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 [75]8.9 0.19 30 1.11 34 0.00 1 0.73 5 5.01 5 0.12 5 1.08 5 3.84 4 0.00 1 0.54 12 4.91 14 0.02 9 4.35 3 7.43 3 0.89 2 1.53 7 8.39 8 1.54 10 0.00 1 0.00 1 0.00 1 3.65 15 12.4 30 1.32 7
RAFT-it+_RVC [198]9.7 0.21 51 1.23 51 0.03 61 0.66 4 4.99 4 0.00 1 0.75 1 2.67 1 0.12 10 0.44 9 4.66 12 0.00 1 4.34 2 7.32 2 0.99 3 0.57 2 4.30 3 0.01 1 0.00 1 0.00 1 0.00 1 2.09 4 7.69 4 0.73 3
RAFT-it [194]10.2 0.19 30 1.14 37 0.03 61 0.89 12 5.66 12 0.11 4 1.12 6 4.00 7 0.37 33 0.19 6 2.07 6 0.00 1 5.27 5 8.96 5 1.62 8 0.52 1 3.21 1 0.46 3 0.00 1 0.00 1 0.00 1 1.66 2 6.10 2 0.42 1
GMFlow_RVC [196]10.5 0.18 21 1.08 28 0.03 61 0.55 1 4.15 1 0.01 2 0.90 2 3.13 2 0.44 40 0.64 15 4.63 11 0.14 15 5.33 6 8.98 6 1.54 7 1.40 6 7.49 7 1.35 7 0.00 1 0.00 1 0.00 1 1.77 3 6.47 3 0.99 4
PMMST [112]13.4 0.20 38 1.20 45 0.03 61 0.57 2 4.20 2 0.21 16 1.12 6 3.98 6 0.06 5 0.16 5 1.79 5 0.00 1 6.17 10 10.4 10 2.09 11 2.24 10 10.3 12 3.42 39 0.00 1 0.00 1 0.00 1 3.14 9 10.1 12 3.34 14
NN-field [71]15.9 0.23 71 1.37 73 0.00 1 0.64 3 4.87 3 0.07 3 1.23 10 4.31 8 0.03 3 0.60 14 5.03 15 0.04 10 4.24 1 7.24 1 0.70 1 5.93 70 6.73 6 2.33 18 0.00 1 0.00 1 0.00 1 3.87 19 13.1 42 1.27 6
MS_RAFT+_RVC [195]17.2 0.18 21 1.06 23 0.05 92 1.35 38 5.59 11 0.87 79 1.60 16 5.66 17 0.77 69 0.35 8 3.84 9 0.00 1 4.51 4 7.68 4 1.17 5 0.58 3 3.30 2 0.49 4 0.00 1 0.00 1 0.00 1 1.31 1 4.47 1 0.49 2
OFLAF [78]18.9 0.20 38 1.21 46 0.00 1 0.92 15 5.66 12 0.25 21 1.22 8 4.32 9 0.12 10 1.03 31 8.42 33 0.22 42 7.31 17 12.4 17 2.79 15 3.20 23 11.6 15 3.15 34 0.00 1 0.00 1 0.00 1 3.66 16 9.73 11 7.15 36
RAFT-TF_RVC [179]22.0 0.31 107 1.83 111 0.03 61 0.90 13 5.96 16 0.14 7 1.80 23 6.24 24 1.47 107 0.13 3 1.41 3 0.00 1 5.34 7 9.09 7 1.25 6 0.68 4 4.55 4 0.15 2 0.00 1 0.00 1 0.00 1 2.62 6 9.40 7 1.08 5
MCPFlow_RVC [197]23.8 0.21 51 1.24 56 0.03 61 1.42 45 7.49 30 0.49 43 2.10 26 7.32 27 0.99 84 0.50 11 4.52 10 0.20 34 6.02 8 10.2 9 1.15 4 1.57 8 8.53 9 0.63 5 0.00 1 0.00 1 0.00 1 3.75 17 11.2 18 3.21 12
ComponentFusion [94]25.2 0.17 15 1.02 19 0.03 61 0.93 16 6.31 18 0.23 20 1.48 13 5.26 13 0.22 18 0.68 16 6.90 23 0.05 11 10.5 55 17.2 58 7.34 57 3.34 25 15.8 45 3.80 52 0.00 1 0.00 1 0.00 1 3.81 18 11.2 18 6.45 30
MDP-Flow2 [68]25.6 0.18 21 1.07 25 0.03 61 0.82 7 5.18 6 0.20 14 1.31 11 4.69 11 0.09 8 1.24 66 11.0 76 0.24 52 9.23 41 15.2 44 5.96 42 2.65 14 11.8 17 3.56 43 0.00 1 0.00 1 0.00 1 3.61 14 11.1 16 5.40 22
Layers++ [37]25.7 0.15 7 0.90 10 0.00 1 0.88 11 6.28 17 0.29 25 1.61 18 5.50 16 0.95 83 0.92 26 5.94 17 0.24 52 6.07 9 9.99 8 3.95 22 6.14 76 15.3 38 5.23 96 0.00 1 0.00 1 0.00 1 4.11 23 10.5 13 7.50 46
TC/T-Flow [77]25.9 0.11 2 0.67 2 0.00 1 1.63 60 8.48 41 0.45 37 2.21 29 7.45 30 0.16 14 1.20 59 10.2 68 0.16 16 9.34 44 14.9 40 6.04 43 1.76 9 9.86 11 1.36 8 0.00 1 0.00 1 0.00 1 4.64 35 12.6 33 7.19 37
PRAFlow_RVC [177]26.5 0.27 92 1.59 93 0.04 86 0.96 17 6.49 20 0.20 14 2.36 34 8.21 40 1.24 96 0.78 20 6.10 18 0.12 13 6.74 14 11.3 13 3.17 16 1.15 5 6.29 5 1.19 6 0.00 1 0.00 1 0.00 1 3.33 10 9.65 10 2.98 10
VCN_RVC [178]29.4 0.22 62 1.30 64 0.00 1 1.26 32 8.68 44 0.35 29 1.51 15 5.37 15 0.76 68 1.00 28 7.56 27 0.17 25 8.68 33 14.6 35 3.68 19 4.80 51 11.9 18 2.78 26 0.00 1 0.00 1 0.00 1 4.42 30 14.3 56 5.70 25
PWC-Net_RVC [143]30.5 0.15 7 0.89 8 0.01 37 1.39 44 10.0 64 0.40 34 2.59 50 8.97 53 0.71 67 0.59 13 4.66 12 0.16 16 9.75 51 16.4 53 4.25 24 6.09 73 15.2 35 3.22 35 0.00 1 0.00 1 0.00 1 3.57 13 12.1 28 3.32 13
CombBMOF [111]30.8 0.20 38 1.18 40 0.03 61 1.05 21 6.42 19 0.16 8 1.66 20 5.67 18 0.01 2 0.79 21 6.82 22 0.16 16 7.66 20 12.5 19 4.37 26 8.16 113 15.3 38 7.67 142 0.00 1 0.00 1 0.00 1 4.31 27 11.0 15 7.79 51
3DFlow [133]31.7 0.26 86 1.57 91 0.00 1 1.31 36 9.13 52 0.31 27 2.56 48 8.87 50 0.25 20 0.11 2 1.19 2 0.00 1 8.69 34 14.2 32 5.21 34 8.16 113 15.8 45 4.22 61 0.00 1 0.00 1 0.00 1 2.86 7 9.33 6 2.36 9
NNF-EAC [101]31.7 0.17 15 1.03 20 0.01 37 1.01 18 5.78 15 0.38 33 1.81 24 6.09 22 0.13 12 1.27 70 11.4 80 0.24 52 8.50 29 14.2 32 5.00 33 4.85 53 12.2 20 4.55 72 0.00 1 0.00 1 0.00 1 4.77 39 13.1 42 7.37 40
WLIF-Flow [91]32.5 0.20 38 1.21 46 0.01 37 0.91 14 5.77 14 0.26 23 2.30 32 7.50 31 0.38 35 1.10 41 8.71 37 0.25 66 8.40 28 14.0 28 4.94 32 4.91 55 13.0 25 3.79 51 0.00 1 0.00 1 0.00 1 4.98 45 12.6 33 8.37 65
MLDP_OF [87]33.0 0.17 15 1.00 17 0.00 1 0.82 7 5.37 9 0.13 6 2.62 51 8.28 42 0.15 13 1.01 30 8.41 32 0.17 25 8.84 35 14.4 34 5.24 36 2.41 12 11.1 13 1.54 10 0.29 140 0.00 1 1.28 143 5.41 58 12.9 39 5.66 24
FC-2Layers-FF [74]33.5 0.19 30 1.10 31 0.00 1 1.53 52 10.0 64 0.68 61 1.47 12 5.05 12 0.37 33 1.07 37 8.29 31 0.22 42 6.46 11 10.5 11 3.24 17 6.93 91 15.2 35 5.43 103 0.00 1 0.00 1 0.00 1 4.89 41 12.6 33 7.93 53
HCFN [157]33.6 0.14 5 0.84 5 0.03 61 1.28 35 8.07 37 0.64 57 1.63 19 5.81 21 0.33 26 1.13 45 9.21 52 0.18 29 8.94 37 14.6 35 5.43 37 3.71 33 12.6 22 2.36 19 0.00 1 0.00 1 0.00 1 5.79 68 15.5 61 10.6 100
CoT-AMFlow [174]33.8 0.18 21 1.09 29 0.03 61 0.81 6 5.19 7 0.26 23 1.74 22 6.17 23 0.70 66 1.28 72 11.4 80 0.25 66 9.52 48 15.2 44 7.79 63 2.74 15 12.4 21 3.73 49 0.00 1 0.00 1 0.00 1 4.20 25 11.7 24 7.48 43
