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        
R1.0
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
RAFT-it [194]8.2 1.00 54 5.96 62 0.30 5 1.64 7 9.26 2 0.53 8 2.13 3 7.60 3 0.54 9 0.46 4 5.08 4 0.00 1 10.7 7 18.0 7 3.18 5 1.01 1 6.84 2 0.49 3 0.00 1 0.00 1 0.00 1 3.98 3 12.7 2 2.42 3
RAFT-it+_RVC [198]9.0 0.99 53 5.88 60 0.31 6 1.34 1 8.58 1 0.49 6 2.04 1 7.24 1 0.25 1 0.69 7 7.34 9 0.00 1 9.78 3 16.6 3 2.50 1 1.23 3 9.31 4 0.04 1 0.00 1 0.02 46 0.00 1 3.92 2 14.3 4 1.48 1
NNF-Local [75]11.2 0.82 11 4.87 13 0.37 21 1.75 10 12.1 13 0.53 8 2.22 4 7.90 4 0.57 11 1.07 13 9.10 15 0.17 10 9.77 2 16.5 2 2.56 3 4.53 10 15.6 9 3.00 10 0.00 1 0.02 46 0.00 1 5.99 14 19.5 31 3.94 6
OFLAF [78]13.7 0.82 11 4.86 11 0.38 24 1.74 8 11.1 9 0.62 17 2.08 2 7.42 2 0.57 11 1.61 21 12.0 21 0.48 22 11.2 9 19.0 9 3.96 10 6.81 35 19.8 19 4.79 35 0.00 1 0.00 1 0.00 1 5.80 11 15.6 7 9.76 32
PMMST [112]14.2 0.65 2 3.86 2 0.05 1 2.23 23 13.5 23 1.21 41 2.81 12 9.66 12 0.83 18 1.29 15 6.70 7 0.42 20 11.7 10 19.1 10 5.55 15 5.50 16 17.8 13 4.52 24 0.00 1 0.02 46 0.00 1 5.44 8 15.8 8 5.70 12
GMFlow_RVC [196]16.3 0.95 45 5.62 49 0.39 31 2.38 31 13.1 19 1.53 61 2.60 10 8.95 8 0.87 23 1.03 11 7.71 11 0.16 9 12.8 17 21.1 16 5.00 12 2.57 6 12.5 7 1.90 7 0.00 1 0.00 1 0.00 1 4.65 5 15.2 6 3.34 5
NN-field [71]17.3 0.89 26 5.29 28 0.40 34 2.06 18 14.1 28 0.62 17 2.49 6 8.79 7 0.68 14 0.99 9 8.66 13 0.09 7 9.99 4 16.8 4 2.51 2 6.53 29 11.2 6 2.42 9 0.01 59 0.02 46 0.00 1 5.86 12 19.6 32 2.84 4
MS_RAFT+_RVC [195]17.8 1.01 58 6.02 65 0.44 52 3.42 71 11.0 8 3.17 108 2.58 7 9.14 10 0.83 18 0.59 5 6.09 5 0.00 1 8.65 1 14.6 1 2.67 4 1.10 2 5.91 1 0.58 4 0.00 1 0.00 1 0.00 1 3.10 1 9.94 1 2.03 2
MDP-Flow2 [68]18.5 0.77 5 4.59 5 0.31 6 1.46 3 9.56 3 0.39 1 2.59 8 9.00 9 0.91 25 2.48 60 17.7 68 0.70 59 14.1 29 23.0 28 8.20 35 5.27 12 18.2 14 4.66 27 0.00 1 0.00 1 0.00 1 5.91 13 16.7 11 8.80 19
RAFT-TF_RVC [179]23.2 1.46 105 8.57 113 0.52 69 1.85 11 11.6 10 0.64 19 3.40 23 11.8 23 2.26 68 0.43 3 4.75 3 0.00 1 11.9 12 20.1 12 3.81 8 1.48 4 8.71 3 0.34 2 0.00 1 0.00 1 0.00 1 6.79 20 20.2 37 4.72 8
Correlation Flow [76]23.6 0.81 8 4.81 9 0.22 2 2.03 15 13.0 16 0.42 2 5.14 63 15.7 59 0.55 10 1.09 14 8.36 12 0.28 15 16.6 51 26.1 51 10.8 59 7.92 47 22.7 34 4.18 21 0.00 1 0.02 46 0.00 1 5.54 9 17.2 12 5.00 10
WLIF-Flow [91]24.5 0.84 18 4.97 19 0.34 13 2.03 15 13.3 21 0.76 27 3.64 27 12.0 25 1.41 41 2.23 45 14.4 36 0.55 30 13.1 19 21.6 19 7.54 26 8.23 53 20.9 24 5.39 46 0.00 1 0.00 1 0.00 1 6.94 25 18.0 17 10.4 39
CoT-AMFlow [174]25.8 0.82 11 4.86 11 0.38 24 1.46 3 9.60 4 0.54 12 2.82 13 9.87 14 1.03 31 2.56 63 18.5 73 0.75 65 14.6 34 23.3 32 10.6 58 5.31 13 18.9 16 4.66 27 0.00 1 0.02 46 0.00 1 6.40 15 17.8 16 9.88 36
NNF-EAC [101]31.8 0.81 8 4.82 10 0.39 31 1.95 14 12.0 12 0.83 30 3.16 16 10.6 16 1.00 28 2.60 66 18.5 73 0.77 67 13.9 26 22.8 27 7.86 30 6.67 30 19.3 17 5.14 43 0.10 78 0.02 46 0.00 1 7.08 30 19.2 25 10.5 40
PRAFlow_RVC [177]32.7 1.20 87 7.06 92 0.55 79 2.87 46 15.5 39 1.25 43 4.68 56 16.0 61 2.63 77 1.04 12 8.82 14 0.13 8 13.3 20 22.1 21 6.20 17 2.14 5 10.6 5 1.68 5 0.00 1 0.02 46 0.00 1 6.57 17 18.4 19 5.73 13
ComponentFusion [94]32.7 0.98 50 5.81 58 0.37 21 1.59 6 10.7 7 0.53 8 2.84 14 9.86 13 0.85 22 1.94 29 13.3 24 0.54 28 15.3 44 24.9 44 10.5 57 6.83 36 26.2 62 5.50 49 0.03 68 0.00 1 0.32 79 6.69 18 18.5 20 9.59 27
TC/T-Flow [77]34.2 0.71 3 4.20 3 0.40 34 2.67 39 15.4 36 0.77 28 3.30 19 11.2 17 0.44 5 2.33 50 15.9 53 0.60 39 14.8 35 23.6 34 8.02 31 3.70 7 15.8 10 2.27 8 0.13 81 0.02 46 1.23 101 7.85 45 21.7 47 10.9 49
AGIF+OF [84]34.4 0.90 28 5.34 30 0.42 43 3.13 57 19.3 60 1.37 49 3.87 32 12.8 28 1.80 54 2.19 42 14.3 34 0.64 45 12.4 13 20.6 13 7.20 23 9.27 72 22.4 31 5.97 68 0.00 1 0.00 1 0.00 1 7.26 33 18.8 22 10.7 46
Layers++ [37]34.5 0.91 32 5.39 34 0.43 48 2.18 22 13.9 27 0.96 32 2.73 11 9.43 11 1.40 40 1.70 23 10.5 19 0.56 31 10.2 5 16.8 4 6.50 20 9.09 67 22.7 34 5.92 63 0.21 91 0.02 46 0.69 83 6.88 21 17.6 15 10.9 49
FC-2Layers-FF [74]35.3 0.87 23 5.16 24 0.42 43 2.70 42 17.8 49 1.20 39 2.59 8 8.73 6 1.39 39 1.88 27 13.3 24 0.50 23 11.1 8 18.0 7 6.07 16 9.16 70 21.3 26 5.89 61 0.04 72 0.02 46 0.22 76 7.48 37 19.4 28 11.1 54
IIOF-NLDP [129]36.2 1.01 58 5.97 63 0.24 4 2.82 45 17.3 46 0.66 21 4.36 49 14.3 46 0.43 4 0.99 9 7.36 10 0.24 13 15.0 38 24.3 38 6.98 21 9.70 83 24.0 49 6.32 83 0.01 59 0.02 46 0.00 1 7.22 32 19.9 35 7.14 16
LME [70]37.1 0.95 45 5.67 51 0.38 24 1.45 2 9.68 5 0.43 3 5.19 64 13.3 36 6.57 111 2.44 56 18.3 71 0.68 52 15.2 42 24.4 39 10.2 54 6.17 26 21.9 27 5.18 44 0.00 1 0.02 46 0.00 1 7.05 27 19.3 26 10.2 37
ALD-Flow [66]38.7 0.79 6 4.72 8 0.38 24 2.44 35 13.5 23 0.80 29 4.33 47 14.7 51 0.88 24 2.92 82 19.4 80 0.82 71 17.5 55 28.1 55 10.0 52 5.61 18 24.7 54 3.10 11 0.00 1 0.00 1 0.00 1 9.09 62 26.3 67 11.9 71
