.62 55 1.77 32 2.48 60 5.86 65 2.77 67
MLDP_OF [87]56.0 4.13 69 10.3 66 3.60 90 2.34 16 7.70 18 1.88 23 4.23 58 10.9 56 1.87 22 2.74 32 14.6 45 1.37 24 3.10 56 3.91 50 2.48 62 3.40 49 9.00 26 3.79 90 3.46 114 4.20 90 5.55 139 2.31 55 4.64 51 1.98 44
AggregFlow [95]56.5 4.25 79 11.9 85 3.26 64 4.46 105 13.7 107 3.43 101 4.76 69 12.4 70 3.93 101 3.28 64 15.6 61 1.68 59 2.89 41 3.89 47 2.08 21 2.32 5 7.75 10 2.14 9 2.06 33 3.77 64 1.48 18 2.07 49 4.11 38 2.36 55
MDP-Flow [26]57.0 3.48 48 9.46 48 3.10 61 2.45 26 7.36 15 2.41 50 3.21 26 8.31 26 2.78 70 3.18 59 17.8 86 1.70 62 3.03 52 3.87 45 2.60 71 3.43 52 12.6 73 2.81 48 2.19 50 3.88 74 1.60 24 4.13 98 9.96 107 3.86 96
IROF-TV [53]57.0 3.40 44 9.29 45 2.95 56 2.99 56 11.1 75 2.53 63 3.81 45 9.81 42 2.44 56 3.25 63 16.9 80 1.78 66 3.27 79 4.10 65 2.93 89 4.47 91 16.0 110 3.53 78 1.70 8 3.21 7 1.12 9 1.91 40 4.75 53 2.19 48
CombBMOF [111]58.5 3.94 62 10.6 70 2.74 43 2.80 41 8.55 29 2.16 35 3.10 25 7.99 25 1.76 17 2.99 47 13.4 24 1.95 74 3.04 53 3.89 47 2.49 63 5.64 120 12.3 67 6.74 134 3.54 117 5.16 125 2.81 89 1.85 38 4.60 48 1.10 10
S2F-IF [121]58.7 4.51 89 13.6 102 3.31 68 2.90 50 10.4 57 2.48 61 4.07 56 10.8 55 3.15 79 3.31 65 15.7 64 1.90 71 3.17 61 4.19 70 2.55 67 2.81 19 11.6 59 2.60 29 1.86 20 3.67 58 1.87 44 2.11 51 4.64 51 2.54 62
WRT [146]59.0 3.74 55 9.34 46 2.48 20 3.37 84 10.2 53 2.58 69 6.80 101 15.3 94 2.24 44 1.58 2 5.01 3 1.09 7 2.89 41 3.68 33 2.35 43 5.52 118 12.0 63 4.21 103 2.30 57 3.85 71 2.34 70 3.20 81 4.91 54 4.21 103
FlowFields [108]61.4 4.57 91 13.7 103 3.38 74 3.01 58 10.6 60 2.59 71 4.19 57 11.1 57 3.30 85 3.17 58 15.0 49 1.96 75 3.21 71 4.24 79 2.61 74 2.91 27 12.4 69 2.66 31 1.84 17 3.46 29 1.84 40 2.50 61 6.15 70 2.79 68
Sparse Occlusion [54]62.8 3.62 51 9.12 41 2.90 52 2.92 52 9.08 37 2.56 65 4.49 66 11.8 67 2.11 37 3.14 55 15.8 65 1.57 51 3.26 77 4.22 74 2.36 44 3.52 59 10.9 45 2.66 31 5.10 149 6.32 147 3.15 110 2.02 44 4.92 55 1.71 32
NL-TV-NCC [25]63.1 3.89 59 9.16 42 2.98 57 2.87 48 9.69 44 1.99 26 4.44 65 11.6 61 1.76 17 2.64 23 11.8 14 1.48 42 3.49 93 4.60 103 2.47 57 4.67 101 13.5 82 4.26 107 2.83 89 4.57 106 2.84 92 2.62 67 6.00 69 2.25 51
EPPM w/o HM [86]63.7 4.25 79 11.1 74 3.13 62 2.36 17 8.35 28 1.76 16 3.72 42 10.2 46 1.81 19 3.24 62 14.5 44 1.94 73 3.16 59 3.94 52 2.82 84 4.78 105 12.9 77 4.32 108 3.64 123 4.54 104 5.73 142 1.76 34 4.11 38 1.94 41
PGM-C [118]63.8 4.62 96 14.0 108 3.39 76 3.29 80 12.3 87 2.70 79 4.39 64 11.7 64 3.43 88 4.00 89 19.8 96 2.15 80 3.19 65 4.23 75 2.54 64 2.79 17 11.9 62 2.45 20 1.83 15 3.21 7 1.83 38 2.31 55 5.87 66 1.82 40
OFH [38]64.0 3.90 61 9.77 54 3.62 93 2.84 44 11.0 74 2.04 30 5.52 84 14.4 87 1.89 24 3.52 72 20.5 108 1.60 55 3.18 63 4.06 61 2.82 84 3.86 72 14.1 90 3.59 80 1.77 13 3.62 55 1.81 36 2.64 68 7.08 83 2.15 46
SegFlow [156]64.7 4.62 96 14.1 111 3.39 76 3.35 83 12.6 94 2.73 81 4.38 61 11.7 64 3.45 91 4.06 92 20.2 104 2.15 80 3.20 67 4.23 75 2.60 71 2.83 21 12.0 63 2.56 23 1.86 20 3.36 19 1.84 40 1.96 43 4.63 50 1.60 28
Occlusion-TV-L1 [63]65.8 3.59 49 9.61 49 2.64 31 2.93 53 10.6 60 2.41 50 6.16 92 15.2 92 2.70 66 3.32 67 17.0 81 1.68 59 3.38 84 4.44 89 2.82 84 3.10 37 13.2 80 2.68 34 2.17 47 3.52 40 1.46 16 4.63 113 11.1 121 3.53 86
Complementary OF [21]67.0 4.44 85 11.2 76 4.04 103 2.51 29 9.77 46 1.74 14 3.93 49 10.6 50 2.04 33 3.87 84 18.8 88 2.19 85 3.17 61 4.00 56 2.92 88 4.64 99 13.8 87 3.64 84 2.17 47 3.36 19 2.51 76 3.08 79 7.04 80 3.65 90
Adaptive [20]68.2 3.29 34 9.43 47 2.28 10 3.10 62 11.4 78 2.46 58 6.58 96 15.7 99 2.52 60 3.14 55 15.6 61 1.56 50 3.67 104 4.46 91 3.48 108 3.32 45 13.0 79 2.38 16 2.76 86 4.39 98 1.93 50 3.58 86 8.18 93 2.88 70
ACK-Prior [27]69.6 4.19 74 9.27 44 3.60 90 2.40 18 8.21 25 1.65 9 3.40 30 8.96 32 1.84 21 2.87 41 14.4 43 1.44 32 3.36 82 4.15 66 3.07 93 6.35 130 16.1 112 4.90 118 4.21 136 4.80 111 6.03 144 3.29 83 5.99 68 2.82 69
CPM-Flow [114]70.6 4.63 98 14.1 111 3.39 76 3.33 81 12.5 91 2.73 81 4.37 60 11.7 64 3.43 88 4.00 89 19.9 99 2.14 79 3.19 65 4.23 75 2.54 64 3.08 35 12.0 63 2.88 52 1.87 22 3.44 26 1.84 40 2.91 75 7.48 89 2.91 72
DPOF [18]70.8 4.67 101 12.6 94 3.30 66 3.57 89 10.6 60 3.12 97 3.09 24 7.50 19 2.32 46 3.06 50 14.8 46 1.82 69 3.21 71 4.18 68 2.79 83 4.47 91 12.5 71 3.33 71 4.09 132 3.92 77 6.96 146 2.09 50 4.39 43 1.74 35
EpicFlow [100]71.1 4.61 95 14.0 108 3.39 76 3.33 81 12.5 91 2.74 83 5.37 80 14.8 90 3.46 92 3.94 87 19.2 92 2.13 78 3.20 67 4.23 75 2.58 70 2.87 25 12.2 66 2.64 30 1.83 15 3.28 14 1.83 38 3.21 82 7.12 84 3.61 87
DeepFlow2 [106]72.5 4.04 66 11.2 76 3.38 74 3.80 92 12.4 90 2.86 89 5.12 75 13.4 78 3.00 75 4.17 96 20.1 101 2.18 84 2.96 47 3.97 54 2.08 21 3.06 34 12.6 73 2.69 35 2.17 47 3.24 10 2.71 84 4.74 115 10.4 115 4.38 109
