Optical flow evaluation results Statistics:     Average   SD   R2.5   R5.0   R10.0   A90   A95   A99  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
R2.5
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
NNF-Local [87]15.8 13.4 5 36.1 10 1.56 3 24.2 3 35.7 9 2.60 5 18.4 26 30.4 10 1.43 3 59.2 21 68.4 59 41.6 19 79.1 16 87.3 9 43.1 29 36.4 19 66.6 22 25.0 28 31.7 14 63.5 12 4.66 22 38.9 12 78.4 11 3.01 11
PH-Flow [101]18.0 13.7 24 37.1 38 1.77 31 24.3 6 35.5 8 2.58 3 18.5 29 30.6 13 1.54 16 58.8 2 66.8 7 41.6 19 79.0 9 87.2 7 42.9 16 36.3 12 67.1 63 24.6 11 31.6 4 63.7 21 4.64 13 39.0 20 78.6 20 3.10 39
NN-field [71]19.0 13.5 10 36.9 32 1.67 12 24.2 3 35.4 7 2.54 1 18.7 42 30.6 13 1.52 13 59.3 32 68.5 64 41.7 27 79.1 16 87.3 9 43.2 47 36.4 19 66.2 8 25.0 28 31.6 4 63.6 15 4.64 13 38.9 12 78.1 8 3.05 21
MDP-Flow2 [68]21.3 13.3 4 35.1 6 1.62 6 24.6 14 36.5 17 2.63 10 18.5 29 30.5 11 1.42 2 59.0 11 67.8 32 41.4 5 79.1 16 87.3 9 43.4 73 36.5 25 66.4 13 25.0 28 32.0 54 63.9 27 4.64 13 39.3 49 78.7 26 3.08 31
PMMST [114]22.0 13.4 5 35.0 5 1.70 18 25.1 35 37.1 29 2.73 20 18.5 29 30.5 11 1.39 1 58.9 5 67.4 17 41.5 13 79.2 37 87.4 17 43.4 73 36.3 12 66.2 8 24.9 20 31.8 24 63.8 23 4.67 25 39.2 41 78.7 26 3.09 35
COFM [59]22.7 13.6 18 36.0 8 1.89 56 24.6 14 36.4 15 2.71 18 18.5 29 30.3 8 1.59 27 58.8 2 66.8 7 41.1 3 79.0 9 87.4 17 42.6 10 35.8 5 67.2 72 24.1 3 31.2 3 61.6 3 4.89 100 38.5 5 78.1 8 3.34 104
Layers++ [37]23.5 14.0 59 37.5 50 1.91 60 24.3 6 35.3 6 2.75 22 18.3 24 31.0 23 1.56 21 59.2 21 67.5 22 41.7 27 79.2 37 87.4 17 43.1 29 36.4 19 66.5 19 25.0 28 31.6 4 63.2 6 4.60 3 38.7 8 77.7 7 3.12 45
AGIF+OF [85]24.5 13.9 49 37.5 50 1.67 12 24.6 14 36.5 17 2.68 14 18.1 19 31.0 23 1.61 32 58.9 5 66.9 9 41.4 5 79.2 37 87.5 46 43.1 29 36.6 37 67.2 72 25.0 28 31.8 24 63.6 15 4.60 3 39.0 20 78.6 20 2.98 7
HAST [109]24.6 13.7 24 36.2 15 1.93 67 24.7 22 37.0 27 2.77 31 18.8 45 32.2 49 1.66 42 59.1 15 67.9 40 41.4 5 79.0 9 87.4 17 42.6 10 36.3 12 66.9 42 24.6 11 31.6 4 63.3 8 4.71 41 39.0 20 78.4 11 3.06 24
Sparse-NonSparse [56]25.1 13.8 36 37.3 43 1.81 35 24.4 9 36.0 11 2.61 6 18.0 17 31.2 28 1.52 13 59.0 11 67.1 12 42.0 50 79.2 37 87.4 17 43.1 29 36.7 53 66.7 26 25.3 71 31.7 14 63.6 15 4.63 8 38.9 12 78.5 18 3.08 31
nLayers [57]25.6 13.9 49 36.7 27 1.85 46 24.5 11 36.1 12 2.76 25 17.7 10 30.0 7 1.44 4 59.2 21 67.6 24 41.6 19 79.3 64 87.5 46 43.3 56 36.4 19 66.8 36 25.1 43 31.7 14 63.2 6 4.72 48 38.7 8 77.6 5 3.03 14
ProbFlowFields [128]28.6 13.5 10 36.6 21 1.82 37 24.4 9 36.4 15 2.68 14 18.5 29 31.2 28 1.49 8 59.2 21 67.2 13 42.1 55 79.3 64 87.5 46 43.6 101 36.5 25 67.0 52 25.2 54 31.6 4 63.5 12 4.64 13 39.0 20 78.4 11 3.06 24
2DHMM-SAS [92]29.9 14.1 69 38.9 99 1.82 37 25.5 56 38.0 43 2.77 31 17.2 6 30.9 20 1.56 21 58.9 5 66.5 4 41.7 27 79.1 16 87.4 17 42.9 16 36.5 25 66.6 22 24.9 20 31.7 14 63.9 27 4.68 33 39.2 41 79.0 41 3.07 27
OFLAF [77]30.2 13.5 10 36.1 10 1.62 6 24.3 6 35.8 10 2.62 9 18.7 42 31.5 35 1.47 6 59.1 15 67.8 32 41.2 4 79.3 64 87.4 17 43.4 73 36.6 37 67.4 88 25.0 28 31.9 39 64.3 39 4.79 77 38.9 12 78.7 26 3.10 39
LSM [39]30.2 13.9 49 38.0 68 1.78 33 24.6 14 36.5 17 2.61 6 18.1 19 32.0 43 1.55 19 59.2 21 67.6 24 42.1 55 79.2 37 87.4 17 43.1 29 36.7 53 66.9 42 25.3 71 31.7 14 63.6 15 4.65 21 38.9 12 78.6 20 3.07 27
FGIK [136]30.7 13.9 49 36.8 30 2.59 114 26.6 93 39.4 82 5.00 126 10.0 3 24.3 3 1.92 81 60.9 115 67.4 17 40.1 1 76.4 2 85.1 2 39.6 2 33.0 2 59.9 2 22.7 1 31.0 2 60.0 2 4.23 1 37.1 2 76.4 2 2.77 2
FMOF [94]32.0 14.2 79 38.6 85 1.91 60 24.5 11 36.2 13 2.70 17 18.4 26 31.2 28 1.77 63 59.5 43 68.0 43 41.5 13 79.2 37 87.4 17 43.1 29 36.6 37 66.8 36 25.0 28 31.6 4 63.3 8 4.61 6 39.1 30 78.4 11 3.11 44
CombBMOF [113]33.5 13.6 18 36.4 18 1.71 21 24.5 11 36.9 26 2.58 3 18.1 19 31.5 35 1.81 71 59.5 43 68.2 49 41.6 19 79.1 16 87.3 9 43.0 22 36.8 65 66.5 19 25.0 28 33.9 140 65.2 93 4.68 33 39.1 30 78.4 11 2.92 4
ComponentFusion [96]33.8 13.4 5 36.1 10 1.72 24 24.6 14 36.8 25 2.57 2 18.9 52 32.9 63 1.69 45 59.1 15 67.8 32 41.4 5 79.2 37 87.4 17 43.6 101 36.5 25 66.3 10 25.1 43 32.0 54 64.8 66 4.76 71 39.1 30 78.7 26 3.10 39
CyclicGen [154]34.1 13.7 24 31.4 4 4.62 143 26.2 83 34.0 3 12.3 152 13.8 5 27.5 5 2.63 128 61.2 126 65.1 1 44.0 127 76.0 1 84.3 1 39.2 1 32.3 1 53.7 1 24.3 6 29.7 1 55.6 1 4.29 2 31.7 1 66.4 1 2.16 1