nLayers [57]39.8 0.88 24 5.25 26 0.44 52 2.79 44 15.6 41 1.47 55 4.34 48 14.4 47 2.33 70 1.54 19 11.6 20 0.52 26 10.4 6 17.1 6 5.51 14 8.89 60 19.3 17 5.79 59 0.31 101 0.00 1 1.16 99 7.27 34 19.3 26 11.3 60
MLDP_OF [87]40.3 0.94 42 5.51 45 0.36 19 1.74 8 11.7 11 0.44 5 4.05 38 13.1 33 0.50 8 1.48 17 12.3 22 0.29 16 15.4 45 24.7 43 9.15 41 5.54 17 18.2 14 3.11 12 1.54 139 0.05 122 9.31 147 8.33 52 21.4 45 9.39 26
3DFlow [133]40.5 0.92 38 5.49 42 0.34 13 2.26 24 15.2 34 0.54 12 3.57 24 12.4 26 0.47 6 0.31 1 3.40 1 0.01 5 13.6 23 22.2 24 7.25 24 12.2 123 27.4 72 7.12 110 2.77 151 0.02 46 10.0 148 5.36 7 15.8 8 4.88 9
HAST [107]40.9 0.92 38 5.41 36 0.35 16 3.21 60 13.6 25 1.99 84 2.45 5 8.47 5 0.29 2 2.24 46 14.5 39 0.40 19 11.7 10 19.4 11 3.63 6 11.0 109 24.2 50 6.87 103 2.75 150 0.00 1 11.6 152 4.05 4 13.1 3 4.43 7
PH-Flow [99]41.7 0.93 40 5.49 42 0.42 43 2.87 46 17.6 48 1.33 48 2.99 15 10.1 15 1.76 53 2.27 47 14.6 41 0.68 52 12.5 14 20.8 15 6.28 18 7.79 44 20.9 24 5.39 46 0.39 109 0.02 46 1.63 112 6.88 21 19.0 24 10.3 38
RNLOD-Flow [119]42.7 0.79 6 4.69 6 0.34 13 2.67 39 17.2 45 1.09 36 4.46 53 14.5 49 1.53 45 2.01 32 14.3 34 0.60 39 14.2 31 23.1 30 8.72 39 8.21 51 19.9 20 5.90 62 0.35 105 0.03 118 1.48 110 6.51 16 17.2 12 9.80 34
ProbFlowFields [126]43.9 1.16 81 6.86 88 0.85 110 2.32 26 14.6 30 1.45 53 4.28 45 14.9 53 2.43 73 1.56 20 9.89 16 0.50 23 18.1 61 29.1 62 11.5 63 4.44 9 20.6 21 4.20 22 0.00 1 0.02 46 0.00 1 8.97 59 25.7 60 9.75 30
IROF++ [58]44.2 0.96 47 5.70 56 0.44 52 3.00 53 19.4 61 1.37 49 3.90 34 12.8 28 1.96 59 2.36 53 15.8 52 0.69 57 14.1 29 23.0 28 8.22 36 9.14 69 25.0 55 6.07 74 0.00 1 0.02 46 0.00 1 7.35 35 20.3 38 10.8 47
SVFilterOh [109]45.7 1.07 67 6.27 72 0.44 52 2.07 19 13.1 19 0.72 23 3.24 17 11.2 17 1.05 32 1.99 31 13.8 28 0.56 31 12.6 16 21.1 16 3.80 7 10.5 99 22.4 31 5.97 68 2.31 145 0.39 142 6.95 140 4.87 6 14.8 5 6.01 14
UnDAF [187]45.8 1.31 99 7.53 101 0.31 6 1.92 13 13.0 16 0.49 6 3.82 29 13.3 36 0.99 27 3.04 87 23.5 109 0.73 64 17.7 57 29.0 60 9.21 42 6.67 30 27.6 75 4.70 32 0.00 1 0.02 46 0.00 1 9.06 61 27.8 72 9.60 28
TC-Flow [46]45.8 0.75 4 4.45 4 0.38 24 2.04 17 12.6 15 0.70 22 4.23 44 14.4 47 0.77 16 2.56 63 17.5 66 0.63 43 17.1 53 27.8 54 9.45 45 5.73 20 25.6 59 3.12 13 0.22 93 0.02 46 2.41 123 10.1 70 25.9 62 15.4 97
Efficient-NL [60]45.9 0.93 40 5.47 41 0.39 31 2.76 43 18.0 53 1.11 37 4.12 42 13.3 36 1.15 34 2.15 39 14.1 31 0.66 47 13.0 18 21.3 18 7.16 22 10.6 101 23.4 42 6.41 90 0.26 96 0.02 46 1.13 97 7.35 35 17.4 14 10.9 49
Classic+CPF [82]47.0 0.89 26 5.26 27 0.41 39 3.03 54 19.4 61 1.27 45 4.14 43 13.6 40 1.64 50 2.12 38 14.4 36 0.64 45 13.6 23 22.2 24 7.82 28 9.85 88 22.6 33 6.18 77 0.36 106 0.02 46 1.50 111 7.07 28 18.5 20 10.5 40
FESL [72]47.0 0.83 16 4.91 17 0.36 19 3.90 91 21.6 84 1.75 71 4.06 39 13.4 39 1.61 47 2.02 34 14.1 31 0.56 31 13.3 20 21.7 20 8.08 33 9.19 71 22.0 28 6.25 80 0.34 104 0.02 46 1.16 99 7.51 38 18.3 18 11.0 53
HCFN [157]47.6 0.82 11 4.88 15 0.38 24 1.89 12 12.1 13 0.94 31 3.35 21 11.8 23 1.00 28 1.83 26 14.6 41 0.52 26 15.0 38 24.4 39 8.25 38 6.71 32 23.3 40 3.52 18 2.50 148 0.30 136 10.4 150 9.77 68 26.2 66 15.5 98
WRT [146]47.7 1.11 73 6.61 80 0.35 16 3.70 83 21.1 78 1.28 46 7.27 93 19.2 71 0.68 14 0.35 2 3.88 2 0.01 5 13.5 22 22.1 21 7.40 25 11.2 115 22.9 37 6.52 91 0.03 68 0.02 46 0.25 77 7.71 40 18.8 22 7.93 18
FMOF [92]48.5 0.83 16 4.92 18 0.43 48 3.35 68 20.0 67 1.57 64 3.37 22 11.4 20 1.46 43 1.98 30 13.8 28 0.56 31 14.2 31 23.2 31 8.08 33 9.98 93 22.7 34 6.19 78 0.42 112 0.02 46 1.87 117 8.11 51 21.0 42 10.5 40
PBOFVI [189]48.5 1.12 76 6.59 79 0.37 21 2.67 39 17.8 49 0.73 24 4.91 61 14.9 53 1.02 30 1.33 16 10.3 18 0.32 18 16.3 49 25.8 48 11.6 64 9.73 84 22.2 29 5.52 50 0.06 75 0.13 126 0.20 72 7.01 26 19.8 33 9.12 23
VCN_RVC [178]49.0 1.05 63 6.21 69 0.51 66 3.04 55 19.4 61 1.50 57 4.69 57 16.1 62 2.91 80 2.49 61 16.9 61 0.68 52 17.2 54 28.7 58 7.85 29 7.05 39 23.4 42 3.46 17 0.00 1 0.02 46 0.00 1 8.36 54 26.1 65 9.33 25
HBM-GC [103]49.5 1.24 91 7.38 94 0.52 69 2.50 37 15.5 39 1.40 51 4.06 39 14.1 44 1.32 37 1.77 24 13.2 23 0.61 41 13.7 25 22.1 21 8.06 32 8.98 64 16.5 11 4.42 23 1.30 136 0.02 46 3.28 130 7.20 31 19.8 33 10.8 47
PMF [73]49.8 1.08 68 6.23 70 0.35 16 2.33 27 14.8 31 0.60 15 3.87 32 13.6 40 0.62 13 2.29 48 14.4 36 0.44 21 14.0 28 23.3 32 3.86 9 9.55 76 28.3 84 6.63 96 0.89 130 0.79 152 3.74 134 5.66 10 15.8 8 8.92 20
ProFlow_ROB [142]50.0 1.18 83 7.01 91 0.57 86 2.87 46 17.8 49 1.32 47 5.44 65 18.3 69 1.71 52 2.83 77 17.9 69 0.70 59 18.5 62 30.3 71 9.32 43 6.29 27 25.3 58 3.36 15 0.00 1 0.00 1 0.00 1 7.96 46 24.6 59 8.97 22
JOF [136]50.3 0.98 50 5.69 53 0.45 57 3.43 72 20.4 71 1.74 70 3.59 26 11.7 22 2.20 64 2.30 49 15.3 49 0.67 50 12.5 14 20.7 14 6.41 19 8.98 64 22.2 29 5.76 56 1.88 142 0.00 1 4.61 135 7.07 28 19.4 28 10.6 44
