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]12.0 13.4 3 36.1 7 1.56 2 24.2 2 35.7 6 2.60 5 18.4 21 30.4 6 1.43 3 59.2 18 68.4 49 41.6 17 79.1 11 87.3 5 43.1 21 36.4 14 66.6 16 25.0 21 31.7 11 63.5 9 4.66 19 38.9 9 78.4 8 3.01 6
PH-Flow [101]13.7 13.7 19 37.1 29 1.77 23 24.3 5 35.5 5 2.58 3 18.5 23 30.6 9 1.54 16 58.8 1 66.8 4 41.6 17 79.0 5 87.2 3 42.9 11 36.3 9 67.1 50 24.6 7 31.6 2 63.7 18 4.64 11 39.0 17 78.6 16 3.10 26
NN-field [71]14.9 13.5 8 36.9 25 1.67 10 24.2 2 35.4 4 2.54 1 18.7 36 30.6 9 1.52 13 59.3 28 68.5 54 41.7 25 79.1 11 87.3 5 43.2 37 36.4 14 66.2 4 25.0 21 31.6 2 63.6 12 4.64 11 38.9 9 78.1 5 3.05 12
MDP-Flow2 [68]16.9 13.3 2 35.1 3 1.62 5 24.6 13 36.5 13 2.63 10 18.5 23 30.5 7 1.42 2 59.0 9 67.8 25 41.4 4 79.1 11 87.3 5 43.4 60 36.5 20 66.4 9 25.0 21 32.0 48 63.9 24 4.64 11 39.3 42 78.7 21 3.08 18
PMMST [114]17.6 13.4 3 35.0 2 1.70 13 25.1 31 37.1 25 2.73 19 18.5 23 30.5 7 1.39 1 58.9 4 67.4 13 41.5 11 79.2 30 87.4 12 43.4 60 36.3 9 66.2 4 24.9 15 31.8 20 63.8 20 4.67 21 39.2 36 78.7 21 3.09 22
COFM [59]17.8 13.6 14 36.0 5 1.89 46 24.6 13 36.4 11 2.71 17 18.5 23 30.3 4 1.59 24 58.8 1 66.8 4 41.1 2 79.0 5 87.4 12 42.6 6 35.8 3 67.2 59 24.1 2 31.2 1 61.6 1 4.89 84 38.5 3 78.1 5 3.34 83
Layers++ [37]18.3 14.0 46 37.5 41 1.91 49 24.3 5 35.3 3 2.75 21 18.3 19 31.0 18 1.56 19 59.2 18 67.5 16 41.7 25 79.2 30 87.4 12 43.1 21 36.4 14 66.5 13 25.0 21 31.6 2 63.2 4 4.60 1 38.7 6 77.7 4 3.12 32
AGIF+OF [85]19.7 13.9 39 37.5 41 1.67 10 24.6 13 36.5 13 2.68 13 18.1 15 31.0 18 1.61 29 58.9 4 66.9 6 41.4 4 79.2 30 87.5 37 43.1 21 36.6 31 67.2 59 25.0 21 31.8 20 63.6 12 4.60 1 39.0 17 78.6 16 2.98 3
Sparse-NonSparse [56]19.9 13.8 28 37.3 34 1.81 26 24.4 8 36.0 8 2.61 6 18.0 13 31.2 23 1.52 13 59.0 9 67.1 9 42.0 44 79.2 30 87.4 12 43.1 21 36.7 44 66.7 20 25.3 60 31.7 11 63.6 12 4.63 6 38.9 9 78.5 14 3.08 18
HAST [109]20.0 13.7 19 36.2 12 1.93 55 24.7 21 37.0 23 2.77 30 18.8 39 32.2 42 1.66 37 59.1 13 67.9 33 41.4 4 79.0 5 87.4 12 42.6 6 36.3 9 66.9 32 24.6 7 31.6 2 63.3 6 4.71 36 39.0 17 78.4 8 3.06 13
nLayers [57]20.5 13.9 39 36.7 21 1.85 37 24.5 10 36.1 9 2.76 24 17.7 6 30.0 3 1.44 4 59.2 18 67.6 18 41.6 17 79.3 54 87.5 37 43.3 46 36.4 14 66.8 27 25.1 35 31.7 11 63.2 4 4.72 41 38.7 6 77.6 3 3.03 8
ProbFlowFields [128]23.0 13.5 8 36.6 16 1.82 28 24.4 8 36.4 11 2.68 13 18.5 23 31.2 23 1.49 8 59.2 18 67.2 10 42.1 48 79.3 54 87.5 37 43.6 84 36.5 20 67.0 40 25.2 44 31.6 2 63.5 9 4.64 11 39.0 17 78.4 8 3.06 13