IROF++ [58]35.1 13.8 36 37.8 60 1.72 24 24.6 14 36.6 22 2.61 6 18.6 38 31.3 31 1.64 39 58.8 2 66.7 6 41.8 35 79.0 9 87.3 9 42.7 13 36.5 25 66.6 22 25.0 28 32.0 54 65.0 74 4.74 62 39.5 77 79.2 58 3.30 99
SepConv-v1 [127]37.3 9.23 1 28.0 2 1.08 1 20.5 2 32.4 2 3.35 92 8.95 2 20.5 2 2.08 100 60.8 113 66.9 9 44.2 129 79.1 16 87.1 5 43.2 47 35.6 3 62.4 3 25.1 43 32.2 84 62.3 4 5.34 136 37.6 3 76.4 2 3.28 95
Ramp [62]37.4 14.1 69 38.7 90 1.92 65 24.6 14 36.6 22 2.69 16 17.9 14 31.0 23 1.47 6 58.9 5 67.0 11 41.9 41 79.2 37 87.5 46 43.1 29 37.0 84 67.4 88 25.5 86 31.6 4 63.5 12 4.63 8 39.1 30 78.9 35 3.19 62
S2F-IF [123]38.1 13.5 10 36.6 21 1.70 18 24.9 29 37.9 39 2.77 31 18.8 45 32.7 59 1.54 16 59.1 15 67.7 28 41.6 19 79.3 64 87.5 46 43.3 56 36.5 25 67.1 63 25.0 28 31.9 39 64.7 62 4.74 62 39.3 49 79.1 51 3.10 39
TV-L1-MCT [64]39.2 14.5 102 39.7 122 1.86 50 25.2 38 37.8 37 2.78 34 17.3 7 31.1 27 1.59 27 58.9 5 66.6 5 41.6 19 79.1 16 87.4 17 42.9 16 36.8 65 66.4 13 25.6 93 31.8 24 64.0 33 4.73 52 39.1 30 79.0 41 3.20 69
FlowFields+ [130]39.9 13.5 10 37.0 35 1.69 17 25.0 32 38.2 49 2.78 34 18.9 52 33.3 75 1.55 19 59.1 15 67.6 24 41.9 41 79.3 64 87.5 46 43.3 56 36.6 37 67.2 72 25.1 43 31.8 24 64.5 53 4.67 25 39.3 49 79.2 58 3.07 27
RNLOD-Flow [121]40.1 13.9 49 37.9 65 1.86 50 25.2 38 37.9 39 2.78 34 19.0 59 32.1 45 1.78 65 59.2 21 67.8 32 41.5 13 79.1 16 87.4 17 43.1 29 36.7 53 66.8 36 25.2 54 31.9 39 64.2 36 4.75 67 39.2 41 79.0 41 3.06 24
FC-2Layers-FF [74]41.1 14.0 59 38.6 85 1.84 42 24.2 3 35.1 4 2.82 44 17.9 14 31.3 31 1.51 11 59.3 32 67.7 28 42.1 55 79.3 64 87.6 84 43.3 56 36.7 53 67.4 88 25.3 71 31.6 4 63.6 15 4.67 25 39.1 30 78.7 26 3.19 62
Classic+NL [31]41.8 14.2 79 38.8 93 1.98 70 24.6 14 36.5 17 2.65 12 17.7 10 30.9 20 1.51 11 59.2 21 67.5 22 42.2 68 79.2 37 87.5 46 43.3 56 37.0 84 67.1 63 25.5 86 31.7 14 63.6 15 4.67 25 39.2 41 79.0 41 3.18 59
Classic+CPF [83]42.4 14.1 69 38.3 79 1.74 27 24.9 29 37.1 29 2.73 20 17.6 9 31.4 33 1.60 30 59.0 11 67.3 15 41.4 5 79.3 64 87.6 84 43.3 56 36.9 73 67.9 115 25.2 54 31.9 39 64.3 39 4.64 13 39.3 49 79.2 58 3.04 17
FlowFields [110]43.0 13.6 18 37.1 38 1.74 27 25.0 32 38.1 44 2.75 22 18.8 45 33.2 73 1.53 15 59.4 37 68.0 43 42.3 76 79.3 64 87.5 46 43.2 47 36.5 25 67.0 52 25.0 28 31.8 24 64.7 62 4.69 36 39.4 64 79.3 66 3.13 47
EAI-Flow [152]43.7 13.7 24 36.3 17 1.91 60 25.7 69 39.1 72 3.01 66 19.0 59 33.4 77 1.67 43 58.9 5 67.2 13 41.4 5 79.2 37 87.3 9 43.0 22 36.9 73 66.7 26 25.2 54 32.0 54 65.0 74 4.78 75 39.3 49 79.1 51 3.03 14
NNF-EAC [103]45.6 14.2 79 37.3 43 2.09 82 25.3 44 37.6 35 2.76 25 18.9 52 30.6 13 1.61 32 59.8 68 68.5 64 43.3 119 79.1 16 87.3 9 43.1 29 36.5 25 66.5 19 25.0 28 32.1 68 64.3 39 4.73 52 39.4 64 79.0 41 3.14 49
CtxSyn [137]45.9 9.68 2 27.4 1 1.15 2 20.4 1 31.4 1 2.64 11 8.05 1 19.1 1 1.57 24 58.6 1 65.2 2 42.5 92 79.0 9 87.1 5 43.0 22 37.9 123 65.3 6 25.7 104 38.4 153 67.7 131 5.17 125 42.3 149 78.4 11 3.48 124
LME [70]46.1 13.5 10 36.1 10 1.62 6 25.3 44 37.8 37 3.44 98 19.0 59 32.8 61 1.63 37 59.0 11 67.8 32 41.5 13 79.7 137 87.9 131 44.4 136 36.5 25 67.0 52 24.9 20 32.0 54 64.2 36 4.66 22 39.0 20 78.6 20 3.09 35
S2D-Matching [84]46.5 14.2 79 38.9 99 1.96 68 25.3 44 37.9 39 2.76 25 17.5 8 31.0 23 1.60 30 59.3 32 67.4 17 42.8 101 79.2 37 87.5 46 43.2 47 36.9 73 67.3 82 25.4 81 31.8 24 63.8 23 4.64 13 39.1 30 78.6 20 3.21 75
WLIF-Flow [93]46.8 13.8 36 37.4 47 1.73 26 24.9 29 37.1 29 2.81 41 18.5 29 30.9 20 1.49 8 59.4 37 67.8 32 42.5 92 79.2 37 87.4 17 43.8 126 37.2 99 67.5 95 25.9 112 31.8 24 63.9 27 4.64 13 39.4 64 78.9 35 3.14 49
FESL [72]49.3 14.4 97 39.1 106 1.83 40 25.0 32 37.4 33 2.76 25 18.2 23 31.6 37 1.70 47 59.7 56 68.5 64 41.7 27 79.3 64 87.6 84 43.3 56 36.9 73 67.9 115 25.2 54 31.8 24 63.8 23 4.61 6 39.3 49 78.8 32 3.04 17
FF++_ROB [146]51.4 13.5 10 36.6 21 1.68 15 25.4 53 38.6 60 2.89 54 19.1 72 33.5 79 1.74 57 59.3 32 68.0 43 41.8 35 79.3 64 87.5 46 43.4 73 37.1 91 66.9 42 25.9 112 31.7 14 64.3 39 4.73 52 39.3 49 79.1 51 3.20 69
JOF [141]51.8 14.4 97 39.1 106 2.17 86 24.7 22 36.3 14 2.87 51 18.1 19 30.6 13 1.54 16 59.7 56 67.9 40 43.2 117 79.3 64 87.5 46 43.6 101 36.9 73 67.0 52 25.4 81 31.6 4 63.4 11 4.66 22 39.1 30 78.7 26 3.29 96
