Optical flow evaluation results Statistics:     Average   SD   R0.5   R1.0   R2.0   A90   A95   A99  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
R1.0
normalized interpolation
error
avg. Mequon
(Hidden texture)
im0   GT   im1
Schefflera
(Hidden texture)
im0   GT   im1
Urban
(Synthetic)
im0   GT   im1
Teddy
(Stereo)
im0   GT   im1
Backyard
(High-speed camera)
im0   GT   im1
Basketball
(High-speed camera)
im0   GT   im1
Dumptruck
(High-speed camera)
im0   GT   im1
Evergreen
(High-speed camera)
im0   GT   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
MDP-Flow2 [68]15.5 6.71 3 9.78 5 8.39 10 6.36 10 11.5 14 6.23 12 7.12 6 9.73 8 5.42 2 21.2 6 18.8 11 41.2 12 30.1 10 26.5 7 45.6 58 27.7 23 19.5 33 36.0 24 6.48 4 13.8 8 10.3 8 8.19 33 16.4 25 7.11 40
PMMST [114]17.1 6.84 11 9.80 6 8.50 20 6.74 28 11.7 16 6.36 29 7.10 5 9.45 4 5.41 1 21.1 2 18.6 5 41.1 4 30.2 15 26.5 7 45.7 73 27.3 4 18.1 8 36.0 24 6.51 6 13.9 13 10.3 8 8.22 37 16.5 34 7.15 51
NNF-Local [87]19.0 6.74 5 10.1 9 8.30 3 5.97 2 10.3 3 6.14 3 7.09 4 9.63 7 5.44 3 21.7 35 20.5 72 41.2 12 30.3 25 26.6 13 45.4 30 27.9 43 20.6 73 36.0 24 6.51 6 13.8 8 10.3 8 8.04 18 16.1 13 7.10 38
PH-Flow [101]19.2 7.05 26 10.9 21 8.50 20 6.10 4 10.6 7 6.14 3 7.18 7 9.83 9 5.55 6 21.1 2 18.5 4 41.1 4 30.1 10 26.6 13 45.2 20 27.9 43 21.7 102 35.7 13 6.60 20 14.3 26 10.3 8 8.11 23 16.3 21 7.14 48
CombBMOF [113]19.6 6.93 15 9.87 8 8.43 13 6.33 9 11.4 11 6.22 11 7.60 48 10.3 16 6.25 86 21.5 21 19.4 27 41.2 12 30.2 15 26.6 13 45.3 26 27.7 23 19.2 25 36.1 37 6.57 14 14.1 16 10.3 8 7.67 5 15.4 8 6.82 4
NN-field [71]23.5 6.88 12 10.8 17 8.48 17 5.99 3 10.3 3 6.13 2 7.65 57 9.54 5 5.81 34 21.9 52 21.0 95 41.4 27 30.2 15 26.6 13 45.4 30 27.8 34 20.0 49 36.0 24 6.48 4 13.7 7 10.3 8 8.02 16 16.1 13 7.04 28
IROF++ [58]29.5 7.07 29 11.3 32 8.50 20 6.64 23 12.0 21 6.19 7 7.54 39 10.6 30 5.84 39 21.2 6 18.6 5 41.5 31 30.2 15 26.9 26 45.0 13 27.6 19 18.8 15 36.2 46 6.69 40 14.7 40 10.5 69 8.17 30 16.4 25 7.33 89
Layers++ [37]30.0 7.17 41 11.1 27 8.79 66 6.14 7 10.3 3 6.41 34 7.34 19 10.3 16 5.69 20 21.3 11 19.0 17 41.3 19 30.5 43 27.1 49 45.4 30 28.1 63 21.1 87 36.2 46 6.51 6 13.8 8 10.2 2 8.20 34 16.4 25 7.13 46
nLayers [57]31.5 7.15 38 10.4 13 8.81 71 6.44 13 11.4 11 6.42 35 7.23 10 9.30 2 5.65 14 21.4 16 19.1 20 41.5 31 30.7 82 27.4 93 45.6 58 28.0 53 20.8 77 36.2 46 6.54 12 13.6 5 10.3 8 8.07 19 16.3 21 6.91 9
Sparse-NonSparse [56]33.8 7.09 30 11.3 32 8.57 30 6.53 18 11.8 19 6.21 9 7.40 27 10.5 26 5.64 10 21.5 21 19.0 17 41.7 51 30.4 32 27.0 36 45.4 30 28.3 76 21.5 98 36.4 70 6.66 30 14.4 29 10.3 8 8.23 38 16.6 39 7.09 35
ProbFlowFields [128]34.4 7.03 22 11.8 59 8.66 45 6.41 11 11.7 16 6.31 22 7.18 7 10.3 16 5.58 7 21.7 35 19.6 34 41.8 59 30.7 82 27.1 49 46.0 122 27.9 43 20.5 64 36.2 46 6.51 6 13.8 8 10.3 8 7.80 8 15.6 9 7.14 48
2DHMM-SAS [92]34.8 7.27 56 12.0 68 8.59 34 7.82 71 14.2 62 6.36 29 7.25 11 10.5 26 5.74 26 21.4 16 18.7 8 41.4 27 30.3 25 26.9 26 45.2 20 27.9 43 20.3 57 36.0 24 6.64 27 14.4 29 10.3 8 8.41 56 17.0 54 7.08 32
AGIF+OF [85]35.4 7.11 33 11.3 32 8.46 14 6.68 27 12.2 25 6.27 16 7.38 24 10.1 12 5.71 24 21.2 6 18.6 5 41.1 4 30.8 94 27.6 117 45.4 30 28.3 76 22.2 120 36.0 24 6.67 32 14.0 15 10.3 8 8.34 48 17.0 54 6.91 9
NNF-EAC [103]35.7 7.35 68 11.1 27 8.79 66 6.92 39 12.5 33 6.29 20 7.52 38 10.1 12 5.76 29 21.8 42 19.5 32 42.8 116 30.2 15 26.6 13 45.4 30 27.5 11 18.9 18 36.0 24 6.58 16 14.2 21 10.4 38 8.32 45 16.8 43 7.19 61
FlowFields [110]35.9 7.02 21 11.5 42 8.54 28 6.66 26 12.5 33 6.44 39 7.45 31 11.5 60 5.64 10 21.9 52 20.5 72 41.8 59 30.6 61 27.0 36 45.5 46 27.7 23 20.2 52 36.0 24 6.59 18 14.3 26 10.4 38 8.00 15 16.2 18 7.08 32
CtxSyn [137]36.4 3.84 1 6.67 1 4.59 1 5.06 1 9.01 1 6.57 54 5.42 1 6.73 1 8.44 139 20.9 1 16.7 1 42.3 94 28.9 5 24.9 5 45.0 13 27.5 11 15.3 3 37.0 112 7.55 129 13.2 4 12.1 144 7.09 2 12.4 2 9.27 147
FlowFields+ [130]36.7 6.99 17 11.4 39 8.47 16 6.61 22 12.3 27 6.48 42 7.42 29 11.5 60 5.67 17 21.7 35 20.3 58 41.6 40 30.7 82 27.2 64 45.6 58 27.8 34 20.3 57 36.1 37 6.61 21 14.4 29 10.4 38 7.99 14 16.2 18 7.03 26
FMOF [94]36.8 7.36 70 12.0 68 8.73 55 6.42 12 11.3 10 6.30 21 7.63 53 10.4 21 6.02 71 21.8 42 19.9 41 41.2 12 30.5 43 27.0 36 45.4 30 28.0 53 20.5 64 36.1 37 6.51 6 13.8 8 10.2 2 8.30 43 16.7 42 7.12 42
S2F-IF [123]37.5 7.01 20 11.5 42 8.48 17 6.57 19 12.2 25 6.42 35 7.40 27 11.2 56 5.64 10 21.6 25 20.1 49 41.3 19 30.7 82 27.3 78 45.7 73 27.8 34 20.4 61 36.1 37 6.71 45 14.9 55 10.4 38 7.98 13 16.1 13 7.04 28
LSM [39]39.4 7.17 41 11.8 59 8.58 32 6.64 23 12.1 24 6.17 6 7.49 34 10.9 45 5.69 20 21.6 25 19.6 34 41.6 40 30.5 43 27.1 49 45.4 30 28.3 76 21.6 100 36.3 61 6.68 38 14.6 35 10.2 2 8.35 51 16.9 52 7.03 26
LME [70]39.9 6.72 4 9.86 7 8.36 6 6.97 41 12.4 30 7.40 97 7.51 36 11.8 69 5.70 23 21.3 11 19.2 23 41.3 19 31.0 123 27.6 117 46.6 136 27.8 34 20.5 64 36.0 24 6.45 3 13.6 5 10.2 2 8.08 21 16.3 21 7.12 42