Sparse-NonSparse [56]50.3 0.88 24 5.21 25 0.40 34 3.16 59 19.8 66 1.53 61 3.90 34 12.9 30 2.00 61 2.18 41 15.2 48 0.66 47 15.6 46 25.4 47 10.1 53 9.38 74 23.7 47 5.97 68 0.31 101 0.00 1 1.28 102 7.74 41 20.9 40 11.2 58
Ramp [62]50.5 0.90 28 5.36 31 0.41 39 3.14 58 20.0 67 1.52 58 3.86 31 12.9 30 1.93 57 2.01 32 14.5 39 0.59 37 15.1 41 24.4 39 9.67 49 9.44 75 22.9 37 5.95 65 0.29 99 0.02 46 1.38 106 7.83 44 20.9 40 11.5 63
CombBMOF [111]51.2 0.91 32 5.38 32 0.33 11 2.30 25 13.4 22 0.64 19 3.33 20 11.5 21 0.78 17 2.08 36 15.3 49 0.77 67 13.9 26 22.3 26 8.24 37 13.0 134 26.2 62 11.4 141 0.56 117 0.02 46 0.86 90 8.93 58 21.1 43 15.6 99
NL-TV-NCC [25]52.1 0.96 47 5.68 52 0.22 2 2.93 50 18.4 55 0.59 14 4.37 51 14.6 50 0.47 6 1.63 22 14.6 41 0.17 10 18.6 64 29.8 65 9.76 51 11.8 122 31.2 110 7.70 121 0.12 79 0.00 1 0.30 78 9.40 65 26.0 64 9.75 30
OFH [38]52.7 0.81 8 4.70 7 0.31 6 2.96 52 17.3 46 1.20 39 6.37 78 19.7 75 1.51 44 2.92 82 20.6 89 0.91 73 20.7 84 32.4 87 14.2 77 6.39 28 31.5 112 3.74 19 0.00 1 0.00 1 0.00 1 11.0 81 33.0 99 12.8 76
LSM [39]53.2 0.86 22 5.13 23 0.40 34 3.22 61 20.3 70 1.54 63 4.08 41 13.6 40 1.93 57 2.09 37 14.9 46 0.63 43 15.6 46 25.3 46 10.2 54 9.58 78 24.6 51 5.95 65 0.30 100 0.02 46 1.43 107 7.97 47 21.7 47 11.1 54
PWC-Net_RVC [143]54.1 1.18 83 6.99 90 0.63 96 3.25 63 20.9 75 1.41 52 6.19 74 21.0 88 3.34 83 1.51 18 9.97 17 0.54 28 19.2 72 31.5 81 9.61 47 8.57 57 28.0 78 4.96 40 0.00 1 0.00 1 0.02 65 6.91 24 22.1 50 6.52 15
Sparse Occlusion [54]54.8 0.90 28 5.06 22 0.46 59 2.35 29 14.9 33 1.01 33 4.83 58 15.7 59 1.09 33 2.38 54 17.2 64 0.66 47 16.7 52 26.9 52 8.75 40 7.98 49 24.6 51 5.42 48 0.60 121 0.61 148 0.84 87 8.41 56 22.7 52 10.5 40
MDP-Flow [26]54.8 0.84 18 5.01 20 0.47 60 2.37 30 13.0 16 1.76 72 4.04 37 14.0 43 2.72 79 2.70 70 21.0 90 0.98 78 18.0 59 28.5 57 13.1 73 8.58 58 26.6 66 5.71 54 0.00 1 0.02 46 0.00 1 12.4 96 31.9 89 16.2 103
Classic+NL [31]54.9 0.91 32 5.38 32 0.45 57 3.22 61 20.4 71 1.49 56 3.97 36 13.1 33 1.97 60 2.33 50 15.0 47 0.68 52 14.9 36 24.0 36 10.2 54 9.83 85 23.9 48 6.24 79 0.33 103 0.02 46 1.28 102 7.80 43 21.2 44 11.1 54
EPPM w/o HM [86]54.9 1.16 81 5.61 48 0.33 11 2.33 27 15.4 36 0.60 15 4.28 45 14.7 51 0.32 3 2.20 43 14.7 44 0.59 37 14.3 33 23.6 34 5.47 13 12.2 123 29.9 99 7.04 106 2.28 144 0.03 118 6.80 139 6.72 19 19.4 28 8.96 21
MCPFlow_RVC [197]55.5 1.65 118 8.92 122 0.70 101 6.02 117 25.7 111 3.57 115 8.48 106 22.3 95 10.8 119 0.77 8 7.21 8 0.26 14 18.0 59 29.2 64 7.65 27 3.89 8 14.4 8 1.75 6 0.00 1 0.02 46 0.00 1 6.90 23 21.4 45 5.44 11
OAR-Flow [123]57.4 1.00 54 5.81 58 0.55 79 3.94 93 18.5 56 1.99 84 6.44 80 20.5 79 2.66 78 2.84 79 18.5 73 0.71 62 18.9 68 30.1 69 11.2 60 5.95 24 26.2 62 3.42 16 0.00 1 0.00 1 0.00 1 9.00 60 26.4 68 12.2 73
CostFilter [40]58.8 1.14 77 6.62 81 0.40 34 2.38 31 14.8 31 0.53 8 3.58 25 12.5 27 0.84 20 2.62 67 17.3 65 0.51 25 14.9 36 24.9 44 4.14 11 9.99 94 29.2 94 6.06 73 1.38 137 0.81 153 6.01 138 8.00 48 23.2 56 9.84 35
Complementary OF [21]58.8 0.91 32 5.39 34 0.43 48 2.42 34 15.2 34 0.74 25 4.36 49 15.5 57 1.16 35 2.63 68 19.5 81 0.76 66 22.5 104 33.0 93 20.1 109 9.92 91 28.5 88 4.80 36 0.00 1 0.00 1 0.00 1 12.6 99 35.6 118 16.9 107
S2D-Matching [83]61.7 1.09 70 6.39 76 0.51 66 3.35 68 20.9 75 1.52 58 5.55 68 17.8 67 2.21 65 1.91 28 13.6 27 0.56 31 15.2 42 24.5 42 9.72 50 10.1 96 23.6 45 6.34 85 0.52 114 0.02 46 2.09 121 7.62 39 20.0 36 11.6 66
IROF-TV [53]61.8 1.10 72 6.24 71 0.57 86 3.29 67 21.5 82 1.72 69 4.40 52 14.2 45 1.87 56 3.04 87 21.7 96 1.11 82 16.2 48 26.0 49 11.3 62 9.60 80 32.4 118 5.72 55 0.00 1 0.02 46 0.00 1 8.00 48 22.4 51 11.2 58
COFM [59]62.1 1.15 78 6.80 86 0.58 90 2.62 38 15.8 43 1.25 43 5.68 70 18.2 68 2.12 62 2.20 43 13.5 26 0.58 36 19.6 75 31.0 78 15.7 92 9.91 90 23.3 40 6.03 72 0.81 127 0.00 1 1.43 107 7.76 42 20.7 39 10.6 44
SimpleFlow [49]62.7 0.94 42 5.57 47 0.44 52 3.52 74 21.7 85 1.79 75 5.82 71 17.6 66 2.36 71 2.55 62 16.5 57 0.81 70 16.3 49 26.0 49 11.8 65 10.3 98 23.1 39 6.33 84 0.24 94 0.00 1 0.81 86 8.33 52 22.7 52 11.5 63
2DHMM-SAS [90]63.1 0.91 32 5.42 37 0.41 39 3.67 81 21.9 87 1.52 58 5.62 69 16.1 62 2.28 69 2.44 56 15.9 53 0.72 63 15.0 38 24.2 37 9.48 46 11.1 112 25.1 57 6.36 87 0.38 108 0.02 46 1.67 114 8.04 50 21.7 47 11.7 67
ACK-Prior [27]63.8 0.82 11 4.87 13 0.32 10 2.12 21 13.7 26 0.43 3 3.68 28 12.9 30 0.92 26 1.77 24 14.0 30 0.19 12 19.5 74 28.2 56 16.7 98 12.3 127 29.1 93 7.52 118 2.44 147 0.30 136 8.47 146 13.9 108 30.2 82 18.0 112
ROF-ND [105]65.4 1.27 95 6.15 68 0.38 24 4.71 104 18.9 58 1.07 35 4.89 59 15.6 58 1.21 36 0.65 6 6.22 6 0.29 16 19.7 76 30.5 73 14.5 79 11.5 120 26.5 65 6.25 80 0.39 109 0.02 46 0.84 87 12.3 95 31.5 87 13.8 87
TV-L1-MCT [64]66.4 0.90 28 5.30 29 0.41 39 3.73 85 22.1 88 1.79 75 4.61 55 15.3 55 1.63 49 2.16 40 14.7 44 0.67 50 17.6 56 27.1 53 15.2 88 11.0 109 25.0 55 6.58 95 0.36 106 0.02 46 2.46 125 9.73 67 23.0 54 16.2 103