PGM-C [120]53.8 13.8 36 37.7 59 1.85 46 25.1 35 38.1 44 2.90 55 19.1 72 33.6 80 1.59 27 59.3 32 68.2 49 41.9 41 79.3 64 87.5 46 43.5 84 36.6 37 67.2 72 25.2 54 31.9 39 64.8 66 4.67 25 39.5 77 79.4 75 3.22 77
PMF [73]54.2 13.7 24 37.1 38 1.66 11 25.5 56 39.3 75 2.71 18 19.0 59 34.9 110 1.74 57 59.4 37 68.4 59 41.8 35 79.4 98 87.6 84 43.3 56 37.3 103 66.9 42 26.2 122 31.9 39 64.3 39 4.73 52 39.3 49 78.8 32 2.93 5
MDP-Flow [26]54.4 13.4 5 36.1 10 1.67 12 24.8 26 37.2 32 2.79 38 18.8 45 32.0 43 1.70 47 59.8 68 68.9 93 42.1 55 79.3 64 87.6 84 43.5 84 36.7 53 67.7 106 25.2 54 32.5 103 65.5 104 4.77 74 39.1 30 79.0 41 3.09 35
SuperFlow [81]56.2 13.8 36 36.2 15 2.27 100 26.3 87 38.7 63 4.39 114 19.1 72 33.1 70 1.99 92 59.6 48 67.7 28 42.2 68 79.4 98 87.5 46 43.7 117 36.1 10 65.9 7 24.8 17 31.7 14 64.5 53 4.80 85 38.9 12 78.9 35 3.19 62
Efficient-NL [60]56.8 14.3 91 38.7 90 1.77 31 25.2 38 37.6 35 2.76 25 19.0 59 31.8 38 2.08 100 59.8 68 68.7 82 41.4 5 79.1 16 87.4 17 43.0 22 36.9 73 68.4 130 24.6 11 32.1 68 64.7 62 4.69 36 40.1 114 79.8 103 3.14 49
TC-Flow [46]57.2 13.7 24 36.9 32 1.91 60 25.3 44 38.5 57 3.05 71 19.3 91 34.1 97 1.73 53 59.2 21 67.8 32 42.2 68 79.3 64 87.5 46 43.5 84 37.1 91 68.0 119 25.6 93 31.9 39 64.3 39 4.71 41 39.0 20 79.0 41 3.13 47
SVFilterOh [111]57.4 14.1 69 37.3 43 1.96 68 24.7 22 36.6 22 2.87 51 18.3 24 30.8 18 1.63 37 59.9 79 68.5 64 43.1 116 79.5 128 87.7 112 44.5 138 36.6 37 66.7 26 25.3 71 31.6 4 62.8 5 5.05 116 38.6 6 78.2 10 3.37 111
AggregFlow [97]59.5 14.5 102 38.3 79 2.20 94 25.7 69 38.5 57 3.23 86 18.6 38 30.8 18 1.44 4 59.7 56 68.4 59 41.7 27 79.4 98 87.6 84 43.8 126 37.5 109 66.9 42 26.4 127 31.8 24 64.2 36 4.70 40 38.9 12 78.4 11 3.08 31
DMF_ROB [140]59.7 13.9 49 37.0 35 1.98 70 25.8 72 39.0 69 2.96 59 19.8 123 35.0 112 2.12 106 59.7 56 68.2 49 41.9 41 79.3 64 87.4 17 43.7 117 36.3 12 66.4 13 25.0 28 32.1 68 64.4 50 4.93 103 39.2 41 79.1 51 3.07 27
EPPM w/o HM [88]59.8 13.4 5 36.6 21 1.61 4 25.5 56 39.3 75 2.76 25 19.4 98 35.7 126 1.99 92 59.6 48 69.3 107 41.9 41 79.2 37 87.4 17 43.1 29 37.0 84 67.5 95 25.3 71 32.8 114 65.0 74 4.85 94 39.4 64 79.0 41 3.04 17
Second-order prior [8]60.0 14.0 59 37.1 38 2.11 83 26.2 83 39.3 75 2.93 57 19.4 98 35.1 116 2.16 111 59.4 37 67.8 32 41.8 35 79.1 16 87.3 9 43.1 29 36.5 25 66.7 26 25.0 28 32.3 91 65.4 99 4.74 62 39.5 77 79.6 91 3.19 62
IROF-TV [53]60.4 14.0 59 38.1 70 1.99 72 24.7 22 36.5 17 2.65 12 19.1 72 34.2 98 1.78 65 59.1 15 67.4 17 42.4 86 79.4 98 87.7 112 43.6 101 36.0 6 66.4 13 24.4 7 32.1 68 64.6 58 4.75 67 39.8 99 79.9 109 3.35 107
PWC-Net_ROB [148]60.5 13.7 24 38.1 70 1.70 18 25.8 72 39.7 88 2.83 46 19.3 91 35.0 112 1.75 60 59.4 37 69.1 104 42.1 55 79.3 64 87.6 84 43.4 73 37.0 84 66.7 26 25.5 86 32.0 54 64.4 50 4.74 62 39.3 49 78.9 35 2.98 7
TF+OM [100]60.5 13.7 24 36.5 19 2.17 86 25.2 38 37.4 33 3.76 101 17.9 14 32.7 59 1.76 62 59.8 68 68.5 64 42.3 76 79.3 64 87.5 46 43.7 117 36.9 73 66.7 26 25.7 104 31.8 24 64.3 39 4.79 77 39.3 49 79.3 66 3.47 123
DeepFlow2 [108]60.5 13.9 49 36.6 21 2.07 80 25.6 64 38.4 53 3.08 73 19.1 72 33.6 80 1.70 47 59.6 48 68.5 64 41.9 41 79.4 98 87.5 46 43.7 117 36.7 53 66.3 10 25.4 81 31.9 39 64.7 62 4.67 25 39.4 64 79.4 75 3.26 91
SuperSlomo [132]60.7 12.3 3 30.3 3 2.92 127 24.8 26 35.2 5 6.60 141 13.6 4 25.5 4 2.01 94 60.5 105 65.5 3 43.9 125 78.3 3 86.6 3 41.9 4 37.4 107 64.3 4 26.4 127 35.3 151 63.9 27 5.33 135 40.3 123 77.6 5 3.51 127
CPM-Flow [116]60.8 13.8 36 37.8 60 1.87 54 25.1 35 38.2 49 2.93 57 19.0 59 33.4 77 1.61 32 59.6 48 68.7 82 42.1 55 79.3 64 87.5 46 43.5 84 36.8 65 66.9 42 25.5 86 32.0 54 65.2 93 4.68 33 39.5 77 79.5 84 3.25 87
ProFlow_ROB [147]61.4 13.6 18 36.5 19 1.85 46 25.3 44 38.4 53 2.96 59 18.9 52 32.9 63 1.62 36 59.7 56 69.6 123 42.5 92 79.4 98 87.6 84 43.4 73 36.6 37 66.7 26 25.1 43 32.1 68 65.1 83 4.71 41 39.7 91 79.7 99 3.20 69
TriFlow [95]62.5 14.2 79 39.0 103 2.20 94 26.6 93 39.3 75 4.59 118 19.0 59 33.7 83 1.71 52 59.9 79 68.7 82 41.4 5 79.2 37 87.5 46 43.5 84 36.7 53 67.1 63 25.2 54 31.8 24 63.9 27 4.69 36 39.1 30 79.0 41 3.23 83
LiteFlowNet [143]62.5 13.8 36 38.6 85 1.68 15 26.0 75 40.1 100 2.84 47 19.2 83 35.3 122 1.64 39 59.8 68 69.4 113 42.3 76 79.1 16 87.4 17 42.9 16 36.6 37 67.6 101 24.4 7 32.9 117 65.8 110 4.81 87 39.6 84 78.9 35 3.03 14