FGIK [136]40.1 8.46 122 10.6 15 11.0 133 9.13 110 15.0 86 10.8 132 5.88 2 10.6 30 6.65 113 23.0 114 20.4 65 40.7 1 25.6 1 21.6 2 41.9 2 24.6 1 14.3 2 33.2 1 6.00 2 11.4 2 9.93 1 7.19 3 14.1 5 7.00 18
WLIF-Flow [93]41.0 6.99 17 11.0 24 8.48 17 6.76 29 12.4 30 6.39 32 7.38 24 10.3 16 5.68 19 21.4 16 18.8 11 41.9 72 30.4 32 26.9 26 45.9 111 28.8 114 21.9 109 36.9 108 6.56 13 13.9 13 10.3 8 8.34 48 16.8 43 7.15 51
TV-L1-MCT [64]41.3 7.50 89 12.5 98 8.79 66 7.19 48 13.4 48 6.37 31 7.28 14 10.6 30 5.80 33 21.4 16 18.8 11 41.3 19 30.5 43 27.1 49 45.1 17 27.9 43 18.6 11 36.6 88 6.72 49 15.0 64 10.4 38 7.92 11 15.9 11 7.20 65
ComponentFusion [96]41.5 6.91 13 10.8 17 8.55 29 6.49 17 12.0 21 6.10 1 7.49 34 11.2 56 5.72 25 21.3 11 19.4 27 41.2 12 30.6 61 27.2 64 45.8 90 27.8 34 19.6 36 36.2 46 6.92 86 16.4 108 10.4 38 8.43 60 17.0 54 7.16 55
COFM [59]42.2 7.04 23 10.7 16 8.70 49 6.60 20 11.9 20 6.35 26 7.26 12 9.93 10 5.63 9 21.2 6 18.8 11 41.0 2 30.4 32 27.3 78 44.9 12 27.7 23 22.6 124 35.1 3 6.86 78 14.7 40 11.2 127 8.67 92 17.2 73 7.78 127
MDP-Flow [26]43.5 6.83 9 10.8 17 8.50 20 6.65 25 12.4 30 6.51 48 7.46 32 10.6 30 5.88 49 22.1 73 20.6 77 41.7 51 30.4 32 26.8 21 45.6 58 28.2 72 21.9 109 36.3 61 6.69 40 14.8 49 10.4 38 8.15 26 16.6 39 7.10 38
HAST [109]44.7 6.97 16 10.2 10 8.69 47 6.46 14 11.6 15 6.26 15 7.72 68 11.1 52 5.97 63 21.1 2 18.7 8 41.1 4 30.5 43 27.5 102 44.8 10 28.2 72 22.8 130 35.5 6 6.76 59 15.2 74 10.4 38 8.81 99 18.0 109 6.96 16
EAI-Flow [152]44.8 7.33 65 11.6 47 8.83 75 7.42 58 13.7 50 7.00 84 7.69 64 12.0 75 5.85 43 21.6 25 19.9 41 41.2 12 30.5 43 27.0 36 45.5 46 27.7 23 18.8 15 36.2 46 6.76 59 15.0 64 10.5 69 7.67 5 15.3 7 7.01 22
RNLOD-Flow [121]44.9 7.12 35 11.5 42 8.64 42 7.38 56 14.0 57 6.35 26 7.55 40 11.2 56 5.83 38 21.3 11 19.0 17 41.1 4 30.5 43 27.2 64 45.4 30 28.3 76 21.6 100 36.2 46 6.62 22 14.2 21 10.4 38 8.70 95 17.7 95 7.02 24
LFNet_ROB [150]45.5 7.27 56 11.6 47 8.82 73 7.96 76 14.9 82 7.11 88 7.95 86 13.8 123 6.10 75 21.8 42 20.6 77 41.3 19 30.1 10 26.6 13 45.1 17 27.9 43 21.0 81 35.9 17 6.51 6 14.1 16 10.3 8 7.84 9 15.7 10 7.00 18
CyclicGen [154]45.6 10.0 141 9.16 4 13.8 144 9.67 118 10.4 6 19.8 152 7.89 82 11.0 48 9.80 146 22.8 107 17.9 2 43.7 126 25.6 1 21.4 1 41.3 1 25.2 2 10.7 1 35.5 6 5.75 1 10.1 1 10.2 2 4.50 1 7.84 1 6.41 1
OFLAF [77]45.7 6.81 8 10.2 10 8.40 11 6.10 4 10.7 8 6.21 9 7.36 21 10.6 30 5.54 5 21.1 2 18.8 11 41.0 2 30.8 94 27.4 93 45.7 73 28.1 63 21.9 109 36.0 24 7.02 98 16.1 104 10.4 38 8.90 107 18.1 117 7.16 55
Ramp [62]48.0 7.31 63 12.1 72 8.78 63 6.60 20 12.0 21 6.27 16 7.36 21 10.4 21 5.65 14 21.3 11 18.9 16 41.4 27 30.5 43 27.1 49 45.4 30 28.7 108 22.3 122 36.6 88 6.73 55 14.9 55 10.3 8 8.55 76 17.3 78 7.26 76
Second-order prior [8]50.1 7.30 62 11.3 32 8.90 83 8.52 94 15.6 97 6.74 68 8.32 110 13.6 119 6.42 104 21.8 42 20.0 45 41.5 31 30.1 10 26.5 7 45.5 46 27.5 11 19.0 20 36.0 24 6.67 32 14.6 35 10.3 8 8.25 39 16.8 43 7.11 40
PGM-C [120]50.1 7.19 46 12.1 72 8.72 52 6.82 31 12.9 37 6.62 56 7.67 61 12.2 82 5.78 32 21.9 52 20.9 89 41.8 59 30.6 61 27.1 49 45.8 90 27.7 23 19.5 33 36.2 46 6.65 28 14.7 40 10.3 8 8.20 34 16.6 39 7.31 83
Classic+NL [31]51.4 7.44 83 12.3 83 8.86 77 6.78 30 12.3 27 6.28 18 7.32 18 10.4 21 5.69 20 21.6 25 19.4 27 41.8 59 30.5 43 27.1 49 45.5 46 28.6 102 21.8 105 36.6 88 6.72 49 14.7 40 10.3 8 8.50 69 17.2 73 7.24 73
FC-2Layers-FF [74]51.4 7.22 49 11.9 66 8.70 49 6.10 4 10.2 2 6.47 41 7.31 17 10.5 26 5.64 10 21.4 16 19.1 20 41.6 40 30.7 82 27.5 102 45.6 58 28.6 102 22.7 127 36.4 70 6.77 62 15.0 64 10.3 8 8.57 80 17.2 73 7.20 65
DeepFlow2 [108]51.4 7.28 58 11.3 32 8.88 80 7.68 66 14.4 70 6.94 82 7.58 46 12.3 86 5.88 49 21.9 52 20.2 54 41.7 51 30.5 43 26.8 21 45.9 111 27.5 11 18.0 7 36.4 70 6.67 32 14.6 35 10.4 38 8.18 31 16.4 25 7.31 83
Aniso. Huber-L1 [22]51.7 7.61 96 12.2 80 9.19 95 8.99 105 15.7 100 7.12 90 7.73 70 11.0 48 5.86 46 21.8 42 20.0 45 41.6 40 30.2 15 26.6 13 45.5 46 27.4 6 19.6 36 35.7 13 6.68 38 14.6 35 10.3 8 8.34 48 16.8 43 7.29 82
SRR-TVOF-NL [91]52.7 7.42 81 11.5 42 8.86 77 7.79 68 14.8 78 7.08 87 7.62 50 11.5 60 5.85 43 21.7 35 19.6 34 41.1 4 30.3 25 27.1 49 45.2 20 27.5 11 20.5 64 35.3 5 6.72 49 14.8 49 10.4 38 8.97 114 18.3 123 7.17 58
PWC-Net_ROB [148]52.9 7.22 49 12.8 108 8.51 26 7.26 52 14.0 57 6.49 45 7.78 75 12.7 99 5.95 59 21.6 25 20.3 58 41.6 40 30.8 94 27.5 102 45.6 58 28.2 72 20.2 52 36.5 79 6.58 16 14.2 21 10.4 38 8.02 16 16.3 21 6.87 7
FF++_ROB [146]53.2 7.00 19 11.4 39 8.50 20 7.08 43 13.3 46 6.62 56 7.67 61 11.9 72 5.93 56 21.9 52 20.6 77 41.5 31 30.8 94 27.4 93 45.7 73 28.4 88 20.5 64 36.9 108 6.67 32 14.6 35 10.4 38 8.08 21 16.4 25 7.09 35
FESL [72]54.1 7.36 70 11.7 53 8.65 44 6.82 31 12.6 35 6.33 24 7.51 36 10.7 39 5.89 52 21.6 25 19.6 34 41.3 19 30.9 117 27.5 102 45.7 73 28.4 88 22.1 118 36.2 46 6.70 43 14.8 49 10.2 2 8.59 81 17.4 85 7.08 32
LiteFlowNet [143]54.1 7.24 53 12.4 93 8.60 37 7.17 45 13.7 50 6.52 49 7.70 66 13.1 108 5.84 39 22.5 99 22.5 129 41.9 72 30.4 32 27.0 36 45.2 20 27.8 34 21.3 93 35.5 6 6.90 85 15.6 89 10.4 38 7.86 10 16.0 12 6.80 3
