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        
R0.5
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+_RVC [198]4.2 1.67 4 9.52 5 0.33 1 3.06 2 17.8 1 1.87 12 4.08 6 12.9 4 0.71 2 0.90 4 9.59 5 0.00 1 18.9 7 28.9 6 7.47 1 2.38 3 15.7 4 0.56 1 0.01 2 0.10 20 0.00 1 8.07 2 25.7 5 4.47 1
RAFT-it [194]7.9 1.95 19 10.7 20 0.45 3 3.70 7 20.1 3 1.95 15 3.66 2 12.6 3 0.71 2 0.67 1 7.46 1 0.00 1 20.8 11 31.2 12 9.94 10 1.53 1 10.2 2 0.56 1 0.13 12 1.26 53 0.00 1 8.25 3 25.0 3 6.04 3
MS_RAFT+_RVC [195]11.7 1.91 18 10.2 13 0.48 4 7.80 67 21.3 5 7.98 105 3.91 4 13.1 5 1.43 12 0.87 3 8.97 3 0.01 4 16.2 1 23.6 1 8.26 5 2.04 2 9.19 1 1.05 3 0.01 2 0.08 17 0.00 1 7.44 1 20.0 1 5.74 2
OFLAF [78]18.4 1.67 4 9.54 6 0.81 18 4.12 12 23.1 10 2.26 22 3.43 1 11.8 1 1.47 13 2.31 18 15.3 15 0.67 16 18.1 3 27.2 4 8.68 7 12.6 51 27.0 19 6.93 40 0.78 39 1.08 46 3.37 47 11.6 14 25.9 6 16.2 30
MDP-Flow2 [68]19.8 1.76 9 9.93 10 0.86 20 3.26 3 20.6 4 1.44 3 4.04 5 13.6 6 1.26 8 3.09 38 21.8 43 0.88 30 22.4 20 32.2 16 14.3 21 9.15 21 23.6 9 5.83 20 2.18 66 0.32 25 4.78 61 10.8 9 26.3 7 15.0 20
NNF-Local [75]21.2 1.75 8 9.66 7 0.87 21 4.56 20 27.6 22 2.46 26 4.52 8 15.6 11 2.18 25 2.57 26 18.4 27 0.86 27 18.8 6 29.2 7 8.22 4 9.37 24 24.2 12 5.22 15 0.95 43 2.02 91 1.90 33 10.6 8 31.8 32 8.21 5
NN-field [71]24.2 2.01 25 11.0 25 1.10 38 5.74 34 30.7 40 3.21 36 4.57 9 15.7 12 2.22 27 1.81 12 15.7 17 0.54 13 19.0 8 29.4 8 8.42 6 10.5 32 20.3 6 3.83 7 1.43 50 2.03 92 3.72 49 10.1 5 31.1 27 6.81 4
PMMST [112]26.3 1.43 2 8.08 2 0.38 2 6.05 40 28.6 27 4.40 49 6.13 27 19.1 24 4.02 50 2.21 14 11.7 6 1.09 42 21.2 12 30.5 11 13.2 16 9.59 26 23.8 10 5.71 18 2.28 69 1.95 86 4.36 55 11.8 15 29.1 13 13.1 16
CoT-AMFlow [174]26.5 1.81 12 10.4 17 0.97 27 3.71 8 22.1 8 2.09 18 4.36 7 14.8 7 1.65 15 3.25 41 23.2 51 0.98 37 23.2 23 32.8 20 17.2 43 8.90 19 24.3 13 5.88 21 2.67 75 1.51 62 5.54 67 11.2 10 27.5 10 15.7 25
RAFT-TF_RVC [179]26.8 3.24 81 16.0 80 0.97 27 4.98 22 24.9 14 3.20 35 5.76 20 19.1 24 3.46 41 0.70 2 7.82 2 0.00 1 24.3 31 37.2 41 9.60 9 3.05 4 15.3 3 1.22 4 0.17 16 1.71 77 0.02 5 14.3 43 36.3 52 9.67 9
WLIF-Flow [91]30.2 1.80 11 9.97 11 0.94 23 6.24 43 28.7 29 4.52 51 5.74 19 18.5 18 3.13 35 3.03 37 19.9 33 1.01 39 21.9 13 32.0 15 14.1 19 12.4 48 27.2 20 6.44 24 3.40 92 0.07 10 8.69 89 11.4 12 26.8 8 15.7 25
ComponentFusion [94]31.4 1.73 7 9.92 9 0.77 15 3.75 9 22.3 9 2.27 23 5.02 13 17.1 14 2.21 26 2.87 31 19.3 31 0.93 31 24.1 26 35.1 29 18.6 51 12.4 48 39.0 91 8.29 74 2.41 70 0.13 23 4.73 60 11.9 18 30.0 22 15.5 24
Correlation Flow [76]32.2 1.96 21 10.9 23 0.66 10 4.21 14 25.5 18 1.35 2 6.69 39 20.7 35 0.94 4 1.68 10 13.3 11 0.48 12 25.4 37 36.9 38 16.3 35 13.5 68 32.5 46 7.88 64 2.82 80 1.63 68 10.8 99 11.3 11 29.7 17 9.89 10
NNF-EAC [101]34.2 1.95 19 10.5 18 1.10 38 4.29 16 25.1 16 2.20 19 5.06 14 16.6 13 1.81 18 3.94 68 23.4 54 1.63 69 22.5 21 32.5 19 14.7 24 11.3 39 25.8 15 6.81 34 2.71 77 2.13 94 4.63 59 12.4 22 30.2 24 16.5 32
Layers++ [37]34.6 1.85 15 10.1 12 1.03 33 6.26 44 27.9 25 4.58 53 4.88 12 15.2 9 3.65 44 2.26 16 14.4 13 0.68 18 17.8 2 25.4 2 12.2 12 13.3 61 28.3 24 6.81 34 4.53 103 2.71 113 7.34 80 13.2 31 29.7 17 19.2 57
LME [70]35.2 1.89 17 10.6 19 0.75 13 3.53 5 21.3 5 1.83 11 7.04 52 18.6 21 8.24 87 3.10 40 23.0 50 0.86 27 24.8 33 35.5 31 17.9 47 10.1 29 30.1 35 6.46 25 2.67 75 1.51 62 5.54 67 12.8 24 30.9 26 17.7 43
UnDAF [187]36.9 2.25 43 12.7 49 0.95 26 3.90 10 24.5 12 1.80 9 5.11 15 17.4 15 1.40 11 3.64 57 27.5 75 0.93 31 25.9 46 37.9 45 15.5 32 10.1 29 32.1 44 5.80 19 2.52 71 1.78 78 4.83 62 13.4 34 36.1 49 15.4 23
PBOFVI [189]37.1 1.83 14 10.3 16 0.55 5 4.52 19 28.4 26 1.52 5 6.11 26 18.9 22 1.33 10 1.61 9 13.0 10 0.42 9 25.7 41 36.4 34 17.3 44 13.6 74 31.1 40 8.72 83 4.23 101 3.80 123 15.1 121 11.8 15 30.4 25 13.5 18
HAST [107]37.3 1.57 3 8.65 3 0.60 6 5.82 38 24.9 14 3.84 41 3.85 3 12.5 2 0.41 1 2.82 30 18.8 28 0.58 14 18.7 5 27.9 5 8.00 2 15.9 110 32.6 47 9.69 98 9.89 143 4.87 137 36.9 153 8.55 4 22.0 2 9.33 7
RNLOD-Flow [119]37.5 1.68 6 9.49 4 0.75 13 5.76 35 30.6 39 3.18 33 6.58 36 21.1 39 2.92 32 2.61 27 17.5 24 0.74 21 22.0 14 32.8 20 14.9 27 11.5 41 28.0 23 7.37 51 5.53 118 4.17 128 15.2 123 11.8 15 27.7 11 15.1 21
nLayers [57]37.7 1.40 1 7.64 1 0.64 8 8.47 79 30.5 38 7.07 93 6.80 45 20.0 30 5.79 76 2.13 13 14.7 14 0.78 24 18.3 4 26.0 3 12.2 12 12.9 57 25.6 14 6.84 36 1.93 62 2.24 98 3.35 46 14.5 46 32.0 35 20.9 69
PRAFlow_RVC [177]38.2 2.23 41 12.5 46 0.67 11 9.04 87 36.1 72 6.17 80 7.97 62 23.4 56 6.47 78 1.37 6 12.4 7 0.14 5 27.0 50 39.9 53 15.9 34 3.98 5 16.6 5 2.91 5 0.20 20 1.93 84 0.10 11 14.0 42 34.5 44 11.8 12
GMFlow_RVC [196]38.8 3.34 85 15.7 78 1.50 79 9.84 97 35.0 58 8.75 109 6.94 49 20.3 31 5.19 70 1.51 8 12.6 8 0.20 7 27.9 53 40.9 61 14.5 22 5.55 6 21.1 7 3.25 6 0.14 13 1.38 56 0.02 5 10.2 6 28.1 12 9.20 6