EpicFlow [102]62.6 13.8 36 37.6 54 1.87 54 25.5 56 38.9 66 2.96 59 18.9 52 33.7 83 1.64 39 59.5 43 68.5 64 42.3 76 79.4 98 87.6 84 43.5 84 36.5 25 67.5 95 24.9 20 32.0 54 65.1 83 4.74 62 39.4 64 79.4 75 3.22 77
DeepFlow [86]63.0 13.7 24 35.7 7 2.03 77 25.6 64 38.2 49 3.30 90 19.2 83 33.9 90 1.74 57 59.7 56 68.0 43 42.2 68 79.4 98 87.5 46 43.7 117 37.3 103 66.4 13 26.2 122 31.8 24 64.8 66 4.63 8 39.3 49 79.3 66 3.26 91
SimpleFlow [49]63.0 14.1 69 38.9 99 1.92 65 25.5 56 37.9 39 2.85 49 19.0 59 32.3 51 2.26 116 59.2 21 67.3 15 42.4 86 79.2 37 87.5 46 43.2 47 36.7 53 67.6 101 25.1 43 32.0 54 66.1 117 5.29 131 39.3 49 79.2 58 3.15 52
SRR-TVOF-NL [91]63.1 14.2 79 37.6 54 2.07 80 26.1 79 39.8 92 3.30 90 19.4 98 33.9 90 1.82 72 59.8 68 68.6 76 41.0 2 79.1 16 87.5 46 42.9 16 36.0 6 66.9 42 24.1 3 32.9 117 64.8 66 4.81 87 39.6 84 79.4 75 3.22 77
CostFilter [40]64.2 13.6 18 37.4 47 1.63 10 25.5 56 39.7 88 2.75 22 19.0 59 36.0 129 1.79 67 59.4 37 68.8 88 42.0 50 79.4 98 87.6 84 43.7 117 38.6 133 67.1 63 28.1 143 31.9 39 64.6 58 4.81 87 39.0 20 78.5 18 3.00 9
OFH [38]64.2 14.1 69 38.2 76 2.03 77 25.6 64 38.4 53 3.01 66 19.4 98 35.1 116 1.79 67 59.5 43 68.8 88 42.3 76 79.1 16 87.4 17 43.1 29 36.7 53 67.6 101 25.2 54 32.1 68 65.1 83 4.79 77 39.2 41 79.2 58 3.15 52
Complementary OF [21]64.8 13.7 24 37.8 60 1.71 21 25.2 38 38.6 60 2.81 41 19.8 123 33.7 83 2.38 121 59.9 79 69.2 105 42.8 101 79.2 37 87.5 46 43.1 29 36.6 37 67.4 88 25.2 54 32.3 91 65.4 99 4.79 77 38.8 10 78.9 35 3.29 96
RFlow [90]65.1 13.8 36 37.8 60 2.02 75 26.0 75 39.1 72 2.85 49 19.0 59 33.1 70 1.86 75 59.7 56 68.4 59 42.2 68 79.2 37 87.6 84 43.4 73 36.1 10 66.8 36 24.5 10 32.2 84 65.1 83 4.82 93 39.7 91 79.8 103 3.34 104
Aniso. Huber-L1 [22]65.3 14.3 91 38.5 83 2.17 86 26.6 93 39.5 85 3.21 85 19.2 83 32.5 57 1.83 74 59.7 56 68.7 82 41.9 41 79.2 37 87.4 17 43.2 47 36.3 12 67.1 63 24.6 11 32.2 84 64.9 72 4.71 41 39.7 91 79.6 91 3.24 86
DPOF [18]65.6 14.2 79 39.1 106 2.19 93 24.8 26 37.0 27 2.80 39 19.3 91 31.9 39 2.01 94 60.2 96 69.5 118 42.3 76 79.1 16 87.4 17 43.1 29 36.7 53 67.1 63 24.6 11 32.4 97 65.3 97 4.81 87 39.5 77 79.5 84 3.18 59
OAR-Flow [125]66.1 14.0 59 36.9 32 2.05 79 25.3 44 38.1 44 3.11 77 19.1 72 34.0 96 1.70 47 59.2 21 68.6 76 41.9 41 79.4 98 87.6 84 43.5 84 36.9 73 67.8 110 25.3 71 32.0 54 65.1 83 4.75 67 39.3 49 79.3 66 3.18 59
TC/T-Flow [76]66.1 14.3 91 38.8 93 1.84 42 25.3 44 38.6 60 2.81 41 18.9 52 32.4 56 1.58 25 59.9 79 69.5 118 42.1 55 79.3 64 87.5 46 43.5 84 37.1 91 68.0 119 25.2 54 32.1 68 65.2 93 4.81 87 39.2 41 79.4 75 3.00 9
Brox et al. [5]67.1 14.0 59 37.4 47 1.90 58 26.4 89 40.1 100 3.08 73 19.3 91 35.0 112 1.97 88 59.7 56 68.2 49 41.7 27 79.4 98 87.6 84 43.6 101 36.6 37 66.9 42 25.1 43 31.9 39 64.8 66 4.73 52 39.4 64 79.5 84 3.15 52
Sparse Occlusion [54]67.3 14.2 79 38.6 85 1.99 72 25.8 72 39.2 74 2.78 34 19.3 91 32.3 51 1.80 70 59.8 68 68.8 88 41.7 27 79.3 64 87.5 46 43.2 47 37.1 91 68.4 130 25.3 71 32.1 68 64.4 50 4.60 3 39.7 91 79.6 91 3.15 52
ContinualFlow_ROB [153]67.9 14.6 106 40.3 129 2.11 83 26.6 93 40.8 115 3.96 105 19.8 123 36.5 136 1.98 89 59.6 48 69.0 98 42.3 76 79.2 37 87.5 46 43.4 73 36.0 6 66.8 36 24.4 7 31.9 39 64.3 39 4.64 13 39.2 41 79.4 75 3.04 17
ComplOF-FED-GPU [35]68.7 14.0 59 38.0 68 1.91 60 25.3 44 38.5 57 2.90 55 20.2 130 34.6 106 2.16 111 59.5 43 68.5 64 42.5 92 79.2 37 87.4 17 43.2 47 36.6 37 67.4 88 25.0 28 32.2 84 65.4 99 4.75 67 39.7 91 79.8 103 3.19 62
Aniso-Texture [82]69.0 13.6 18 36.6 21 1.82 37 26.2 83 39.3 75 3.20 84 19.6 109 33.0 67 1.96 87 59.7 56 68.5 64 42.6 97 79.4 98 87.6 84 43.6 101 37.0 84 68.4 130 25.7 104 31.9 39 63.8 23 4.63 8 39.4 64 79.3 66 3.16 56
LFNet_ROB [150]69.0 13.8 36 37.5 50 1.80 34 27.0 108 41.7 128 3.08 73 19.6 109 35.5 123 1.87 76 59.2 21 67.4 17 41.7 27 79.1 16 87.4 17 42.8 15 36.8 65 67.3 82 24.8 17 33.2 124 65.7 109 4.79 77 40.4 129 80.0 113 3.26 91
GraphCuts [14]69.2 15.1 120 39.3 111 2.68 116 26.4 89 39.4 82 4.50 116 19.2 83 30.7 17 2.69 129 60.7 111 68.6 76 42.8 101 79.0 9 87.4 17 42.5 8 35.6 3 66.7 26 23.7 2 32.0 54 65.0 74 5.04 115 39.0 20 79.2 58 3.48 124