S2F-IF [121]68.5 1.28 97 7.44 98 0.84 109 3.48 73 22.4 91 1.86 79 5.52 66 19.0 70 3.05 82 2.96 84 16.9 61 1.21 87 21.3 92 34.1 101 14.5 79 5.45 14 25.6 59 4.62 25 0.00 1 0.00 1 0.00 1 12.0 91 32.3 94 14.7 90
RFlow [88]68.6 0.91 32 5.43 38 0.47 60 2.46 36 15.6 41 1.13 38 6.42 79 19.3 74 1.66 51 2.77 73 21.4 94 1.16 85 20.7 84 31.7 83 18.0 104 9.69 82 30.4 103 6.14 75 0.01 59 0.02 46 0.15 69 10.9 80 30.0 81 13.1 79
Occlusion-TV-L1 [63]68.8 0.98 50 5.50 44 0.48 62 3.25 63 19.5 64 1.82 78 7.36 95 21.2 89 2.44 74 2.73 71 20.4 87 0.93 76 20.5 81 32.1 84 15.5 90 8.22 52 28.1 80 6.69 98 0.00 1 0.00 1 0.00 1 13.1 103 33.5 106 15.9 102
DeepFlow2 [106]69.7 1.04 62 5.76 57 0.54 77 3.86 89 19.7 65 2.02 87 6.79 83 20.5 79 3.55 89 3.64 102 22.5 101 1.44 95 18.8 66 30.1 69 12.0 67 7.01 38 27.7 76 4.65 26 0.00 1 0.02 46 0.00 1 12.6 99 32.0 91 16.9 107
DPOF [18]70.5 1.11 73 6.56 78 0.53 72 4.51 102 21.0 77 2.42 99 3.25 18 11.3 19 0.84 20 2.03 35 15.3 49 0.70 59 17.8 58 28.8 59 9.36 44 11.4 119 26.9 67 6.26 82 4.21 155 0.02 46 10.5 151 10.2 71 26.7 69 11.8 69
FlowFields+ [128]71.6 1.31 99 7.52 100 0.92 119 3.61 77 23.0 95 1.98 83 6.08 72 20.6 81 3.39 86 2.82 76 16.4 56 1.23 88 21.4 95 34.3 104 14.1 75 5.45 14 27.5 74 4.68 31 0.00 1 0.02 46 0.00 1 11.3 83 33.1 102 11.4 61
TF+OM [98]73.3 1.11 73 6.49 77 0.69 100 2.94 51 16.8 44 1.78 73 7.92 100 20.7 83 9.65 116 2.85 80 20.5 88 1.05 81 22.0 101 32.2 85 20.3 110 8.74 59 28.3 84 4.67 29 0.00 1 0.02 46 0.00 1 12.1 93 30.5 84 15.8 101
FlowFields [108]74.3 1.32 101 7.63 103 0.93 121 3.61 77 22.9 93 2.00 86 6.11 73 20.6 81 3.58 90 2.85 80 16.6 59 1.24 89 21.9 100 35.0 114 15.1 86 5.70 19 28.0 78 4.72 33 0.00 1 0.02 46 0.00 1 11.7 86 33.4 104 11.5 63
CRTflow [81]74.7 1.02 61 5.69 53 0.58 90 3.12 56 18.1 54 1.46 54 6.89 86 20.9 85 2.40 72 3.38 96 22.2 98 1.42 94 19.7 76 31.3 80 12.3 68 11.0 109 35.9 135 10.1 135 0.00 1 0.00 1 0.00 1 12.0 91 33.6 107 14.7 90
LiteFlowNet [138]75.5 1.49 106 8.56 112 0.62 95 4.27 97 23.7 103 1.92 81 6.82 84 22.9 100 3.44 87 2.47 59 16.3 55 0.62 42 25.7 122 39.8 133 17.5 101 9.55 76 30.2 101 4.00 20 0.00 1 0.00 1 0.00 1 10.7 77 30.5 84 12.2 73
AggregFlow [95]75.9 1.68 120 9.22 124 0.86 112 4.76 105 25.3 109 2.56 102 7.33 94 22.6 98 5.07 107 2.64 69 16.5 57 0.69 57 19.1 71 30.7 75 11.2 60 5.11 11 17.3 12 3.29 14 0.14 83 0.02 46 0.96 93 9.35 64 25.7 60 13.1 79
Steered-L1 [116]76.4 0.63 1 3.72 1 0.42 43 1.53 5 10.4 6 0.75 26 3.84 30 13.2 35 1.32 37 2.80 74 21.1 92 0.98 78 21.2 91 31.2 79 20.3 110 10.7 105 29.3 96 7.45 117 4.27 156 0.34 139 19.6 158 16.5 122 33.3 103 24.6 129
TCOF [69]77.4 1.00 54 5.63 50 0.59 93 3.53 75 21.5 82 1.69 68 7.64 98 22.0 93 3.79 93 2.80 74 19.9 85 0.77 67 21.1 89 32.7 89 13.9 74 7.79 44 20.7 22 5.77 57 0.92 131 0.03 118 3.23 129 8.40 55 23.2 56 11.4 61
ComplOF-FED-GPU [35]77.8 0.85 20 5.04 21 0.42 43 3.90 91 21.4 80 1.78 73 4.90 60 16.8 64 1.41 41 3.18 91 21.1 92 1.03 80 21.6 98 33.8 99 15.4 89 10.8 106 34.7 131 5.93 64 0.12 79 0.02 46 1.43 107 11.9 88 34.2 110 15.3 95
Adaptive [20]79.3 1.05 63 6.01 64 0.48 62 3.27 65 20.1 69 1.79 75 7.11 90 20.1 76 1.62 48 3.29 94 22.4 99 1.15 84 18.8 66 29.8 65 12.6 70 10.6 101 28.4 87 6.72 101 0.57 120 0.71 151 0.96 93 8.64 57 23.1 55 10.9 49
SRR-TVOF-NL [89]80.8 1.15 78 6.13 67 0.60 94 5.04 107 23.3 98 2.68 104 8.17 102 22.9 100 4.22 104 2.76 72 16.9 61 0.68 52 19.8 78 29.0 60 17.7 103 8.07 50 27.0 69 6.17 76 0.16 85 0.02 46 0.86 90 11.8 87 25.9 62 15.3 95
SegFlow [156]81.8 1.53 110 8.74 118 0.98 124 3.72 84 23.2 97 2.06 89 6.24 76 20.9 85 3.89 96 3.83 109 22.9 105 1.68 106 21.5 96 34.5 110 15.1 86 7.54 41 28.3 84 5.95 65 0.00 1 0.02 46 0.00 1 10.6 75 31.3 86 12.1 72
DeepFlow [85]81.8 1.19 85 6.04 66 0.57 86 4.41 98 21.3 79 2.41 98 8.35 105 22.9 100 6.63 112 4.03 115 24.5 114 1.69 108 19.0 70 30.9 76 11.8 65 7.29 40 29.5 98 4.88 38 0.00 1 0.02 46 0.00 1 15.7 121 35.1 116 23.4 125
TV-L1-improved [17]82.2 0.94 42 5.45 39 0.52 69 2.91 49 17.8 49 1.58 65 7.00 88 20.2 78 2.24 67 3.00 85 21.5 95 1.16 85 20.6 82 32.3 86 15.0 84 12.2 123 34.2 127 7.87 122 0.19 89 0.30 136 0.49 81 10.7 77 29.7 80 12.8 76
PGM-C [118]82.6 1.52 109 8.68 115 0.99 128 3.66 79 23.0 95 2.03 88 6.30 77 21.2 89 3.90 97 3.82 108 22.9 105 1.68 106 21.3 92 34.3 104 14.1 75 6.89 37 28.8 90 5.60 52 0.00 1 0.02 46 0.00 1 11.9 88 34.3 111 14.2 89
Aniso. Huber-L1 [22]85.1 1.06 65 5.69 53 0.65 97 5.24 109 25.4 110 3.29 110 8.19 103 21.4 92 4.09 102 3.10 89 21.0 90 0.97 77 18.5 62 29.1 62 12.6 70 9.08 66 27.0 69 5.56 51 0.68 123 0.08 125 2.93 128 9.25 63 24.1 58 11.8 69
CPM-Flow [114]85.4 1.53 110 8.72 117 0.98 124 3.74 86 23.5 99 2.08 91 6.22 75 20.9 85 3.88 95 3.78 106 22.5 101 1.64 104 21.3 92 34.4 106 14.2 77 7.87 46 28.8 90 6.40 89 0.00 1 0.02 46 0.00 1 12.5 98 35.6 118 14.9 93