ProFlow_ROB [142]39.2 2.91 74 15.3 75 1.30 53 5.38 26 30.3 37 3.10 30 8.14 64 26.3 66 3.45 40 3.50 50 23.3 53 0.98 37 29.0 65 42.5 69 17.0 40 8.52 15 33.1 50 4.71 11 0.00 1 0.02 1 0.00 1 12.1 20 36.2 50 12.3 13
FC-2Layers-FF [74]39.4 1.81 12 9.71 8 1.07 36 6.99 52 33.9 54 4.71 54 4.71 10 15.0 8 3.63 43 2.67 28 18.3 26 0.87 29 20.6 10 29.7 9 14.5 22 13.3 61 28.4 25 7.26 47 5.67 122 1.82 79 14.9 118 12.9 28 29.4 14 18.4 51
SVFilterOh [109]40.5 2.18 36 11.4 30 0.78 16 5.94 39 29.2 31 3.13 31 4.85 11 15.2 9 2.01 22 2.35 19 17.4 22 0.63 15 20.4 9 30.1 10 8.12 3 14.7 99 29.5 31 8.51 80 10.3 144 3.98 126 31.3 143 12.0 19 26.9 9 13.4 17
TC/T-Flow [77]41.3 2.19 38 11.8 38 1.21 48 5.00 23 29.4 32 1.89 14 5.57 17 18.5 18 1.28 9 3.63 56 23.7 57 1.24 49 24.1 26 35.4 30 15.2 30 7.02 8 25.8 15 5.43 16 3.79 96 2.13 94 19.3 132 14.6 49 36.2 50 17.9 46
3DFlow [133]41.5 1.97 22 10.7 20 0.63 7 5.21 24 29.9 35 1.88 13 5.17 16 17.4 15 1.02 5 1.00 5 9.03 4 0.18 6 22.3 19 32.8 20 13.2 16 19.1 132 42.2 110 12.7 121 11.7 152 1.61 66 31.8 146 11.5 13 29.9 20 9.34 8
AGIF+OF [84]41.6 1.99 24 10.9 23 1.16 43 8.96 84 37.8 78 6.95 88 6.31 30 20.4 32 3.86 48 2.89 32 19.1 29 0.93 31 22.1 15 32.4 17 14.8 25 12.9 57 28.6 27 6.79 33 3.48 95 0.08 17 8.67 88 12.8 24 29.9 20 17.5 39
TC-Flow [46]42.8 2.04 26 11.0 25 0.94 23 3.69 6 23.4 11 1.68 6 5.96 25 19.9 29 1.06 6 3.73 60 23.6 56 1.24 49 25.7 41 38.0 46 14.8 25 8.99 20 34.6 56 5.03 14 2.82 80 2.47 105 15.9 127 16.0 59 38.1 59 22.0 73
HBM-GC [103]43.0 2.10 31 10.8 22 0.94 23 7.69 66 31.9 47 6.10 78 6.21 29 18.5 18 3.82 46 2.22 15 15.5 16 0.78 24 22.1 15 31.8 13 14.2 20 13.3 61 24.1 11 7.49 55 8.91 140 1.87 80 21.4 136 12.7 23 31.1 27 16.7 35
IIOF-NLDP [129]45.3 2.63 61 13.9 61 1.09 37 7.53 63 38.0 81 3.28 37 6.98 51 22.1 48 1.85 20 2.28 17 15.7 17 0.95 35 25.2 35 37.6 44 12.5 14 13.4 66 35.9 66 8.72 83 0.78 39 0.39 31 3.57 48 15.4 56 37.7 56 15.1 21
ALD-Flow [66]45.7 2.22 40 11.8 38 1.02 32 4.33 17 24.7 13 2.04 17 6.35 32 20.9 36 1.56 14 3.67 58 24.0 61 1.10 43 25.8 43 37.5 43 15.8 33 8.24 11 32.7 49 4.68 9 3.06 85 2.62 112 16.6 129 15.6 58 39.3 62 19.8 62
ProbFlowFields [126]46.8 3.29 83 17.1 86 1.88 99 6.54 46 29.8 33 5.50 65 7.69 59 23.8 58 6.90 80 3.09 38 17.1 20 1.28 51 27.8 52 39.5 52 19.2 57 6.56 7 27.2 20 5.00 13 0.09 9 0.03 5 0.86 22 17.1 66 39.4 63 17.5 39
IROF++ [58]47.6 2.18 36 11.5 34 1.33 56 7.91 68 36.5 73 5.96 73 6.71 41 21.7 45 4.85 68 3.62 55 22.8 46 1.63 69 24.2 29 34.9 28 17.1 42 13.3 61 33.4 52 7.82 62 0.55 35 1.09 47 1.01 25 12.8 24 32.9 39 16.7 35
FESL [72]49.2 1.86 16 10.2 13 0.99 29 10.4 106 39.3 90 7.94 102 6.79 44 21.2 41 4.35 57 2.39 21 16.2 19 0.76 23 24.2 29 34.7 26 19.2 57 12.6 51 27.7 22 7.10 46 3.35 90 2.20 97 8.03 84 14.5 46 31.2 29 17.6 42
HCFN [157]49.6 1.97 22 11.4 30 0.83 19 3.40 4 21.7 7 1.76 8 5.64 18 19.6 27 1.83 19 2.80 29 20.6 36 0.71 19 25.1 34 36.8 37 16.3 35 11.6 42 36.5 71 7.26 47 11.4 151 7.50 152 35.3 152 17.6 72 42.4 68 25.3 91
FMOF [92]49.8 2.09 29 11.2 29 1.44 70 9.20 88 37.9 79 6.96 89 6.14 28 19.5 26 3.82 46 2.52 24 17.4 22 0.73 20 24.1 26 34.8 27 17.7 46 13.5 68 28.4 25 6.99 43 4.64 106 1.63 68 14.5 115 14.5 46 32.7 37 17.2 38
Classic+CPF [82]49.9 2.16 34 11.6 35 1.42 68 8.04 71 36.6 74 5.76 69 6.70 40 21.8 47 3.86 48 3.02 36 21.2 41 1.14 45 23.6 25 34.2 25 17.0 40 13.4 66 29.1 28 7.03 45 4.58 105 1.50 61 13.6 111 12.9 28 29.7 17 17.5 39
MLDP_OF [87]50.7 2.46 54 13.6 58 1.14 42 4.43 18 27.8 24 1.99 16 6.80 45 21.7 45 1.89 21 2.52 24 19.6 32 0.75 22 28.2 54 40.4 56 19.2 57 11.8 44 29.6 32 9.40 93 8.30 138 2.15 96 31.7 145 13.3 32 33.4 42 15.9 27
PH-Flow [99]50.9 2.30 47 12.2 42 1.45 72 7.61 64 35.2 60 5.81 70 5.92 24 19.0 23 4.67 66 3.52 51 22.1 44 1.49 61 23.4 24 33.9 24 16.3 35 12.4 48 29.4 30 6.87 37 4.88 110 2.25 100 14.0 113 12.2 21 30.1 23 16.6 33
Efficient-NL [60]52.1 2.41 52 11.8 38 1.55 84 8.28 75 35.4 63 5.90 71 6.72 42 20.9 36 3.78 45 2.95 35 19.1 29 1.20 47 22.1 15 32.4 17 15.3 31 14.6 95 31.0 39 8.05 69 3.32 88 2.40 104 7.02 76 13.6 37 29.6 15 18.2 48
PMF [73]52.2 2.30 47 12.8 50 1.01 30 5.64 33 31.4 44 2.51 27 6.83 47 22.5 53 1.72 17 3.26 42 21.1 38 0.94 34 24.3 31 36.7 36 9.56 8 14.4 91 40.0 97 8.40 77 7.45 135 8.62 155 24.8 137 10.4 7 25.6 4 12.7 14
WRT [146]53.1 2.74 66 13.5 55 0.68 12 10.0 102 40.0 92 5.90 71 9.48 74 24.9 63 2.26 28 1.42 7 12.9 9 0.47 11 22.7 22 33.5 23 13.6 18 16.4 114 36.2 69 9.46 94 4.01 97 0.45 34 10.3 95 15.4 56 35.3 47 13.0 15
OAR-Flow [123]53.4 2.96 75 15.1 74 1.58 86 6.72 49 31.3 43 4.10 46 9.12 72 27.1 70 4.72 67 3.73 60 23.9 59 1.17 46 28.3 56 40.8 58 17.6 45 8.30 12 33.5 54 4.69 10 0.25 23 0.17 24 2.56 40 17.5 71 40.5 65 22.6 76
JOF [136]54.6 2.08 27 11.0 25 1.19 45 7.97 70 35.7 69 6.06 77 5.84 22 18.1 17 4.57 64 3.34 46 21.1 38 1.52 63 22.1 15 31.9 14 15.0 29 14.2 85 29.3 29 8.17 70 10.6 147 4.81 135 30.7 142 12.8 24 29.6 15 17.7 43