nLayers [57]34.1 0.19 30 1.13 36 0.00 1 1.04 20 7.08 28 0.31 27 2.42 40 8.37 45 0.50 43 1.10 41 8.82 39 0.38 84 6.91 15 11.4 15 3.98 23 6.52 82 12.6 22 5.28 98 0.00 1 0.00 1 0.00 1 4.63 34 12.5 32 8.25 61
FlowFields+ [128]35.0 0.15 7 0.88 7 0.01 37 1.38 42 8.90 49 0.68 61 2.23 31 7.99 34 0.44 40 0.70 17 6.60 21 0.20 34 12.0 67 19.4 70 7.65 62 2.62 13 16.5 60 1.82 14 0.00 1 0.00 1 0.00 1 5.64 65 18.0 78 5.92 27
IIOF-NLDP [129]35.0 0.32 112 1.90 114 0.00 1 1.27 33 8.57 42 0.16 8 3.02 65 9.58 60 0.20 15 0.48 10 3.49 8 0.13 14 9.15 39 14.9 40 4.86 30 6.07 72 14.8 34 4.05 59 0.00 1 0.00 1 0.00 1 4.43 31 12.0 26 5.52 23
Correlation Flow [76]35.4 0.25 82 1.46 83 0.00 1 1.10 25 7.16 29 0.22 18 4.18 86 12.3 82 0.35 30 0.74 18 5.14 16 0.22 42 11.5 62 17.7 60 9.04 78 4.12 42 13.1 26 2.69 24 0.00 1 0.00 1 0.00 1 3.48 11 10.9 14 3.71 17
UnDAF [187]36.3 0.26 86 1.57 91 0.03 61 0.83 9 5.28 8 0.25 21 1.60 16 5.70 19 0.38 35 1.27 70 11.2 79 0.24 52 9.48 46 15.5 49 6.61 50 2.81 18 12.7 24 3.69 47 0.00 1 0.00 1 0.00 1 4.13 24 11.7 24 7.21 39
PH-Flow [99]37.9 0.20 38 1.16 38 0.00 1 1.36 39 7.94 35 0.53 47 1.69 21 5.76 20 0.64 60 1.10 41 8.60 36 0.24 52 6.59 12 11.1 12 3.26 18 3.52 29 11.6 15 3.39 37 0.13 130 0.00 1 0.44 125 4.21 26 11.4 21 7.94 56
PMF [73]38.6 0.20 38 1.19 42 0.03 61 1.06 24 6.51 21 0.18 11 1.50 14 5.33 14 0.09 8 1.26 69 9.04 46 0.23 46 7.32 18 12.4 17 1.91 9 5.47 62 16.3 52 4.67 76 0.09 124 0.00 1 0.25 120 3.51 12 9.50 8 6.99 34
AGIF+OF [84]38.6 0.21 51 1.25 60 0.00 1 1.48 50 8.75 46 0.37 31 2.50 45 8.15 38 0.38 35 1.14 48 8.88 40 0.23 46 7.56 19 12.5 19 4.30 25 6.71 85 15.2 35 4.99 87 0.00 1 0.00 1 0.00 1 5.07 49 13.0 41 8.68 73
IROF++ [58]39.1 0.23 71 1.37 73 0.00 1 1.37 41 8.26 39 0.45 37 2.40 38 7.86 32 0.51 46 1.16 55 9.50 59 0.24 52 8.06 24 13.2 23 4.86 30 5.64 67 16.4 55 4.51 70 0.00 1 0.00 1 0.00 1 4.62 32 12.7 38 7.93 53
HAST [107]39.8 0.21 51 1.27 62 0.03 61 1.55 55 6.58 22 0.85 77 1.07 4 3.84 4 0.06 5 1.18 58 9.57 61 0.19 32 6.70 13 11.3 13 2.10 12 5.68 68 14.2 30 5.14 94 0.01 106 0.00 1 0.05 109 2.21 5 7.87 5 2.21 8
ProbFlowFields [126]40.7 0.20 38 1.18 40 0.03 61 1.25 30 7.90 34 0.64 57 2.55 47 8.95 51 1.08 89 0.25 7 2.68 7 0.05 11 12.5 78 19.9 76 8.91 76 2.82 19 15.8 45 2.70 25 0.00 1 0.00 1 0.00 1 5.90 71 18.1 79 6.95 33
SVFilterOh [109]43.3 0.22 62 1.31 65 0.05 92 1.14 27 6.84 25 0.30 26 2.13 27 7.39 28 0.69 65 0.86 22 7.24 25 0.16 16 8.17 25 13.8 26 2.18 13 6.69 83 15.3 38 4.47 69 0.27 139 0.00 1 0.74 130 2.89 8 9.59 9 3.97 19
TC-Flow [46]43.5 0.13 3 0.77 3 0.00 1 1.38 42 8.10 38 0.47 40 2.97 64 10.0 65 0.34 28 1.36 80 10.5 74 0.25 66 11.2 59 18.1 62 7.49 59 3.36 26 17.1 69 1.78 13 0.00 1 0.00 1 0.00 1 6.35 77 17.8 77 10.0 95
EPPM w/o HM [86]43.6 0.21 51 1.25 60 0.03 61 1.05 21 6.95 27 0.19 12 2.42 40 8.24 41 0.08 7 1.00 28 7.81 29 0.21 39 7.69 21 13.0 21 2.55 14 6.45 81 18.5 84 4.04 58 0.43 147 0.00 1 0.76 131 3.98 21 11.1 16 7.10 35
CostFilter [40]44.0 0.22 62 1.32 69 0.03 61 1.16 28 6.61 23 0.22 18 1.22 8 4.37 10 0.21 17 1.29 73 10.2 68 0.21 39 7.77 22 13.2 23 2.07 10 5.43 60 15.9 49 3.96 57 0.07 121 0.00 1 0.12 114 4.75 38 13.5 49 7.19 37
FlowFields [108]46.8 0.16 12 0.97 13 0.02 56 1.54 54 9.90 63 0.72 65 2.38 36 8.48 47 0.58 57 1.03 31 9.05 47 0.31 76 12.5 78 20.3 83 8.76 75 3.16 22 18.0 83 3.08 33 0.00 1 0.00 1 0.00 1 6.22 75 19.0 82 6.76 31
ALD-Flow [66]46.9 0.14 5 0.85 6 0.01 37 1.70 63 8.34 40 0.50 44 2.94 62 9.96 64 0.38 35 1.68 92 13.0 90 0.32 78 11.8 66 18.8 67 8.42 72 2.93 20 16.4 55 1.70 12 0.00 1 0.00 1 0.00 1 5.91 73 17.4 73 8.45 68
C-RAFT_RVC [181]47.9 0.21 51 1.24 56 0.03 61 2.91 114 12.3 91 1.74 116 3.29 69 11.4 73 1.02 86 0.77 19 6.11 19 0.17 25 12.6 81 19.9 76 9.24 84 2.33 11 11.5 14 1.98 15 0.00 1 0.00 1 0.00 1 4.04 22 13.5 49 3.38 15
COFM [59]48.2 0.28 96 1.64 96 0.06 98 1.31 36 7.81 32 0.57 52 3.57 76 12.0 79 1.10 91 0.91 25 7.78 28 0.16 16 11.7 65 18.5 66 10.3 96 4.05 39 13.7 29 4.28 64 0.00 1 0.00 1 0.00 1 3.96 20 11.5 22 6.40 29
WRT [146]48.4 0.37 118 2.21 122 0.00 1 1.78 68 11.7 80 0.42 36 5.99 115 14.9 105 0.52 49 0.10 1 1.14 1 0.00 1 9.05 38 14.7 38 5.43 37 8.84 126 15.6 42 4.60 75 0.00 1 0.00 1 0.00 1 5.13 51 12.2 29 5.72 26
RNLOD-Flow [119]48.5 0.17 15 1.03 20 0.00 1 1.50 51 9.63 58 0.56 51 3.15 68 10.1 67 0.56 55 1.14 48 9.02 45 0.20 34 9.73 50 15.7 50 6.54 49 5.43 60 14.7 32 4.56 74 0.06 119 0.00 1 0.34 121 4.41 28 11.3 20 7.56 47
LSM [39]48.6 0.21 51 1.23 51 0.00 1 1.88 77 11.5 78 0.82 74 2.45 42 8.04 35 0.52 49 1.12 44 9.06 48 0.23 46 9.27 43 15.1 43 6.05 44 7.21 96 16.5 60 5.47 104 0.00 1 0.00 1 0.00 1 5.29 55 13.8 52 8.49 70
Sparse-NonSparse [56]48.8 0.22 62 1.31 65 0.00 1 1.87 75 11.4 77 0.80 72 2.47 44 8.05 36 0.52 49 1.15 54 8.89 41 0.24 52 9.37 45 15.3 46 5.94 41 7.18 94 16.3 52 5.47 104 0.00 1 0.00 1 0.00 1 5.08 50 13.1 42 8.42 66
S2F-IF [121]49.0 0.18 21 1.07 25 0.02 56 1.53 52 10.0 64 0.72 65 2.37 35 8.45 46 0.54 52 1.21 60 9.59 62 0.35 80 12.7 83 20.3 83 9.20 83 3.41 27 17.7 78 3.70 48 0.00 1 0.00 1 0.00 1 5.36 57 16.5 67 6.13 28
FMOF [92]50.0 0.20 38 1.19 42 0.00 1 1.61 58 9.42 55 0.53 47 2.03 25 6.86 25 0.22 18 1.04 33 8.71 37 0.16 16 8.59 30 14.0 28 4.44 27 7.80 106 16.2 50 5.73 113 0.09 124 0.00 1 0.81 133 5.75 67 14.6 59 8.44 67