DF-Auto [115]54.2 7.54 91 11.1 27 9.32 104 8.42 90 14.5 73 8.82 111 7.35 20 10.3 16 5.65 14 22.0 64 20.2 54 41.5 31 30.4 32 26.7 20 45.8 90 27.5 11 18.7 13 36.1 37 6.82 70 15.3 78 10.5 69 8.43 60 17.1 62 7.20 65
Classic+CPF [83]54.5 7.22 49 11.6 47 8.52 27 6.90 38 12.6 35 6.28 18 7.37 23 10.6 30 5.76 29 21.2 6 18.7 8 41.1 4 31.1 128 27.9 126 45.5 46 28.7 108 23.1 135 36.3 61 6.92 86 15.3 78 10.3 8 8.75 97 17.9 104 6.99 17
CPM-Flow [116]54.5 7.21 47 12.2 80 8.71 51 6.83 34 12.9 37 6.65 60 7.61 49 11.7 66 5.88 49 22.2 80 21.4 110 41.8 59 30.6 61 27.1 49 45.8 90 27.9 43 19.1 21 36.6 88 6.67 32 14.7 40 10.3 8 8.16 28 16.5 34 7.34 92
S2D-Matching [84]56.4 7.37 73 12.3 83 8.80 69 7.62 65 14.2 62 6.43 38 7.28 14 10.4 21 5.74 26 21.6 25 19.1 20 42.2 91 30.6 61 27.3 78 45.4 30 28.6 102 22.5 123 36.4 70 6.76 59 14.5 33 10.3 8 8.46 63 17.0 54 7.32 86
IROF-TV [53]56.7 7.33 65 12.3 83 8.82 73 6.83 34 12.3 27 6.23 12 7.70 66 12.9 105 5.93 56 21.5 21 19.5 32 42.0 81 30.8 94 27.3 78 45.9 111 27.5 11 20.2 52 35.6 10 6.75 57 15.1 72 10.5 69 8.18 31 16.4 25 7.37 96
DeepFlow [86]57.0 7.21 47 11.0 24 8.88 80 7.79 68 14.3 65 7.33 96 7.64 55 12.6 95 5.95 59 22.1 73 20.1 49 42.0 81 30.6 61 26.8 21 46.1 127 28.0 53 17.9 6 37.2 118 6.57 14 14.1 16 10.4 38 8.07 19 16.2 18 7.32 86
EPPM w/o HM [88]57.2 6.77 7 10.4 13 8.32 4 7.00 42 13.4 48 6.16 5 8.19 102 13.6 119 6.26 87 21.7 35 20.3 58 41.5 31 30.5 43 27.2 64 45.5 46 28.5 96 21.8 105 36.5 79 6.84 72 15.6 89 10.6 96 8.41 56 17.1 62 6.95 15
Brox et al. [5]58.2 7.28 58 11.4 39 8.76 57 7.86 72 14.6 75 6.92 81 8.03 92 13.1 108 6.34 95 21.9 52 19.9 41 41.4 27 30.6 61 27.0 36 45.8 90 27.7 23 19.5 33 36.2 46 6.80 65 15.4 84 10.4 38 8.16 28 16.5 34 7.19 61
p-harmonic [29]58.2 7.04 23 11.3 32 8.62 40 8.81 99 15.8 103 6.98 83 7.76 73 13.1 108 6.18 83 22.4 93 20.7 82 41.9 72 30.5 43 27.0 36 45.5 46 27.8 34 19.2 25 36.4 70 6.71 45 15.1 72 10.3 8 8.29 42 16.8 43 7.12 42
Efficient-NL [60]58.4 7.28 58 11.6 47 8.61 39 7.24 51 13.3 46 6.35 26 8.21 104 10.8 41 6.39 101 21.7 35 19.6 34 41.2 12 30.4 32 27.0 36 45.3 26 28.3 76 22.8 130 35.6 10 6.86 78 15.6 89 10.4 38 9.10 121 18.3 123 7.14 48
ProFlow_ROB [147]59.0 7.15 38 11.3 32 8.77 60 7.31 53 14.3 65 6.72 66 7.57 45 11.5 60 5.76 29 22.0 64 21.2 107 42.2 91 30.8 94 27.4 93 45.6 58 27.6 19 18.7 13 36.1 37 6.81 68 15.3 78 10.3 8 8.55 76 17.3 78 7.31 83
JOF [141]59.3 7.63 97 12.3 83 9.19 95 6.48 15 11.4 11 6.48 42 7.27 13 10.1 12 5.67 17 21.8 42 19.2 23 42.6 112 30.8 94 27.3 78 45.8 90 28.7 108 22.2 120 36.6 88 6.59 18 14.1 16 10.3 8 8.55 76 17.1 62 7.46 103
SepConv-v1 [127]59.6 4.07 2 8.88 2 4.61 2 6.87 36 13.0 41 7.47 98 6.42 3 9.58 6 9.25 144 23.4 125 20.0 45 44.0 130 30.2 15 26.3 6 45.7 73 27.9 43 16.5 5 37.4 124 7.61 132 15.6 89 12.9 150 7.71 7 13.8 4 9.78 149
SuperSlomo [132]61.5 6.74 5 9.03 3 8.40 11 9.03 108 13.1 43 12.7 143 8.09 99 10.5 26 9.15 142 22.7 105 18.4 3 43.7 126 28.3 3 24.4 3 44.1 4 28.5 96 15.3 3 38.7 140 7.11 103 12.9 3 12.9 150 7.43 4 13.2 3 9.86 150
EpicFlow [102]61.9 7.18 43 12.0 68 8.72 52 7.42 58 14.4 70 6.72 66 7.68 63 12.1 79 5.92 55 22.1 73 21.1 100 42.0 81 30.7 82 27.1 49 45.8 90 27.5 11 19.9 47 35.9 17 6.79 64 15.2 74 10.4 38 8.40 55 17.1 62 7.33 89
DPOF [18]62.8 7.58 95 13.2 118 9.07 86 6.27 8 11.0 9 6.54 51 8.10 100 10.6 30 6.27 89 22.0 64 20.5 72 41.9 72 30.2 15 26.8 21 45.4 30 28.0 53 21.2 89 35.8 16 6.84 72 15.0 64 10.7 106 8.62 85 17.4 85 7.26 76
PMF [73]62.8 6.83 9 10.3 12 8.37 8 6.96 40 13.1 43 6.19 7 7.86 79 13.1 108 6.03 72 21.5 21 19.4 27 41.3 19 31.0 123 27.7 121 45.8 90 28.7 108 20.5 64 37.2 118 6.80 65 15.0 64 10.5 69 8.87 103 18.2 120 7.00 18
ComplOF-FED-GPU [35]64.0 7.23 52 11.8 59 8.72 52 7.20 49 13.9 54 6.62 56 8.43 115 12.6 95 6.45 105 21.9 52 20.8 88 42.3 94 30.4 32 26.9 26 45.4 30 27.7 23 20.1 50 36.1 37 6.86 78 15.4 84 10.5 69 8.55 76 17.3 78 7.28 81
DMF_ROB [140]64.5 7.31 63 11.8 59 8.81 71 7.86 72 14.9 82 6.69 64 8.52 118 13.8 123 6.40 103 22.1 73 20.7 82 41.5 31 30.5 43 26.9 26 46.0 122 27.4 6 18.9 18 36.1 37 6.95 93 14.3 26 11.2 127 8.13 24 16.4 25 7.19 61
Sparse Occlusion [54]65.2 7.37 73 12.3 83 8.87 79 8.04 79 15.3 90 6.48 42 7.58 46 10.8 41 5.87 47 22.0 64 20.4 65 41.5 31 30.6 61 27.2 64 45.5 46 28.3 76 21.8 105 36.4 70 6.80 65 15.3 78 10.3 8 8.74 96 17.7 95 7.18 60
TC/T-Flow [76]65.5 7.37 73 11.8 59 8.59 34 7.31 53 14.0 57 6.42 35 7.47 33 11.1 52 5.81 34 21.8 42 20.5 72 41.7 51 30.8 94 27.5 102 45.7 73 28.1 63 20.9 78 36.2 46 7.03 100 16.0 102 10.6 96 8.62 85 17.6 92 7.13 46
AggregFlow [97]67.5 7.71 103 12.6 101 9.11 88 7.50 62 13.9 54 7.06 85 7.19 9 9.98 11 5.53 4 21.9 52 20.4 65 41.6 40 30.8 94 27.3 78 46.1 127 29.0 118 19.7 43 37.9 132 6.75 57 14.7 40 10.5 69 8.32 45 16.8 43 7.40 100
CLG-TV [48]67.9 7.52 90 12.3 83 9.14 90 8.67 97 15.8 103 7.11 88 7.97 88 12.7 99 6.26 87 22.1 73 20.3 58 42.0 81 30.5 43 26.9 26 45.7 73 27.6 19 19.1 21 36.2 46 6.71 45 14.9 55 10.4 38 8.53 75 17.3 78 7.24 73