Sparse-NonSparse [56]54.7 2.11 32 11.7 36 1.39 62 7.47 62 35.1 59 5.75 68 6.48 34 21.2 41 4.34 55 3.52 51 22.9 47 1.38 56 26.1 47 37.3 42 19.6 64 13.5 68 31.2 42 7.42 52 5.02 114 1.18 51 13.5 110 13.5 35 31.7 30 18.8 55
OFH [38]55.0 2.82 69 13.9 61 2.01 100 4.91 21 28.6 27 2.33 24 8.97 71 28.0 75 2.88 31 4.00 71 27.0 72 1.43 59 31.0 76 44.5 81 22.7 71 10.5 32 41.8 108 6.88 38 0.03 5 0.02 1 0.27 16 17.1 66 46.4 87 19.2 57
Ramp [62]55.9 2.21 39 12.1 41 1.45 72 7.45 61 35.5 66 5.63 67 6.33 31 20.6 34 4.23 52 3.43 47 22.5 45 1.38 56 25.8 43 37.0 39 19.3 61 13.5 68 30.3 36 7.45 53 4.89 111 1.97 88 15.1 121 13.1 30 31.9 33 18.0 47
NL-TV-NCC [25]56.0 2.25 43 11.7 36 0.78 16 6.94 51 35.5 66 2.54 28 6.48 34 21.1 39 1.08 7 2.48 23 21.5 42 0.46 10 31.5 79 46.7 95 16.7 38 17.3 118 41.0 106 10.2 102 4.41 102 0.10 20 10.1 94 18.4 74 43.2 72 18.2 48
LSM [39]56.0 2.24 42 12.4 44 1.39 62 7.37 59 35.4 63 5.47 64 6.61 37 21.6 44 4.24 53 3.46 49 23.8 58 1.30 53 25.8 43 37.0 39 19.3 61 13.7 75 32.1 44 7.36 50 5.34 117 1.11 49 14.5 115 13.7 40 32.3 36 18.2 48
Sparse Occlusion [54]57.2 2.14 33 11.4 30 1.03 33 7.32 57 31.0 41 6.11 79 7.29 56 22.9 55 2.48 30 3.29 43 22.9 47 1.03 40 26.9 49 39.4 50 14.9 27 13.0 59 33.3 51 7.63 58 7.80 136 8.76 158 12.2 106 14.8 51 34.8 46 16.9 37
Classic+NL [31]57.2 2.08 27 11.4 30 1.35 58 7.33 58 35.9 70 5.30 61 6.47 33 21.0 38 4.53 62 3.59 53 22.9 47 1.49 61 25.4 37 36.3 33 19.4 63 13.8 78 31.1 40 7.57 56 5.78 124 2.32 103 15.0 119 13.5 35 31.9 33 18.7 54
IROF-TV [53]59.5 2.51 57 13.5 55 1.41 66 8.08 72 38.7 87 6.19 83 6.97 50 22.3 50 4.43 59 4.23 74 28.8 81 1.72 74 28.3 56 39.9 53 22.6 70 13.8 78 40.0 97 8.01 67 0.23 21 0.39 31 0.67 19 13.7 40 33.6 43 17.8 45
TV-L1-MCT [64]60.8 2.09 29 11.1 28 1.39 62 9.67 91 39.0 89 7.35 94 7.11 54 22.3 50 4.27 54 2.94 34 20.7 37 1.13 44 28.4 58 39.4 50 25.8 88 16.0 112 35.0 59 9.27 90 1.27 48 0.57 36 7.24 78 14.8 51 33.2 41 23.3 81
RFlow [88]60.9 2.42 53 13.5 55 1.16 43 3.98 11 25.2 17 1.81 10 8.89 70 27.5 72 3.13 35 3.45 48 26.8 70 1.60 67 30.5 74 43.6 73 24.5 81 14.2 85 38.1 83 7.94 66 3.36 91 1.65 71 8.47 87 16.9 65 42.3 67 20.5 67
S2D-Matching [83]61.1 2.39 50 13.0 51 1.52 81 7.22 55 35.6 68 5.13 59 7.63 58 24.4 60 4.38 58 3.30 44 20.5 35 1.35 55 25.3 36 36.0 32 19.2 57 14.1 82 31.5 43 7.77 61 6.21 128 2.24 98 16.9 130 13.6 37 31.7 30 19.3 59
COFM [59]61.5 2.51 57 13.9 61 1.42 68 5.54 29 28.9 30 3.40 38 7.79 61 23.6 57 4.53 62 2.90 33 18.2 25 0.95 35 29.1 66 40.8 58 25.4 85 15.5 106 30.7 38 9.39 92 4.69 107 1.23 52 15.4 126 16.8 64 37.1 53 21.8 72
Occlusion-TV-L1 [63]63.2 2.47 55 13.1 52 1.12 40 6.32 45 32.2 49 4.45 50 9.86 78 28.3 76 4.44 60 3.86 66 26.7 69 1.43 59 31.9 85 44.3 79 27.1 94 11.3 39 35.3 63 10.4 106 0.47 33 1.16 50 0.67 19 19.8 81 46.6 89 22.9 79
Complementary OF [21]63.5 2.69 65 15.0 72 1.33 56 4.19 13 26.9 20 1.70 7 7.15 55 24.4 60 3.09 34 3.86 66 26.1 66 1.41 58 33.2 92 44.6 83 29.7 108 13.3 61 40.7 105 7.00 44 0.74 38 0.03 5 7.12 77 23.9 106 53.1 114 33.9 120
CostFilter [40]64.1 2.65 62 14.9 70 1.01 30 5.51 28 31.6 45 2.23 21 7.39 57 24.1 59 3.06 33 3.82 64 26.1 66 1.08 41 25.4 37 38.9 49 10.2 11 15.1 102 42.7 112 8.52 81 8.99 141 10.3 160 29.5 141 14.4 45 37.2 54 16.1 29
ACK-Prior [27]64.3 2.16 34 12.4 44 0.64 8 4.26 15 25.9 19 1.33 1 5.91 23 20.4 32 1.67 16 2.39 21 20.4 34 0.33 8 30.0 70 41.1 62 24.4 80 19.2 133 40.3 102 12.2 119 14.4 156 6.30 148 40.9 156 21.0 88 43.6 74 27.5 101
MDP-Flow [26]64.9 2.33 49 13.4 54 1.20 46 5.61 32 26.9 20 4.88 56 6.76 43 22.6 54 5.72 75 4.13 72 29.5 86 1.92 78 28.7 61 40.8 58 23.2 76 12.8 56 36.7 73 8.04 68 2.54 72 2.96 115 4.43 57 19.4 80 44.6 80 26.0 96
PWC-Net_RVC [143]65.9 4.13 107 21.0 108 2.11 102 8.97 85 40.1 94 6.18 82 10.7 84 31.8 87 8.37 88 2.38 20 17.1 20 0.67 16 34.8 106 50.7 117 21.3 66 11.8 44 39.2 93 6.97 42 0.15 14 1.43 57 0.07 10 14.9 53 38.2 60 15.9 27
2DHMM-SAS [90]66.0 2.28 46 12.3 43 1.46 74 8.45 78 38.1 82 6.02 76 8.34 66 24.4 60 5.21 71 3.73 60 23.4 54 1.62 68 25.5 40 36.6 35 18.8 52 14.5 92 33.4 52 8.46 79 5.07 115 2.05 93 15.3 124 13.3 32 32.9 39 18.5 53
SimpleFlow [49]66.8 2.39 50 12.6 48 1.60 88 9.03 86 38.3 83 7.38 95 8.52 68 25.7 65 5.41 72 4.36 79 25.5 65 2.48 87 26.8 48 38.0 46 21.6 67 14.0 81 29.7 33 7.65 59 2.77 79 1.97 88 6.48 73 14.3 43 32.8 38 19.7 61
VCN_RVC [178]67.4 3.61 99 19.9 102 1.82 97 9.33 89 40.0 92 6.89 87 9.86 78 31.1 82 6.93 81 4.43 82 30.6 91 1.52 63 32.3 87 48.1 102 18.0 48 10.5 32 38.7 87 5.51 17 0.02 4 0.10 20 0.05 8 16.2 60 44.5 79 16.4 31
Steered-L1 [116]67.5 1.78 10 10.2 13 0.92 22 2.76 1 19.0 2 1.44 3 5.78 21 19.7 28 2.10 23 3.99 70 27.5 75 1.53 66 31.3 78 43.3 71 27.6 97 14.6 95 39.2 93 9.88 99 14.6 157 5.70 144 47.1 157 22.4 95 48.1 93 29.3 107
AggregFlow [95]70.0 3.49 91 17.6 90 1.74 90 10.4 106 42.0 103 6.99 90 11.4 91 30.6 81 9.73 98 3.75 63 21.1 38 1.52 63 28.9 64 41.8 66 18.2 49 7.46 9 22.8 8 4.30 8 1.95 63 2.54 107 4.24 54 20.5 83 42.7 71 25.8 94