Fusion [6]69.8 13.8 36 38.4 82 1.84 42 25.3 44 38.1 44 2.88 53 19.1 72 32.2 49 1.90 80 60.9 115 69.8 124 41.8 35 79.1 16 87.9 131 42.1 5 36.0 6 67.8 110 24.1 3 32.7 111 66.3 121 4.88 99 39.5 77 80.4 130 3.26 91
Classic++ [32]70.5 14.0 59 38.1 70 2.17 86 25.7 69 38.8 64 2.96 59 19.3 91 33.9 90 1.93 83 59.7 56 67.9 40 42.8 101 79.2 37 87.5 46 43.3 56 37.4 107 67.0 52 26.6 131 31.8 24 64.3 39 4.78 75 39.4 64 79.5 84 3.36 108
DF-Auto [115]70.5 14.2 79 36.7 27 2.25 98 26.5 91 39.0 69 4.23 109 18.8 45 31.4 33 1.58 25 60.1 91 69.3 107 41.6 19 79.3 64 87.5 46 43.6 101 36.6 37 67.0 52 25.1 43 32.3 91 65.1 83 4.81 87 39.9 100 80.1 118 3.22 77
Steered-L1 [118]71.4 13.7 24 37.5 50 1.84 42 25.5 56 38.9 66 3.17 83 19.7 118 33.1 70 2.40 122 60.2 96 68.5 64 42.8 101 79.4 98 87.7 112 43.5 84 36.6 37 67.0 52 25.6 93 31.8 24 64.6 58 4.96 109 38.6 6 79.0 41 3.36 108
ALD-Flow [66]71.6 14.1 69 37.9 65 2.17 86 25.4 53 38.4 53 3.14 79 19.1 72 33.9 90 1.73 53 59.6 48 69.0 98 42.6 97 79.4 98 87.6 84 43.6 101 37.0 84 67.5 95 25.6 93 31.7 14 64.0 33 4.69 36 39.4 64 79.5 84 3.20 69
p-harmonic [29]72.5 13.5 10 36.7 27 1.85 46 26.7 103 39.9 96 3.25 88 19.4 98 35.2 118 2.10 103 60.1 91 68.7 82 42.2 68 79.3 64 87.5 46 43.3 56 36.7 53 66.7 26 25.3 71 32.6 107 65.8 110 4.76 71 39.4 64 79.5 84 3.17 57
AugFNG_ROB [144]76.3 14.6 106 39.7 122 2.31 102 27.3 115 41.3 122 4.30 113 19.5 105 37.8 140 1.92 81 59.8 68 68.8 88 42.1 55 79.4 98 87.7 112 43.3 56 36.3 12 66.4 13 24.9 20 32.7 111 65.6 107 4.73 52 38.8 10 78.6 20 2.84 3
Shiralkar [42]76.5 14.2 79 39.0 103 2.02 75 26.8 104 40.3 106 2.98 63 18.5 29 38.0 143 2.48 125 60.1 91 67.7 28 41.8 35 78.8 5 87.2 7 42.3 7 37.7 116 67.2 72 26.2 122 33.2 124 67.1 127 4.94 105 39.4 64 79.3 66 3.10 39
HBM-GC [105]79.4 14.7 110 39.4 117 2.41 108 25.4 53 38.1 44 3.07 72 18.0 17 29.8 6 1.56 21 59.8 68 68.2 49 42.8 101 80.1 143 88.0 137 45.9 147 37.5 109 68.2 126 26.1 120 31.9 39 63.3 8 4.99 111 39.3 49 79.1 51 3.30 99
FlowNet2 [122]79.5 15.9 134 41.4 133 2.76 119 27.1 110 40.2 103 4.29 111 19.6 109 34.3 100 1.88 77 60.0 85 70.2 128 42.0 50 79.4 98 87.7 112 43.3 56 36.4 19 66.3 10 24.9 20 32.1 68 64.5 53 4.71 41 39.6 84 79.2 58 3.08 31
SIOF [67]80.7 14.7 110 39.5 119 2.23 97 27.1 110 40.3 106 4.25 110 19.1 72 32.9 63 1.82 72 59.8 68 68.6 76 42.1 55 79.1 16 87.4 17 43.0 22 37.1 91 67.1 63 25.5 86 32.4 97 64.9 72 4.79 77 40.1 114 79.9 109 3.40 115
CLG-TV [48]80.8 14.3 91 38.8 93 2.17 86 26.6 93 39.8 92 3.24 87 19.5 105 33.9 90 2.11 105 60.0 85 69.0 98 42.4 86 79.3 64 87.6 84 43.5 84 36.6 37 66.9 42 25.1 43 32.1 68 65.1 83 4.71 41 39.9 100 80.0 113 3.20 69
MLDP_OF [89]81.0 13.9 49 38.1 70 1.81 35 25.6 64 38.9 66 2.80 39 18.8 45 32.3 51 1.61 32 59.6 48 68.3 56 42.3 76 79.3 64 87.6 84 43.9 130 39.6 146 68.7 137 28.5 145 33.0 122 65.3 97 5.09 119 39.6 84 79.2 58 3.51 127
EPMNet [133]81.1 15.7 132 42.3 137 2.55 111 26.9 105 39.5 85 4.05 107 19.6 109 34.3 100 1.88 77 60.1 91 70.4 134 42.0 50 79.4 98 87.7 112 43.3 56 36.5 25 66.9 42 24.9 20 32.1 68 64.5 53 4.71 41 40.0 107 79.3 66 3.05 21
Local-TV-L1 [65]84.0 14.9 115 37.3 43 3.21 133 27.3 115 39.5 85 4.67 119 18.9 52 32.3 51 1.70 47 61.3 128 68.6 76 47.1 145 79.3 64 87.6 84 43.6 101 39.0 138 66.7 26 28.9 147 31.7 14 64.3 39 4.79 77 39.3 49 79.1 51 3.41 118
F-TV-L1 [15]84.8 15.0 116 39.3 111 2.88 126 27.2 113 40.2 103 3.69 99 19.2 83 34.5 105 2.19 113 59.7 56 68.4 59 42.8 101 78.9 6 87.4 17 42.7 13 37.3 103 67.0 52 25.6 93 32.1 68 64.5 53 4.89 100 40.1 114 80.0 113 3.42 119
3DFlow [135]84.8 14.1 69 38.7 90 1.71 21 25.2 38 38.2 49 2.84 47 19.0 59 32.3 51 1.69 45 59.9 79 69.0 98 42.4 86 79.6 132 87.6 84 45.1 143 37.7 116 69.2 144 25.4 81 33.7 135 66.7 124 4.86 97 39.9 100 79.8 103 3.12 45
IAOF [50]84.9 15.5 128 39.2 110 2.93 129 29.4 133 43.0 135 5.18 130 17.8 12 33.0 67 2.04 97 60.8 113 68.9 93 42.2 68 79.2 37 87.4 17 43.3 56 36.8 65 67.2 72 25.1 43 32.7 111 65.6 107 4.67 25 40.0 107 80.0 113 3.20 69
OFRF [134]85.2 16.1 136 39.8 124 3.51 137 27.6 119 40.2 103 4.76 121 18.4 26 34.3 100 1.75 60 60.4 101 68.9 93 43.0 112 79.2 37 87.5 46 43.1 29 38.1 125 68.1 123 26.4 127 32.2 84 65.0 74 4.79 77 39.0 20 79.1 51 3.05 21
TCOF [69]85.6 14.4 97 39.3 111 1.83 40 27.3 115 40.9 118 3.35 92 18.7 42 32.1 45 1.50 10 60.2 96 70.2 128 42.1 55 79.3 64 87.6 84 43.2 47 36.9 73 68.5 133 24.8 17 33.3 126 65.8 110 4.72 48 41.2 140 81.4 143 3.46 121