TCOF [69]72.7 4.17 71 10.4 68 3.71 96 3.17 65 10.7 67 2.59 71 6.58 96 15.7 99 3.82 99 3.69 82 16.1 71 2.37 94 3.78 108 4.95 126 2.47 57 2.59 10 8.47 17 2.58 26 3.66 125 4.83 112 2.67 82 1.83 37 4.20 41 1.46 25
ROF-ND [105]72.8 4.12 67 10.0 59 3.37 73 2.78 38 8.82 33 2.12 34 4.61 68 11.9 68 2.09 36 2.23 12 6.56 5 1.69 61 3.60 100 4.75 114 2.85 87 4.92 108 13.6 85 3.75 88 4.59 142 5.18 126 4.10 131 2.67 70 5.19 60 3.46 83
HBM-GC [103]74.4 5.25 110 10.5 69 4.34 110 3.17 65 8.78 32 2.94 93 4.38 61 10.6 50 2.68 65 3.59 76 12.8 17 2.47 97 2.96 47 3.64 30 2.64 76 3.96 78 8.26 13 3.56 79 4.40 139 5.92 142 3.62 122 2.55 63 6.34 73 3.29 78
RFlow [88]75.1 3.82 56 10.0 59 3.44 83 2.61 33 9.73 45 2.02 28 5.66 86 14.5 88 2.05 34 3.93 86 23.1 121 1.90 71 3.24 73 4.19 70 2.66 78 4.12 84 15.2 105 3.34 73 2.61 75 3.56 47 2.65 81 4.48 108 10.5 118 3.93 100
Steered-L1 [116]76.1 3.30 36 8.44 25 2.91 53 1.89 1 7.14 11 1.60 7 3.61 36 9.91 44 1.89 24 3.45 70 19.4 95 1.64 57 3.42 86 4.30 81 3.39 101 5.18 113 14.5 93 4.37 111 5.09 148 5.05 121 10.1 150 5.56 122 10.2 113 6.24 128
DMF_ROB [135]77.1 4.37 82 12.3 87 3.62 93 3.46 87 12.9 97 2.60 73 5.98 89 15.8 101 3.23 83 4.05 91 19.8 96 2.15 80 3.10 56 4.06 61 2.57 69 3.79 67 14.3 91 3.13 59 1.88 23 3.12 5 1.99 55 4.34 101 10.0 108 3.87 97
SRR-TVOF-NL [89]77.2 4.47 87 10.9 72 3.32 70 4.04 96 13.2 102 2.90 91 4.81 70 12.5 71 3.15 79 3.33 68 15.3 53 1.61 56 3.24 73 4.03 60 2.70 80 3.94 76 11.8 61 3.33 71 4.16 133 5.21 129 3.44 121 2.06 48 3.48 30 2.42 56
ComplOF-FED-GPU [35]77.9 4.28 81 11.3 78 3.70 95 3.25 73 13.0 99 2.16 35 4.06 55 11.2 58 1.95 27 3.91 85 19.2 92 2.01 76 3.20 67 4.15 66 2.64 76 4.61 97 16.1 112 3.90 92 2.98 97 3.77 64 3.69 123 2.85 73 7.44 88 2.53 61
FF++_ROB [141]78.9 4.84 105 14.8 119 3.46 84 3.18 68 11.4 78 2.69 78 5.30 79 14.1 83 3.73 98 3.31 65 14.2 37 2.20 86 3.26 77 4.29 80 2.72 81 4.58 96 12.7 75 3.70 87 1.91 25 3.46 29 2.19 66 3.65 88 7.31 85 5.97 125
TF+OM [98]81.0 3.97 63 10.2 62 2.94 55 2.91 51 9.12 38 2.57 68 5.22 78 11.5 60 6.92 114 3.59 76 16.1 71 2.28 91 3.20 67 3.97 54 3.11 94 4.70 103 14.5 93 4.32 108 3.06 102 4.84 114 2.71 84 3.93 93 8.79 98 4.32 107
Aniso. Huber-L1 [22]81.5 3.71 54 10.1 61 3.08 60 4.36 104 13.0 99 3.77 105 6.92 102 15.3 94 3.60 95 3.54 73 15.9 68 2.04 77 3.38 84 4.45 90 2.47 57 3.88 73 12.9 77 2.74 41 3.37 111 4.36 96 2.85 95 3.16 80 7.52 90 2.90 71
DeepFlow [85]82.5 4.49 88 11.7 82 4.14 105 4.26 100 12.8 95 3.36 99 5.96 88 14.2 85 5.10 105 4.89 110 23.1 121 2.67 100 2.98 49 4.00 56 2.11 26 3.26 41 13.5 82 2.84 51 2.09 39 3.10 3 2.77 86 5.83 124 11.4 123 5.45 122
Classic++ [32]83.8 3.37 41 9.67 53 2.91 53 3.28 78 12.1 85 2.61 76 5.46 83 14.1 83 3.00 75 3.63 78 20.2 104 1.70 62 3.24 73 4.34 83 2.60 71 4.65 100 16.0 110 3.60 81 3.09 103 3.94 80 3.28 117 4.64 114 10.4 115 3.71 92
TV-L1-improved [17]84.3 3.36 39 9.63 50 2.62 28 2.82 42 10.7 67 2.23 39 6.50 95 15.8 101 2.73 68 3.80 83 21.3 113 1.76 65 3.34 81 4.38 87 2.39 49 5.97 124 18.1 125 5.67 125 3.57 119 4.92 119 3.43 120 4.01 96 9.84 106 3.44 82
C-RAFT_RVC [182]85.2 8.04 133 17.7 130 5.83 124 5.93 117 12.9 97 5.70 120 6.68 98 14.2 85 6.14 111 3.99 88 13.3 23 2.76 101 4.04 125 5.02 131 3.54 110 3.51 58 9.20 28 3.62 82 2.76 86 4.72 109 1.78 33 1.59 25 3.15 23 1.07 9
LocallyOriented [52]86.6 4.54 90 12.8 96 3.27 65 4.73 110 14.8 114 3.73 104 7.77 109 18.3 117 3.44 90 3.56 74 15.6 61 2.22 87 3.46 90 4.47 92 2.69 79 3.15 39 10.2 39 3.19 63 2.61 75 4.20 90 2.52 77 4.39 105 8.52 95 5.23 118
SIOF [67]87.0 4.23 76 10.2 62 3.31 68 3.97 94 14.5 112 2.97 94 7.81 110 16.4 105 7.48 117 4.82 106 20.1 101 2.96 104 3.54 96 4.49 93 3.12 95 4.31 86 13.5 82 4.13 99 2.36 60 3.59 51 1.68 27 3.46 85 7.39 86 3.37 80
LiteFlowNet [138]88.5 6.29 117 16.5 125 4.45 112 3.68 90 10.8 71 3.13 98 5.43 81 13.7 81 3.60 95 3.57 75 12.8 17 2.25 90 3.85 115 4.78 116 3.61 113 4.37 88 12.5 71 3.63 83 2.55 70 4.51 103 1.52 20 4.05 97 7.05 82 5.16 114
Brox et al. [5]90.0 4.44 85 12.4 88 4.22 108 3.72 91 13.5 106 3.06 95 4.97 73 13.3 77 3.11 77 4.58 102 22.0 116 2.37 94 3.79 110 4.60 103 4.33 135 3.91 75 17.0 119 3.45 75 2.22 54 3.79 66 1.19 10 4.62 112 10.0 108 3.38 81
TriangleFlow [30]90.5 4.12 67 10.6 70 3.47 85 3.47 88 13.1 101 2.41 50 6.00 90 15.2 92 2.17 39 2.99 47 16.0 69 1.58 52 4.46 139 5.79 145 4.15 131 5.42 117 13.9 89 5.24 120 3.10 105 5.47 135 2.90 99 3.02 77 6.82 77 3.64 89
CRTflow [81]90.6 4.18 72 11.8 84 3.20 63 3.22 72 10.8 71 2.43 53 6.20 93 15.5 97 2.63 63 4.21 97 22.0 116 2.24 88 3.32 80 4.34 83 2.44 55 7.43 137 19.3 132 8.15 140 2.55 70 4.09 86 2.59 80 4.60 111 11.2 122 4.45 110