TF+OM [98]70.6 2.89 73 14.7 68 1.35 58 5.44 27 27.6 22 3.94 42 10.2 80 26.3 66 12.8 110 3.61 54 24.6 63 1.28 51 29.8 69 40.5 57 25.7 86 12.7 55 34.9 58 6.11 22 5.62 121 4.89 138 14.0 113 21.5 90 46.5 88 23.8 84
EPPM w/o HM [86]72.4 3.53 93 16.6 83 1.44 70 5.80 36 35.3 62 2.22 20 8.01 63 26.3 66 2.45 29 4.38 80 28.0 77 1.77 76 27.0 50 40.0 55 13.0 15 18.6 126 44.4 122 10.8 109 10.5 146 2.30 102 37.7 154 13.6 37 35.6 48 13.9 19
Adaptive [20]72.8 2.49 56 13.2 53 1.13 41 7.17 53 34.5 57 4.97 57 10.2 80 28.7 78 4.34 55 4.31 78 28.2 78 1.66 71 34.5 100 48.1 102 28.2 99 14.3 89 36.1 67 8.24 71 4.04 99 4.49 133 7.32 79 14.7 50 34.7 45 18.9 56
MCPFlow_RVC [197]73.1 4.64 111 20.6 107 2.44 121 21.0 125 53.4 132 18.5 123 20.6 123 42.9 124 29.3 127 1.72 11 14.3 12 0.83 26 38.3 121 55.8 132 23.1 74 8.67 17 26.2 18 4.71 11 0.15 14 1.48 59 0.12 13 17.1 66 43.7 76 11.1 11
DeepFlow2 [106]73.1 3.18 80 16.9 85 1.48 76 6.68 48 33.7 53 4.15 47 10.7 84 31.1 82 7.69 84 5.96 104 31.1 96 3.33 102 28.5 59 41.3 63 19.1 54 9.45 25 34.7 57 6.60 28 1.60 55 1.66 73 10.4 97 23.5 101 47.9 92 30.2 110
CombBMOF [111]74.3 2.67 63 14.4 65 1.05 35 7.17 53 33.9 54 4.00 43 6.89 48 21.4 43 4.18 51 5.20 94 28.8 81 3.04 99 28.2 54 41.7 65 18.5 50 21.8 139 39.5 95 20.1 143 4.02 98 4.61 134 6.08 70 17.1 66 37.5 55 24.5 86
ComplOF-FED-GPU [35]76.2 2.87 72 15.6 77 1.35 58 6.14 41 33.6 52 3.15 32 8.26 65 27.4 71 3.30 38 4.29 75 28.2 78 1.71 73 33.1 91 47.9 101 24.1 79 14.7 99 45.7 125 9.19 89 3.33 89 1.48 59 15.0 119 18.8 77 48.4 96 22.0 73
TCOF [69]77.5 3.05 77 15.4 76 1.75 91 8.12 74 38.6 85 5.20 60 13.8 105 34.5 99 13.2 112 8.75 129 29.0 83 8.90 134 33.8 96 47.3 98 23.1 74 9.33 23 25.9 17 6.64 30 2.59 73 1.95 86 6.38 72 15.3 55 39.1 61 18.4 51
ROF-ND [105]78.4 3.29 83 14.7 68 1.29 52 7.42 60 31.8 46 2.42 25 7.10 53 22.1 48 2.13 24 3.68 59 23.2 51 2.87 96 31.1 77 43.7 74 23.6 78 19.3 136 38.5 85 10.7 108 8.90 139 2.99 116 24.8 137 21.9 92 48.6 97 22.7 78
Classic++ [32]78.5 2.59 60 13.9 61 1.51 80 6.79 50 32.3 50 5.37 63 9.15 73 27.8 74 5.54 73 4.29 75 29.0 83 1.77 76 30.2 72 43.9 75 22.8 72 14.8 101 40.0 97 8.36 76 6.82 131 4.17 128 16.5 128 16.5 61 39.5 64 19.8 62
BriefMatch [122]79.0 2.27 45 12.5 46 1.23 50 6.23 42 32.1 48 3.54 39 6.68 38 22.3 50 3.16 37 3.32 45 23.9 59 1.23 48 30.8 75 43.3 71 26.8 91 23.9 142 43.6 116 21.0 145 11.0 150 4.44 132 33.1 149 21.5 90 44.8 81 29.2 106
DeepFlow [85]79.2 3.36 87 17.3 87 1.54 83 7.91 68 35.2 60 5.35 62 12.1 96 33.0 92 10.5 105 6.24 106 32.1 99 3.55 105 28.8 62 42.3 67 18.8 52 9.77 28 37.4 78 6.90 39 1.30 49 0.37 28 9.70 93 27.4 122 52.7 110 35.8 123
TV-L1-improved [17]80.2 2.56 59 13.6 58 1.20 46 5.80 36 30.0 36 4.04 44 9.84 77 28.4 77 4.60 65 4.16 73 27.0 72 1.66 71 31.5 79 45.4 89 23.0 73 17.5 119 45.5 124 13.7 129 7.01 133 4.32 131 20.5 134 17.1 66 42.5 70 20.4 65
S2F-IF [121]81.2 4.50 110 23.8 116 2.14 106 8.86 81 42.8 108 6.52 84 11.0 86 34.0 98 9.17 91 4.86 85 29.2 85 2.39 85 35.6 108 51.0 119 26.9 92 8.49 14 36.6 72 6.30 23 0.60 36 0.03 5 2.49 39 23.6 102 52.7 110 25.9 95
Bartels [41]81.6 3.26 82 16.7 84 1.37 61 5.33 25 29.8 33 3.18 33 8.40 67 26.9 69 4.45 61 4.40 81 26.9 71 2.16 81 32.7 88 45.4 89 28.4 103 14.3 89 38.1 83 12.9 123 8.20 137 3.82 124 31.3 143 18.4 74 43.7 76 23.3 81
SIOF [67]82.8 2.67 63 13.6 58 1.23 50 7.65 65 37.9 79 4.78 55 14.2 108 32.9 91 15.4 114 6.36 107 34.7 106 3.84 108 34.0 97 45.8 92 33.2 115 13.5 68 35.7 65 10.5 107 1.99 64 0.99 44 4.21 53 20.5 83 45.6 83 30.7 113
DMF_ROB [135]84.2 3.59 98 19.4 100 1.80 95 8.09 73 35.4 63 5.96 73 11.6 92 33.7 95 7.90 86 5.84 102 32.4 100 3.42 104 33.7 94 47.0 96 28.7 105 12.6 51 37.5 80 8.25 73 0.50 34 0.35 27 2.46 38 26.5 115 52.6 109 32.2 117
F-TV-L1 [15]84.3 3.34 85 17.3 87 1.80 95 9.99 101 38.6 85 7.03 91 13.2 103 32.6 90 7.82 85 5.85 103 32.9 101 2.91 98 31.5 79 45.0 86 25.2 83 15.1 102 38.7 87 8.99 87 2.19 67 3.29 119 3.03 44 15.1 54 38.0 58 16.6 33
SegFlow [156]84.6 4.79 116 24.9 123 2.32 115 9.79 92 42.1 104 7.91 101 11.2 88 33.9 96 9.54 95 5.29 98 34.7 106 2.51 90 34.6 102 49.1 109 27.2 95 9.75 27 36.4 70 6.96 41 0.43 32 0.07 10 1.82 29 23.1 99 51.5 104 24.9 89
PGM-C [118]84.9 4.80 118 24.9 123 2.34 118 9.79 92 42.4 105 7.86 99 11.3 90 34.5 99 9.49 93 5.28 97 34.6 105 2.54 91 34.5 100 49.1 109 26.5 89 9.26 22 37.2 75 6.72 32 0.42 30 0.07 10 1.85 31 23.7 103 53.0 113 25.6 93
CRTflow [81]85.2 3.53 93 18.6 94 1.79 93 6.54 46 34.0 56 4.08 45 10.5 82 31.6 86 5.02 69 4.95 89 30.6 91 2.31 82 30.1 71 44.2 78 19.1 54 24.2 143 50.1 136 26.0 149 1.80 60 0.92 42 6.63 74 22.7 97 52.1 106 30.0 109
FlowFields+ [128]86.1 4.68 113 24.5 119 2.22 109 9.86 98 44.7 115 7.63 96 12.1 96 37.3 109 10.3 104 4.92 88 30.3 89 2.61 92 36.3 109 51.6 123 28.3 102 8.62 16 38.7 87 6.57 27 0.41 26 0.02 1 1.92 34 23.7 103 53.6 118 25.5 92