HBM-GC [103]50.0 0.29 99 1.72 103 0.03 61 1.36 39 8.81 47 0.71 64 2.92 60 10.0 65 0.79 70 1.21 60 8.97 43 0.37 82 8.90 36 14.6 35 5.72 40 5.58 65 9.50 10 3.51 42 0.00 1 0.00 1 0.00 1 5.23 54 15.1 60 8.28 62
LME [70]50.2 0.24 75 1.40 77 0.04 86 0.84 10 5.51 10 0.21 16 3.70 78 8.78 48 5.39 125 1.38 82 11.0 76 0.37 82 9.52 48 15.3 46 7.58 60 3.73 34 16.9 67 4.43 67 0.00 1 0.00 1 0.00 1 4.62 32 12.6 33 7.77 50
MDP-Flow [26]50.8 0.13 3 0.78 4 0.00 1 1.05 21 6.71 24 0.64 57 2.31 33 8.09 37 1.26 97 1.35 78 12.5 89 0.28 71 10.4 54 16.8 56 7.29 55 5.39 59 16.9 67 4.89 83 0.00 1 0.00 1 0.00 1 8.69 112 21.5 102 12.1 112
DPOF [18]50.8 0.17 15 0.99 15 0.00 1 2.06 90 10.3 69 0.92 84 0.99 3 3.51 3 0.05 4 1.08 38 9.87 66 0.17 25 8.25 27 13.8 26 3.72 20 9.58 136 18.7 85 5.78 114 1.06 153 0.00 1 2.93 151 4.41 28 13.4 48 3.94 18
NL-TV-NCC [25]50.8 0.24 75 1.43 81 0.01 37 1.43 47 9.86 62 0.16 8 3.10 67 10.1 67 0.20 15 1.13 45 9.56 60 0.16 16 11.5 62 18.3 65 7.31 56 8.51 118 20.7 111 4.68 77 0.00 1 0.00 1 0.00 1 5.59 63 16.1 64 5.10 21
FESL [72]51.1 0.23 71 1.35 72 0.00 1 1.71 65 9.38 54 0.54 49 2.22 30 7.40 29 0.31 22 1.08 38 9.18 50 0.16 16 7.97 23 13.0 21 4.61 28 7.68 103 16.5 60 5.87 116 0.09 124 0.00 1 0.17 117 4.96 44 12.4 30 8.31 63
Classic+NL [31]51.8 0.23 71 1.34 71 0.01 37 1.93 80 11.7 80 0.80 72 2.57 49 8.35 43 0.58 57 1.22 63 9.29 55 0.24 52 8.66 32 14.1 30 5.48 39 7.52 101 16.3 52 5.42 101 0.00 1 0.00 1 0.00 1 5.06 47 12.9 39 8.47 69
ResPWCR_ROB [140]53.5 0.19 30 1.10 31 0.00 1 1.62 59 9.55 56 0.40 34 3.47 74 11.6 77 1.29 102 1.04 33 8.53 35 0.22 42 11.3 60 18.2 63 7.48 58 6.92 90 17.5 76 5.48 106 0.00 1 0.00 1 0.00 1 6.95 85 20.1 90 8.98 80
Classic+CPF [82]54.5 0.21 51 1.23 51 0.01 37 1.47 49 8.95 50 0.37 31 2.73 53 8.84 49 0.35 30 1.14 48 9.32 56 0.23 46 8.60 31 14.1 30 5.23 35 8.01 110 16.4 55 5.26 97 0.20 136 0.00 1 0.86 135 4.71 36 12.0 26 8.34 64
ProFlow_ROB [142]55.0 0.28 96 1.66 97 0.01 37 1.65 62 10.1 68 0.73 67 3.30 70 11.4 73 0.64 60 1.35 78 10.4 72 0.23 46 12.1 68 19.8 74 6.97 54 3.91 37 16.6 64 2.12 16 0.00 1 0.00 1 0.00 1 5.60 64 16.8 70 7.48 43
Efficient-NL [60]55.2 0.22 62 1.29 63 0.00 1 1.25 30 7.99 36 0.48 42 2.92 60 9.31 54 0.31 22 1.23 65 9.67 65 0.31 76 8.23 26 13.5 25 4.72 29 8.45 117 17.1 69 6.06 119 0.12 129 0.00 1 0.54 127 4.71 36 11.6 23 7.75 49
JOF [136]55.3 0.31 107 1.77 109 0.07 110 1.97 85 10.7 71 1.00 89 2.14 28 7.04 26 0.60 59 1.13 45 8.98 44 0.24 52 7.05 16 11.9 16 3.77 21 6.22 78 14.7 32 5.04 89 0.01 106 0.00 1 0.00 1 4.83 40 13.1 42 8.17 60
Complementary OF [21]56.7 0.15 7 0.89 8 0.00 1 1.43 47 8.69 45 0.35 29 2.54 46 8.95 51 0.28 21 1.45 84 12.4 86 0.28 71 14.9 114 21.6 107 15.4 120 7.75 104 17.6 77 3.64 45 0.00 1 0.00 1 0.00 1 7.27 93 22.2 111 9.59 90
SRR-TVOF-NL [89]56.8 0.19 30 1.05 22 0.03 61 3.08 116 13.8 110 1.68 114 3.97 82 12.4 83 0.84 71 1.22 63 9.35 58 0.20 34 11.5 62 16.7 55 12.3 106 2.79 16 13.5 27 3.68 46 0.00 1 0.00 1 0.00 1 5.69 66 13.1 42 10.1 96
LiteFlowNet [138]57.7 0.31 107 1.86 112 0.03 61 1.96 84 11.5 78 0.68 61 3.06 66 10.4 69 0.51 46 0.89 24 6.31 20 0.19 32 13.1 86 20.9 89 8.46 73 5.32 58 16.5 60 2.97 31 0.00 1 0.00 1 0.00 1 6.37 78 17.6 76 8.62 71
IROF-TV [53]58.9 0.22 62 1.24 56 0.01 37 1.83 73 11.9 84 0.87 79 2.96 63 9.37 55 0.50 43 1.70 93 14.6 100 0.46 90 9.51 47 15.4 48 6.49 48 4.78 50 22.9 126 4.55 72 0.00 1 0.00 1 0.00 1 5.17 52 14.4 58 8.73 75
Ramp [62]59.1 0.21 51 1.24 56 0.00 1 1.77 67 11.1 74 0.79 70 2.39 37 7.95 33 0.55 54 1.17 57 9.16 49 0.24 52 9.25 42 14.9 40 6.31 46 7.18 94 15.7 43 5.42 101 0.19 135 0.00 1 0.96 137 5.18 53 13.3 47 8.87 79
OFH [38]59.7 0.17 15 1.00 17 0.00 1 1.80 70 9.80 60 0.66 60 4.49 92 13.2 94 0.47 42 1.62 90 13.6 95 0.35 80 13.2 89 20.8 88 10.2 94 3.85 35 20.4 108 2.41 21 0.00 1 0.00 1 0.00 1 7.06 89 21.6 104 9.31 85
ROF-ND [105]60.4 0.29 99 1.73 105 0.01 37 2.75 110 11.0 72 0.73 67 3.45 73 10.7 70 0.51 46 0.13 3 1.44 4 0.00 1 12.2 70 18.8 67 10.5 97 6.28 80 17.1 69 4.80 81 0.00 1 0.00 1 0.00 1 8.30 108 21.5 102 9.38 86
PBOFVI [189]61.2 0.37 118 2.18 120 0.00 1 1.95 83 12.6 98 0.54 49 4.00 83 11.7 78 0.57 56 0.94 27 6.98 24 0.24 52 11.0 58 16.9 57 9.27 85 8.10 111 15.7 43 4.40 66 0.01 106 0.00 1 0.00 1 5.06 47 13.9 53 7.93 53
OAR-Flow [123]61.8 0.19 30 1.12 35 0.06 98 2.86 111 12.0 85 1.41 109 4.36 89 13.9 97 1.43 106 1.51 86 11.7 83 0.23 46 12.6 81 20.0 80 8.47 74 2.80 17 16.4 55 1.37 9 0.00 1 0.00 1 0.00 1 5.56 62 16.7 68 8.15 59
FF++_ROB [141]63.0 0.29 99 1.66 97 0.06 98 1.74 66 11.3 76 0.84 76 3.66 77 12.1 81 1.40 105 1.14 48 9.66 64 0.33 79 12.4 73 20.1 82 8.17 69 3.96 38 15.4 41 2.67 23 0.00 1 0.00 1 0.00 1 5.83 70 16.3 65 9.01 81
TCOF [69]63.5 0.18 21 1.06 23 0.00 1 1.56 56 9.24 53 0.60 54 4.63 95 12.8 90 0.89 74 1.34 77 12.4 86 0.20 34 12.4 73 19.6 73 9.52 87 6.02 71 14.3 31 5.03 88 0.34 145 0.00 1 1.23 142 4.94 42 13.6 51 8.00 57
TV-L1-MCT [64]64.3 0.22 62 1.33 70 0.00 1 1.64 61 9.85 61 0.52 45 2.86 59 9.38 56 0.32 25 1.14 48 8.89 41 0.24 52 10.6 56 16.4 53 9.05 79 8.81 124 17.2 73 5.12 93 0.08 123 0.00 1 0.84 134 5.93 74 14.3 56 10.1 96
ACK-Prior [27]65.1 0.15 7 0.91 11 0.00 1 1.21 29 7.63 31 0.19 12 2.41 39 8.36 44 0.35 30 1.25 68 10.5 74 0.18 29 12.4 73 18.0 61 11.2 99 9.00 130 19.4 97 6.39 126 0.17 133 0.00 1 1.01 139 9.72 121 20.1 90 13.3 117