OFRF [132]91.7 4.77 104 11.6 80 4.03 102 8.72 132 15.3 119 8.51 135 8.49 121 16.7 107 7.32 115 4.55 101 15.3 53 3.16 111 2.92 44 3.87 45 2.13 29 3.76 66 9.69 34 3.22 65 2.98 97 4.50 102 4.04 129 4.59 110 5.76 64 8.61 136
BriefMatch [122]92.2 3.44 46 9.01 39 2.77 46 2.85 47 9.93 47 2.23 39 2.97 20 7.65 24 1.94 26 3.64 79 20.1 101 1.75 64 4.10 129 4.90 124 5.82 145 7.95 139 17.8 122 8.08 139 4.73 144 5.20 127 12.2 152 7.88 141 12.0 127 13.7 147
Rannacher [23]93.1 4.13 69 11.0 73 3.61 92 3.39 85 12.3 87 2.80 87 7.26 104 17.4 113 3.59 94 4.40 99 23.1 121 2.24 88 3.43 88 4.54 99 2.56 68 5.41 116 18.5 127 4.23 104 2.92 94 3.91 76 2.82 90 3.45 84 9.14 99 3.27 77
F-TV-L1 [15]93.9 5.44 113 12.5 93 5.69 122 5.46 114 15.0 117 4.03 108 7.48 106 16.3 104 3.42 87 5.08 113 23.3 124 2.81 103 3.42 86 4.34 83 3.03 91 4.05 81 15.1 102 3.18 62 2.43 64 3.92 77 1.87 44 3.90 92 9.35 103 2.61 64
TriFlow [93]95.0 4.73 103 12.4 88 3.49 87 4.03 95 12.5 91 3.70 103 8.18 118 17.2 111 10.4 127 3.50 71 15.4 56 2.32 93 3.43 88 4.21 73 3.42 102 3.90 74 12.3 67 3.76 89 7.86 154 5.72 138 16.2 154 2.80 71 5.89 67 2.50 59
Local-TV-L1 [65]95.3 5.33 111 12.6 94 5.19 117 6.90 124 15.7 122 6.22 123 10.0 127 18.2 116 8.89 120 5.81 122 24.7 130 3.70 120 3.05 54 4.00 56 2.39 49 4.05 81 14.6 95 3.09 58 1.95 27 3.11 4 2.15 62 5.85 125 10.8 119 7.34 131
DF-Auto [113]95.3 5.04 109 13.7 103 3.30 66 6.51 121 14.1 111 6.09 122 8.14 114 16.5 106 10.2 126 5.06 112 21.3 113 3.10 110 3.74 106 4.91 125 3.25 98 2.67 14 11.4 53 2.14 9 3.36 110 5.23 131 1.45 15 4.45 107 9.18 100 4.28 106
ContinualFlow_ROB [148]95.4 7.36 126 17.7 130 5.46 119 5.94 118 12.2 86 5.98 121 8.16 117 18.3 117 7.89 118 5.11 114 19.3 94 3.18 112 4.15 132 5.04 132 3.68 115 5.65 121 15.1 102 6.17 131 1.72 9 3.34 16 1.11 8 2.34 57 4.48 44 2.25 51
CLG-TV [48]96.2 4.00 64 10.3 66 3.40 80 4.33 103 12.3 87 4.08 109 6.78 99 15.5 97 3.64 97 4.07 93 17.7 85 2.39 96 3.79 110 4.86 119 3.23 97 4.48 93 16.5 117 3.80 91 3.55 118 4.65 108 2.89 98 4.00 95 10.1 111 3.18 76
CBF [12]96.7 3.88 58 10.2 62 3.50 88 4.60 107 11.3 77 5.06 114 5.43 81 13.1 75 3.39 86 4.09 94 21.2 112 2.16 83 3.80 113 4.72 112 3.52 109 4.33 87 14.4 92 3.01 56 4.97 146 5.51 136 4.93 137 3.99 94 9.27 102 3.91 99
Bartels [41]99.2 4.43 83 11.1 74 4.17 107 2.83 43 8.84 34 2.56 65 4.54 67 12.5 71 2.80 71 4.87 107 22.1 118 3.05 108 3.58 99 4.35 86 4.15 131 5.55 119 17.5 120 5.78 126 3.74 126 5.02 120 5.98 143 5.21 121 11.9 126 5.20 117
Fusion [6]100.1 4.43 83 13.7 103 4.08 104 2.47 27 8.91 35 2.24 41 3.70 40 9.68 40 3.12 78 3.68 81 19.8 96 2.54 99 4.26 136 5.16 137 4.31 134 6.32 127 16.8 118 6.15 130 4.55 141 5.78 140 3.10 106 7.12 135 13.6 136 7.86 135
p-harmonic [29]100.2 4.64 99 13.0 98 4.43 111 3.41 86 11.9 82 2.93 92 7.60 107 18.1 115 3.96 102 4.65 103 21.0 110 2.97 106 3.46 90 4.33 82 3.34 100 4.75 104 17.5 120 4.60 115 3.05 100 4.17 88 2.15 62 5.09 120 10.9 120 3.77 94
CNN-flow-warp+ref [115]100.8 4.93 107 14.5 116 4.29 109 4.18 98 11.9 82 4.24 111 8.23 119 19.7 125 6.35 113 5.13 115 24.4 129 2.96 104 3.55 97 4.40 88 3.85 120 3.82 69 15.0 99 3.39 74 1.96 28 3.44 26 2.14 61 10.0 145 14.8 142 10.8 143
CompactFlow_ROB [155]101.0 8.85 138 18.7 134 5.45 118 5.55 115 12.0 84 5.64 119 8.73 123 17.0 110 11.7 131 5.19 117 17.5 83 3.62 118 4.11 130 4.99 129 3.72 117 4.37 88 14.6 95 4.01 96 1.75 10 3.64 57 0.96 3 4.14 99 7.40 87 5.55 123
Dynamic MRF [7]101.5 4.58 93 12.4 88 4.14 105 3.25 73 13.9 108 2.27 44 6.02 91 16.8 108 2.36 48 4.39 98 22.6 120 2.51 98 3.61 101 4.55 100 3.46 104 6.81 132 22.2 142 6.78 136 2.41 62 3.48 33 3.69 123 9.26 143 17.8 146 10.2 140
EAI-Flow [147]102.0 7.40 127 16.3 123 6.04 126 5.29 113 15.0 117 4.27 112 6.28 94 15.0 91 5.22 108 4.99 111 19.1 91 3.49 115 3.55 97 4.55 100 3.01 90 4.69 102 14.8 97 4.25 106 4.16 133 4.83 112 2.55 79 2.61 66 6.99 79 2.48 58
FlowNetS+ft+v [110]103.3 4.22 75 12.1 86 3.48 86 4.50 106 13.4 104 3.85 106 8.29 120 18.4 119 6.20 112 4.87 107 21.6 115 3.01 107 3.93 120 5.04 132 3.47 107 3.71 64 15.3 106 3.21 64 3.32 108 5.12 123 3.87 125 3.76 90 9.44 104 3.74 93
SegOF [10]103.3 5.85 115 13.5 101 3.98 100 7.40 125 14.9 115 8.13 133 8.55 122 17.3 112 9.01 121 6.50 129 18.1 87 5.14 131 3.90 119 4.53 97 4.81 139 6.57 131 21.7 140 6.81 137 1.65 7 3.49 35 1.08 6 3.71 89 9.23 101 3.63 88
LDOF [28]103.8 4.60 94 13.0 98 3.77 97 4.67 108 15.5 121 3.67 102 5.63 85 14.0 82 4.21 103 5.80 121 27.1 139 3.43 114 3.52 95 4.50 95 3.46 104 4.84 107 17.8 122 4.04 97 2.46 68 4.14 87 3.25 114 4.85 117 12.0 127 3.78 95