FlowFields [108]86.1 4.67 112 24.4 118 2.22 109 9.80 94 44.3 112 7.67 97 11.8 94 36.4 106 10.1 102 4.90 87 30.5 90 2.63 93 36.4 111 51.6 123 28.9 106 8.76 18 38.7 87 6.48 26 0.85 41 0.03 5 2.71 42 23.3 100 53.7 119 22.3 75
CPM-Flow [114]87.1 4.79 116 24.9 123 2.32 115 9.83 95 42.4 105 7.89 100 11.2 88 33.9 96 9.50 94 5.25 95 34.3 103 2.50 89 34.7 104 49.3 113 26.7 90 10.3 31 37.5 80 7.62 57 0.42 30 0.07 10 1.82 29 24.5 109 54.2 120 26.8 99
Rannacher [23]87.5 3.03 76 16.1 81 1.59 87 8.35 76 36.9 75 6.87 86 11.1 87 31.8 87 6.71 79 4.88 86 29.7 87 2.34 83 31.7 84 45.9 93 23.3 77 16.8 115 44.0 118 10.3 105 4.89 111 2.57 109 12.1 105 16.7 63 41.9 66 19.9 64
TriangleFlow [30]87.5 2.81 68 14.9 70 1.22 49 7.27 56 37.1 76 3.76 40 9.83 76 30.2 80 3.34 39 3.84 65 27.1 74 1.72 74 39.4 126 53.7 128 34.8 121 21.8 139 43.5 114 16.0 134 4.72 109 7.40 151 8.30 86 18.5 76 44.3 78 21.5 71
SRR-TVOF-NL [89]87.5 3.16 79 16.2 82 1.49 77 8.87 82 38.5 84 5.57 66 12.3 98 33.4 93 8.53 89 3.96 69 26.6 68 1.34 54 32.8 89 44.6 83 27.2 95 13.8 78 39.0 91 8.34 75 5.55 120 5.38 142 17.8 131 22.0 93 43.3 73 25.2 90
EpicFlow [100]87.8 4.80 118 24.9 123 2.33 117 9.90 99 42.9 109 7.95 103 11.8 94 35.7 104 9.56 96 5.26 96 34.4 104 2.49 88 34.6 102 49.2 112 27.0 93 10.8 36 37.5 80 7.33 49 0.41 26 0.07 10 1.80 27 24.1 107 53.5 116 26.4 97
CVENG22+RIC [199]88.0 4.77 115 24.6 120 2.27 111 10.7 109 44.9 116 8.19 106 12.8 100 37.8 114 9.25 92 5.46 100 35.2 109 2.68 94 37.4 116 51.4 122 32.7 112 11.1 38 38.5 85 7.92 65 0.41 26 0.07 10 1.80 27 18.2 73 48.1 93 19.4 60
LocallyOriented [52]88.2 4.06 103 20.2 104 1.87 98 12.1 111 47.6 119 8.49 108 15.9 113 39.1 117 11.1 107 5.10 92 28.6 80 2.84 95 34.0 97 47.4 99 25.7 86 11.8 44 32.6 47 7.84 63 1.10 44 1.51 62 6.95 75 20.3 82 46.8 91 23.1 80
Aniso. Huber-L1 [22]89.1 2.84 71 14.5 66 1.46 74 14.0 114 42.6 107 12.9 113 13.4 104 31.3 84 13.0 111 6.50 108 35.2 109 4.19 111 29.7 68 42.4 68 21.8 69 14.5 92 35.0 59 8.43 78 5.54 119 3.18 118 12.8 108 16.6 62 37.7 56 20.9 69
Dynamic MRF [7]90.7 3.39 88 18.9 97 1.30 53 5.60 31 33.5 51 2.81 29 9.67 75 31.3 84 3.54 42 4.64 84 33.7 102 2.39 85 38.0 118 51.2 120 34.9 122 19.2 133 51.8 140 15.2 132 3.41 93 0.37 28 20.9 135 25.1 112 52.2 107 31.7 115
FF++_ROB [141]91.9 4.95 121 25.8 130 2.27 111 10.3 105 44.5 113 7.95 103 13.1 102 37.6 113 12.4 109 5.12 93 31.4 97 2.87 96 36.3 109 52.0 127 28.2 99 10.9 37 36.9 74 7.65 59 1.46 51 0.96 43 4.19 52 20.8 87 49.0 98 22.6 76
DPOF [18]92.5 4.03 101 21.8 110 2.11 102 9.50 90 40.4 96 5.97 75 8.88 69 27.5 72 6.05 77 4.29 75 30.8 93 2.08 80 31.5 79 45.1 87 21.6 67 15.9 110 37.3 77 9.53 96 15.3 158 1.61 66 47.3 158 22.1 94 46.3 86 28.5 103
CBF [12]95.7 2.82 69 15.0 72 1.32 55 18.0 120 40.4 96 21.6 126 10.6 83 29.2 79 9.72 97 6.57 109 34.8 108 4.55 114 31.5 79 44.0 77 24.5 81 14.5 92 35.0 59 8.92 86 10.9 149 6.02 146 26.2 140 20.7 86 43.6 74 27.2 100
Brox et al. [5]96.0 3.55 96 18.8 96 1.64 89 10.1 104 39.6 91 8.97 110 11.7 93 33.4 93 8.96 90 6.57 109 36.4 112 3.41 103 38.2 120 47.6 100 45.3 146 13.5 68 42.4 111 9.63 97 0.27 24 0.99 44 0.47 18 31.0 129 56.4 125 43.3 136
Fusion [6]96.2 3.40 89 19.1 98 2.16 108 5.57 30 31.1 42 4.53 52 7.70 60 25.2 64 7.53 83 5.78 101 35.6 111 4.10 110 36.6 112 47.1 97 38.8 132 14.2 85 41.9 109 13.2 124 6.84 132 5.31 140 11.7 103 24.8 110 51.1 103 31.6 114
Local-TV-L1 [65]98.8 4.05 102 19.4 100 2.51 123 17.1 119 43.6 111 15.9 120 19.8 121 37.3 109 23.3 122 9.20 132 43.3 126 6.89 131 28.6 60 41.3 63 20.2 65 14.1 82 35.1 62 8.67 82 1.24 46 0.62 37 3.94 50 33.5 138 57.2 127 49.6 143
CLG-TV [48]98.9 2.80 67 14.6 67 1.41 66 14.0 114 40.7 99 14.1 117 12.7 99 32.0 89 11.0 106 8.13 122 47.7 135 5.99 127 32.0 86 45.2 88 25.2 83 14.1 82 40.1 101 10.9 110 6.45 129 5.82 145 10.4 97 19.0 78 42.4 68 26.6 98
LiteFlowNet [138]99.2 6.03 131 30.6 134 2.46 122 12.8 112 48.7 120 9.20 111 14.4 109 42.4 122 9.92 101 5.00 90 30.8 93 2.05 79 43.8 134 61.4 138 32.8 113 16.3 113 47.6 131 8.24 71 0.10 10 0.87 41 0.32 17 22.5 96 52.4 108 24.5 86
p-harmonic [29]101.0 3.47 90 19.1 98 2.29 113 8.40 77 35.9 70 6.80 85 12.8 100 34.6 101 9.84 100 9.04 130 47.6 134 6.72 129 37.1 114 48.7 107 39.6 133 13.1 60 44.0 118 11.2 112 3.43 94 2.50 106 6.33 71 21.2 89 45.2 82 30.5 111
LDOF [28]101.4 4.09 105 20.0 103 2.31 114 9.96 100 41.8 101 7.06 92 14.1 106 37.0 107 10.1 102 8.41 124 43.3 126 4.97 117 34.4 99 46.2 94 32.5 111 12.2 47 41.0 106 8.88 85 1.63 57 2.00 90 5.79 69 29.9 124 56.0 123 38.8 132
DF-Auto [113]101.6 4.71 114 22.2 111 2.11 102 21.1 126 49.4 122 21.6 126 20.3 122 39.8 119 31.0 129 7.62 118 37.5 114 5.08 120 33.6 93 43.9 75 33.3 116 8.36 13 29.8 34 7.48 54 2.60 74 5.21 139 2.22 35 32.4 133 53.1 114 43.2 135
TriFlow [93]102.2 3.53 93 17.9 91 1.77 92 11.0 110 37.3 77 10.6 112 16.7 116 35.8 105 25.3 124 4.44 83 30.9 95 2.34 83 35.0 107 44.3 79 35.7 123 10.7 35 30.4 37 6.68 31 33.4 161 9.63 159 90.0 163 30.3 127 55.2 122 36.8 127