2DHMM-SAS [92]24.4 14.1 56 38.9 84 1.82 28 25.5 49 38.0 39 2.77 30 17.2 2 30.9 15 1.56 19 58.9 4 66.5 1 41.7 25 79.1 11 87.4 12 42.9 11 36.5 20 66.6 16 24.9 15 31.7 11 63.9 24 4.68 28 39.2 36 79.0 33 3.07 16
LSM [39]24.5 13.9 39 38.0 58 1.78 25 24.6 13 36.5 13 2.61 6 18.1 15 32.0 37 1.55 18 59.2 18 67.6 18 42.1 48 79.2 30 87.4 12 43.1 21 36.7 44 66.9 32 25.3 60 31.7 11 63.6 12 4.65 18 38.9 9 78.6 16 3.07 16
OFLAF [77]24.8 13.5 8 36.1 7 1.62 5 24.3 5 35.8 7 2.62 9 18.7 36 31.5 30 1.47 6 59.1 13 67.8 25 41.2 3 79.3 54 87.4 12 43.4 60 36.6 31 67.4 72 25.0 21 31.9 34 64.3 35 4.79 66 38.9 9 78.7 21 3.10 26
FMOF [94]25.8 14.2 64 38.6 72 1.91 49 24.5 10 36.2 10 2.70 16 18.4 21 31.2 23 1.77 53 59.5 37 68.0 35 41.5 11 79.2 30 87.4 12 43.1 21 36.6 31 66.8 27 25.0 21 31.6 2 63.3 6 4.61 4 39.1 26 78.4 8 3.11 31
CombBMOF [113]27.7 13.6 14 36.4 14 1.71 15 24.5 10 36.9 22 2.58 3 18.1 15 31.5 30 1.81 60 59.5 37 68.2 40 41.6 17 79.1 11 87.3 5 43.0 16 36.8 56 66.5 13 25.0 21 33.9 123 65.2 80 4.68 28 39.1 26 78.4 8 2.92 1
ComponentFusion [96]27.9 13.4 3 36.1 7 1.72 17 24.6 13 36.8 21 2.57 2 18.9 46 32.9 55 1.69 39 59.1 13 67.8 25 41.4 4 79.2 30 87.4 12 43.6 84 36.5 20 66.3 6 25.1 35 32.0 48 64.8 56 4.76 61 39.1 26 78.7 21 3.10 26
IROF++ [58]28.9 13.8 28 37.8 50 1.72 17 24.6 13 36.6 18 2.61 6 18.6 32 31.3 26 1.64 35 58.8 1 66.7 3 41.8 32 79.0 5 87.3 5 42.7 9 36.5 20 66.6 16 25.0 21 32.0 48 65.0 64 4.74 53 39.5 66 79.2 46 3.30 79
SepConv-v1 [127]30.3 9.23 1 28.0 1 1.08 1 20.5 1 32.4 1 3.35 79 8.95 1 20.5 1 2.08 80 60.8 94 66.9 6 44.2 107 79.1 11 87.1 2 43.2 37 35.6 1 62.4 1 25.1 35 32.2 73 62.3 2 5.34 115 37.6 1 76.4 1 3.28 76
Ramp [62]30.8 14.1 56 38.7 76 1.92 53 24.6 13 36.6 18 2.69 15 17.9 10 31.0 18 1.47 6 58.9 4 67.0 8 41.9 37 79.2 30 87.5 37 43.1 21 37.0 72 67.4 72 25.5 73 31.6 2 63.5 9 4.63 6 39.1 26 78.9 29 3.19 47
S2F-IF [123]31.8 13.5 8 36.6 16 1.70 13 24.9 26 37.9 35 2.77 30 18.8 39 32.7 51 1.54 16 59.1 13 67.7 21 41.6 17 79.3 54 87.5 37 43.3 46 36.5 20 67.1 50 25.0 21 31.9 34 64.7 52 4.74 53 39.3 42 79.1 43 3.10 26
TV-L1-MCT [64]32.7 14.5 85 39.7 104 1.86 40 25.2 34 37.8 33 2.78 33 17.3 3 31.1 22 1.59 24 58.9 4 66.6 2 41.6 17 79.1 11 87.4 12 42.9 11 36.8 56 66.4 9 25.6 78 31.8 20 64.0 29 4.73 45 39.1 26 79.0 33 3.20 54
RNLOD-Flow [121]33.2 13.9 39 37.9 55 1.86 40 25.2 34 37.9 35 2.78 33 19.0 51 32.1 39 1.78 54 59.2 18 67.8 25 41.5 11 79.1 11 87.4 12 43.1 21 36.7 44 66.8 27 25.2 44 31.9 34 64.2 32 4.75 57 39.2 36 79.0 33 3.06 13