DMF_ROB [135]85.4 1.06 65 6.27 72 0.56 82 4.09 94 20.7 74 2.13 93 7.51 96 23.3 104 3.01 81 3.67 103 23.0 108 1.51 98 20.9 87 32.8 91 16.6 97 10.2 97 30.1 100 7.29 113 0.00 1 0.02 46 0.00 1 14.3 116 35.7 120 17.3 111
Classic++ [32]86.1 1.00 54 5.92 61 0.56 82 3.28 66 19.2 59 1.87 80 6.88 85 20.7 83 3.38 85 3.41 98 23.6 111 1.30 90 20.8 86 33.2 96 15.0 84 10.0 95 31.8 114 6.69 98 0.66 122 0.02 46 2.59 126 11.3 83 29.5 77 13.5 85
Bartels [41]87.0 1.28 97 7.59 102 0.50 64 2.39 33 15.4 36 1.04 34 5.52 66 19.2 71 2.54 76 2.83 77 19.9 85 1.30 90 22.7 107 34.1 101 20.4 112 9.92 91 30.5 105 6.93 104 1.88 142 0.02 46 12.3 153 12.7 101 31.9 89 16.4 105
EpicFlow [100]88.2 1.51 107 8.63 114 0.98 124 3.76 87 23.5 99 2.11 92 7.14 91 23.6 106 3.97 99 3.79 107 22.6 103 1.64 104 21.5 96 34.4 106 14.8 82 8.97 63 29.2 94 6.53 92 0.00 1 0.02 46 0.00 1 12.4 96 34.5 112 15.2 94
CBF [12]88.2 0.85 20 4.89 16 0.43 48 4.99 106 22.3 90 4.63 119 6.60 81 19.2 71 4.08 101 3.61 101 24.5 114 1.49 97 20.0 79 30.9 76 16.2 95 9.67 81 27.4 72 5.64 53 2.65 149 0.37 140 6.97 141 11.5 85 28.4 75 16.9 107
C-RAFT_RVC [181]88.2 2.88 141 14.1 142 1.36 140 10.0 130 35.2 133 7.14 129 11.8 121 30.0 126 13.3 123 2.46 58 14.2 33 1.46 96 28.3 140 42.8 143 20.6 115 5.87 23 20.8 23 4.67 29 0.01 59 0.02 46 0.00 1 10.3 72 27.3 70 9.29 24
FF++_ROB [141]88.9 1.67 119 9.54 127 0.97 122 3.68 82 22.9 93 2.07 90 6.93 87 22.8 99 3.99 100 3.03 86 17.5 66 1.31 92 22.1 102 35.6 119 14.8 82 6.77 34 25.9 61 4.87 37 0.17 86 0.22 129 0.79 85 10.5 73 30.3 83 13.1 79
LocallyOriented [52]89.6 1.78 127 9.64 129 0.77 106 6.11 119 28.2 119 3.79 116 10.9 117 28.0 120 5.52 109 3.28 93 19.5 81 1.55 99 22.8 109 33.9 100 17.6 102 9.84 87 24.6 51 6.63 96 0.00 1 0.00 1 0.00 1 11.9 88 29.6 79 15.7 100
CLG-TV [48]91.1 1.01 58 5.46 40 0.50 64 4.16 96 23.5 99 2.40 97 7.52 97 21.2 89 2.51 75 3.33 95 22.8 104 1.14 83 20.9 87 32.4 87 15.6 91 8.94 62 31.7 113 6.35 86 1.27 135 1.18 156 3.55 132 11.1 82 28.2 74 13.5 85
CVENG22+RIC [199]92.6 1.64 117 9.35 126 1.00 129 4.42 99 26.3 113 2.37 95 8.05 101 25.4 109 3.84 94 3.96 112 23.8 112 1.82 110 24.8 116 37.5 125 21.2 121 8.91 61 30.3 102 6.70 100 0.00 1 0.02 46 0.00 1 10.6 75 32.0 91 11.7 67
TriangleFlow [30]92.7 1.19 85 6.73 85 0.53 72 3.88 90 21.8 86 1.64 67 6.61 82 20.1 76 1.59 46 2.35 52 19.3 79 0.89 72 25.6 121 37.3 124 23.5 128 13.4 136 30.5 105 8.48 130 0.81 127 0.17 128 1.33 105 10.7 77 28.1 73 13.1 79
Fusion [6]93.2 1.15 78 6.83 87 0.71 103 2.10 20 14.5 29 1.23 42 4.58 54 15.4 56 3.60 91 3.73 105 27.2 126 2.38 118 23.9 113 33.7 98 26.4 133 8.36 54 27.3 71 7.11 109 1.00 132 0.64 150 2.66 127 14.5 117 34.0 109 18.7 114
Rannacher [23]93.4 1.09 70 6.27 72 0.54 77 3.77 88 22.1 88 2.27 94 7.89 99 22.4 96 3.34 83 3.67 103 23.5 109 1.61 101 21.1 89 33.1 94 15.8 93 12.9 132 35.4 134 7.98 123 0.43 113 0.02 46 1.63 112 10.5 73 29.5 77 12.8 76
SIOF [67]93.7 1.24 91 6.63 82 0.51 66 5.26 110 26.2 112 3.22 109 11.5 118 26.1 111 12.3 121 4.49 119 27.4 129 2.29 116 22.8 109 33.3 97 23.4 127 8.56 56 28.8 90 7.15 111 0.00 1 0.02 46 0.00 1 13.6 107 32.1 93 23.6 127
ResPWCR_ROB [140]95.1 1.22 88 7.22 93 0.68 99 5.04 107 24.6 106 2.77 106 9.17 109 26.7 114 6.63 112 3.22 92 22.4 99 1.31 92 22.7 107 35.5 118 18.0 104 10.9 107 32.3 116 7.99 124 0.00 1 0.02 46 0.00 1 14.2 113 37.2 123 16.5 106
F-TV-L1 [15]95.8 1.22 88 6.63 82 0.53 72 5.86 115 24.8 108 3.51 114 9.25 110 23.4 105 3.44 87 3.91 110 24.9 116 1.61 101 20.3 80 31.5 81 16.2 95 11.3 117 30.9 108 7.40 116 0.15 84 0.47 145 0.17 70 9.88 69 27.6 71 11.1 54
Local-TV-L1 [65]96.7 1.57 112 7.45 99 0.67 98 7.93 123 28.0 117 5.97 125 12.9 125 26.6 113 12.2 120 6.04 136 31.1 135 3.55 135 18.7 65 29.9 68 12.9 72 9.33 73 28.1 80 5.97 68 0.00 1 0.02 46 0.00 1 21.0 139 37.7 125 37.5 144
BriefMatch [122]97.6 0.96 47 5.52 46 0.53 72 3.55 76 18.6 57 1.97 82 4.95 62 16.9 65 1.82 55 2.57 65 19.7 83 0.92 75 21.8 99 32.7 89 20.8 117 16.2 145 33.7 125 13.5 147 3.95 154 0.97 155 15.8 154 17.3 127 34.7 114 25.4 131
p-harmonic [29]97.7 1.08 68 6.28 75 0.55 79 3.66 79 20.5 73 2.48 101 8.22 104 23.0 103 3.92 98 5.04 124 28.4 132 3.51 133 24.8 116 34.1 101 30.1 138 7.78 43 32.3 116 6.54 93 0.19 89 0.44 144 0.00 1 14.2 113 33.0 99 21.8 122
OFRF [132]99.5 1.68 120 8.84 120 0.73 104 12.5 138 28.4 121 11.9 140 12.8 124 24.7 107 13.6 124 4.30 117 18.9 77 2.52 119 18.9 68 30.4 72 9.65 48 11.5 120 27.9 77 5.03 42 0.13 81 0.00 1 0.71 84 20.9 138 32.7 98 40.3 147
ContinualFlow_ROB [148]100.1 2.51 136 13.8 141 1.37 141 9.26 128 34.0 131 7.16 130 13.6 127 32.9 130 18.7 129 3.59 100 18.0 70 2.00 112 27.7 137 44.1 146 16.1 94 11.1 112 34.2 127 7.02 105 0.00 1 0.02 46 0.00 1 9.54 66 28.7 76 7.73 17
TriFlow [93]100.4 1.51 107 8.71 116 0.78 107 4.56 103 22.8 92 3.37 112 12.5 123 28.2 121 17.8 128 2.41 55 18.3 71 0.91 73 24.8 116 34.4 106 25.7 131 5.97 25 23.5 44 4.74 34 19.3 162 0.27 134 59.0 162 13.2 104 32.5 96 14.1 88