ResPWCR_ROB [140]103.9 7.29 125 16.3 123 6.15 128 4.28 101 11.4 78 3.95 107 5.85 87 13.6 80 5.20 107 4.75 105 17.5 83 3.50 116 3.80 113 4.53 97 4.12 130 4.96 111 15.0 99 4.81 117 3.52 116 5.22 130 2.40 72 3.61 87 6.77 76 4.27 105
LSM_FLOW_RVC [183]104.4 9.03 139 21.8 144 7.45 136 6.24 120 17.5 129 5.30 117 9.61 125 23.0 132 7.32 115 6.08 126 23.9 128 4.08 123 4.01 124 4.95 126 3.55 112 5.00 112 15.3 106 5.06 119 2.01 32 3.95 81 1.48 18 2.20 53 5.00 57 1.71 32
Second-order prior [8]104.8 4.03 65 11.6 80 3.35 71 3.88 93 14.0 110 3.08 96 7.21 103 17.6 114 3.57 93 4.14 95 19.9 99 2.31 92 3.66 103 4.86 119 2.73 82 7.32 135 21.2 138 6.76 135 4.02 129 4.58 107 4.01 127 4.27 100 10.4 115 5.12 113
WOLF_ROB [144]106.0 5.79 114 16.6 126 4.49 113 7.62 127 21.2 141 5.10 116 9.70 126 21.0 130 5.66 110 5.32 118 19.0 89 3.78 121 3.61 101 4.49 93 3.54 110 4.63 98 13.6 85 4.34 110 2.30 57 3.89 75 2.16 65 4.37 103 7.52 90 6.03 126
AugFNG_ROB [139]107.0 8.29 134 19.2 136 5.66 121 7.67 128 16.0 125 8.01 132 10.1 128 20.5 128 11.0 129 5.13 115 15.5 59 3.64 119 4.11 130 4.97 128 3.93 122 4.45 90 15.1 102 4.20 101 2.27 55 4.37 97 1.23 13 3.80 91 6.87 78 4.34 108
StereoFlow [44]110.3 17.1 156 28.1 156 17.9 155 18.7 153 29.7 154 16.5 148 20.1 153 30.9 153 17.5 148 21.2 153 38.3 155 17.9 151 4.60 140 5.05 134 5.52 141 2.38 6 11.5 57 1.77 3 1.25 1 2.92 2 0.71 2 4.49 109 10.3 114 4.23 104
FlowNet2 [120]110.4 8.58 137 18.6 132 6.31 129 9.39 137 17.6 130 9.09 138 8.06 113 15.8 101 9.81 124 5.61 120 16.2 73 4.12 124 4.04 125 4.88 121 3.79 118 4.92 108 16.2 114 4.50 112 4.28 137 6.73 149 2.84 92 2.05 47 4.54 46 1.41 22
IRR-PWC_RVC [181]110.7 9.55 141 20.9 142 6.05 127 7.60 126 15.8 124 7.44 127 10.1 128 19.7 125 12.6 135 6.06 125 14.2 37 4.96 128 3.98 122 4.74 113 3.86 121 3.99 79 13.3 81 3.24 69 3.34 109 5.99 143 1.93 50 4.35 102 8.07 92 4.75 111
EPMNet [131]112.0 8.37 136 18.8 135 6.44 131 9.35 136 18.4 132 8.78 137 7.42 105 14.7 89 8.61 119 5.98 124 20.4 107 4.27 126 4.04 125 4.88 121 3.79 118 4.92 108 16.2 114 4.50 112 3.65 124 6.14 145 2.42 74 2.60 65 6.15 70 1.74 35
Ad-TV-NDC [36]112.4 8.36 135 14.0 108 11.1 148 12.9 144 19.9 138 12.8 144 14.4 140 23.1 133 12.1 133 7.40 132 20.6 109 6.33 132 3.47 92 4.66 108 2.39 49 3.95 77 13.8 87 3.51 77 2.48 69 3.75 62 2.05 57 9.75 144 12.1 129 16.7 151
LFNet_ROB [145]113.2 7.69 128 19.8 137 5.72 123 4.70 109 13.3 103 4.13 110 8.15 116 20.0 127 5.42 109 4.73 104 17.1 82 3.42 113 4.15 132 5.10 136 4.05 126 5.28 115 18.0 124 4.64 116 2.87 91 4.74 110 1.98 54 4.92 118 11.4 123 5.01 112
Shiralkar [42]114.3 4.64 99 14.1 111 3.94 98 4.29 102 16.9 127 2.77 85 7.75 108 18.8 121 3.19 82 5.54 119 25.0 132 3.56 117 3.51 94 4.55 100 3.04 92 7.41 136 20.1 136 6.41 132 3.76 127 4.35 95 5.28 138 6.56 131 14.4 141 5.30 120
Learning Flow [11]115.3 4.23 76 11.7 82 3.41 82 4.16 97 15.3 119 3.42 100 6.78 99 16.9 109 3.83 100 6.41 128 25.3 133 4.25 125 4.66 142 6.01 150 4.00 125 6.33 129 20.7 137 5.30 121 3.09 103 4.84 114 2.91 101 7.08 134 15.0 143 5.27 119
StereoOF-V1MT [117]115.8 4.71 102 14.1 111 3.95 99 5.10 112 20.3 140 2.78 86 7.98 112 20.7 129 2.57 62 4.48 100 21.1 111 2.79 102 4.20 135 5.29 139 4.10 128 6.85 134 22.3 143 6.42 133 2.45 67 4.17 88 3.15 110 10.5 146 18.4 149 10.5 141
IAOF2 [51]117.0 5.38 112 13.7 103 4.50 114 5.95 119 14.6 113 5.61 118 8.80 124 18.8 121 9.40 122 12.2 142 23.8 127 13.1 146 3.86 116 4.89 123 3.12 95 5.21 114 14.9 98 4.54 114 4.33 138 5.15 124 3.93 126 4.39 105 8.57 96 3.87 97
TVL1_RVC [176]118.6 11.3 145 19.8 137 13.0 150 13.0 145 19.6 137 13.7 146 17.4 147 27.8 146 18.0 149 12.6 144 28.9 141 11.8 144 3.71 105 4.78 116 3.46 104 4.21 85 18.1 125 3.98 94 1.78 14 3.54 45 1.21 11 7.64 139 13.9 139 9.00 138
Modified CLG [34]119.5 7.17 124 17.1 129 6.47 132 6.85 123 14.9 115 7.48 128 14.0 136 24.8 137 15.7 144 8.35 135 27.3 140 6.36 133 3.96 121 4.99 129 4.08 127 4.54 95 19.3 132 4.15 100 2.33 59 3.86 73 2.40 72 6.00 126 13.8 138 5.40 121
GraphCuts [14]120.0 6.25 116 14.3 115 5.53 120 8.60 131 20.1 139 6.61 125 7.91 111 15.4 96 10.9 128 4.88 109 19.0 89 3.05 108 3.78 108 4.71 110 3.94 123 8.74 144 16.4 116 5.39 123 4.04 130 4.87 116 4.85 136 6.35 129 12.2 130 6.05 127
Filter Flow [19]120.3 6.48 118 14.6 117 4.96 115 5.73 116 15.7 122 5.07 115 10.1 128 18.6 120 14.3 140 9.04 137 23.3 124 7.80 137 3.98 122 4.71 110 4.21 133 5.86 123 15.0 99 5.41 124 4.98 147 6.87 150 2.78 87 4.82 116 8.66 97 3.65 90
2D-CLG [1]120.3 10.1 142 22.6 147 7.59 138 9.84 139 16.9 127 11.1 143 16.9 146 28.2 147 18.8 152 14.1 146 31.1 145 13.1 146 3.86 116 4.62 106 4.53 136 5.98 125 21.2 138 5.97 128 1.76 12 3.14 6 1.46 16 6.29 128 12.9 135 5.81 124