SuperFlow [81]68.0 7.43 82 11.5 42 9.30 101 8.55 95 14.8 78 9.15 115 7.91 84 12.0 75 6.31 92 22.1 73 19.9 41 42.0 81 30.7 82 27.2 64 45.9 111 27.3 4 18.4 10 35.9 17 6.86 78 15.8 96 10.6 96 8.15 26 16.5 34 7.16 55
RFlow [90]68.1 7.24 53 12.1 72 8.90 83 8.42 90 15.6 97 6.49 45 7.72 68 12.2 82 6.01 70 22.0 64 20.6 77 41.7 51 30.4 32 27.1 49 45.7 73 27.4 6 19.8 46 35.6 10 6.84 72 15.9 100 10.5 69 8.91 110 18.0 109 7.47 107
SIOF [67]69.0 7.66 100 12.6 101 9.09 87 9.45 116 16.6 117 8.48 106 7.65 57 11.9 72 5.98 64 21.9 52 20.1 49 41.8 59 30.0 8 26.5 7 45.3 26 28.1 63 19.7 43 36.6 88 6.63 25 14.7 40 10.5 69 8.82 100 17.9 104 7.46 103
TCOF [69]69.0 7.36 70 12.1 72 8.68 46 9.41 115 16.6 117 7.17 92 7.38 24 10.7 39 5.61 8 21.8 42 20.4 65 41.8 59 30.4 32 27.0 36 45.6 58 28.1 63 21.8 105 35.9 17 6.85 75 15.7 95 10.4 38 9.30 131 19.0 136 7.61 121
TC-Flow [46]69.1 7.18 43 11.8 59 8.78 63 7.46 61 14.6 75 6.77 72 7.86 79 12.6 95 5.89 52 21.8 42 20.3 58 41.9 72 30.7 82 27.4 93 45.7 73 28.3 76 21.0 81 36.6 88 6.73 55 14.8 49 10.5 69 8.51 71 17.3 78 7.24 73
3DFlow [135]69.5 7.09 30 11.7 53 8.46 14 6.89 37 13.0 41 6.39 32 8.03 92 10.6 30 5.98 64 21.6 25 19.3 25 41.9 72 30.8 94 27.1 49 47.6 144 29.0 118 23.9 142 36.4 70 7.05 101 16.2 105 10.5 69 8.83 102 18.0 109 7.15 51
IAOF [50]69.9 8.70 127 12.9 111 10.3 125 12.4 141 19.2 147 9.77 127 7.74 71 12.0 75 6.21 84 22.8 107 20.2 54 42.0 81 30.2 15 26.5 7 45.5 46 27.7 23 19.6 36 36.1 37 6.67 32 15.0 64 10.3 8 8.41 56 17.1 62 7.12 42
OAR-Flow [125]70.9 7.45 85 11.7 53 8.98 85 7.57 64 14.4 70 6.91 80 7.62 50 12.4 89 5.82 36 21.6 25 20.3 58 41.6 40 30.9 117 27.5 102 45.8 90 28.0 53 20.5 64 36.4 70 6.97 95 15.6 89 10.5 69 8.46 63 17.1 62 7.34 92
ContinualFlow_ROB [153]71.7 7.92 109 13.9 130 9.35 106 8.28 84 15.5 93 8.57 107 8.24 106 14.0 128 6.28 90 21.9 52 21.0 95 41.9 72 30.6 61 27.3 78 45.5 46 27.4 6 20.1 50 35.5 6 6.65 28 14.4 29 10.4 38 8.65 89 17.9 104 6.94 13
ALD-Flow [66]72.9 7.54 91 12.1 72 9.14 90 7.43 60 14.3 65 6.85 77 7.66 60 12.5 92 5.87 47 21.8 42 20.4 65 42.3 94 30.8 94 27.4 93 45.9 111 28.1 63 19.9 47 36.6 88 6.62 22 14.2 21 10.5 69 8.68 93 17.5 91 7.46 103
SVFilterOh [111]73.8 7.18 43 10.9 21 8.76 57 6.48 15 11.7 16 6.45 40 7.62 50 10.2 15 5.99 67 21.7 35 19.4 27 42.5 106 31.3 133 28.0 132 46.6 136 28.6 102 22.0 114 36.5 79 6.92 86 14.1 16 11.4 133 8.97 114 17.8 101 8.09 133
OFH [38]74.3 7.39 78 12.1 72 8.88 80 8.07 80 15.0 86 6.66 62 8.03 92 13.8 123 5.96 62 21.9 52 21.1 100 42.1 88 30.5 43 27.3 78 45.4 30 27.8 34 20.4 61 36.2 46 7.11 103 16.4 108 10.5 69 8.61 84 17.6 92 7.19 61
MLDP_OF [89]75.3 7.10 32 11.2 31 8.64 42 7.33 55 13.7 50 6.31 22 7.44 30 10.9 45 5.75 28 22.0 64 19.8 40 42.3 94 30.6 61 27.3 78 46.2 133 31.0 146 22.6 124 40.0 146 6.93 89 15.2 74 11.0 121 8.65 89 17.4 85 7.79 129
ResPWCR_ROB [145]75.9 7.34 67 12.4 93 8.76 57 7.92 75 15.1 88 7.28 94 8.37 112 13.4 116 6.22 85 22.7 105 22.2 124 43.1 122 29.7 6 26.5 7 44.6 7 32.9 150 21.5 98 43.1 150 6.66 30 14.9 55 10.3 8 8.50 69 17.4 85 7.00 18
CostFilter [40]76.3 6.91 13 11.1 27 8.37 8 6.82 31 12.9 37 6.25 14 7.99 89 13.9 126 6.10 75 21.9 52 20.6 77 41.7 51 31.1 128 27.9 126 45.9 111 29.8 133 20.3 57 39.1 142 6.94 91 15.8 96 10.6 96 8.82 100 18.1 117 7.09 35
Fusion [6]76.6 7.13 37 12.3 83 8.60 37 7.18 47 13.1 43 6.56 52 7.63 53 10.9 45 6.13 80 22.5 99 21.1 100 41.5 31 30.7 82 28.2 137 44.3 5 28.1 63 23.8 140 35.2 4 7.22 113 17.9 123 10.6 96 9.64 139 19.9 143 7.32 86
Modified CLG [34]77.7 7.63 97 11.6 47 9.65 108 10.7 129 17.2 126 10.7 131 8.25 107 14.3 132 6.60 111 22.4 93 21.1 100 41.8 59 30.6 61 26.9 26 45.8 90 27.7 23 19.2 25 36.3 61 6.69 40 14.9 55 10.4 38 8.41 56 17.0 54 7.35 95
IIOF-NLDP [131]78.3 7.04 23 10.9 21 8.36 6 7.81 70 14.8 78 6.64 59 8.07 98 11.0 48 6.12 77 22.3 87 20.0 45 42.8 116 30.4 32 27.0 36 45.9 111 29.1 124 23.2 136 36.5 79 8.40 149 24.6 150 11.3 130 8.78 98 17.8 101 6.86 6
F-TV-L1 [15]78.9 8.24 116 13.1 115 9.92 117 9.28 111 16.3 112 7.48 99 8.00 90 13.2 114 6.35 97 22.3 87 20.9 89 42.3 94 29.9 7 26.9 26 44.8 10 27.9 43 19.4 30 36.5 79 6.87 82 15.4 84 10.5 69 8.46 63 16.8 43 7.58 117
FlowNet2 [122]79.7 9.30 132 14.6 135 10.5 128 8.42 90 14.6 75 9.24 119 8.03 92 12.5 92 6.14 81 22.2 80 21.9 120 41.8 59 30.9 117 27.5 102 45.8 90 28.0 53 20.5 64 36.0 24 6.72 49 14.9 55 10.4 38 8.31 44 16.9 52 7.01 22
EPMNet [133]79.8 9.02 130 14.8 138 10.2 123 8.29 86 14.1 61 8.78 110 8.03 92 12.5 92 6.15 82 22.8 107 23.9 143 41.7 51 30.9 117 27.5 102 45.8 90 28.0 53 21.4 95 35.9 17 6.72 49 14.9 55 10.4 38 8.21 36 16.8 43 6.83 5
Complementary OF [21]80.3 7.11 33 12.1 72 8.50 20 7.17 45 14.0 57 6.58 55 8.76 126 12.0 75 6.55 108 22.3 87 21.4 110 42.6 112 30.6 61 27.5 102 45.2 20 28.1 63 20.9 78 36.4 70 7.15 107 16.7 112 10.5 69 9.09 119 18.7 130 7.38 97
AugFNG_ROB [144]80.5 8.05 110 12.5 98 9.84 116 8.99 105 15.9 108 9.32 122 8.37 112 15.6 138 6.30 91 22.5 99 22.3 125 41.9 72 31.2 131 28.0 132 45.6 58 27.8 34 20.2 52 35.9 17 6.83 71 15.0 64 10.4 38 7.96 12 16.4 25 6.68 2