CRTflow [81]65.6 0.18 21 0.99 15 0.03 61 1.70 63 9.09 51 0.59 53 4.56 93 12.8 90 0.68 62 2.03 110 15.1 106 0.64 100 12.4 73 20.0 80 8.26 70 4.42 43 24.0 131 3.47 40 0.00 1 0.00 1 0.00 1 7.88 100 22.0 110 10.4 99
2DHMM-SAS [90]65.7 0.20 38 1.21 46 0.00 1 1.80 70 10.4 70 0.63 56 4.15 84 11.3 72 0.86 72 1.24 66 9.61 63 0.25 66 9.18 40 14.8 39 6.44 47 8.98 129 17.3 74 4.98 85 0.13 130 0.00 1 0.69 129 5.55 61 14.2 55 9.22 83
PGM-C [118]66.1 0.20 38 1.19 42 0.07 110 1.87 75 11.8 83 0.85 77 2.76 54 9.82 63 0.92 79 1.99 106 15.1 106 0.74 109 13.1 86 21.2 92 9.19 82 3.52 29 19.2 93 2.47 22 0.00 1 0.00 1 0.00 1 6.38 79 19.5 86 8.65 72
SegFlow [156]67.1 0.21 51 1.23 51 0.07 110 1.94 81 12.1 86 0.89 81 2.78 57 9.81 62 1.02 86 1.99 106 15.0 104 0.74 109 13.4 94 21.4 99 10.1 90 4.64 47 18.9 89 3.07 32 0.00 1 0.00 1 0.00 1 5.47 59 16.8 70 7.48 43
SimpleFlow [49]68.5 0.22 62 1.31 65 0.00 1 1.78 68 11.0 72 0.82 74 4.30 88 12.5 86 1.22 95 1.16 55 9.20 51 0.24 52 9.84 53 15.8 51 6.94 53 8.51 118 17.3 74 6.11 122 0.09 124 0.00 1 0.39 123 5.01 46 14.1 54 8.00 57
CPM-Flow [114]69.2 0.21 51 1.23 51 0.07 110 1.92 79 12.1 86 0.89 81 2.64 52 9.39 57 0.92 79 1.96 103 14.8 101 0.72 107 13.1 86 21.2 92 8.92 77 4.84 52 19.1 92 3.40 38 0.00 1 0.00 1 0.00 1 6.92 84 20.5 93 9.43 88
Sparse Occlusion [54]69.5 0.24 75 1.38 75 0.06 98 1.27 33 7.83 33 0.45 37 3.42 71 11.1 71 0.33 26 1.52 88 11.4 80 0.28 71 10.9 57 17.6 59 6.76 52 4.10 41 16.2 50 4.27 63 0.03 111 0.17 156 0.15 115 5.90 71 15.7 62 8.69 74
ComplOF-FED-GPU [35]70.4 0.19 30 1.10 31 0.03 61 2.32 97 12.5 96 0.92 84 2.76 54 9.65 61 0.31 22 1.65 91 13.1 91 0.38 84 13.4 94 21.2 92 10.2 94 8.60 122 22.8 124 4.22 61 0.00 1 0.00 1 0.00 1 7.44 94 22.4 112 9.81 91
EpicFlow [100]73.8 0.20 38 1.17 39 0.07 110 1.91 78 12.1 86 0.90 83 3.70 78 12.7 88 0.89 74 1.96 103 14.8 101 0.74 109 13.4 94 21.3 97 9.97 89 6.71 85 19.3 95 3.90 54 0.00 1 0.00 1 0.00 1 7.03 86 20.1 90 9.91 92
TF+OM [98]75.4 0.16 12 0.98 14 0.01 37 1.85 74 10.0 64 1.15 101 4.71 99 12.6 87 5.84 126 1.79 98 14.0 98 0.69 104 15.4 120 22.1 112 16.5 126 5.62 66 19.8 102 3.95 56 0.00 1 0.00 1 0.00 1 8.18 105 20.6 95 12.0 111
S2D-Matching [83]75.8 0.33 114 1.92 116 0.06 98 2.04 88 12.4 93 0.79 70 4.15 84 13.0 92 1.09 90 1.09 40 8.04 30 0.24 52 9.82 52 15.9 52 6.68 51 7.85 107 16.4 55 5.58 108 0.20 136 0.00 1 0.96 137 4.94 42 12.6 33 8.81 77
DeepFlow2 [106]75.8 0.26 86 1.53 88 0.08 119 2.56 105 11.7 80 1.30 107 3.73 80 11.5 76 0.90 76 1.99 106 15.1 106 0.65 102 12.3 71 19.5 72 9.07 80 4.57 45 18.7 85 2.81 28 0.00 1 0.00 1 0.00 1 8.01 104 21.0 97 10.8 103
AggregFlow [95]76.8 0.53 129 2.62 137 0.12 133 2.72 108 13.2 103 1.45 110 3.90 81 13.0 92 1.85 112 1.06 36 9.26 53 0.18 29 12.1 68 19.4 70 7.83 65 3.05 21 12.1 19 2.29 17 0.04 117 0.00 1 0.44 125 5.82 69 15.9 63 9.26 84
ContinualFlow_ROB [148]77.6 0.26 86 1.50 85 0.02 56 3.07 115 15.6 117 1.24 103 5.35 106 16.3 120 3.58 122 1.36 80 10.4 72 0.21 39 13.9 103 22.7 117 7.58 60 8.27 116 19.4 97 5.84 115 0.00 1 0.00 1 0.00 1 5.35 56 17.5 74 4.42 20
Adaptive [20]77.8 0.29 99 1.72 103 0.06 98 2.04 88 12.5 96 1.13 99 5.51 109 14.7 103 0.68 62 1.83 99 13.9 97 0.59 98 12.7 83 19.9 76 10.1 90 7.15 92 18.9 89 4.08 60 0.00 1 0.00 1 0.00 1 6.38 79 16.4 66 8.82 78
IRR-PWC_RVC [180]78.3 0.49 127 2.34 128 0.11 130 4.76 133 20.4 136 2.29 124 6.66 125 17.5 127 7.60 136 0.88 23 8.47 34 0.16 16 13.0 85 21.0 91 7.81 64 3.54 31 19.9 103 2.36 19 0.00 1 0.00 1 0.00 1 7.77 97 22.6 115 6.89 32
CompactFlow_ROB [155]79.8 0.20 38 1.21 46 0.04 86 2.54 104 13.2 103 1.01 90 5.96 114 15.9 116 7.15 133 1.38 82 11.1 78 0.50 93 14.3 107 23.2 124 9.15 81 4.08 40 21.0 114 3.62 44 0.00 1 0.00 1 0.00 1 8.21 106 22.4 112 10.6 100
LFNet_ROB [145]82.0 0.25 82 1.50 85 0.04 86 1.94 81 12.3 91 0.95 87 4.69 97 14.9 105 1.47 107 1.14 48 9.32 56 0.51 94 16.3 128 24.6 139 15.5 121 5.01 56 22.7 122 3.48 41 0.00 1 0.00 1 0.00 1 8.24 107 23.7 124 11.4 108
Steered-L1 [116]82.3 0.10 1 0.59 1 0.01 37 1.01 18 6.84 25 0.52 45 2.76 54 9.44 58 0.91 77 1.78 96 14.9 103 0.51 94 14.0 106 20.5 85 15.2 118 9.02 131 19.9 103 6.57 130 1.07 154 0.00 1 7.19 155 12.1 130 22.9 117 20.6 136
DMF_ROB [135]82.4 0.18 21 1.07 25 0.03 61 2.32 97 12.7 99 1.10 96 4.84 101 15.1 112 1.27 100 2.06 113 15.9 113 0.75 113 13.7 99 21.2 92 12.3 106 7.35 99 21.7 118 5.05 90 0.00 1 0.00 1 0.00 1 8.30 108 21.8 107 11.1 105
RFlow [88]83.1 0.20 38 1.21 46 0.01 37 1.58 57 9.77 59 0.77 69 4.69 97 13.5 95 0.34 28 2.30 124 17.7 125 0.80 116 14.3 107 21.4 99 15.1 117 5.47 62 20.9 113 4.98 85 0.01 106 0.00 1 0.15 115 7.91 102 21.0 97 10.6 100
EAI-Flow [147]84.7 0.27 92 1.59 93 0.06 98 3.31 118 15.7 118 1.68 114 5.29 104 15.9 116 2.31 115 1.73 95 13.1 91 0.59 98 14.9 114 23.3 126 11.0 98 4.60 46 17.7 78 2.85 29 0.00 1 0.00 1 0.00 1 7.19 91 19.6 88 11.2 107
TriangleFlow [30]85.0 0.24 75 1.39 76 0.00 1 2.50 103 14.3 111 0.98 88 4.46 91 12.7 88 0.41 39 1.49 85 12.2 85 0.42 88 15.8 123 23.1 121 16.4 124 8.57 120 17.7 78 4.86 82 0.03 111 0.00 1 0.05 109 6.59 81 17.3 72 9.55 89
Occlusion-TV-L1 [63]85.5 0.27 92 1.55 90 0.06 98 1.99 87 12.1 86 1.14 100 5.42 107 14.9 105 0.93 81 1.83 99 14.0 98 0.49 92 13.6 98 21.2 92 11.5 101 6.13 75 19.6 101 5.37 100 0.00 1 0.00 1 0.00 1 9.19 115 23.4 123 11.5 109