SPSA-learn [13]121.3 6.84 123 16.7 127 6.74 133 8.47 130 19.4 135 7.49 129 12.5 132 23.1 133 13.1 138 8.40 136 25.8 136 7.08 135 3.87 118 4.66 108 4.10 128 6.32 127 18.8 128 6.89 138 2.56 72 3.85 71 1.79 34 7.29 136 12.5 132 7.47 133
HBpMotionGpu [43]122.7 6.57 120 15.0 120 5.17 116 8.29 129 18.0 131 8.29 134 14.1 137 26.5 140 13.2 139 6.12 127 25.3 133 3.94 122 3.79 110 4.62 106 3.97 124 4.80 106 15.7 108 4.11 98 4.40 139 5.20 127 2.87 97 6.28 127 11.7 125 7.31 130
IAOF [50]123.8 6.49 119 14.6 117 6.42 130 9.22 135 18.5 133 7.94 131 16.4 145 27.4 144 13.0 137 8.22 133 22.2 119 7.73 136 3.77 107 4.76 115 3.42 102 6.84 133 18.8 128 4.23 104 3.59 120 4.46 100 2.83 91 7.51 138 10.1 111 10.6 142
GroupFlow [9]124.5 8.00 130 18.6 132 8.09 140 11.1 142 23.7 146 10.3 141 12.6 133 25.6 138 12.8 136 5.84 123 20.3 106 4.39 127 4.69 143 5.81 146 3.67 114 9.29 145 22.4 144 10.1 147 2.11 42 3.99 82 2.29 68 5.75 123 10.0 108 7.39 132
Black & Anandan [4]125.0 6.81 122 15.4 121 7.43 135 8.77 133 19.5 136 7.35 126 13.0 134 22.9 131 12.5 134 8.29 134 26.1 137 6.77 134 4.18 134 5.28 138 3.69 116 6.19 126 20.0 135 5.34 122 3.63 121 5.05 121 1.79 34 6.45 130 12.2 130 5.17 116
BlockOverlap [61]128.0 6.67 121 13.1 100 5.87 125 6.62 122 13.9 108 6.53 124 10.6 131 19.5 124 10.1 125 6.97 131 24.9 131 5.13 130 4.38 137 4.61 105 6.37 148 7.47 138 15.7 108 6.05 129 6.23 150 6.41 148 13.0 153 6.92 133 9.60 105 12.2 145
Nguyen [33]128.9 7.88 129 16.8 128 7.02 134 13.4 147 19.0 134 15.3 147 17.6 148 28.9 148 17.2 147 12.0 141 26.9 138 11.6 143 4.38 137 5.07 135 5.58 144 5.69 122 19.7 134 5.93 127 2.75 84 4.02 84 1.91 49 6.59 132 12.5 132 6.52 129
2bit-BM-tele [96]129.7 8.00 130 15.8 122 8.40 142 4.91 111 13.4 104 4.67 113 8.14 114 19.0 123 5.12 106 6.62 130 23.5 126 5.04 129 4.08 128 4.78 116 4.61 138 8.68 143 18.8 128 8.31 141 6.46 152 7.08 152 9.47 149 7.36 137 14.1 140 9.62 139
UnFlow [127]129.8 14.6 154 25.8 152 9.09 144 9.40 138 16.8 126 9.89 140 14.2 138 26.9 141 11.2 130 10.0 138 25.4 135 8.67 139 5.43 150 5.90 147 6.72 149 8.64 142 24.0 146 9.41 145 3.51 115 4.90 117 1.37 14 4.37 103 12.6 134 3.33 79
Horn & Schunck [3]135.5 8.01 132 19.9 139 8.38 141 9.13 134 23.2 145 7.71 130 14.2 138 25.9 139 14.6 142 12.4 143 30.6 143 11.3 142 4.64 141 5.64 142 4.60 137 8.21 141 24.4 147 8.45 142 4.01 128 5.41 132 1.95 52 9.16 142 17.5 144 8.86 137
SILK [80]137.0 9.34 140 20.4 140 10.5 147 10.4 140 21.9 142 10.3 141 16.0 144 27.5 145 14.5 141 10.3 139 29.0 142 8.54 138 4.81 144 5.65 143 5.56 143 9.41 146 25.4 149 8.74 143 2.79 88 3.68 59 4.62 134 10.9 147 17.8 146 12.3 146
Heeger++ [102]138.7 11.9 148 21.8 144 8.08 139 12.5 143 29.7 154 9.42 139 14.8 141 27.1 142 9.68 123 14.3 147 31.0 144 12.7 145 4.98 146 5.74 144 4.97 140 17.5 154 34.1 155 18.4 154 2.75 84 5.44 133 2.15 62 12.3 149 18.8 150 14.8 149
TI-DOFE [24]139.7 13.4 152 23.2 148 16.5 154 16.5 150 24.1 147 18.2 152 20.2 154 31.1 154 20.6 153 19.9 152 32.9 148 20.8 153 4.89 145 5.90 147 5.54 142 8.04 140 23.9 145 8.81 144 2.97 96 4.34 94 1.88 46 10.9 147 17.7 145 11.9 144
H+S_RVC [177]139.9 12.8 150 27.1 155 9.43 145 13.2 146 24.7 149 13.1 145 18.4 152 30.6 152 18.2 151 24.9 155 35.5 152 25.3 155 5.24 147 5.33 140 8.05 151 13.9 152 30.6 153 16.1 152 2.14 46 4.43 99 2.05 57 15.1 153 20.0 152 14.2 148
HCIC-L [97]144.0 15.7 155 22.0 146 10.1 146 31.5 156 26.6 152 41.0 156 14.8 141 23.1 133 16.8 146 18.4 151 34.4 150 18.2 152 5.94 151 6.35 151 6.35 147 10.6 149 19.2 131 11.4 149 18.7 156 17.8 156 19.2 155 4.93 119 8.34 94 5.16 114
SLK [47]144.1 11.6 146 26.0 153 14.6 153 15.3 149 25.0 150 17.5 150 17.8 150 30.1 151 18.1 150 25.4 156 33.6 149 28.0 156 5.25 148 5.90 147 7.03 150 10.3 148 27.4 151 10.6 148 2.89 93 4.47 101 2.94 103 14.9 152 20.7 153 18.8 152
FFV1MT [104]145.0 12.0 149 23.3 149 8.83 143 10.7 141 26.6 152 8.71 136 15.6 143 29.0 149 12.0 132 16.6 150 36.3 154 15.5 149 6.51 154 6.40 152 10.4 154 16.2 153 30.7 154 17.7 153 3.41 113 5.44 133 3.35 119 12.3 149 18.8 150 14.8 149
Adaptive flow [45]146.9 13.2 151 20.8 141 14.0 152 17.1 152 22.0 143 17.9 151 18.1 151 27.1 142 22.8 155 11.8 140 31.1 145 10.5 140 6.35 153 7.13 154 6.25 146 9.87 147 21.8 141 9.44 146 12.6 155 11.4 155 20.0 156 7.75 140 13.6 136 7.73 134
PGAM+LK [55]148.3 11.8 147 25.6 150 13.9 151 14.8 148 24.4 148 16.7 149 13.2 135 24.0 136 15.0 143 16.2 149 41.2 156 15.3 148 5.40 149 5.45 141 8.10 152 12.3 151 26.5 150 12.1 150 7.42 153 8.24 154 7.87 147 13.2 151 18.3 148 19.4 153
Periodicity [79]149.1 11.2 144 27.0 154 7.46 137 16.6 151 29.8 156 18.2 152 25.3 156 31.2 156 24.9 156 12.7 145 35.7 153 11.1 141 31.7 156 41.4 156 25.1 156 23.8 156 41.5 156 23.8 156 2.92 94 5.62 137 6.90 145 18.6 155 33.1 156 22.3 154