BriefMatch [124]87.3 14.0 59 37.0 35 2.17 86 25.6 64 38.8 64 3.98 106 19.7 118 33.0 67 2.69 129 61.1 123 69.0 98 46.4 142 79.3 64 87.6 84 43.8 126 40.5 149 67.9 115 30.6 149 31.8 24 64.0 33 4.94 105 39.0 20 78.8 32 3.34 104
IIOF-NLDP [131]88.5 14.1 69 38.2 76 1.62 6 26.1 79 39.9 96 2.98 63 19.3 91 32.1 45 1.77 63 60.6 110 69.4 113 43.2 117 79.3 64 87.5 46 43.6 101 37.8 121 68.6 134 25.6 93 34.1 144 69.5 145 5.66 147 39.9 100 79.6 91 3.01 11
Adaptive [20]88.6 14.5 102 39.6 121 2.31 102 27.1 110 40.4 109 3.35 92 18.6 38 33.7 83 1.98 89 59.6 48 68.2 49 42.4 86 79.4 98 87.6 84 43.4 73 37.1 91 67.5 95 25.7 104 32.4 97 64.8 66 4.73 52 40.0 107 80.1 118 3.38 113
CNN-flow-warp+ref [117]89.0 13.8 36 36.0 8 2.35 105 26.6 93 39.8 92 3.83 102 20.0 128 35.5 123 2.34 118 60.9 115 68.9 93 43.0 112 79.4 98 87.6 84 43.7 117 36.8 65 67.0 52 25.6 93 32.1 68 66.2 119 4.94 105 39.4 64 79.5 84 3.19 62
FlowNetS+ft+v [112]89.7 14.7 110 38.1 70 2.80 122 27.5 118 40.6 114 4.81 123 19.6 109 34.9 110 2.07 99 60.1 91 69.5 118 42.2 68 79.4 98 87.7 112 43.4 73 36.6 37 67.1 63 25.2 54 32.0 54 65.4 99 4.73 52 39.6 84 79.7 99 3.21 75
SPSA-learn [13]90.9 14.8 114 37.8 60 2.72 118 27.6 119 40.1 100 4.71 120 20.5 132 33.7 83 2.97 136 60.4 101 67.6 24 41.5 13 79.3 64 87.5 46 43.5 84 36.8 65 67.2 72 25.2 54 33.4 128 70.8 152 6.21 152 39.7 91 79.6 91 3.19 62
AdaConv-v1 [126]91.8 16.5 140 42.3 137 4.36 142 30.4 139 43.8 139 9.06 148 20.6 135 36.3 133 4.45 148 64.5 146 71.3 144 45.3 137 78.4 4 86.7 4 42.2 6 36.3 12 64.9 5 25.4 81 32.5 103 63.7 21 5.53 142 38.0 4 77.4 4 3.53 130
LDOF [28]91.9 15.0 116 38.8 93 2.92 127 28.0 126 41.1 120 5.03 127 19.7 118 34.8 109 2.15 109 60.0 85 68.9 93 42.6 97 79.4 98 87.6 84 43.5 84 36.9 73 66.8 36 25.5 86 31.9 39 65.1 83 4.73 52 39.5 77 79.6 91 3.23 83
ResPWCR_ROB [145]92.0 13.9 49 38.2 76 1.89 56 26.5 91 40.4 109 3.42 97 19.9 127 35.6 125 1.95 85 60.5 105 70.2 128 43.3 119 78.9 6 87.4 17 42.5 8 42.1 150 67.7 106 32.5 150 33.9 140 65.4 99 4.85 94 40.1 114 79.7 99 3.17 57
ROF-ND [107]92.4 15.1 120 37.9 65 1.86 50 26.3 87 40.5 113 3.12 78 19.6 109 32.8 61 1.68 44 60.9 115 71.1 143 41.9 41 79.3 64 87.5 46 43.5 84 37.0 84 68.2 126 24.9 20 34.3 146 68.3 138 5.28 130 40.5 134 80.5 133 3.25 87
CRTflow [80]92.5 14.4 97 38.9 99 2.38 106 26.0 75 39.0 69 3.14 79 20.2 130 36.2 132 2.37 120 60.5 105 69.5 118 44.1 128 79.3 64 87.5 46 43.4 73 37.1 91 67.3 82 25.7 104 32.0 54 64.6 58 4.85 94 39.6 84 79.6 91 3.45 120
HBpMotionGpu [43]92.7 15.8 133 40.2 128 3.66 139 29.5 134 42.8 134 6.27 135 18.5 29 31.9 39 1.73 53 61.3 128 69.9 125 43.9 125 79.1 16 87.6 84 43.0 22 37.6 115 67.6 101 25.9 112 32.0 54 64.3 39 4.67 25 40.0 107 79.9 109 3.75 139
Occlusion-TV-L1 [63]92.9 14.3 91 39.1 106 2.21 96 26.6 93 40.0 98 3.14 79 19.2 83 34.2 98 2.15 109 60.0 85 68.5 64 42.8 101 79.3 64 87.5 46 43.6 101 37.5 109 67.0 52 26.2 122 32.9 117 65.1 83 5.16 124 40.0 107 79.8 103 3.30 99
Modified CLG [34]93.5 14.1 69 37.6 54 2.33 104 28.5 130 41.4 126 5.68 131 19.6 109 35.8 128 2.31 117 60.2 96 68.6 76 42.1 55 79.4 98 87.5 46 43.5 84 36.7 53 67.2 72 25.2 54 32.3 91 66.0 115 4.76 71 40.2 120 80.4 130 3.40 115
CBF [12]94.6 13.7 24 37.2 42 2.15 85 26.0 75 39.4 82 3.28 89 19.1 72 32.1 45 1.79 67 61.0 121 70.0 127 45.8 139 79.6 132 87.8 129 44.9 142 36.8 65 67.4 88 25.2 54 32.2 84 65.5 104 5.22 127 40.0 107 80.2 125 3.99 145
TriangleFlow [30]96.8 14.7 110 40.0 127 2.29 101 26.6 93 40.8 115 3.03 69 19.4 98 33.3 75 2.10 103 60.4 101 69.9 125 42.8 101 79.0 9 87.4 17 42.6 10 37.7 116 68.3 129 25.3 71 33.1 123 67.8 133 5.24 129 40.4 129 80.6 135 3.32 103
2D-CLG [1]97.4 14.5 102 37.6 54 2.76 119 29.8 136 42.4 131 6.69 142 19.7 118 35.2 118 2.74 132 60.7 111 68.7 82 41.5 13 79.4 98 87.7 112 43.5 84 36.6 37 67.0 52 25.1 43 32.5 103 66.7 124 4.90 102 40.2 120 80.1 118 3.25 87
ACK-Prior [27]97.9 13.8 36 38.1 70 1.74 27 25.5 56 39.3 75 2.82 44 19.6 109 33.8 89 2.45 124 60.5 105 70.3 131 42.3 76 80.2 144 88.0 137 45.8 146 38.2 126 67.8 110 26.9 135 32.6 107 66.2 119 5.35 137 38.9 12 79.7 99 3.60 135
Nguyen [33]97.9 15.6 129 38.5 83 3.62 138 30.1 138 43.2 136 6.04 133 19.6 109 36.3 133 2.25 115 61.1 123 69.4 113 42.0 50 79.2 37 87.5 46 43.1 29 36.4 19 67.2 72 24.7 16 34.3 146 67.4 130 5.00 112 40.2 120 80.3 126 3.29 96