DeepFlow [85]85.9 0.34 117 1.74 107 0.09 121 2.87 112 12.4 93 1.56 111 4.42 90 12.4 83 2.69 119 2.20 118 16.1 115 0.81 117 12.3 71 19.8 74 8.36 71 4.85 53 20.1 105 2.95 30 0.00 1 0.00 1 0.00 1 9.35 116 23.3 122 12.7 114
Aniso. Huber-L1 [22]86.0 0.29 99 1.66 97 0.06 98 2.43 102 13.1 102 1.12 98 5.68 110 14.3 101 1.27 100 1.56 89 12.4 86 0.30 75 12.4 73 19.2 69 10.1 90 4.70 49 17.1 69 4.45 68 0.17 133 0.00 1 0.89 136 6.28 76 16.7 68 8.80 76
CBF [12]87.4 0.18 21 1.09 29 0.01 37 2.37 100 12.9 100 1.94 119 4.28 87 12.0 79 1.13 93 1.97 105 16.1 115 0.66 103 13.3 93 20.5 85 12.7 110 5.89 69 18.8 88 4.73 78 0.45 149 0.00 1 1.33 145 7.67 96 18.9 81 12.7 114
CVENG22+RIC [199]88.0 0.22 62 1.31 65 0.06 98 2.33 99 14.3 111 1.02 91 4.56 93 14.6 102 0.91 77 2.05 111 15.3 109 0.83 119 16.5 131 24.4 137 16.4 124 6.74 88 21.7 118 5.60 109 0.00 1 0.00 1 0.00 1 7.03 86 20.8 96 9.21 82
OFRF [132]88.7 0.54 131 2.51 132 0.12 133 7.58 146 15.8 119 7.13 151 7.71 130 15.0 108 5.91 128 1.78 96 9.27 54 1.09 128 11.3 60 18.2 63 6.18 45 6.74 88 13.5 27 2.79 27 0.00 1 0.00 1 0.00 1 12.7 132 19.0 82 27.9 146
LocallyOriented [52]88.9 0.49 127 2.66 138 0.06 98 3.28 117 15.4 115 1.91 118 6.59 122 16.9 122 1.20 94 1.29 73 10.1 67 0.52 97 14.6 110 21.5 102 12.6 108 7.79 105 16.7 65 4.33 65 0.00 1 0.00 1 0.00 1 7.87 99 19.1 84 11.1 105
LSM_FLOW_RVC [182]90.6 0.40 120 2.35 129 0.10 127 3.70 122 20.0 135 2.10 121 6.26 119 19.4 135 2.49 117 2.47 127 15.7 111 1.00 125 13.5 97 21.9 110 8.02 66 3.57 32 20.6 109 3.27 36 0.00 1 0.00 1 0.00 1 6.80 82 21.6 104 7.68 48
TV-L1-improved [17]91.0 0.25 82 1.46 83 0.07 110 1.82 72 11.1 74 1.02 91 5.46 108 15.0 108 1.32 103 2.26 121 16.4 118 0.79 115 13.8 101 21.5 102 11.8 102 9.40 133 23.6 130 6.48 127 0.00 1 0.00 1 0.00 1 7.89 101 21.3 101 10.3 98
DF-Auto [113]91.9 0.61 137 2.33 127 0.10 127 4.04 126 15.3 114 2.49 128 6.59 122 14.8 104 6.66 130 1.84 101 15.0 104 0.51 94 14.9 114 21.5 102 16.8 128 3.47 28 16.7 65 3.82 53 0.00 1 0.00 1 0.00 1 7.99 103 19.5 86 11.6 110
FlowNet2 [120]92.0 0.74 142 3.32 145 0.12 133 5.00 135 17.2 125 2.46 127 6.13 117 15.0 108 5.85 127 1.29 73 10.3 71 0.40 87 13.2 89 21.6 107 8.11 67 7.27 97 17.7 78 6.06 119 0.00 1 0.00 1 0.05 109 5.52 60 17.5 74 3.70 16
TriFlow [93]92.5 0.27 92 1.62 95 0.01 37 2.27 96 13.2 103 1.24 103 7.10 127 16.9 122 7.37 134 1.31 76 11.7 83 0.43 89 17.3 135 23.4 130 20.6 137 3.24 24 15.8 45 3.91 55 4.67 161 0.00 1 18.1 161 6.86 83 18.1 79 7.89 52
EPMNet [131]94.0 0.64 140 3.15 142 0.09 121 5.25 136 18.8 131 2.74 133 5.08 103 14.0 98 2.76 120 1.51 86 13.3 93 0.28 71 13.2 89 21.6 107 8.11 67 7.27 97 17.7 78 6.06 119 0.00 1 0.00 1 0.02 108 7.03 86 23.1 118 3.19 11
Brox et al. [5]94.6 0.25 82 1.45 82 0.03 61 2.22 95 13.7 109 1.07 94 3.44 72 11.4 73 0.68 62 2.20 118 16.7 122 0.72 107 17.8 140 23.4 130 24.6 146 8.90 128 24.6 134 6.63 131 0.00 1 0.00 1 0.00 1 10.6 125 25.9 132 14.8 124
CLG-TV [48]94.8 0.31 107 1.67 101 0.06 98 2.10 92 13.0 101 0.92 84 5.33 105 14.2 100 1.04 88 1.71 94 13.7 96 0.38 84 13.9 103 21.4 99 12.0 103 5.20 57 22.7 122 5.07 91 0.20 136 0.00 1 1.01 139 7.85 98 19.4 85 9.91 92
Bartels [41]95.6 0.24 75 1.40 77 0.01 37 1.42 45 8.88 48 0.62 55 3.51 75 12.4 83 1.00 85 2.26 121 15.8 112 0.95 122 15.5 121 23.3 126 15.8 123 7.99 109 23.0 127 5.20 95 0.33 142 0.00 1 1.92 148 9.95 123 24.0 125 13.7 119
SegOF [10]96.6 0.24 75 1.41 79 0.05 92 4.72 132 21.4 137 3.68 137 9.28 137 19.5 136 4.83 123 1.05 35 7.42 26 0.78 114 20.7 150 27.1 148 28.6 151 10.4 140 26.0 138 7.80 143 0.00 1 0.00 1 0.00 1 7.25 92 20.0 89 7.44 42
Fusion [6]96.8 0.24 75 1.41 79 0.05 92 1.13 26 8.57 42 0.47 40 2.45 42 8.15 38 0.93 81 2.12 117 18.3 131 1.21 129 16.2 127 23.1 121 19.6 135 6.72 87 18.7 85 5.67 111 0.07 121 0.15 154 0.10 113 10.4 124 24.9 129 14.6 123
Classic++ [32]97.9 0.26 86 1.50 85 0.07 110 2.08 91 12.2 90 1.03 93 4.84 101 14.0 98 1.26 97 2.07 115 16.1 115 0.64 100 13.9 103 22.5 114 10.1 90 6.11 74 23.1 128 5.28 98 0.06 119 0.00 1 0.34 121 8.66 111 21.7 106 11.0 104
Rannacher [23]99.3 0.33 114 1.95 117 0.07 110 2.21 94 13.4 107 1.29 106 5.78 111 15.6 114 1.48 109 2.51 129 17.8 126 0.95 122 14.5 109 22.5 114 12.2 105 9.72 137 24.8 135 6.66 132 0.00 1 0.00 1 0.00 1 7.50 95 21.1 100 9.97 94
BriefMatch [122]101.2 0.16 12 0.94 12 0.01 37 1.97 85 9.60 57 1.10 96 2.79 58 9.56 59 0.54 52 2.11 116 15.6 110 0.70 105 14.6 110 21.5 102 15.2 118 10.4 140 22.0 120 8.36 146 2.52 160 0.62 164 13.7 160 13.6 139 25.5 131 22.0 140
AugFNG_ROB [139]101.3 0.57 135 2.19 121 0.11 130 4.08 128 16.3 122 2.52 130 8.00 132 19.2 134 8.51 138 1.21 60 10.2 68 0.26 70 16.5 131 25.6 145 13.4 112 7.17 93 24.2 132 5.99 117 0.00 1 0.00 1 0.00 1 8.96 114 25.1 130 9.39 87
Local-TV-L1 [65]102.1 0.53 129 2.10 118 0.12 133 4.96 134 18.0 129 3.44 136 8.54 135 16.7 121 6.16 129 2.47 127 18.5 133 1.01 127 12.5 78 19.9 76 9.65 88 5.53 64 19.5 99 4.95 84 0.00 1 0.00 1 0.00 1 13.4 136 24.2 126 27.1 145
SIOF [67]102.7 0.42 123 2.28 123 0.08 119 3.55 121 17.7 128 2.05 120 8.15 133 17.9 130 7.78 137 2.41 126 17.9 127 1.00 125 15.5 121 22.7 117 17.8 132 4.67 48 19.5 99 4.77 80 0.00 1 0.00 1 0.00 1 9.35 116 21.8 107 17.7 130