FOLKI [16]150.0 10.5 143 25.6 150 11.9 149 20.9 154 26.2 151 26.1 154 17.6 148 31.1 154 16.5 145 15.4 148 32.6 147 16.0 150 6.16 152 6.53 153 9.07 153 12.2 150 29.7 152 13.0 151 4.67 143 5.83 141 9.41 148 18.2 154 22.8 154 25.1 155
Pyramid LK [2]152.8 13.9 153 20.9 142 21.4 156 24.1 155 23.1 144 30.2 155 20.9 155 29.5 150 21.9 154 22.2 154 34.6 151 25.0 154 18.7 155 23.1 155 20.2 155 21.2 155 24.5 148 21.0 155 6.41 151 7.02 151 10.8 151 25.6 156 31.5 155 34.5 156
AdaConv-v1 [124]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
SepConv-v1 [125]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
SuperSlomo [130]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
CtxSyn [134]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
CyclicGen [149]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
TOF-M [150]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
MPRN [151]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
DAIN [152]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
FRUCnet [153]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
OFRI [154]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
FGME [158]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
MS-PFT [159]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
MEMC-Net+ [160]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
ADC [161]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
DSepConv [162]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
MAF-net [163]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
STAR-Net [164]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
AdaCoF [165]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
TC-GAN [166]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
FeFlow [167]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
DAI [168]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
SoftSplat [169]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
STSR [170]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
EAFI [171]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
BMBC [172]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
GDCN [173]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
EDSC [174]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
DCM [185]157.4 39.2 157 39.9 157 41.8 157 73.0 157 74.5 157 71.1 157 70.1 157 67.3 157 71.8 157 64.4 157 66.2 157 65.9 157 76.5 158 78.1 158 72.0 158 68.2 158 64.9 158 66.5 158 52.3 158 45.1 158 70.9 158 81.8 157 81.6 157 82.3 157
AVG_FLOW_ROB [137]174.5 62.1 185 56.6 185 61.5 185 99.9 185 96.7 185 99.9 185 81.2 185 81.9 185 80.3 185 65.8 185 68.9 185 67.4 185 68.4 157 75.2 157 67.5 157 62.4 157 55.3 157 59.6 157 31.5 157 28.0 157 29.3 157 86.1 185 96.7 185 87.2 185
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 Tarik Arici and Vural Aksakalli. Energy minimization based motion estimation using adaptive smoothness priors. VISAPP 2012.
[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 Duc Dung Nguyen and Jae Wook Jeon. Enhancing accuracy and sharpness of motion field with adaptive scheme and occlusion-aware filter. IET Image Processing 7.2 (2013): 144-153.
[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 Alper Ayvaci, Michalis Raptis, and Stefano Soatto. Sparse occlusion detection with optical flow. IJCV 97(3):322-338, 2012.
[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 Zhuoyuan Chen, Jiang Wang, and Ying Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. CVPR 2012.
[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 Michael Santoro, Ghassan AlRegib, and Yucel Altunbasak. Motion estimation using block overlap minimization. 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 Weisheng Dong, Guangming Shi, Xiaocheng Hu, and Yi Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. IEEE TIP 23(10):4527-4538, 2014.
[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] NNF-Local 673 2 color Zhuoyuan Chen, Hailin Jin, Zhe Lin, Scott Cohen, and Ying Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[76] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[77] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[78] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[79] Periodicity 8000 4 color Georgii Khachaturov, Silvia Gonzalez-Brambila, and Jesus Gonzalez-Trejo. Periodicity-based computation of optical flow. Computacion y Sistemas (CyS) 2014.
[80] SILK 572 2 gray Pascal Zille, Thomas Corpetti, Liang Shao, and Xu Chen. Observation model based on scale interactions for optical flow estimation. IEEE TIP 23(8):3281-3293, 2014.
[81] 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.