FlowNetS+ft+v [110]105.3 3.75 100 18.5 93 2.13 105 10.0 102 38.8 88 8.25 107 16.3 114 37.5 112 20.0 115 7.89 120 37.0 113 5.17 121 36.9 113 48.2 104 35.7 123 11.6 42 40.0 97 9.13 88 4.56 104 4.02 127 14.6 117 23.8 105 51.0 101 31.9 116
Second-order prior [8]106.3 3.49 91 18.6 94 1.79 93 9.83 95 40.6 98 7.83 98 14.1 106 39.0 116 9.82 99 6.20 105 31.4 97 3.83 107 34.7 104 49.4 114 27.6 97 18.7 128 52.1 141 11.4 114 9.18 142 3.60 121 20.1 133 19.1 79 48.2 95 24.4 85
Learning Flow [11]107.4 3.56 97 18.2 92 1.56 85 8.71 80 41.5 100 6.17 80 14.5 110 37.8 114 11.8 108 7.92 121 41.1 122 5.02 118 40.9 130 51.7 125 42.4 137 15.4 105 47.2 130 11.4 114 2.73 78 6.19 147 7.64 83 23.0 98 49.9 99 28.9 105
OFRF [132]107.6 3.10 78 15.9 79 1.40 65 21.2 127 45.4 117 20.7 125 18.7 119 34.6 101 22.6 121 7.09 111 30.2 88 5.59 124 30.2 72 44.8 85 16.7 38 18.6 126 43.5 114 10.2 102 6.14 127 3.78 122 25.5 139 34.2 139 53.5 116 54.4 148
C-RAFT_RVC [181]107.8 8.00 137 31.4 136 3.20 131 28.1 135 62.8 143 25.4 132 26.2 133 48.7 135 35.6 134 5.09 91 24.9 64 3.25 101 48.3 144 65.4 148 39.7 134 12.6 51 35.3 63 10.2 102 0.88 42 2.59 111 2.64 41 24.1 107 51.9 105 20.7 68
CNN-flow-warp+ref [115]111.2 4.85 120 24.6 120 2.62 125 13.2 113 41.8 101 12.9 113 17.7 118 39.6 118 25.0 123 8.67 128 44.8 129 5.78 126 38.1 119 48.2 104 43.5 141 13.7 75 40.4 103 9.32 91 1.80 60 1.29 55 9.16 90 33.2 135 57.7 129 42.9 134
ContinualFlow_ROB [148]112.0 8.33 139 33.5 140 3.16 130 25.9 134 54.7 133 25.7 134 24.1 129 50.5 138 32.1 130 7.50 117 42.2 124 4.65 115 48.0 143 67.8 152 28.9 106 21.7 138 56.2 146 19.3 142 0.08 8 0.79 40 0.10 11 20.6 85 46.6 89 20.4 65
Ad-TV-NDC [36]112.3 10.3 145 20.2 104 18.1 157 38.1 144 53.0 130 43.3 148 28.0 138 45.6 127 35.7 135 20.6 142 48.9 138 23.8 143 29.1 66 42.5 69 19.1 54 13.7 75 36.1 67 9.46 94 2.03 65 1.43 57 4.38 56 41.4 148 65.3 144 57.0 150
WOLF_ROB [144]114.1 5.72 129 29.1 131 2.14 106 18.8 122 56.5 137 14.1 117 22.4 127 48.9 136 20.6 117 8.21 123 40.5 120 5.30 122 41.7 132 56.1 134 40.9 135 17.2 117 46.4 127 10.1 101 0.70 37 0.40 33 2.78 43 29.8 123 62.4 139 38.0 131
StereoOF-V1MT [117]114.3 4.08 104 23.0 112 1.49 77 10.4 106 53.3 131 4.35 48 16.3 114 49.5 137 5.71 74 7.37 115 48.5 136 4.03 109 46.7 139 62.9 142 42.9 140 21.9 141 64.7 152 17.0 135 1.58 54 1.87 80 9.43 92 33.2 135 66.2 145 36.5 125
CompactFlow_ROB [155]115.2 9.03 143 36.7 146 4.21 138 22.9 128 58.1 138 21.8 128 30.0 143 56.5 142 47.0 150 7.34 114 41.4 123 4.65 115 49.0 145 67.4 150 37.1 128 15.7 108 55.6 144 11.5 116 0.03 5 0.34 26 0.02 5 26.3 114 59.9 133 23.5 83
BlockOverlap [61]116.0 4.14 109 17.3 87 3.50 132 23.3 129 43.1 110 25.5 133 21.0 124 37.2 108 27.8 125 13.1 135 39.0 117 13.7 138 28.8 62 38.6 48 28.2 99 18.7 128 37.2 75 13.3 125 12.6 154 6.40 150 40.8 155 26.8 120 45.8 84 43.3 136
Shiralkar [42]116.6 4.11 106 23.3 113 1.52 81 8.88 83 44.5 113 5.07 58 14.5 110 41.9 121 6.96 82 7.32 113 44.7 128 4.37 112 38.8 125 55.2 131 33.1 114 26.7 148 60.7 147 18.5 140 10.4 145 3.38 120 32.9 148 26.7 118 61.6 135 29.5 108
EAI-Flow [147]117.0 6.63 133 29.9 133 2.74 127 16.6 118 49.7 124 13.0 115 19.1 120 46.0 129 20.3 116 7.88 119 42.2 124 5.06 119 43.3 133 60.6 136 34.1 118 15.3 104 46.8 128 10.9 110 5.09 116 0.08 17 13.8 112 26.7 118 57.1 126 30.6 112
LSM_FLOW_RVC [182]117.7 11.1 148 43.5 155 7.09 146 25.8 133 64.4 146 23.1 130 29.0 140 64.1 153 28.6 126 11.0 134 49.8 140 8.84 133 46.9 140 65.1 147 37.1 128 14.6 95 55.6 144 12.8 122 0.10 10 0.02 1 0.96 24 25.0 111 59.9 133 24.5 86
LFNet_ROB [145]118.0 8.75 141 41.6 153 3.69 136 18.9 123 59.4 139 15.2 119 24.3 130 60.8 151 21.2 118 8.64 127 49.0 139 5.67 125 50.3 148 66.9 149 46.2 147 17.8 120 52.5 142 12.5 120 0.17 16 0.05 9 1.03 26 26.6 116 61.9 137 27.8 102
SegOF [10]119.7 6.07 132 25.2 127 3.62 134 36.7 142 55.3 134 41.7 145 26.1 132 43.8 125 39.2 139 15.2 138 45.4 130 12.3 136 46.5 138 56.0 133 57.5 151 18.2 125 49.9 135 14.9 131 0.19 18 0.71 39 0.86 22 31.1 130 52.9 112 35.9 124
HBpMotionGpu [43]120.0 5.00 122 21.6 109 2.81 128 31.1 138 49.5 123 35.0 138 26.3 135 45.3 126 37.1 137 9.18 131 39.3 118 7.65 132 33.7 94 45.6 91 32.2 110 15.7 108 37.4 78 9.89 100 5.71 123 4.19 130 12.5 107 33.4 137 56.3 124 47.8 141
ResPWCR_ROB [140]120.3 5.84 130 29.6 132 2.83 129 15.8 116 51.1 126 13.4 116 21.2 125 48.5 134 21.2 118 8.43 125 47.3 133 5.39 123 41.2 131 57.0 135 37.4 130 19.2 133 53.0 143 15.6 133 1.16 45 1.66 73 5.49 66 31.6 131 62.2 138 34.6 122
2bit-BM-tele [96]120.9 5.17 124 23.4 114 3.54 133 16.3 117 40.3 95 16.7 121 15.2 112 34.6 101 14.2 113 8.49 126 37.6 115 6.75 130 32.8 89 44.5 81 28.6 104 24.3 144 43.9 117 22.5 147 15.6 159 8.72 157 50.0 160 26.2 113 50.8 100 37.5 129
StereoFlow [44]121.5 28.4 162 55.1 163 37.7 162 81.1 163 92.6 163 77.8 162 65.0 161 82.9 163 51.1 157 69.6 162 90.7 163 65.5 159 52.7 153 67.5 151 44.9 145 8.13 10 33.5 54 6.60 28 0.05 7 0.37 28 0.17 14 32.2 132 54.8 121 40.4 133