Second-order prior [8]106.0 0.26 86 1.53 88 0.05 92 2.88 113 15.5 116 1.60 112 5.87 112 15.3 113 1.11 92 2.21 120 17.2 124 0.94 121 13.8 101 21.3 97 12.6 108 7.46 100 27.8 144 5.71 112 0.16 132 0.00 1 0.76 131 8.65 110 21.0 97 13.9 121
p-harmonic [29]106.1 0.29 99 1.73 105 0.02 56 2.16 93 13.2 103 1.33 108 5.87 112 15.8 115 1.59 110 2.55 130 17.9 127 1.49 132 17.0 133 22.7 117 23.3 143 4.53 44 21.5 117 4.53 71 0.03 111 0.02 153 0.00 1 9.65 120 23.2 121 15.0 125
Dynamic MRF [7]106.8 0.30 106 1.79 110 0.04 86 2.37 100 14.9 113 1.09 95 4.81 100 15.0 108 0.86 72 2.66 131 18.2 130 1.25 130 17.6 138 25.7 146 18.1 133 10.9 145 30.4 149 7.45 139 0.00 1 0.00 1 0.00 1 15.1 142 29.9 147 21.9 139
Shiralkar [42]107.2 0.28 96 1.66 97 0.02 56 3.80 124 19.8 134 1.78 117 6.50 120 16.1 119 1.26 97 3.17 135 20.8 137 1.56 134 16.3 128 25.1 143 14.5 115 12.4 149 29.4 147 6.20 123 0.00 1 0.00 1 0.00 1 12.6 131 30.1 148 13.8 120
CNN-flow-warp+ref [115]109.9 0.33 114 1.91 115 0.09 121 2.72 108 12.4 93 2.32 125 6.77 126 18.9 133 2.09 113 2.28 123 16.4 118 0.82 118 17.7 139 23.9 134 22.8 142 9.40 133 24.3 133 6.73 133 0.00 1 0.00 1 0.00 1 14.0 140 26.8 138 20.2 135
F-TV-L1 [15]110.4 0.46 124 2.58 134 0.07 110 4.05 127 16.2 121 2.21 122 6.59 122 15.9 116 1.39 104 2.35 125 17.9 127 0.88 120 13.7 99 21.5 102 11.4 100 7.53 102 21.1 116 4.75 79 0.03 111 0.17 156 0.05 109 7.15 90 20.5 93 7.39 41
GraphCuts [14]112.7 0.29 99 1.67 101 0.16 141 6.77 143 22.4 141 3.81 138 7.73 131 17.2 125 9.04 139 1.86 102 16.8 123 0.46 90 15.8 123 24.0 135 14.1 114 20.2 158 22.8 124 12.5 155 0.00 1 0.00 1 0.00 1 13.4 136 27.0 141 23.4 142
StereoOF-V1MT [117]113.6 0.41 121 2.35 129 0.04 86 4.27 130 21.6 138 1.66 113 6.25 118 17.7 128 0.50 43 3.13 134 23.2 141 1.41 131 19.4 147 27.9 152 20.7 139 11.6 147 32.5 151 7.60 141 0.00 1 0.00 1 0.00 1 16.7 146 32.8 151 21.3 137
HBpMotionGpu [43]116.6 0.80 144 2.79 140 0.18 142 5.57 137 23.8 145 4.00 139 13.1 146 27.8 152 11.6 146 2.05 111 16.4 118 0.74 109 17.9 141 25.1 143 22.3 141 6.69 83 21.0 114 6.04 118 0.00 1 0.00 1 0.00 1 14.1 141 27.7 142 25.1 143
Ad-TV-NDC [36]117.0 0.79 143 2.68 139 0.12 133 13.0 154 26.5 147 12.9 154 12.9 145 22.0 140 9.24 140 5.02 140 20.3 136 4.82 140 13.2 89 20.5 85 9.43 86 6.17 77 20.3 107 5.07 91 0.03 111 0.00 1 0.00 1 20.5 151 26.9 139 40.8 158
Filter Flow [19]117.7 0.58 136 2.59 135 0.11 130 4.48 131 19.7 132 2.66 132 12.1 140 23.7 143 13.5 151 14.5 151 30.4 147 15.0 151 18.7 146 23.7 133 27.5 150 8.11 112 20.7 111 6.48 127 0.00 1 0.00 1 0.00 1 11.0 127 21.9 109 17.2 128
StereoFlow [44]118.0 2.82 162 6.92 161 1.29 161 21.5 160 42.6 163 13.8 155 20.5 161 33.3 162 20.4 157 20.6 158 51.2 161 18.6 156 14.9 114 22.6 116 13.7 113 3.89 36 18.9 89 3.74 50 0.00 1 0.00 1 0.00 1 11.3 129 25.9 132 18.7 133
WOLF_ROB [144]119.0 0.56 133 3.04 141 0.09 121 6.60 140 23.5 143 3.40 135 8.20 134 18.2 132 2.44 116 2.06 113 13.3 93 0.98 124 16.4 130 23.3 126 18.2 134 9.74 138 19.2 93 6.28 125 0.01 106 0.00 1 0.20 119 9.49 118 23.1 118 14.3 122
Modified CLG [34]120.3 0.62 138 2.54 133 0.12 133 3.52 120 18.7 130 2.59 131 12.2 142 23.5 142 12.5 148 3.25 136 20.1 135 2.03 136 18.6 145 25.0 142 25.0 147 8.86 127 26.9 143 7.14 137 0.00 1 0.00 1 0.00 1 13.4 136 29.8 146 21.8 138
2bit-BM-tele [96]121.7 0.54 131 2.59 135 0.20 143 2.58 106 16.3 122 1.26 105 6.04 116 17.8 129 2.26 114 2.77 133 19.7 134 1.50 133 15.8 123 23.3 126 16.5 126 8.58 121 22.4 121 5.62 110 1.37 156 0.00 1 5.84 154 10.7 126 24.8 128 16.5 127
Learning Flow [11]122.0 0.32 112 1.89 113 0.01 37 2.61 107 16.0 120 1.21 102 6.52 121 17.9 130 1.65 111 4.69 139 24.9 144 3.14 139 20.8 151 27.4 151 26.9 149 10.9 145 28.6 146 7.90 144 0.10 128 0.00 1 0.64 128 13.3 135 28.5 145 18.1 131
SPSA-learn [13]123.8 0.86 146 3.30 144 0.28 149 6.02 139 22.0 139 4.09 140 10.6 138 21.3 138 9.82 144 5.83 143 22.9 139 5.66 144 17.9 141 23.4 130 23.4 144 10.2 139 25.0 136 8.09 145 0.00 1 0.00 1 0.00 1 15.9 145 28.1 143 23.3 141
FlowNetS+ft+v [110]124.2 0.31 107 1.76 108 0.09 121 3.39 119 13.5 108 2.49 128 7.24 128 16.9 122 5.12 124 3.32 137 18.3 131 2.07 137 17.1 134 23.2 124 20.3 136 6.23 79 23.2 129 5.50 107 0.35 146 0.52 161 1.50 147 8.79 113 23.1 118 13.6 118
IAOF2 [51]125.3 0.47 126 2.28 123 0.33 150 3.77 123 16.3 122 2.22 123 7.40 129 17.2 125 7.06 132 14.7 152 29.4 146 16.6 153 15.2 119 23.0 120 14.7 116 10.5 142 20.6 109 7.03 136 0.32 141 0.00 1 2.00 150 11.2 128 22.6 115 15.4 126
UnFlow [127]125.4 1.88 156 6.59 158 0.87 157 6.75 142 27.2 148 4.57 142 12.5 144 27.9 153 7.37 134 5.65 142 21.0 138 5.26 142 22.5 154 30.2 155 26.4 148 9.48 135 30.5 150 7.32 138 0.00 1 0.00 1 0.00 1 9.58 119 26.9 139 12.3 113
TVL1_RVC [175]127.2 1.04 148 3.71 147 0.27 148 9.05 148 24.7 146 7.74 152 14.6 149 25.4 147 12.6 149 10.6 146 31.1 149 11.5 148 17.4 136 24.5 138 20.6 137 9.21 132 25.5 137 6.84 134 0.00 1 0.00 1 0.00 1 21.9 153 31.0 149 39.9 156
LDOF [28]127.2 0.41 121 2.31 126 0.09 121 3.85 125 17.3 126 2.32 125 4.68 96 13.5 95 2.59 118 3.97 138 24.8 143 2.14 138 16.1 126 23.1 121 17.6 130 8.24 115 26.0 138 6.50 129 0.33 142 0.34 158 1.95 149 9.77 122 26.7 136 12.9 116