[82] Classic+CPF 640 2 gray Zhigang Tu, Nico van der Aa, Coert Van Gemeren, and Remco Veltkamp. A combined post-filtering method to improve accuracy of variational optical flow estimation. Pattern Recognition 47(5):1926-1940, 2014.
[83] S2D-Matching 1200 2 color Marius Leordeanu, Andrei Zanfir, and Cristian Sminchisescu. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013.
[84] AGIF+OF 438 2 gray Zhigang Tu, Ronald Poppe, and Remco Veltkamp. Adaptive guided image filter for warping in variational optical flow computation. Signal Processing 127:253-265, 2016.
[85] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[86] 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.
[87] 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.
[88] 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.
[89] 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.
[90] 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.
[91] 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.
[92] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[93] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[94] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[95] 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.
[96] 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.
[97] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[98] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[99] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[100] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[101] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[102] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[103] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[104] 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.
[105] 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.
[106] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[107] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[108] 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.
[109] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[110] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[111] 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.)
[112] 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.
[113] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[114] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[115] 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.
[116] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[117] 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.
[118] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[119] 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.
[120] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[121] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[122] 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.
[123] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[124] AdaConv-v1 2.8 2 color Simon Niklaus, Long Mai, and Feng Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[125] SepConv-v1 0.2 2 color Simon Niklaus, Long Mai, and Feng Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[126] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[127] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[128] 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.
[129] 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.
[130] 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.
[131] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[132] 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.
[133] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
[134] CtxSyn 0.07 2 color Simon Niklaus and Feng Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[135] 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.
[136] 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.
[137] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[138] 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.
[139] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[140] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[141] 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.
[142] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[143] PWC-Net_RVC 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. Also RVC 2020 baseline submission.
[144] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[145] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
[146] 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.
[147] 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.
[148] ContinualFlow_ROB 0.5 all color Michal Neoral, Jan Sochman, and Jiri Matas. Continual occlusions and optical flow estimation. ACCV 2018.