SimpleFlow [49]80.6 7.37 73 12.4 93 8.74 56 7.88 74 14.3 65 6.50 47 8.59 121 11.5 60 6.51 106 21.6 25 19.3 25 41.8 59 30.6 61 27.3 78 45.5 46 28.5 96 22.9 133 36.2 46 7.66 135 20.5 143 10.8 116 8.89 106 18.2 120 7.15 51
LDOF [28]81.8 8.08 111 12.3 83 9.79 114 8.94 103 14.9 82 9.18 117 8.23 105 13.5 118 6.52 107 22.3 87 21.1 100 42.4 104 30.6 61 27.0 36 45.8 90 27.9 43 18.8 15 36.6 88 6.77 62 15.3 78 10.4 38 8.44 62 17.1 62 7.38 97
TF+OM [100]81.9 7.41 79 12.1 72 9.19 95 7.21 50 12.9 37 7.83 101 7.55 40 12.3 86 5.82 36 22.2 80 21.0 95 41.9 72 30.8 94 27.5 102 46.0 122 28.3 76 20.5 64 36.8 103 6.97 95 16.3 106 10.5 69 8.65 89 17.3 78 7.75 125
ROF-ND [107]82.4 7.46 86 11.0 24 8.77 60 7.96 76 15.4 91 6.76 71 7.55 40 11.0 48 5.85 43 23.3 122 23.5 141 41.6 40 30.6 61 27.1 49 45.8 90 28.3 76 22.7 127 35.9 17 7.52 127 17.5 118 11.4 133 9.25 129 18.7 130 7.27 78
TriFlow [95]83.5 7.77 105 13.7 127 9.28 99 8.98 104 15.7 100 9.30 121 7.65 57 12.4 89 5.84 39 22.0 64 20.9 89 41.1 4 30.9 117 27.7 121 45.7 73 28.4 88 21.3 93 36.3 61 6.85 75 15.5 88 10.4 38 8.69 94 17.4 85 7.23 72
Local-TV-L1 [65]83.6 8.46 122 12.6 101 10.4 126 9.68 119 16.0 110 8.93 113 7.56 44 11.2 56 5.84 39 23.1 117 20.4 65 46.0 143 30.6 61 27.1 49 45.9 111 30.1 138 19.1 21 39.9 145 6.72 49 14.9 55 10.5 69 8.13 24 16.1 13 7.58 117
Classic++ [32]84.3 7.49 88 12.5 98 9.11 88 8.07 80 15.2 89 6.67 63 7.89 82 12.6 95 6.04 73 22.3 87 20.7 82 42.2 91 30.6 61 27.2 64 45.7 73 29.0 118 21.0 81 37.6 127 6.81 68 15.2 74 10.5 69 8.62 85 17.4 85 7.46 103
Occlusion-TV-L1 [63]84.6 7.44 83 12.3 83 9.14 90 8.91 102 16.5 115 6.85 77 7.83 77 12.8 102 6.32 93 22.6 104 21.5 115 42.5 106 30.5 43 26.9 26 45.8 90 28.4 88 19.6 36 37.1 114 7.15 107 14.8 49 10.7 106 8.51 71 17.1 62 7.34 92
2D-CLG [1]86.1 8.44 120 12.3 83 10.6 130 11.9 137 18.0 136 12.3 141 8.94 129 13.9 126 7.33 130 23.1 117 21.2 107 41.3 19 30.5 43 26.9 26 45.8 90 27.6 19 19.2 25 36.2 46 7.14 105 17.2 116 10.5 69 8.37 53 16.5 34 7.20 65
Nguyen [33]86.1 9.74 137 12.6 101 12.4 141 12.3 139 18.6 142 11.1 133 8.27 109 14.8 134 6.69 114 23.4 125 21.7 117 41.8 59 30.3 25 26.8 21 45.3 26 27.4 6 19.6 36 35.7 13 7.24 115 18.3 126 10.5 69 8.37 53 17.0 54 7.22 71
FlowNetS+ft+v [112]86.5 7.81 107 11.7 53 9.63 107 9.77 121 16.8 119 9.16 116 8.06 97 13.4 116 6.36 98 22.1 73 20.7 82 42.1 88 30.8 94 27.4 93 45.8 90 27.7 23 19.4 30 36.3 61 7.01 97 16.4 108 10.5 69 8.51 71 17.2 73 7.33 89
Aniso-Texture [82]87.3 7.16 40 11.6 47 8.78 63 8.84 100 16.5 115 6.86 79 8.38 114 11.8 69 5.99 67 22.4 93 21.4 110 42.5 106 31.0 123 27.5 102 46.0 122 29.0 118 24.2 144 36.7 98 6.70 43 14.7 40 10.3 8 8.90 107 18.0 109 7.27 78
Adaptive [20]87.7 7.71 103 13.2 118 9.21 98 9.40 114 16.8 119 7.07 86 7.87 81 12.4 89 6.12 77 22.0 64 20.3 58 41.8 59 30.7 82 27.3 78 45.6 58 28.4 88 20.7 76 36.8 103 6.95 93 16.0 102 10.4 38 8.87 103 17.9 104 7.55 114
Shiralkar [42]87.8 7.48 87 12.8 108 8.80 69 9.00 107 15.8 103 6.65 60 8.52 118 16.1 139 6.84 119 23.4 125 22.3 125 41.6 40 30.0 8 27.0 36 44.5 6 28.7 108 21.1 87 37.1 114 7.49 125 18.7 134 10.6 96 8.64 88 17.7 95 6.93 11
CNN-flow-warp+ref [117]91.7 7.35 68 10.8 17 9.30 101 8.87 101 16.2 111 8.14 105 8.60 122 14.1 130 6.62 112 23.7 130 21.9 120 42.7 114 30.8 94 27.3 78 45.9 111 28.0 53 19.1 21 36.7 98 7.37 120 18.5 131 10.6 96 8.33 47 16.8 43 7.27 78
CRTflow [80]92.0 7.69 101 12.6 101 9.28 99 8.45 93 15.5 93 6.81 75 8.55 120 14.0 128 7.29 128 22.4 93 20.7 82 43.8 129 30.7 82 27.2 64 45.7 73 28.1 63 19.6 36 36.7 98 6.87 82 15.8 96 10.6 96 8.59 81 17.2 73 7.65 122
Black & Anandan [4]92.2 8.54 124 12.8 108 10.2 123 10.9 131 17.3 129 9.40 123 9.06 131 13.6 119 6.99 123 22.9 113 21.3 109 41.7 51 30.7 82 27.2 64 45.9 111 28.0 53 18.6 11 36.7 98 6.93 89 15.9 100 10.4 38 8.46 63 17.0 54 7.20 65
HBpMotionGpu [43]92.7 9.39 134 14.6 135 11.3 136 11.7 136 18.9 144 11.5 136 7.55 40 11.1 52 6.00 69 23.3 122 22.3 125 43.5 125 30.3 25 27.2 64 45.2 20 28.7 108 20.9 78 37.1 114 6.62 22 14.2 21 10.5 69 8.99 116 17.8 101 8.04 132
GraphCuts [14]92.8 8.65 126 14.1 133 9.83 115 8.28 84 14.2 62 9.28 120 9.89 141 10.6 30 7.38 131 23.0 114 21.1 100 42.5 106 30.3 25 27.3 78 44.7 9 27.2 3 21.4 95 34.7 2 7.42 123 17.8 121 11.0 121 9.32 132 18.9 134 7.66 123
StereoOF-V1MT [119]93.2 7.65 99 13.5 124 8.77 60 8.69 98 15.9 108 6.52 49 9.43 137 15.4 136 7.23 126 24.4 136 22.3 125 43.2 123 30.5 43 27.2 64 45.0 13 28.9 116 21.2 89 37.2 118 7.77 138 19.4 138 11.0 121 8.26 41 16.4 25 6.93 11
CBF [12]94.2 7.41 79 11.9 66 9.31 103 8.07 80 14.9 82 7.14 91 7.69 64 11.1 52 5.95 59 22.8 107 20.7 82 45.1 139 30.8 94 27.3 78 47.0 141 28.2 72 20.6 73 36.5 79 7.17 110 16.6 111 11.2 127 9.16 126 17.9 104 8.83 142
HBM-GC [105]94.2 7.91 108 12.6 101 9.75 112 7.51 63 13.9 54 6.80 74 7.29 16 9.43 3 5.94 58 22.0 64 19.7 39 42.3 94 32.1 144 28.6 141 48.0 146 30.0 135 24.6 147 37.8 129 7.14 105 14.8 49 11.6 137 8.95 113 17.7 95 8.28 135