SPSA-learn [13]122.1 5.52 126 25.3 129 4.12 137 25.2 132 50.0 125 26.8 135 25.1 131 45.7 128 36.7 136 19.0 139 54.2 142 20.8 140 38.6 122 48.4 106 44.4 143 17.9 123 45.3 123 17.6 137 1.60 55 0.54 35 5.27 65 39.6 145 57.9 130 53.3 146
IRR-PWC_RVC [180]122.3 11.3 149 39.2 150 4.42 141 34.4 140 61.6 142 36.8 140 33.5 147 56.7 143 45.7 148 13.9 137 40.6 121 12.0 135 44.7 135 62.7 141 30.0 109 14.6 95 49.8 134 11.2 112 0.41 26 1.93 84 0.71 21 30.0 125 63.0 141 33.1 119
IAOF2 [51]122.7 4.13 107 20.4 106 2.02 101 18.0 120 45.9 118 18.0 122 17.1 117 37.3 109 21.4 120 46.4 153 57.8 144 56.1 156 37.4 116 48.8 108 35.9 125 25.5 145 42.7 112 20.4 144 6.62 130 3.04 117 15.3 124 26.8 120 51.0 101 37.9 130
FlowNet2 [120]123.7 7.84 136 30.7 135 2.58 124 41.4 148 65.2 148 44.4 149 29.6 142 48.0 132 46.8 149 5.31 99 24.0 61 3.06 100 47.8 141 64.8 145 36.3 126 17.8 120 44.3 120 13.4 126 2.93 83 8.71 156 5.22 63 30.2 126 61.7 136 28.8 104
Filter Flow [19]124.1 5.13 123 23.5 115 2.40 120 20.5 124 51.3 127 19.6 124 23.3 128 42.6 123 35.3 133 27.2 145 48.8 137 28.3 145 39.4 126 49.1 109 44.6 144 17.9 123 40.5 104 11.8 118 7.39 134 7.67 154 11.5 102 26.6 116 46.0 85 33.9 120
EPMNet [131]125.1 7.68 135 33.7 141 2.38 119 39.6 146 72.0 157 40.0 144 27.9 137 46.4 130 44.6 146 7.12 112 38.7 116 3.78 106 47.8 141 64.8 145 36.3 126 17.8 120 44.3 120 13.4 126 1.56 53 5.60 143 2.27 36 33.0 134 70.0 151 32.3 118
AugFNG_ROB [139]125.2 9.81 144 36.9 148 4.29 139 38.3 145 64.3 145 42.6 147 29.2 141 57.1 144 38.5 138 7.41 116 39.4 119 4.51 113 50.9 149 70.1 155 37.7 131 17.0 116 50.1 136 13.6 128 0.23 21 2.25 100 0.17 14 36.5 142 68.9 150 36.5 125
Black & Anandan [4]125.6 5.52 126 25.2 127 4.71 142 24.4 131 52.8 128 24.4 131 26.8 136 48.3 133 34.4 132 20.9 143 60.4 145 22.4 142 38.7 124 49.7 115 42.8 139 18.9 130 49.4 132 17.1 136 1.78 59 2.57 109 3.30 45 36.0 140 57.3 128 49.5 142
Modified CLG [34]128.1 7.42 134 31.9 138 5.50 143 31.7 139 52.9 129 37.6 142 28.4 139 50.8 139 40.4 141 20.3 141 60.5 146 21.3 141 39.5 128 51.2 120 42.2 136 14.2 85 45.8 126 11.5 116 3.24 87 1.70 76 9.31 91 40.3 146 65.1 143 54.7 149
IAOF [50]128.6 5.70 128 24.0 117 3.65 135 30.0 137 48.7 120 33.9 137 26.2 133 47.8 131 29.5 128 28.0 146 51.3 141 32.9 146 37.3 115 50.2 116 34.4 120 26.2 146 50.9 139 18.0 139 5.85 125 1.63 68 11.7 103 36.3 141 59.4 132 51.9 144
TVL1_RVC [175]129.8 16.9 153 35.6 143 25.3 159 53.6 155 60.6 141 64.0 156 36.2 149 58.6 145 48.0 153 44.5 152 72.3 152 52.0 153 39.5 128 50.7 117 42.5 138 15.5 106 47.1 129 14.1 130 0.39 25 0.66 38 1.87 32 47.3 153 70.9 153 59.9 154
GraphCuts [14]130.3 5.45 125 24.7 122 2.64 126 24.3 130 55.8 136 21.9 129 21.4 126 40.8 120 32.4 131 9.25 133 46.4 131 6.31 128 38.6 122 51.7 125 33.8 117 28.8 151 39.7 96 18.7 141 12.1 153 2.87 114 35.1 151 38.5 143 58.4 131 53.9 147
2D-CLG [1]133.7 14.0 151 40.7 151 8.09 149 45.8 150 59.5 140 54.5 153 36.8 151 60.4 150 47.3 151 48.9 155 75.1 156 54.2 155 44.9 136 54.8 129 52.5 148 19.0 131 50.3 138 17.8 138 1.26 47 0.07 10 4.43 57 47.4 154 71.2 154 59.9 154
GroupFlow [9]135.1 8.95 142 33.2 139 7.07 145 43.6 149 70.7 153 45.5 150 32.7 145 59.8 149 42.4 144 13.2 136 46.6 132 12.4 137 51.1 150 70.0 154 34.2 119 30.8 153 62.8 149 33.8 154 1.54 52 2.56 108 4.14 51 39.0 144 67.0 147 47.4 140
Nguyen [33]136.1 8.19 138 31.4 136 4.40 140 54.9 156 55.7 135 70.2 158 33.6 148 54.6 140 43.3 145 43.5 151 60.9 147 50.5 152 45.1 137 54.9 130 54.2 149 21.1 137 49.4 132 21.0 145 2.92 82 1.87 80 7.39 81 44.7 151 66.2 145 58.5 152
UnFlow [127]136.2 22.1 160 43.6 156 7.44 148 52.6 154 73.8 158 54.3 152 47.7 157 74.9 160 47.5 152 26.4 144 68.7 150 24.7 144 64.5 158 75.5 160 65.6 158 28.5 150 67.0 156 27.1 151 0.19 18 1.87 80 0.05 8 30.4 128 62.4 139 36.8 127
Horn & Schunck [3]138.7 8.56 140 35.5 142 7.11 147 29.4 136 65.4 149 28.1 136 33.4 146 64.4 154 41.2 143 30.6 147 67.2 149 33.6 147 49.1 147 61.3 137 55.5 150 26.4 147 64.7 152 26.1 150 3.02 84 3.95 125 2.44 37 48.8 155 75.0 156 58.8 153
SILK [80]141.1 10.7 146 35.7 144 14.6 154 37.7 143 64.2 144 42.5 146 32.3 144 59.3 147 40.6 142 19.9 140 56.8 143 20.4 139 51.6 152 62.6 140 59.6 154 27.2 149 63.0 150 23.2 148 4.92 113 1.68 75 13.1 109 46.9 152 71.6 155 61.7 157
TI-DOFE [24]145.5 21.2 158 43.7 157 34.5 161 64.6 161 71.9 156 76.5 161 47.1 156 75.6 161 53.7 158 57.3 157 76.4 157 65.6 160 51.5 151 63.9 143 60.0 155 30.4 152 65.8 155 33.2 152 2.24 68 1.65 71 5.22 63 59.1 159 82.1 161 71.2 160
Periodicity [79]145.6 11.0 147 41.5 152 5.85 144 35.3 141 64.5 147 36.8 140 51.0 158 55.5 141 61.7 160 49.6 156 81.4 159 48.4 151 66.0 160 83.6 163 59.0 152 46.1 158 76.4 160 43.0 158 1.67 58 5.33 141 8.13 85 48.8 155 78.9 158 57.5 151