SegOF [10]98.0 14.2 79 36.8 30 2.54 110 27.0 108 40.0 98 4.18 108 21.1 139 36.1 131 3.15 141 60.5 105 70.7 139 41.6 19 79.4 98 87.6 84 43.6 101 36.9 73 68.2 126 25.2 54 32.5 103 68.0 137 5.31 134 39.6 84 79.4 75 3.22 77
BlockOverlap [61]98.1 15.1 120 37.6 54 3.31 135 27.7 122 39.3 75 5.73 132 18.6 38 30.3 8 2.09 102 60.9 115 68.2 49 47.1 145 80.2 144 87.9 131 46.5 148 39.0 138 67.3 82 28.4 144 31.9 39 63.9 27 5.09 119 39.7 91 79.3 66 3.55 131
IAOF2 [51]99.1 15.6 129 41.3 132 2.58 113 27.6 119 41.4 126 4.29 111 17.8 12 33.6 80 1.94 84 61.2 126 70.8 140 42.8 101 79.4 98 87.7 112 43.3 56 37.2 99 67.5 95 25.6 93 32.3 91 65.0 74 4.63 8 40.6 135 80.4 130 3.40 115
TV-L1-improved [17]100.4 14.2 79 38.8 93 2.25 98 26.9 105 40.3 106 3.40 96 19.5 105 33.9 90 2.44 123 59.9 79 69.0 98 42.7 100 79.4 98 87.7 112 43.5 84 37.2 99 67.6 101 25.8 109 32.1 68 66.1 117 5.05 116 39.9 100 80.0 113 3.46 121
Correlation Flow [75]101.0 14.0 59 38.3 79 1.61 4 26.2 83 39.8 92 2.98 63 19.1 72 31.9 39 1.73 53 60.4 101 69.4 113 43.6 122 80.2 144 87.9 131 47.8 151 38.0 124 68.7 137 26.0 117 33.4 128 67.2 128 5.29 131 40.1 114 80.3 126 3.39 114
Dynamic MRF [7]101.2 13.9 49 38.6 85 1.90 58 26.1 79 40.4 109 3.08 73 20.0 128 37.7 139 2.73 131 61.3 128 69.3 107 44.6 132 79.1 16 87.6 84 43.0 22 37.7 116 68.0 119 25.9 112 32.6 107 67.2 128 5.08 118 40.4 129 80.5 133 3.49 126
StereoOF-V1MT [119]101.2 14.6 106 39.9 125 2.00 74 27.2 113 41.9 129 3.04 70 20.9 138 37.8 140 2.85 135 61.3 128 68.3 56 43.8 123 79.2 37 87.5 46 42.9 16 38.2 126 67.8 110 26.3 126 33.8 136 68.5 139 5.36 138 40.0 107 79.4 75 3.09 35
WRT [151]102.5 14.3 91 39.0 103 1.76 30 26.6 93 39.7 88 3.14 79 20.8 136 31.9 39 2.57 126 60.2 96 69.5 118 42.3 76 79.6 132 87.7 112 44.4 136 37.8 121 69.5 149 25.5 86 34.2 145 71.4 153 6.06 150 39.7 91 79.8 103 2.95 6
Rannacher [23]104.2 14.4 97 39.3 111 2.38 106 26.9 105 40.4 109 3.36 95 19.5 105 34.6 106 2.58 127 59.8 68 68.8 88 42.8 101 79.4 98 87.7 112 43.6 101 37.2 99 67.8 110 25.8 109 32.2 84 66.0 115 5.02 113 39.9 100 79.9 109 3.56 132
Black & Anandan [4]104.5 15.3 124 38.8 93 2.96 131 28.4 128 40.9 118 4.78 122 20.5 132 35.2 118 2.74 132 60.9 115 69.3 107 42.1 55 79.4 98 87.7 112 43.6 101 37.1 91 66.6 22 25.6 93 32.9 117 65.9 114 4.72 48 40.3 123 80.3 126 3.25 87
LocallyOriented [52]106.9 15.0 116 40.3 129 2.53 109 27.7 122 41.3 122 3.86 103 19.4 98 34.4 103 1.95 85 61.1 123 70.6 136 43.3 119 79.2 37 87.5 46 43.3 56 39.1 142 68.1 123 27.6 141 32.9 117 65.8 110 4.72 48 40.6 135 80.6 135 3.37 111
UnFlow [129]108.8 16.0 135 42.8 140 2.87 125 30.6 142 45.2 148 4.52 117 21.3 142 39.4 146 2.81 134 60.0 85 68.3 56 42.1 55 79.2 37 87.4 17 43.5 84 37.5 109 68.0 119 25.2 54 33.8 136 65.1 83 4.98 110 43.2 152 81.8 147 3.67 137
Filter Flow [19]113.3 15.0 116 39.4 117 2.78 121 28.4 128 40.8 115 6.31 136 18.5 29 32.9 63 2.14 107 61.7 134 69.3 107 45.3 137 79.7 137 88.0 137 44.5 138 37.3 103 67.7 106 26.1 120 32.1 68 65.2 93 4.93 103 40.3 123 80.7 138 3.97 144
TVL1_ROB [139]114.6 16.2 137 39.3 111 4.14 141 30.4 139 43.4 137 6.39 137 19.0 59 35.0 112 2.05 98 61.4 133 69.2 105 43.0 112 79.5 128 87.7 112 43.8 126 37.5 109 67.2 72 26.0 117 32.4 97 66.3 121 4.95 108 40.1 114 80.3 126 3.30 99
StereoFlow [44]114.6 22.8 152 51.1 153 4.80 144 36.2 152 51.1 153 6.57 139 19.2 83 34.6 106 1.89 79 60.0 85 68.5 64 42.4 86 80.3 147 89.1 152 43.9 130 39.0 138 74.1 153 25.3 71 32.1 68 65.0 74 4.73 52 40.3 123 80.9 139 3.36 108
WOLF_ROB [149]119.2 15.6 129 41.7 135 2.64 115 27.8 124 41.3 122 3.72 100 19.7 118 35.2 118 2.02 96 61.3 128 71.8 145 44.5 131 79.4 98 87.8 129 43.7 117 38.8 136 67.9 115 27.5 140 34.4 148 67.7 131 5.09 119 39.9 100 79.6 91 3.22 77
Ad-TV-NDC [36]119.5 17.2 143 39.9 125 5.26 146 29.6 135 42.1 130 6.18 134 19.2 83 33.7 83 1.98 89 62.4 136 70.3 131 45.2 136 79.6 132 87.9 131 43.9 130 38.3 129 67.3 82 27.2 139 32.3 91 65.5 104 4.80 85 40.3 123 80.1 118 3.58 134
Bartels [41]120.3 14.6 106 39.3 111 2.80 122 26.1 79 39.7 88 4.45 115 19.0 59 33.2 73 2.14 107 62.1 135 70.9 141 48.9 147 80.7 151 88.1 140 49.2 153 43.7 152 69.0 143 34.8 153 32.4 97 65.0 74 5.76 148 40.4 129 80.1 118 4.26 147