TriangleFlow [30]94.7 7.79 106 13.0 114 9.16 94 8.36 89 15.5 93 6.69 64 8.20 103 11.9 72 6.59 109 22.5 99 21.0 95 42.5 106 30.1 10 27.0 36 45.0 13 28.9 116 22.6 124 36.5 79 7.42 123 18.3 126 11.0 121 9.49 136 19.3 138 7.47 107
Steered-L1 [118]94.9 7.06 28 12.2 80 8.59 34 7.40 57 14.3 65 6.83 76 8.48 117 11.7 66 6.69 114 22.8 107 20.9 89 42.7 114 31.2 131 28.1 135 45.8 90 28.3 76 21.2 89 36.7 98 7.25 116 17.8 121 10.9 117 9.00 117 18.3 123 7.58 117
Correlation Flow [75]95.0 7.05 26 11.7 53 8.32 4 8.29 86 15.6 97 6.56 52 7.64 55 10.8 41 5.89 52 22.2 80 20.1 49 42.9 120 31.7 138 27.7 121 49.9 151 29.6 129 23.8 140 37.2 118 7.62 133 19.0 136 11.3 130 9.22 128 18.6 129 7.51 113
IAOF2 [51]97.7 8.43 119 13.6 126 9.76 113 9.86 123 17.4 130 8.67 108 7.74 71 12.2 82 6.33 94 23.1 117 21.7 117 42.3 94 31.0 123 27.9 126 45.6 58 28.5 96 21.0 81 36.6 88 6.71 45 15.0 64 10.3 8 9.14 124 18.4 126 7.49 111
WRT [151]100.1 7.26 55 11.8 59 8.58 32 8.55 95 14.8 78 6.77 72 9.36 136 10.8 41 6.71 118 22.2 80 20.1 49 42.0 81 31.3 133 28.0 132 46.9 140 29.4 126 25.4 149 36.5 79 9.01 152 28.1 153 11.7 140 9.92 143 21.0 147 6.94 13
BriefMatch [124]100.2 7.38 77 12.0 68 8.85 76 7.71 67 14.5 73 7.86 102 8.77 127 11.7 66 7.25 127 24.2 134 22.0 122 46.2 144 30.8 94 27.4 93 46.1 127 31.8 149 21.7 102 41.3 149 6.85 75 15.3 78 10.7 106 8.51 71 17.1 62 7.56 116
SegOF [10]101.9 8.16 114 12.4 93 10.1 122 9.10 109 15.5 93 8.83 112 9.48 138 14.1 130 7.46 133 22.8 107 23.0 139 41.6 40 30.8 94 27.4 93 45.8 90 28.3 76 22.0 114 36.3 61 7.83 139 21.5 145 11.0 121 8.46 63 17.1 62 7.17 58
TV-L1-improved [17]103.0 7.55 93 12.9 111 9.15 93 9.36 112 16.9 121 7.19 93 8.63 124 12.2 82 6.92 121 22.2 80 21.0 95 42.3 94 30.8 94 27.5 102 45.6 58 28.5 96 21.4 95 36.8 103 7.38 121 18.6 133 10.7 106 8.94 111 18.0 109 7.75 125
BlockOverlap [61]103.3 8.81 128 12.4 93 11.1 135 10.0 126 15.8 103 10.6 130 7.84 78 10.4 21 6.59 109 23.3 122 20.4 65 46.3 145 31.9 141 27.9 126 48.8 149 30.3 142 19.7 43 39.8 144 7.08 102 14.5 33 11.7 140 8.35 51 16.1 13 8.60 140
OFRF [134]103.8 9.30 132 13.4 123 11.0 133 9.59 117 15.7 100 9.07 114 7.92 85 12.7 99 6.05 74 22.3 87 20.2 54 42.8 116 31.0 123 27.9 126 45.4 30 29.6 129 23.3 137 37.4 124 7.34 118 17.7 120 10.5 69 9.09 119 18.8 133 7.05 30
Dynamic MRF [7]104.5 7.29 61 13.1 115 8.69 47 8.20 83 16.3 112 6.74 68 9.18 133 16.4 142 7.22 125 24.5 138 23.1 140 44.4 133 30.3 25 27.2 64 45.1 17 29.2 125 23.4 138 37.2 118 7.64 134 19.8 141 10.7 106 9.14 124 18.0 109 7.48 110
LocallyOriented [52]105.0 8.08 111 13.1 115 9.72 110 9.73 120 17.0 124 7.88 103 8.34 111 12.8 102 6.34 95 23.0 114 22.1 123 43.0 121 30.6 61 27.2 64 45.6 58 30.0 135 21.9 109 38.5 139 7.02 98 15.8 96 10.5 69 9.05 118 18.4 126 7.39 99
AdaConv-v1 [126]105.3 9.81 139 13.9 130 11.6 139 12.1 138 17.6 132 16.0 148 11.4 148 16.1 139 13.1 151 26.5 147 24.4 148 45.3 140 28.4 4 24.4 3 44.6 7 28.4 88 18.1 8 37.7 128 7.74 137 16.3 106 13.1 152 8.25 39 15.1 6 10.1 151
SPSA-learn [13]106.0 8.28 117 12.9 111 9.95 119 9.92 124 16.3 112 9.49 124 9.15 132 12.8 102 7.30 129 23.1 117 20.5 72 41.6 40 30.8 94 27.5 102 45.7 73 28.0 53 20.4 61 36.3 61 8.81 151 27.1 152 11.8 142 10.0 145 21.0 147 7.20 65
Rannacher [23]106.1 7.69 101 13.2 118 9.32 104 9.37 113 16.9 121 7.28 94 8.67 125 13.0 106 6.91 120 22.2 80 21.1 100 42.4 104 30.8 94 27.5 102 45.7 73 28.5 96 21.2 89 36.9 108 7.35 119 18.5 131 10.7 106 8.90 107 18.0 109 7.78 127
Ad-TV-NDC [36]107.6 10.8 144 13.9 130 13.4 143 11.6 135 17.6 132 11.2 134 7.77 74 12.3 86 6.12 77 24.0 132 21.6 116 44.4 133 31.1 128 27.6 117 46.1 127 29.0 118 19.3 29 38.0 133 6.87 82 15.4 84 10.5 69 8.59 81 17.0 54 7.71 124
ACK-Prior [27]107.7 7.12 35 11.7 53 8.57 30 7.08 43 13.8 53 6.34 25 8.81 128 11.8 69 6.69 114 22.5 99 21.4 110 42.3 94 32.6 148 29.3 147 48.2 147 30.7 145 25.6 150 38.1 135 7.95 142 18.8 135 12.0 143 10.8 150 21.8 150 8.53 139
TVL1_ROB [139]109.1 10.2 143 13.8 128 12.5 142 12.6 145 19.1 145 11.9 138 8.01 91 13.7 122 6.37 99 23.6 128 21.4 110 42.3 94 30.8 94 27.3 78 46.0 122 28.6 102 20.2 52 37.1 114 7.29 117 17.6 119 10.7 106 8.49 68 17.1 62 7.40 100
Horn & Schunck [3]109.2 8.45 121 13.3 122 10.0 120 11.4 134 18.1 139 9.84 128 9.65 139 16.1 139 7.89 136 24.6 139 22.8 133 42.8 116 30.6 61 27.2 64 45.6 58 28.3 76 19.4 30 36.8 103 7.41 122 18.0 125 10.6 96 8.94 111 17.7 95 7.55 114
UnFlow [129]111.6 9.13 131 15.0 140 10.7 131 10.9 131 18.1 139 9.23 118 9.21 134 16.9 145 7.18 124 22.4 93 21.8 119 41.8 59 30.8 94 27.6 117 45.9 111 28.6 102 22.7 127 36.0 24 6.94 91 15.6 89 10.5 69 10.0 145 19.3 138 7.47 107
StereoFlow [44]112.3 13.8 149 20.2 152 14.0 145 14.1 149 21.3 152 12.0 140 7.79 76 13.3 115 5.98 64 22.4 93 20.9 89 42.1 88 33.7 152 32.3 152 46.1 127 30.5 143 31.8 153 36.3 61 6.63 25 14.7 40 10.4 38 9.98 144 21.0 147 7.42 102