Heeger++ [102]146.8 24.4 161 45.8 158 9.72 151 47.8 152 85.9 162 37.8 143 66.2 162 69.8 157 75.2 161 59.7 159 88.6 162 56.9 157 66.6 161 80.3 162 62.4 157 65.6 163 87.3 163 67.1 163 4.14 100 1.26 53 7.39 81 41.9 149 68.8 148 43.4 138
SLK [47]149.8 17.8 155 50.1 161 21.7 158 62.2 160 77.8 160 74.7 160 40.4 154 72.7 159 48.1 154 66.2 160 73.9 154 76.1 162 60.9 156 71.2 156 72.9 162 33.1 154 68.3 158 35.4 156 5.99 126 1.09 47 11.4 101 60.5 161 81.9 160 75.0 161
H+S_RVC [176]150.1 19.7 156 52.3 162 11.9 153 58.6 158 81.6 161 62.5 155 52.6 159 80.3 162 49.7 156 73.2 163 84.5 160 79.6 163 67.5 162 71.8 157 92.4 163 48.7 159 77.5 161 53.6 161 3.15 86 1.51 62 10.3 95 74.3 163 85.2 163 76.6 162
FFV1MT [104]150.6 22.0 159 42.2 154 9.20 150 41.0 147 76.9 159 36.1 139 66.5 163 71.9 158 79.2 162 58.5 158 87.7 161 57.1 158 64.8 159 76.5 161 70.3 161 64.8 162 85.8 162 65.3 162 4.70 108 4.86 136 11.3 100 41.9 149 68.8 148 43.4 138
Adaptive flow [45]151.0 16.0 152 36.3 145 17.5 156 57.9 157 67.3 150 64.2 157 38.7 153 59.2 146 48.8 155 39.9 149 69.2 151 44.2 150 49.0 145 62.0 139 43.6 142 39.1 157 62.2 148 34.3 155 34.2 162 23.4 162 82.8 161 40.6 147 64.9 142 51.9 144
FOLKI [16]152.6 13.4 150 45.9 159 16.0 155 48.5 153 67.4 151 57.8 154 36.6 150 66.2 155 40.3 140 32.2 148 66.9 148 37.2 148 52.9 154 64.2 144 60.1 156 34.7 155 65.7 154 40.2 157 12.9 155 7.56 153 33.8 150 55.3 158 78.0 157 70.7 159
PGAM+LK [55]155.0 17.6 154 48.4 160 26.7 160 45.8 150 71.8 155 49.9 151 38.3 152 67.6 156 44.6 146 42.8 150 79.5 158 42.6 149 56.5 155 69.9 153 59.0 152 37.8 156 70.5 159 33.6 153 23.5 160 15.0 161 48.8 159 54.6 157 80.9 159 61.1 156
Pyramid LK [2]155.8 19.8 157 36.7 146 40.3 163 61.8 159 68.8 152 74.6 159 43.5 155 63.7 152 58.2 159 46.9 154 72.7 153 54.1 154 61.5 157 74.5 159 65.8 159 51.3 160 64.1 151 50.1 159 10.8 148 6.30 148 31.9 147 68.2 162 84.9 162 84.8 163
HCIC-L [97]158.6 29.6 163 37.7 149 11.4 152 77.3 162 71.7 154 90.9 163 63.0 160 59.4 148 83.6 163 66.9 161 74.8 155 69.8 161 68.1 163 74.1 158 66.1 160 54.4 161 67.4 157 52.5 160 58.9 163 43.5 163 89.4 162 59.4 160 70.0 151 67.4 158
AdaConv-v1 [124]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
SepConv-v1 [125]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
SuperSlomo [130]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
CtxSyn [134]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
CyclicGen [149]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
TOF-M [150]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
MPRN [151]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
DAIN [152]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
FRUCnet [153]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
OFRI [154]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
FGME [158]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
MS-PFT [159]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
MEMC-Net+ [160]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
ADC [161]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
DSepConv [162]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
MAF-net [163]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
STAR-Net [164]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
AdaCoF [165]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
TC-GAN [166]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
FeFlow [167]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
DAI [168]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
SoftSplat [169]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
STSR [170]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
BMBC [171]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
GDCN [172]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
EDSC [173]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
MV_VFI [183]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
DistillNet [184]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
SepConv++ [185]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
EAFI [186]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
FLAVR [188]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
SoftsplatAug [190]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
ProBoost-Net [191]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
IDIAL [192]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
IFRNet [193]164.5 82.5 164 78.4 164 94.0 165 98.6 164 99.3 164 97.9 164 99.9 164 99.9 164 99.9 164 97.4 165 96.9 165 99.7 165 100.0 165 99.9 165 99.8 165 93.4 164 95.5 165 93.4 164 86.5 165 85.7 165 99.4 165 99.9 164 99.9 164 99.9 164
AVG_FLOW_ROB [137]177.1 93.7 199 89.5 199 90.8 164 99.0 199 99.4 199 98.5 199 99.9 164 99.9 164 99.9 164 95.9 164 91.8 164 95.9 164 99.8 164 99.7 164 99.7 164 96.8 199 95.1 164 94.6 199 85.8 164 76.3 164 97.8 164 100.0 199 100.0 199 99.9 164
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.