Nguyen [33]128.0 0.83 145 3.37 146 0.22 144 7.27 145 22.1 140 6.46 146 15.4 152 26.8 150 12.4 147 17.6 155 30.4 147 20.2 158 18.5 144 24.7 140 24.5 145 8.82 125 28.5 145 8.81 148 0.00 1 0.00 1 0.00 1 18.9 150 31.7 150 29.4 148
IAOF [50]128.7 0.46 124 2.11 119 0.10 127 6.63 141 19.7 132 4.61 143 13.8 148 23.3 141 9.33 141 9.91 145 23.2 141 11.3 147 14.8 113 22.2 113 15.5 121 10.6 143 26.8 142 6.99 135 0.05 118 0.00 1 0.42 124 18.0 149 24.4 127 35.4 154
BlockOverlap [61]130.2 0.62 138 2.30 125 0.14 140 4.11 129 17.6 127 3.02 134 9.12 136 19.6 137 6.97 131 2.74 132 16.5 121 1.72 135 14.7 112 20.9 89 16.8 128 7.89 108 19.3 95 6.25 124 2.12 157 0.52 161 10.9 159 15.2 143 22.4 112 32.3 152
GroupFlow [9]130.6 0.56 133 3.20 143 0.05 92 9.79 150 32.3 154 7.11 150 11.4 139 24.6 144 9.68 143 2.01 109 16.0 114 0.70 105 19.8 148 29.9 154 12.0 103 15.2 155 32.5 151 15.4 157 0.33 142 0.00 1 1.11 141 13.2 134 28.4 144 17.2 128
2D-CLG [1]131.5 1.77 155 6.22 156 0.51 155 5.91 138 22.4 141 4.54 141 16.4 153 28.6 155 18.1 156 17.9 156 35.8 152 19.9 157 20.4 149 25.8 147 29.3 152 12.0 148 29.6 148 11.4 152 0.00 1 0.00 1 0.00 1 17.7 148 32.8 151 26.2 144
Heeger++ [102]132.6 0.95 147 4.26 150 0.26 147 11.8 153 39.5 161 6.54 147 12.3 143 24.7 146 3.51 121 10.7 147 37.1 154 8.97 145 30.7 160 36.7 160 39.2 158 21.4 160 46.3 161 18.3 160 0.00 1 0.00 1 0.00 1 24.4 155 37.0 154 31.9 150
FFV1MT [104]136.2 1.42 151 6.80 160 0.25 145 10.3 151 35.9 158 6.76 149 18.0 155 30.0 157 16.5 153 17.2 154 51.3 162 16.2 152 31.5 161 37.1 161 43.2 162 20.9 159 44.0 160 17.2 158 0.00 1 0.00 1 0.00 1 24.4 155 37.0 154 31.9 150
TI-DOFE [24]136.4 1.58 153 5.19 153 0.36 152 16.8 156 34.3 156 17.7 157 19.3 160 30.2 159 21.6 159 23.3 159 39.1 156 27.6 159 21.1 152 27.1 148 29.5 153 14.4 153 35.1 155 12.1 154 0.00 1 0.00 1 0.00 1 27.2 159 40.8 158 41.2 159
H+S_RVC [176]138.8 2.45 161 6.66 159 0.87 157 10.3 151 34.2 155 6.70 148 17.8 154 31.4 160 16.6 155 29.5 163 41.8 158 33.2 163 27.7 159 31.9 157 42.8 161 24.2 161 48.0 162 25.0 161 0.00 1 0.00 1 0.00 1 38.2 162 44.9 161 45.2 160
Black & Anandan [4]140.4 0.68 141 2.46 131 0.13 139 7.01 144 23.6 144 4.65 144 12.1 140 21.6 139 9.40 142 5.45 141 23.1 140 4.84 141 17.5 137 24.3 136 21.6 140 10.6 143 26.6 141 7.49 140 0.43 147 0.15 154 1.31 144 12.7 132 26.7 136 18.8 134
Horn & Schunck [3]140.8 1.05 149 4.22 149 0.25 145 7.74 147 29.1 151 5.17 145 13.6 147 24.6 144 10.8 145 12.7 149 36.1 153 12.8 149 21.4 153 27.3 150 30.9 155 13.9 152 35.2 156 11.6 153 0.03 111 0.00 1 0.17 117 22.3 154 37.9 156 31.7 149
SILK [80]144.5 1.05 149 4.27 151 0.44 153 9.69 149 27.9 149 8.93 153 15.2 151 26.9 151 13.1 150 6.14 144 25.9 145 5.57 143 23.0 155 29.2 153 34.1 156 12.6 150 33.9 153 9.78 150 0.81 152 0.00 1 3.50 152 21.5 152 33.3 153 34.5 153
HCIC-L [97]146.4 1.95 157 6.24 157 0.99 160 28.7 162 32.2 153 35.8 162 18.6 158 26.2 148 25.7 162 25.4 162 46.6 160 27.7 160 15.1 118 21.9 110 12.7 110 8.77 123 20.2 106 9.24 149 6.40 163 0.49 160 23.0 163 15.3 144 26.4 135 18.4 132
SLK [47]149.7 1.44 152 5.58 154 0.49 154 14.4 155 35.8 157 14.8 156 18.5 156 30.1 158 21.4 158 24.6 160 35.7 151 27.7 160 26.3 158 31.9 157 39.4 159 15.6 156 38.8 158 13.6 156 0.55 151 0.00 1 1.35 146 31.7 160 41.0 159 49.0 161
Adaptive flow [45]150.6 1.75 154 5.07 152 0.34 151 18.4 158 28.3 150 18.5 159 18.5 156 28.6 155 22.9 160 13.3 150 37.4 155 13.9 150 17.9 141 24.7 140 17.7 131 12.9 151 26.2 140 8.68 147 5.20 162 0.61 163 22.8 162 16.7 146 26.0 134 28.2 147
PGAM+LK [55]150.9 2.98 163 6.17 155 6.36 198 16.8 156 36.2 159 17.8 158 14.7 150 26.5 149 14.5 152 19.1 157 53.9 163 18.3 155 23.1 156 30.6 156 29.9 154 14.4 153 36.8 157 11.1 151 1.07 154 0.00 1 4.16 153 25.9 157 40.1 157 40.3 157
FOLKI [16]151.5 1.98 158 7.18 162 0.87 157 24.5 161 36.3 160 30.3 161 18.7 159 32.4 161 16.5 153 15.2 153 33.2 150 18.1 154 26.0 157 32.3 159 36.0 157 17.7 157 40.6 159 17.9 159 2.33 159 0.00 1 10.6 157 33.9 161 43.6 160 52.7 162
Periodicity [79]152.3 2.36 160 9.12 163 0.79 156 19.1 159 40.7 162 20.6 160 28.2 163 35.2 163 26.8 163 11.2 148 40.6 157 10.3 146 42.3 163 55.4 163 41.1 160 31.7 162 56.3 163 27.7 162 0.54 150 0.00 1 7.78 156 26.1 158 51.0 162 36.2 155
Pyramid LK [2]161.3 2.31 159 4.20 148 3.47 197 31.6 163 32.0 152 40.4 163 21.0 162 28.5 154 24.0 161 24.6 160 43.7 159 28.6 162 37.5 162 46.6 162 43.7 163 33.1 163 34.2 154 31.3 163 2.17 158 0.47 159 10.7 158 46.5 163 57.3 163 67.2 163
AdaConv-v1 [124]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
SepConv-v1 [125]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
SuperSlomo [130]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
CtxSyn [134]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
CyclicGen [149]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
TOF-M [150]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
MPRN [151]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
DAIN [152]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
FRUCnet [153]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
OFRI [154]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
FGME [158]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
MS-PFT [159]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