Dynamic MRF [7]101.4 1.26 94 7.42 96 0.57 86 3.39 70 21.4 80 1.58 65 7.00 88 22.5 97 2.22 66 3.40 97 24.1 113 1.69 108 25.9 127 37.6 126 24.8 130 14.4 140 41.5 146 9.85 134 0.09 76 0.00 1 0.96 93 19.2 134 39.4 134 25.5 132
LFNet_ROB [145]102.8 1.98 132 11.1 134 0.90 114 5.93 116 28.1 118 3.47 113 10.5 115 32.4 129 6.86 114 3.11 90 19.2 78 1.60 100 30.0 145 44.1 146 28.0 136 9.85 88 35.2 132 7.05 108 0.00 1 0.00 1 0.00 1 14.2 113 39.1 132 17.0 110
DF-Auto [113]103.2 1.84 128 8.87 121 0.90 114 8.40 125 30.1 124 6.82 126 13.3 126 27.9 119 19.6 130 5.29 128 26.6 122 3.01 126 22.2 103 32.9 92 21.0 118 5.80 21 23.6 45 5.02 41 0.18 88 0.61 148 0.00 1 14.8 118 32.4 95 19.9 117
CompactFlow_ROB [155]104.7 3.02 142 15.6 146 1.51 145 8.12 124 31.9 126 5.83 124 16.4 133 35.0 136 28.8 148 3.55 99 22.0 97 1.62 103 28.8 141 45.1 149 19.8 108 7.97 48 36.0 136 6.39 88 0.00 1 0.00 1 0.00 1 13.5 106 37.8 126 13.4 84
LSM_FLOW_RVC [182]104.8 2.85 140 15.4 145 1.28 139 9.47 129 38.2 139 6.84 127 16.1 132 42.4 146 16.1 126 5.15 126 26.4 121 2.93 125 27.9 138 43.6 144 19.7 107 6.74 33 35.3 133 5.33 45 0.00 1 0.00 1 0.00 1 13.2 104 39.0 130 13.2 83
Brox et al. [5]104.8 1.22 88 6.66 84 0.70 101 4.15 95 24.3 105 2.39 96 7.21 92 22.1 94 4.18 103 4.91 122 26.3 120 2.65 120 26.2 130 35.7 120 31.4 141 10.5 99 33.4 123 7.34 115 0.01 59 0.13 126 0.00 1 17.1 126 39.1 132 23.0 124
IRR-PWC_RVC [180]106.9 3.82 150 18.7 153 1.84 148 12.6 139 41.2 144 9.42 136 17.5 137 37.9 141 25.9 143 4.45 118 19.8 84 2.85 123 25.3 119 40.3 138 14.5 79 7.62 42 33.5 124 5.78 58 0.00 1 0.02 46 0.00 1 14.9 119 39.0 130 14.8 92
FlowNet2 [120]107.4 2.63 138 12.9 139 1.14 134 17.9 144 43.1 146 16.1 146 17.0 134 32.9 130 25.3 142 3.92 111 16.7 60 2.16 113 25.8 125 40.2 136 17.0 99 10.6 101 28.2 82 8.09 125 0.02 65 0.00 1 0.20 72 12.2 94 34.5 112 9.71 29
EAI-Flow [147]109.7 1.85 129 10.2 131 0.87 113 7.43 121 29.8 123 4.76 121 10.7 116 28.8 122 8.51 115 4.64 120 22.9 105 2.75 122 26.8 133 41.4 139 20.4 112 9.10 68 31.4 111 5.88 60 0.17 86 0.02 46 1.11 96 13.9 108 35.9 121 18.8 115
EPMNet [131]111.6 2.58 137 13.6 140 1.08 131 17.2 143 45.9 148 14.3 142 15.3 131 31.5 128 21.6 133 4.71 121 24.9 116 2.35 117 25.8 125 40.2 136 17.0 99 10.6 101 28.2 82 8.09 125 0.01 59 0.00 1 0.10 67 15.0 120 44.1 143 9.78 33
Second-order prior [8]112.6 1.24 91 6.93 89 0.58 90 5.26 110 27.0 115 3.34 111 9.68 112 26.8 115 5.39 108 4.25 116 26.1 119 2.25 114 22.5 104 34.4 106 19.0 106 12.9 132 41.2 145 8.26 129 1.14 134 0.07 124 2.41 123 12.7 101 32.5 96 18.2 113
SegOF [10]115.1 1.62 115 9.24 125 1.14 134 14.8 141 38.8 140 14.3 142 17.8 138 33.2 132 22.3 135 6.57 137 27.5 130 4.43 138 32.5 149 41.8 142 43.4 153 14.1 139 38.0 140 10.5 137 0.00 1 0.00 1 0.00 1 14.0 110 33.7 108 12.6 75
AugFNG_ROB [139]115.2 3.78 149 18.3 152 1.78 146 15.9 142 39.3 141 15.3 145 17.3 135 37.8 140 24.2 139 3.99 113 18.6 76 2.27 115 29.6 142 45.3 150 21.5 122 11.1 112 34.5 130 7.60 119 0.00 1 0.00 1 0.00 1 18.5 132 46.2 146 18.8 115
StereoOF-V1MT [117]116.4 1.42 104 8.08 108 0.56 82 6.56 120 34.1 132 2.73 105 10.0 114 29.8 124 2.19 63 4.91 122 34.6 140 2.66 121 31.4 148 44.5 148 31.4 141 15.8 144 48.0 152 11.6 142 0.05 73 0.00 1 0.52 82 24.0 142 48.7 150 28.5 135
Shiralkar [42]116.5 1.27 95 7.43 97 0.53 72 5.83 114 30.1 124 2.93 107 9.62 111 26.2 112 3.70 92 5.11 125 30.7 134 3.08 128 25.7 122 39.1 132 22.5 125 17.9 146 45.5 148 9.73 133 1.80 140 0.00 1 8.23 145 18.4 131 44.9 144 19.9 117
WOLF_ROB [144]117.5 2.17 133 11.1 134 0.90 114 11.0 132 38.1 138 6.99 128 14.3 128 33.5 133 10.3 117 5.21 127 25.8 118 3.01 126 26.8 133 38.9 131 26.6 134 12.4 128 30.4 103 7.26 112 0.09 76 0.00 1 0.84 87 16.8 124 39.6 136 24.5 128
FlowNetS+ft+v [110]117.8 1.40 103 7.39 95 0.80 108 5.75 113 23.6 102 4.35 118 11.7 120 27.3 117 12.4 122 5.33 129 27.2 126 3.18 130 25.7 122 35.4 117 26.9 135 8.52 55 32.0 115 6.85 102 2.34 146 1.61 159 10.1 149 14.0 110 34.9 115 20.1 120
CNN-flow-warp+ref [115]119.5 1.63 116 9.14 123 0.91 118 5.41 112 24.0 104 4.66 120 11.6 119 29.8 124 10.7 118 5.59 131 27.1 125 3.43 131 26.6 132 36.0 121 31.5 143 11.3 117 33.1 121 7.62 120 0.03 68 0.25 132 0.07 66 20.4 136 40.5 138 28.3 134
StereoFlow [44]119.6 7.67 159 21.8 156 3.86 155 51.5 162 74.0 163 46.2 159 43.7 163 63.5 163 36.8 154 51.6 161 79.4 163 47.5 160 26.1 128 38.0 128 21.1 119 5.83 22 26.9 67 4.93 39 0.00 1 0.02 46 0.00 1 20.7 137 38.1 128 29.7 136
2bit-BM-tele [96]119.7 1.75 123 9.59 128 0.85 110 4.44 100 24.7 107 2.62 103 8.64 107 25.8 110 4.56 105 3.99 113 27.8 131 1.98 111 22.6 106 33.1 94 20.5 114 14.6 141 32.7 120 10.7 138 5.96 159 1.68 160 21.9 160 14.1 112 33.4 104 19.9 117
Learning Flow [11]120.1 1.35 102 7.83 105 0.56 82 4.48 101 26.8 114 2.43 100 9.85 113 27.1 116 5.06 106 6.65 138 33.5 138 4.13 136 29.9 144 40.0 135 34.1 147 12.8 130 38.5 142 8.86 132 0.28 98 0.29 135 1.13 97 17.0 125 37.6 124 22.8 123