TI-DOFE [24]112.7 11.8 146 14.7 137 14.8 147 13.9 148 20.3 149 13.5 146 9.26 135 16.5 144 7.69 135 25.1 141 22.8 133 43.3 124 30.2 15 27.1 49 45.4 30 28.4 88 19.6 36 36.8 103 7.22 113 17.2 116 10.7 106 9.21 127 18.1 117 7.59 120
Filter Flow [19]118.2 8.30 118 13.2 118 10.0 120 10.8 130 17.1 125 11.7 137 7.96 87 12.1 79 6.38 100 23.7 130 20.9 89 44.5 137 31.5 137 28.2 137 46.7 138 28.8 114 21.0 81 37.3 123 7.15 107 17.0 115 10.7 106 9.54 138 18.9 134 8.47 138
WOLF_ROB [149]118.2 8.87 129 16.2 145 9.71 109 9.97 125 16.9 121 7.77 100 8.60 122 13.0 106 6.39 101 23.2 121 23.5 141 43.7 126 30.9 117 27.9 126 45.8 90 30.1 138 22.8 130 38.2 137 7.54 128 19.0 136 10.7 106 9.12 123 18.7 130 7.06 31
NL-TV-NCC [25]120.9 7.56 94 12.7 107 8.62 40 8.00 78 15.4 91 6.74 68 8.46 116 13.1 108 6.70 117 24.2 134 24.0 146 45.0 138 32.8 149 28.3 140 52.0 154 29.4 126 24.1 143 36.9 108 7.89 141 17.9 123 12.4 148 10.1 147 19.9 143 8.92 143
Bartels [41]122.4 8.10 113 13.8 128 9.94 118 8.35 88 15.8 103 8.75 109 8.11 101 12.1 79 6.97 122 24.1 133 22.7 130 47.6 147 32.4 145 27.8 125 51.1 153 35.4 152 23.0 134 46.5 153 7.18 111 14.9 55 12.3 147 9.36 135 18.0 109 9.76 148
SILK [79]122.5 9.77 138 15.1 141 11.8 140 12.3 139 18.7 143 11.2 134 10.3 142 16.4 142 8.14 138 25.2 142 22.8 133 45.9 142 30.8 94 27.5 102 45.7 73 30.6 144 20.3 57 40.1 147 7.19 112 16.8 113 10.9 117 8.87 103 17.6 92 7.50 112
H+S_ROB [138]122.7 9.52 135 14.2 134 11.3 136 12.4 141 18.0 136 11.9 138 12.0 149 20.2 150 9.80 146 28.3 149 22.7 130 44.0 130 30.6 61 27.7 121 45.6 58 28.4 88 21.0 81 36.5 79 8.24 145 22.1 146 11.4 133 9.34 134 17.7 95 7.84 130
SLK [47]128.4 11.4 145 15.4 142 14.4 146 12.4 141 18.0 136 12.6 142 10.9 146 17.6 147 8.85 141 27.8 148 25.2 149 46.6 146 30.6 61 28.1 135 43.6 3 29.0 118 21.9 109 37.0 112 8.25 146 22.4 147 11.3 130 9.33 133 18.5 128 7.91 131
GroupFlow [9]129.3 10.1 142 16.9 147 11.3 136 10.4 128 17.8 135 10.0 129 10.8 145 17.5 146 9.21 143 23.6 128 23.9 143 42.5 106 31.9 141 29.3 147 46.2 133 30.1 138 24.5 146 37.8 129 7.55 129 18.4 129 10.6 96 9.52 137 19.8 142 6.89 8
Heeger++ [104]129.9 9.81 139 17.3 148 10.4 126 11.3 133 17.2 126 9.67 125 13.6 151 23.8 152 10.2 149 26.3 145 22.8 133 44.4 133 31.8 140 28.9 146 46.3 135 29.6 129 22.0 114 37.5 126 8.17 144 19.8 141 10.9 117 9.10 121 18.2 120 7.02 24
Learning Flow [11]131.4 8.21 115 14.8 138 9.74 111 9.78 122 17.6 132 8.11 104 9.68 140 15.5 137 7.56 134 25.0 140 24.3 147 45.4 141 31.9 141 28.7 144 47.3 142 29.4 126 22.0 114 37.8 129 7.49 125 18.3 126 10.9 117 10.2 148 20.2 145 8.31 136
2bit-BM-tele [98]132.4 8.61 125 13.5 124 10.5 128 10.0 126 17.5 131 9.73 126 8.26 108 11.5 60 7.40 132 24.4 136 22.7 130 48.1 148 32.5 147 28.6 141 50.2 152 34.7 151 24.3 145 44.9 151 9.35 153 26.2 151 13.8 153 9.25 129 17.3 78 10.2 152
FFV1MT [106]137.1 9.53 136 16.7 146 10.7 131 12.6 145 18.2 141 12.8 144 13.3 150 23.5 151 10.5 150 26.3 145 22.8 133 44.4 133 31.4 136 28.2 137 46.1 127 29.8 133 20.6 73 38.1 135 8.32 148 20.5 143 11.0 121 10.5 149 20.4 146 8.45 137
Adaptive flow [45]140.0 13.2 148 15.9 143 16.2 149 14.2 150 19.9 148 16.4 149 9.02 130 13.1 108 8.03 137 26.0 144 22.8 133 48.6 149 32.4 145 29.4 149 47.9 145 30.1 138 24.6 147 38.0 133 7.55 129 16.9 114 12.2 145 9.85 140 19.5 140 8.97 146
FOLKI [16]140.4 15.0 151 17.4 149 19.4 151 14.3 151 20.9 151 14.4 147 10.7 144 19.2 149 9.99 148 29.8 151 26.8 150 53.1 152 31.3 133 28.6 141 45.8 90 30.0 135 21.7 102 38.9 141 7.85 140 19.4 138 11.6 137 9.85 140 19.2 137 8.80 141
Pyramid LK [2]142.8 16.3 152 16.1 144 21.6 152 16.0 152 20.3 149 18.2 151 16.7 152 15.3 135 14.3 152 35.7 153 36.7 153 56.5 153 32.8 149 31.2 151 45.7 73 29.7 132 22.1 118 38.2 137 8.31 147 23.1 148 11.6 137 11.8 151 25.0 151 8.22 134
PGAM+LK [55]144.0 12.7 147 18.1 150 15.3 148 12.4 141 19.1 145 13.0 145 11.1 147 18.6 148 9.33 145 29.2 150 27.5 151 51.6 151 31.7 138 28.8 145 46.7 138 31.3 147 23.7 139 40.1 147 7.67 136 19.4 138 11.4 133 9.89 142 19.5 140 8.95 144
HCIC-L [99]144.9 18.0 153 18.7 151 23.1 153 12.7 147 17.2 126 17.0 150 10.5 143 14.4 133 8.49 140 25.7 143 23.9 143 44.3 132 33.2 151 29.8 150 49.0 150 31.7 148 26.4 152 39.2 143 7.98 143 18.4 129 12.4 148 12.4 152 25.3 153 8.96 145
Periodicity [78]151.6 14.9 150 20.8 153 18.2 150 20.1 153 22.0 153 21.5 153 17.7 153 26.4 153 16.1 153 29.8 151 34.8 152 49.7 150 35.4 153 34.2 153 48.7 148 37.1 153 25.8 151 47.4 154 8.68 150 23.6 149 12.2 145 13.3 153 25.1 152 11.6 153
AVG_FLOW_ROB [142]153.5 46.4 154 51.9 154 42.8 154 44.1 154 40.8 154 44.3 154 39.2 154 37.3 154 32.5 154 57.2 154 58.7 154 63.7 154 41.6 154 42.4 154 47.5 143 46.3 154 59.4 154 45.4 152 25.5 154 33.4 154 16.2 154 33.6 154 39.6 154 34.2 154
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

Methodtime*framescolor Reference and notes
[1] 2D-CLG 844 2 gray The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences.
[2] Pyramid LK 12 2 color A modification of Bouguet's pyramidal implementation of Lucas-Kanade.
[3] Horn & Schunck 49 2 gray A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data.