MEMC-Net+ [160]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
ADC [161]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
DSepConv [162]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
MAF-net [163]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
STAR-Net [164]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
AdaCoF [165]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
TC-GAN [166]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
FeFlow [167]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
DAI [168]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
SoftSplat [169]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
STSR [170]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
BMBC [171]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
GDCN [172]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
EDSC [173]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
MV_VFI [183]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
DistillNet [184]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
SepConv++ [185]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
EAFI [186]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
FLAVR [188]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
SoftsplatAug [190]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
ProBoost-Net [191]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
IDIAL [192]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
IFRNet [193]164.3 6.16 164 11.8 164 2.11 162 91.0 164 93.3 164 87.2 164 83.4 164 79.4 164 87.3 164 47.3 164 64.4 164 46.2 164 89.6 164 93.2 165 73.3 164 69.7 165 60.5 164 67.1 165 41.7 165 14.2 165 92.5 165 99.6 165 98.7 165 100.0 165
AVG_FLOW_ROB [137]179.1 41.6 199 34.9 199 54.2 199 94.7 199 94.6 199 92.2 199 90.3 199 88.2 199 90.3 199 80.5 199 73.8 199 82.4 199 91.3 199 92.4 164 87.0 199 67.7 164 60.9 199 64.7 164 20.2 164 0.00 1 42.1 164 93.8 164 92.8 164 98.2 164
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 Tan Khoa Mai, Michele Gouiffes, and Samia Bouchafa. Optical flow refinement using iterative propagation under colour, proximity and flow reliability constraints. IET Image Processing 2020.
[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 Bo Yan, Weimin Tan, Chuming Lin, and Liquan Shen. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. IEEE Transactions on Broadcasting, 2020.
[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 Mengshun Hu, Jing Xiao, Liang Liao, Zheng Wang, Chia-Wen Lin, Mi Wang, and Shinichi Satoh. Capturing small, fast-moving objects: Frame interpolation via recurrent motion enhancement. IEEE TCSVT 2021.
[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] BMBC 0.77 2 color Anonymous. (Interpolation results only.) BMBC: Bilateral motion estimation with bilateral cost volume for video interpolation. ECCV 2020 submission 2095.
[172] GDCN 1.0 2 color Anonymous. (Interpolation results only.) Video interpolation via generalized deformable convolution. ECCV 2020 submission 4347.
[173] 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.
[174] 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.
[175] 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.
[176] 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.
[177] PRAFlow_RVC 0.34 2 color Zhexiong Wan, Yuxin Mao, and Yuchao Dai. Pyramid recurrent all-pairs flow. RVC 2020 submission.
[178] VCN_RVC 0.84 2 color Gengshan Yang and Deva Ramanan. Volumetric correspondence networks for optical flow. NeurIPS 2019. RVC 2020 submission.
[179] 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.
[180] 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.
[181] C-RAFT_RVC 0.60 2 color Henrique Morimitsu and Xiangyang Ji. Classification RAFT. RVC 2020 submission.
[182] 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.
[183] MV_VFI 0.23 2 color Zhenfang Wang, Yanjiang Wang, and Baodi Liu. (Interpolation results only.) Multi-view based video interpolation algorithm. ICASSP 2021 submission.
[184] DistillNet 0.12 2 color Anonymous. (Interpolation results only.) A teacher-student optical-flow distillation framework for video frame interpolation. CVPR 2021 submission 7534.
[185] SepConv++ 0.1 2 color Simon Niklaus, Long Mai, and Oliver Wang. (Interpolation results only.) Revisiting adaptive convolutions for video frame interpolation. WACV 2021.
[186] EAFI 0.18 2 color Anonymous. (Interpolation results only.) Error-aware spatial ensembles for video frame interpolation. ICCV 2021 submission 8020.
[187] UnDAF 0.04 2 color Anonymous. UnDAF: A general unsupervised domain adaptation framework for disparity, optical flow or scene flow estimation. CVPR 2021 submission 236.
[188] FLAVR 0.029 all color Anonymous. (Interpolation results only.) FLAVR frame interpolation. NeurIPS 2021 submission 1300.
[189] PBOFVI 150 2 color Zemin Cai, Jianhuang Lai, Xiaoxin Liao, and Xucong Chen. Physics-based optical flow under varying illumination. Submitted to IEEE TCSVT 2021.
[190] SoftsplatAug 0.17 2 color Anonymous. (Interpolation results only.) Transformation data augmentation for sports video frame interpolation. ICCV 2021 submission 3245.
* 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.