SPSA-learn [13]120.5 1.77 125 7.72 104 0.90 114 11.0 132 33.2 128 9.40 135 17.3 135 34.2 135 22.7 137 11.0 140 32.2 136 10.9 140 26.1 128 34.9 113 31.8 145 12.8 130 34.2 127 11.9 143 0.00 1 0.03 118 0.00 1 25.5 146 39.4 134 39.6 146
LDOF [28]120.6 1.59 114 8.06 106 0.97 122 6.08 118 27.9 116 3.79 116 8.98 108 25.2 108 6.05 110 5.90 134 33.2 137 3.14 129 23.5 111 34.5 110 22.7 126 9.83 85 34.0 126 7.30 114 0.86 129 1.28 157 3.67 133 16.7 123 39.7 137 23.5 126
Ad-TV-NDC [36]121.0 3.59 146 8.26 109 6.67 159 21.3 148 38.0 136 22.4 151 19.7 141 33.6 134 21.8 134 13.5 143 33.9 139 15.0 144 19.4 73 30.6 74 12.5 69 9.58 78 28.6 89 6.54 93 0.21 91 0.37 140 0.17 70 28.1 148 43.2 141 47.4 154
BlockOverlap [61]123.0 1.73 122 8.32 110 1.07 130 8.43 126 28.3 120 7.39 131 14.3 128 29.4 123 16.3 127 6.01 135 26.7 124 4.24 137 20.6 82 29.8 65 20.6 115 12.4 128 29.4 97 8.20 128 3.91 153 0.92 154 16.5 156 19.1 133 31.7 88 36.0 140
Filter Flow [19]124.1 1.97 131 10.2 131 1.14 134 8.79 127 33.9 130 5.66 122 18.8 139 35.7 137 26.2 144 21.9 147 42.4 144 22.0 147 27.9 138 36.8 123 35.0 148 13.2 135 32.6 119 8.11 127 0.05 73 0.02 46 0.37 80 17.5 128 33.0 99 25.2 130
HBpMotionGpu [43]125.5 2.47 135 11.8 136 1.09 132 11.4 135 35.3 134 10.0 138 20.3 144 38.5 143 26.3 145 5.67 132 26.6 122 3.51 133 24.1 114 34.8 112 26.1 132 10.9 107 30.7 107 7.04 106 0.27 97 0.05 122 0.89 92 19.3 135 37.1 122 32.8 138
TVL1_RVC [175]127.4 3.70 147 15.6 146 1.78 146 28.4 153 41.7 145 33.0 155 26.1 150 42.0 145 37.7 157 27.8 151 55.0 152 33.1 153 27.0 135 37.7 127 30.2 139 12.2 123 36.9 137 10.2 136 0.00 1 0.00 1 0.00 1 32.5 154 47.9 148 49.5 156
GraphCuts [14]127.9 1.57 112 8.32 110 0.92 119 12.3 137 39.3 141 8.40 132 15.2 130 31.3 127 23.1 138 5.40 130 28.8 133 2.88 124 25.4 120 38.0 128 21.1 119 24.5 156 31.1 109 14.4 149 1.86 141 0.02 46 7.91 144 23.9 141 41.6 140 37.4 143
IAOF [50]128.7 1.77 125 8.80 119 0.98 124 11.2 134 32.5 127 9.32 134 19.8 142 35.7 137 20.2 131 17.5 145 37.6 141 19.8 145 23.7 112 35.0 114 22.3 124 18.1 149 40.2 143 10.9 139 0.56 117 0.02 46 2.17 122 24.8 144 37.8 126 43.9 149
UnFlow [127]129.2 7.34 156 24.6 161 3.32 152 21.7 149 50.1 151 19.1 147 26.8 152 53.1 158 25.0 140 13.7 144 42.5 145 12.5 143 42.2 157 53.7 159 45.6 156 15.1 143 46.2 149 12.1 144 0.00 1 0.00 1 0.00 1 17.5 128 43.7 142 21.5 121
IAOF2 [51]130.5 1.85 129 9.64 129 1.13 133 7.56 122 29.4 122 5.66 122 12.2 122 27.5 118 15.7 125 32.6 154 43.3 147 38.7 157 24.3 115 35.0 114 23.9 129 17.9 146 33.1 121 13.0 145 1.11 133 0.25 132 4.83 136 17.8 130 35.5 117 25.9 133
Black & Anandan [4]132.3 1.75 123 8.07 107 0.73 104 11.6 136 36.6 135 8.94 133 18.9 140 36.4 139 20.3 132 12.4 142 40.5 143 12.0 142 26.3 131 36.2 122 30.5 140 13.4 136 37.3 138 11.0 140 0.75 125 0.42 143 1.90 119 21.4 140 38.6 129 32.5 137
Nguyen [33]135.2 2.73 139 11.0 133 1.16 138 33.4 156 38.0 136 43.1 158 24.6 148 41.9 144 32.1 151 28.7 152 46.5 148 32.2 152 29.8 143 39.8 133 35.5 149 13.9 138 40.4 144 13.0 145 0.03 68 0.02 46 0.20 72 31.6 149 46.3 147 50.5 157
Modified CLG [34]136.4 2.46 134 12.2 137 1.37 141 10.5 131 33.6 129 9.99 137 20.2 143 37.9 141 27.9 147 9.52 139 38.0 142 7.95 139 27.6 136 38.6 130 31.7 144 11.2 115 37.6 139 8.53 131 0.70 124 0.24 131 3.33 131 24.7 143 45.8 145 38.5 145
2D-CLG [1]138.6 6.98 155 23.0 158 3.54 153 20.1 147 40.7 143 21.4 149 26.6 151 44.0 147 36.7 152 34.7 155 55.1 153 39.7 158 31.1 147 41.5 141 38.2 150 15.0 142 42.0 147 13.6 148 0.02 65 0.02 46 0.12 68 31.7 150 51.0 152 44.9 150
SILK [80]141.5 3.45 145 15.8 148 2.61 150 19.0 145 44.9 147 19.5 148 23.5 147 44.1 148 26.6 146 12.0 141 42.7 146 11.1 141 35.3 152 46.3 153 44.8 154 18.0 148 49.4 153 14.5 150 1.53 138 0.00 1 5.00 137 32.1 153 50.8 151 47.1 153
GroupFlow [9]142.0 3.39 144 16.8 150 1.37 141 23.0 150 51.6 153 21.5 150 20.7 145 45.1 150 22.3 135 5.67 132 27.3 128 3.50 132 34.6 151 51.5 156 22.0 123 22.4 153 47.9 151 25.4 157 0.55 116 0.47 145 1.70 115 25.2 145 47.9 148 33.5 139
Horn & Schunck [3]143.9 3.02 142 12.7 138 1.15 137 14.5 140 45.9 148 11.1 139 22.6 146 44.4 149 25.2 141 21.6 146 47.3 149 22.5 148 34.0 150 43.8 145 43.1 152 19.6 150 51.5 155 18.6 153 0.56 117 0.22 129 1.77 116 34.9 156 55.9 156 46.4 152
Heeger++ [102]145.0 3.74 148 16.1 149 1.49 144 23.6 151 64.4 162 14.1 141 36.0 159 49.4 156 37.3 156 38.6 159 67.3 159 38.6 156 46.7 161 58.2 161 50.9 159 36.6 160 68.1 163 34.5 161 0.41 111 0.00 1 1.87 117 31.8 151 51.3 153 37.0 141
TI-DOFE [24]145.8 7.50 157 18.0 151 10.6 160 41.8 160 54.1 156 49.7 160 31.9 156 54.7 161 39.7 159 41.8 160 61.8 156 48.6 161 35.5 154 45.7 152 45.0 155 21.9 152 52.6 156 21.7 155 0.25 95 0.00 1 1.31 104 43.7 159 61.4 159 58.6 159