[4] Black & Anandan 328 2 gray A modern Matlab implementation of the Black & Anandan method by Deqing Sun.
[5] Brox et al. 18 2 color T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.)
[6] Fusion 2,666 2 color V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008.
[7] Dynamic MRF 366 2 gray B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.)
[8] Second-order prior 14 2 gray W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[9] GroupFlow 600 2 gray X. Ren. Local Grouping for Optical Flow. CVPR 2008.
[10] SegOF 60 2 color L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available.
[11] Learning Flow 825 2 gray D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008.
[12] CBF 69 2 color W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[13] SPSA-learn 200 2 color Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008.
[14] GraphCuts 1,200 2 color T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008.
[15] F-TV-L1 8 2 gray A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008.
[16] FOLKI 1.4 2 gray G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005.
[17] TV-L1-improved 2.9 2 gray A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision.
[18] DPOF 287 2 color C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.)
[19] Filter Flow 34,000 2 color S. Seitz and S. Baker. Filter flow. ICCV 2009.
[20] Adaptive 9.2 2 gray A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009.
[21] Complementary OF 44 2 color H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[22] Aniso. Huber-L1 2 2 gray M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision.
[23] Rannacher 0.12 2 gray J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009.
[24] TI-DOFE 260 2 gray C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009.
[25] NL-TV-NCC 20 2 color M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010.
[26] MDP-Flow 188 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010.
[27] ACK-Prior 5872 2 color K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010.
[28] LDOF 122 2 color T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011.
[29] p-harmonic 565 2 gray J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010.
[30] TriangleFlow 4200 2 gray B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010.
[31] Classic+NL 972 2 color D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code.
[32] Classic++ 486 2 gray A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010.
[33] Nguyen 33 2 gray D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011.
[34] Modified CLG 133 2 gray R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010.
[35] ComplOF-FED-GPU 0.97 2 color P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010.
[36] Ad-TV-NDC 35 2 gray M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010.
[37] Layers++ 18206 2 color D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010.
[38] OFH 620 3 color H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011.
[39] LSM 1615 2 color K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011.
[40] CostFilter 55 2 color C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011.
[41] Bartels 0.15 2 gray C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU.
[42] Shiralkar 600 2 gray M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242.
[43] HBpMotionGpu 1000 5 gray S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.)
[44] StereoFlow 7200 2 color G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772.
[45] Adaptive flow 121 2 gray T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011.
[46] TC-Flow 2500 5 color S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011.
[47] SLK 300 2 gray T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011.
[48] CLG-TV 29 2 gray M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code.
[49] SimpleFlow 1.7 2 color M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012.
[50] IAOF 57 2 gray D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011.
[51] IAOF2 56 2 gray D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011.
[52] LocallyOriented 9541 2 gray Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012.
[53] IROF-TV 261 2 color H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop.
[54] Sparse Occlusion 2312 2 color A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011.
[55] PGAM+LK 0.37 2 gray A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010.
[56] Sparse-NonSparse 713 2 color L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013.
[57] nLayers 36150 4 color D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012.
[58] IROF++ 187 2 color H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013.
[59] COFM 600 3 color M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013.
[60] Efficient-NL 400 2 color P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012.
[61] BlockOverlap 2 2 gray M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to MMSP 2012.
[62] Ramp 1200 2 color A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012.
[63] Occlusion-TV-L1 538 3 gray C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012.
[64] TV-L1-MCT 90 2 color M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012.
[65] Local-TV-L1 500 2 gray L. Raket. Local smoothness for global optical flow. ICIP 2012.
[66] ALD-Flow 61 2 color M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012.
[67] SIOF 234 2 color L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012.
[68] MDP-Flow2 342 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available.
[69] TCOF 1421 all gray J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013.
[70] LME 476 2 color W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013.
[71] NN-field 362 2 color L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[72] FESL 3310 2 color W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013.
[73] PMF 35 2 color J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013.
[74] FC-2Layers-FF 2662 4 color D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013.
[75] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[76] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[77] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[78] Periodicity 8000 4 color G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013.
[79] SILK 572 2 gray P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP.
[80] CRTflow 13 3 color O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013.
[81] SuperFlow 178 2 color Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507.
[82] Aniso-Texture 300 2 color Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267.
[83] Classic+CPF 640 2 gray Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013.
[84] S2D-Matching 1200 2 color Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479.
[85] AGIF+OF 438 2 gray Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015.
[86] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[87] NNF-Local 673 2 color Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014.
[88] EPPM w/o HM 2.5 2 color L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014.
[89] MLDP_OF 165 2 gray M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014.
[90] RFlow 20 2 gray S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014.
[91] SRR-TVOF-NL 32 all color P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014.
[92] 2DHMM-SAS 157 2 color M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission.
[93] WLIF-Flow 700 2 color Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014.
[94] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[95] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[96] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[97] AggregFlow 1642 2 color D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759.
[98] 2bit-BM-tele 124 2 gray R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013.
[99] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[100] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[101] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[102] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[103] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[104] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[105] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[106] FFV1MT 358 5 gray F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015.
[107] ROF-ND 4 2 color S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015.
[108] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[109] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[110] FlowFields 15 2 color C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015.
[111] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[112] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[113] CombBMOF 51 2 color M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.)
[114] PMMST 182 2 color F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015.
[115] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[116] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[117] CNN-flow-warp+ref 1.4 3 color D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016.
[118] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[119] StereoOF-V1MT 343 2 gray Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132.
[120] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[121] RNLOD-Flow 1040 2 gray C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. IEEE TIP 26(8):4055-4067, 2017.
[122] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[123] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[124] BriefMatch 0.068 2 gray G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62.
[125] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[126] AdaConv-v1 2.8 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[127] SepConv-v1 0.2 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[128] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[129] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[130] FlowFields+ 10.5 2 color C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017.
[131] IIOF-NLDP 150 2 color D.-H. Trinh, W. Blondel, and C. Daul. A general form of illumination-invariant descriptors in variational optical flow estimation. ICIP 2017.
[132] SuperSlomo 0.5 2 color Anonymous. (Interpolation results only.) Super SloMo: High quality estimation of multiple intermediate frames for video interpolation. CVPR 2018 submission 325.
[133] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[134] OFRF 90 2 color T. Mai, M. Gouiffes, and S. Bouchafa. Optical Flow refinement using iterative propagation under color, proximity and flow reliability constraints. Submitted to Signal, Image and Video Processing 2017.
[135] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
[136] FGIK 0.18 2 color Anonymous. (Interpolation results only.) Learning flow-guided interpolation kernels for video frame synthesis. ECCV 2018 submission 433.
[137] CtxSyn 0.07 2 color S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[138] H+S_ROB 5 2 color ROB 2018 baseline submission, based on: E. Meinhardt-Llopis, J. Sanchez, and D. Kondermann. Horn-Schunck optical flow with a multi-scale strategy. Image Processing On Line 3:151–172, 2013.
[139] TVL1_ROB 1 2 color ROB 2018 baseline submission, based on: J. Sanchez, E. Meinhardt-Llopis, and G. Facciolo. TV-L1 optical flow estimation. Image Processing On Line 3:137-150, 2013.
[140] DMF_ROB 10 2 color ROB 2018 baseline submission, based on: P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[141] JOF 657 2 gray C. Zhang, L. Ge, Z. Chen, M. Li, W. Liu, and H. Chen. Refined TV-L1 optical flow estimation using joint filtering. Submitted to IEEE TMM, 2018.
[142] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[143] LiteFlowNet 0.06 2 color T.-W. Hui, X. Tang, and C. C. Loy. LiteFlowNet: A lightweight convolutional neural network for optical flow estimation. CVPR 2018.
[144] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[145] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[146] FF++_ROB 17.43 2 color R. Schuster, C. Bailer, O. Wasenmueller, D. Stricker. FlowFields++: Accurate optical flow correspondences meet robust interpolation. ICIP 2018. Submitted to ROB 2018.
[147] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[148] PWC-Net_ROB 0.069 2 color D. Sun, X. Yang, M.-Y. Liu, and J. Kautz. PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. CVPR 2018.
[149] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[150] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
[151] WRT 9 2 color L. Mei, J. Lai, X. Xie, J. Zhu, and J. Chen. Illumination-invariance optical flow estimation using weighted regularization transform. Submitted to IEEE TCSVT 2018.
[152] EAI-Flow 2.1 2 color Anonymous. Hierarchical coherency sensitive hashing and interpolation with RANSAC for large displacement optical flow. CVIU 2018 submission 17-678.
[153] ContinualFlow_ROB 0.5 all color Anonymous. Continual Flow. ACCV 2018 submission 273.
[154] CyclicGen 0.088 2 color Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
* The "time" column lists the reported runtime in seconds on the "Urban" sequence. Note that these runtimes are not normalized by processor speed or type.