TI-DOFE [24]122.5 17.9 146 43.0 141 5.41 147 32.3 148 46.2 150 7.98 146 20.5 132 38.1 144 2.97 136 63.1 143 70.6 136 43.8 123 79.1 16 87.6 84 43.1 29 37.7 116 67.4 88 25.8 109 33.4 128 67.8 133 5.09 119 41.6 144 81.5 145 3.68 138
Horn & Schunck [3]123.1 15.3 124 40.4 131 2.69 117 29.0 131 42.7 132 5.10 128 21.1 139 37.9 142 3.33 142 62.5 138 70.3 131 43.0 112 79.3 64 87.7 112 43.6 101 37.5 109 67.3 82 25.9 112 33.9 140 68.5 139 5.03 114 41.2 140 81.2 142 3.57 133
GroupFlow [9]126.2 16.8 142 43.4 142 3.43 136 29.1 132 43.9 140 5.11 129 22.2 145 39.3 145 3.53 143 61.0 121 70.6 136 42.5 92 79.7 137 88.1 140 44.0 133 39.0 138 69.4 148 26.8 134 32.8 114 66.8 126 4.87 98 40.4 129 80.1 118 3.01 11
2bit-BM-tele [98]127.7 15.3 124 39.5 119 3.22 134 27.8 124 41.2 121 4.90 124 18.8 45 32.5 57 2.34 118 62.4 136 71.0 142 49.0 148 80.6 149 88.2 145 47.9 152 42.8 151 69.3 147 32.9 151 33.4 128 70.0 149 6.77 153 40.3 123 79.4 75 4.33 150
SLK [47]128.7 17.4 144 43.9 145 4.90 145 30.5 141 44.0 141 7.18 144 22.5 146 39.8 147 4.15 147 64.5 146 70.5 135 46.7 143 78.9 6 87.7 112 41.6 3 38.5 131 68.8 139 26.0 117 33.8 136 70.1 151 5.50 141 41.6 144 81.4 143 3.91 142
SILK [79]129.7 16.3 138 42.0 136 4.01 140 29.9 137 43.5 138 6.44 138 21.6 143 37.4 138 3.55 144 62.6 139 69.4 113 47.0 144 79.3 64 87.7 112 43.6 101 39.9 147 68.1 123 29.2 148 32.8 114 67.8 133 5.14 123 40.6 135 80.6 135 3.52 129
NL-TV-NCC [25]130.0 15.1 120 41.6 134 1.86 50 26.6 93 41.3 122 3.02 68 20.8 136 35.7 126 2.24 114 63.2 144 73.9 149 45.9 140 81.3 153 88.7 151 49.9 154 38.6 133 69.8 151 25.6 93 37.6 152 69.5 145 5.62 145 42.4 150 82.1 150 4.00 146
HCIC-L [99]131.4 23.2 153 49.0 152 11.0 153 32.1 147 44.4 142 9.93 149 23.2 148 36.4 135 3.02 138 64.4 145 72.1 146 44.9 133 80.6 149 88.5 149 46.6 149 39.1 142 68.9 141 27.1 137 32.4 97 65.0 74 5.53 142 39.1 30 79.3 66 3.65 136
H+S_ROB [138]132.7 16.5 140 43.7 143 2.94 130 31.9 145 44.6 143 6.58 140 24.0 149 42.8 150 4.50 149 65.7 149 69.3 107 44.4 130 79.4 98 88.2 145 43.1 29 38.5 131 68.6 134 25.6 93 34.6 149 70.0 149 5.57 144 43.1 151 81.5 145 3.83 141
Heeger++ [104]133.2 17.5 145 47.2 151 2.80 122 31.1 144 44.9 146 4.93 125 26.6 151 47.7 152 4.79 150 62.6 139 68.0 43 45.1 134 79.8 141 88.4 148 44.1 134 39.1 142 68.9 141 26.5 130 34.8 150 67.9 136 5.23 128 41.5 143 80.1 118 3.23 83
FFV1MT [106]135.3 16.4 139 44.7 147 3.13 132 31.9 145 44.7 144 7.15 143 25.4 150 45.6 151 5.04 151 62.6 139 68.0 43 45.1 134 79.6 132 87.9 131 44.1 134 38.9 137 67.7 106 27.1 137 34.0 143 68.5 139 5.29 131 41.8 147 81.0 140 4.48 152
Learning Flow [11]135.3 15.3 124 42.7 139 2.55 111 28.0 126 42.7 132 3.95 104 21.1 139 37.0 137 3.03 140 63.0 142 73.3 148 46.2 141 80.0 142 88.2 145 45.1 143 38.2 126 68.6 134 26.7 132 33.8 136 68.5 139 5.21 126 41.9 148 82.3 151 3.95 143
Adaptive flow [45]138.8 19.6 148 44.1 146 6.76 148 32.8 149 45.7 149 10.2 150 19.8 123 34.4 103 3.02 138 64.7 148 72.1 146 49.4 149 80.3 147 88.6 150 45.6 145 38.3 129 69.2 144 26.7 132 32.6 107 66.5 123 5.45 140 41.0 138 81.1 141 3.75 139
Pyramid LK [2]140.8 21.2 151 43.7 143 10.7 152 33.1 151 45.1 147 11.9 151 27.3 152 36.0 129 6.46 152 70.7 153 78.5 153 57.7 153 79.5 128 88.1 140 43.3 56 38.6 133 68.8 139 27.0 136 33.5 133 68.8 143 6.00 149 41.0 138 81.8 147 4.31 149
FOLKI [16]144.5 20.9 149 46.0 148 9.48 151 32.8 149 47.4 151 8.75 147 21.6 143 40.7 148 4.10 146 67.2 152 74.2 151 53.7 152 79.5 128 88.1 140 43.7 117 39.2 145 69.2 144 27.9 142 33.4 128 69.5 145 5.65 146 41.7 146 82.3 151 4.28 148
PGAM+LK [55]144.9 19.4 147 46.4 149 6.81 149 30.9 143 44.8 145 7.52 145 22.7 147 40.9 149 3.99 145 66.6 151 73.9 149 52.4 151 79.7 137 88.1 140 44.5 138 40.2 148 69.7 150 28.8 146 33.3 126 69.3 144 5.42 139 41.4 142 81.8 147 4.36 151
Periodicity [78]151.0 21.0 150 47.0 150 9.32 150 38.1 153 48.1 152 14.7 153 29.8 153 47.9 153 9.27 153 66.0 150 77.1 152 50.7 150 80.8 152 89.3 153 46.8 150 45.1 153 70.6 152 35.5 154 33.5 133 69.6 148 6.07 151 43.5 153 84.0 153 6.51 153
AVG_FLOW_ROB [142]153.2 51.4 154 76.8 154 29.6 154 67.5 154 74.0 154 36.6 154 51.8 154 59.9 154 20.1 154 84.7 154 90.1 154 64.7 154 81.8 154 91.0 154 44.5 138 51.7 154 87.4 154 33.4 152 57.5 154 81.8 154 10.1 154 63.2 154 86.1 154 26.5 154
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.