FFV1MT [104]148.3 4.51 152 19.1 154 2.74 151 19.4 146 58.6 160 14.7 144 40.8 161 53.4 160 50.0 162 38.5 158 73.8 162 37.7 154 46.4 160 56.0 160 56.7 162 33.1 159 66.2 160 31.1 159 0.75 125 0.02 46 2.04 120 31.8 151 51.3 153 37.0 141
H+S_RVC [176]149.2 9.14 163 27.7 197 4.78 158 30.6 155 62.4 161 28.2 153 33.9 158 55.7 162 37.0 155 51.7 162 69.5 161 57.6 162 46.2 159 52.7 158 65.6 163 37.1 162 67.0 161 40.3 162 0.02 65 0.02 46 0.20 72 57.5 163 67.8 162 63.1 162
Adaptive flow [45]150.5 4.48 151 15.3 144 1.90 149 37.1 158 47.9 150 40.5 156 28.1 153 45.1 150 37.9 158 23.3 149 53.8 151 24.8 149 30.1 146 41.4 139 28.5 137 22.6 154 46.3 150 15.6 151 17.3 161 5.51 162 58.1 161 26.0 147 41.5 139 40.5 148
Periodicity [79]151.0 6.73 154 29.6 198 3.88 156 24.0 152 52.2 154 25.5 152 36.6 160 47.1 153 40.1 160 23.0 148 60.3 155 20.8 146 53.1 163 69.7 163 49.1 158 36.9 161 67.0 161 33.4 160 0.54 115 0.02 46 7.78 143 34.7 155 64.9 161 46.1 151
SLK [47]151.2 8.22 162 24.0 160 12.3 161 41.4 159 57.7 159 50.8 161 29.7 155 53.3 159 36.7 152 52.4 163 57.7 154 61.8 163 42.6 158 52.1 157 54.9 160 23.9 155 54.4 158 24.4 156 3.11 152 0.00 1 7.07 142 45.8 161 61.9 160 61.9 160
PGAM+LK [55]155.4 7.83 160 22.3 157 13.7 162 29.1 154 54.2 157 31.3 154 25.6 149 48.1 155 29.9 150 29.7 153 68.4 160 28.3 151 38.2 155 50.8 155 43.0 151 25.1 157 56.4 159 21.4 154 6.54 160 0.57 147 19.1 157 38.5 157 60.8 158 51.7 158
FOLKI [16]155.9 5.65 153 23.4 159 4.60 157 35.1 157 52.9 155 42.6 157 28.3 154 52.7 157 29.6 149 24.1 150 53.7 150 27.7 150 38.9 156 49.3 154 47.8 157 25.3 158 54.3 157 27.7 158 5.73 158 1.38 158 20.1 159 43.9 160 60.5 157 62.2 161
HCIC-L [97]156.2 8.04 161 19.9 155 3.64 154 56.4 163 56.0 158 70.0 163 40.9 162 45.5 152 62.3 163 38.3 157 62.5 157 38.2 155 35.3 152 45.3 150 32.0 146 20.7 151 38.1 141 18.5 152 26.5 163 13.0 163 59.2 163 40.6 158 51.8 155 48.7 155
Pyramid LK [2]158.7 7.59 158 14.5 143 15.4 163 47.0 161 50.5 152 58.8 162 32.1 157 47.7 154 42.4 161 36.1 156 62.9 158 41.1 159 48.9 162 61.1 162 55.0 161 41.7 163 50.3 154 40.3 162 4.64 157 2.07 161 16.3 155 56.9 162 71.9 163 77.2 163
AdaConv-v1 [124]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
SepConv-v1 [125]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
SuperSlomo [130]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
CtxSyn [134]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
CyclicGen [149]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
TOF-M [150]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
MPRN [151]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
DAIN [152]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
FRUCnet [153]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
OFRI [154]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
FGME [158]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
MS-PFT [159]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
MEMC-Net+ [160]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
ADC [161]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
DSepConv [162]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
MAF-net [163]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
STAR-Net [164]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
AdaCoF [165]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
TC-GAN [166]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
FeFlow [167]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
DAI [168]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
SoftSplat [169]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
STSR [170]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
BMBC [171]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
GDCN [172]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
EDSC [173]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
MV_VFI [183]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
DistillNet [184]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
SepConv++ [185]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
EAFI [186]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
FLAVR [188]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
SoftsplatAug [190]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
ProBoost-Net [191]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
IDIAL [192]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
IFRNet [193]164.2 25.9 164 27.4 162 29.8 164 96.8 164 97.6 164 95.4 164 93.0 164 90.8 164 99.0 164 88.2 164 85.6 164 91.5 164 97.0 164 98.5 165 88.6 164 86.2 164 81.3 164 83.9 164 64.9 165 56.4 165 97.3 165 100.0 165 99.9 165 99.9 165
AVG_FLOW_ROB [137]187.3 73.2 199 62.5 199 69.7 199 98.2 199 97.8 199 97.4 199 99.9 199 99.9 199 99.8 199 92.1 199 87.3 199 92.8 199 98.1 199 97.7 164 97.7 199 87.7 199 86.5 199 83.9 164 58.7 164 25.5 164 95.7 164 98.8 164 99.4 164 99.7 164
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.