[149] CyclicGen 0.088 2 color Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
[150] TOF-M 0.393 2 color Tianfan Xue, Baian Chen, Jiajun Wu, Donglai Wei, and William Freeman. Video enhancement with task-oriented flow. arXiv 1711.09078, 2017.
[151] MPRN 0.32 4 color Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[152] DAIN 0.13 2 color Wenbo Bao, Wei-Sheng Lai, Chao Ma, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019.
[153] FRUCnet 0.65 2 color Van Thang Nguyen, Kyujoong Lee, and Hyuk-Jae Lee. (Interpolation results only.) A stacked deep MEMC network for frame rate up conversion and its application to HEVC. Submitted to IEEE TCSVT 2019.
[154] OFRI 0.31 2 color Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
[155] CompactFlow_ROB 0.05 2 color Anonymous. CompactFlow: spatially shiftable window revisited. CVPR 2019 submission 1387.
[156] SegFlow 3.2 2 color Jun Chen, Zemin Cai, Jianhuang Lai, and Xiaohua Xie. Efficient segmentation-based PatchMatch for large displacement optical flow estimation. IEEE TCSVT 2018.
[157] HCFN 0.18 2 color Anonymous. Practical coarse-to-fine optical flow with deep networks. ICCV 2019 submission 116.
[158] FGME 0.23 2 color Anonymous. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. ICCV 2019 submission 4327.
[159] MS-PFT 0.44 2 color Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) A multi-scale position feature transform network for video frame interpolation. IEEE TCSVT 2020.
[160] MEMC-Net+ 0.12 2 color Wenbo Bao, Wei-Sheng Lai, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang. (Interpolation results only.) MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement. Submitted to PAMI 2018.
[161] ADC 0.01 2 color Anonymous. (Interpolation results only.) Learning spatial transform for video frame interpolation. ICCV 2019 submission 5424.
[162] DSepConv 0.3 2 color Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) Video frame interpolation via deformable separable convolution. AAAI 2020.
[163] MAF-net 0.3 2 color Anonymous. (Interpolation results only.) MAF-net: Motion attention feedback network for video frame interpolation. AAAI 2020 submission 9862.
[164] STAR-Net 0.049 2 color Anonymous. (Interpolation results only.) Space-time-aware multiple resolution for video enhancement. CPVR 2020 submission 430.
[165] AdaCoF 0.03 2 color Hyeongmin Lee, Taeoh Kim, Tae-young Chung, Daehyun Pak, Yuseok Ban, and Sangyoun Lee. (Interpolation results only.) AdaCoF: Adaptive collaboration of flows for video frame interpolation. CVPR 2020. Code available.
[166] TC-GAN 0.13 2 color Anonymous. (Interpolation results only.) A temporal and contextual generative adversarial network for video frame interpolation. CVPR 2020 submission 111.
[167] FeFlow 0.52 2 color Shurui Gui, Chaoyue Wang, Qihua Chen, and Dacheng Tao. (Interpolation results only.) FeatureFlow: Robust video interpolation via structure-to-texture generation. CVPR 2020. Code available.
[168] DAI 0.23 2 color Anonymous. (Interpolation results only.) Deep animation inbetweening. CVPR 2020 submission 6404.
[169] SoftSplat 0.1 2 color Simon Niklaus and Feng Liu. (Interpolation results only.) Softmax splatting for video frame interpolation. CVPR 2020.
[170] STSR 5.35 2 color Anonymous. (Interpolation results only.) Spatial and temporal video super-resolution with a frequency domain loss. ECCV 2020 submission 2340.
[171] EAFI 0.13 2 color Anonymous. (Interpolation results only.) Fast & small: Error-aware frame interpolation. ECCV 2020 submission 5256.
[172] BMBC 0.77 2 color Anonymous. (Interpolation results only.) BMBC: Bilateral motion estimation with bilateral cost volume for video interpolation. ECCV 2020 submission 2095.
[173] GDCN 1.0 2 color Anonymous. (Interpolation results only.) Video interpolation via generalized deformable convolution. ECCV 2020 submission 4347.
[174] EDSC 0.56 2 color Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) Multiple video frame interpolation via enhanced deformable separable convolution. Submitted to PAMI 2020.
[175] CoT-AMFlow 0.04 2 color Anonymous. CoT-AMFlow: Adaptive modulation network with co-teaching strategy for unsupervised optical flow estimation. CoRL 2020 submission 36.
[176] TVL1_RVC 11.6 2 color RVC 2020 baseline submission by Toby Weed, based on: Javier Sanchez, Enric Meinhardt-Llopis, and Gabriele Facciolo. TV-L1 optical flow estimation. IPOL 3:137-150, 2013.
[177] H+S_RVC 44.7 2 color RVC 2020 baseline submission by Toby Weed, based on: Enric Meinhardt-Llopis, Javier Sanchez, and Daniel Kondermann. Horn-Schunck optical flow with a multi-scale strategy. IPOL 3:151–172, 2013.
[178] PRAFlow_RVC 0.34 2 color Zhexiong Wan, Yuxin Mao, and Yuchao Dai. Pyramid recurrent all-pairs flow. RVC 2020 submission.
[179] VCN_RVC 0.84 2 color Gengshan Yang and Deva Ramanan. Volumetric correspondence networks for optical flow. NeurIPS 2019. RVC 2020 submission.
[180] RAFT-TF_RVC 1.51 2 color Deqing Sun, Charles Herrmann, Varun Jampani, Mike Krainin, Forrester Cole, Austin Stone, Rico Jonschkowski, Ramin Zabih, William Freeman, and Ce Liu. A TensorFlow implementation of RAFT (Zachary Teed and Jia Deng. RAFT: Recurrent all-pairs field transforms for optical flow. ECCV 2020.) RVC 2020 submission.
[181] IRR-PWC_RVC 0.18 2 color Junhwa Hur and Stefan Roth. Iterative residual refinement for joint optical flow and occlusion estimation. CVPR 2019. RVC 2020 submission.
[182] C-RAFT_RVC 0.60 2 color Henrique Morimitsu and Xiangyang Ji. Classification RAFT. RVC 2020 submission.
[183] LSM_FLOW_RVC 0.2 2 color Chengzhou Tang, Lu Yuan, and Ping Tan. LSM: Learning subspace minimization for low-level vision. CVPR 2020. RVC 2020 submission.
[184] UnDAF 0.04 2 color Anonymous. UnDAF: A general unsupervised domain adaptation framework for disparity, optical flow or scene flow estimation. AAAI 2021 submission 6648.
[185] DCM 0.13 2 color Anonymous. (Interpolation results only.) Distill from a cheating model for flow-based video frame interpolation. AAAI 2021 submission 4425.
* 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.