FC-2Layers-FF [74]34.0 14.0 46 38.6 72 1.84 33 24.2 2 35.1 2 2.82 42 17.9 10 31.3 26 1.51 11 59.3 28 67.7 21 42.1 48 79.3 54 87.6 69 43.3 46 36.7 44 67.4 72 25.3 60 31.6 2 63.6 12 4.67 21 39.1 26 78.7 21 3.19 47
Classic+NL [31]34.5 14.2 64 38.8 78 1.98 58 24.6 13 36.5 13 2.65 11 17.7 6 30.9 15 1.51 11 59.2 18 67.5 16 42.2 59 79.2 30 87.5 37 43.3 46 37.0 72 67.1 50 25.5 73 31.7 11 63.6 12 4.67 21 39.2 36 79.0 33 3.18 44
Classic+CPF [83]35.2 14.1 56 38.3 66 1.74 20 24.9 26 37.1 25 2.73 19 17.6 5 31.4 28 1.60 27 59.0 9 67.3 11 41.4 4 79.3 54 87.6 69 43.3 46 36.9 63 67.9 97 25.2 44 31.9 34 64.3 35 4.64 11 39.3 42 79.2 46 3.04 9
FlowFields [110]35.7 13.6 14 37.1 29 1.74 20 25.0 29 38.1 40 2.75 21 18.8 39 33.2 64 1.53 15 59.4 32 68.0 35 42.3 67 79.3 54 87.5 37 43.2 37 36.5 20 67.0 40 25.0 21 31.8 20 64.7 52 4.69 31 39.4 53 79.3 53 3.13 33
NNF-EAC [103]37.9 14.2 64 37.3 34 2.09 69 25.3 39 37.6 31 2.76 24 18.9 46 30.6 9 1.61 29 59.8 58 68.5 54 43.3 100 79.1 11 87.3 5 43.1 21 36.5 20 66.5 13 25.0 21 32.1 60 64.3 35 4.73 45 39.4 53 79.0 33 3.14 35
LME [70]38.4 13.5 8 36.1 7 1.62 5 25.3 39 37.8 33 3.44 84 19.0 51 32.8 53 1.63 33 59.0 9 67.8 25 41.5 11 79.7 113 87.9 108 44.4 114 36.5 20 67.0 40 24.9 15 32.0 48 64.2 32 4.66 19 39.0 17 78.6 16 3.09 22
S2D-Matching [84]38.9 14.2 64 38.9 84 1.96 56 25.3 39 37.9 35 2.76 24 17.5 4 31.0 18 1.60 27 59.3 28 67.4 13 42.8 86 79.2 30 87.5 37 43.2 37 36.9 63 67.3 67 25.4 70 31.8 20 63.8 20 4.64 11 39.1 26 78.6 16 3.21 58
WLIF-Flow [93]38.9 13.8 28 37.4 38 1.73 19 24.9 26 37.1 25 2.81 39 18.5 23 30.9 15 1.49 8 59.4 32 67.8 25 42.5 79 79.2 30 87.4 12 43.8 105 37.2 85 67.5 79 25.9 94 31.8 20 63.9 24 4.64 11 39.4 53 78.9 29 3.14 35
FESL [72]41.5 14.4 81 39.1 90 1.83 31 25.0 29 37.4 29 2.76 24 18.2 18 31.6 32 1.70 40 59.7 49 68.5 54 41.7 25 79.3 54 87.6 69 43.3 46 36.9 63 67.9 97 25.2 44 31.8 20 63.8 20 4.61 4 39.3 42 78.8 26 3.04 9
PGM-C [120]45.0 13.8 28 37.7 49 1.85 37 25.1 31 38.1 40 2.90 48 19.1 61 33.6 68 1.59 24 59.3 28 68.2 40 41.9 37 79.3 54 87.5 37 43.5 67 36.6 31 67.2 59 25.2 44 31.9 34 64.8 56 4.67 21 39.5 66 79.4 61 3.22 60
PMF [73]45.9 13.7 19 37.1 29 1.66 9 25.5 49 39.3 65 2.71 17 19.0 51 34.9 96 1.74 50 59.4 32 68.4 49 41.8 32 79.4 82 87.6 69 43.3 46 37.3 89 66.9 32 26.2 102 31.9 34 64.3 35 4.73 45 39.3 42 78.8 26 2.93 2
MDP-Flow [26]46.0 13.4 3 36.1 7 1.67 10 24.8 24 37.2 28 2.79 36 18.8 39 32.0 37 1.70 40 59.8 58 68.9 82 42.1 48 79.3 54 87.6 69 43.5 67 36.7 44 67.7 89 25.2 44 32.5 90 65.5 90 4.77 64 39.1 26 79.0 33 3.09 22
SuperFlow [81]46.8 13.8 28 36.2 12 2.27 85 26.3 74 38.7 55 4.39 96 19.1 61 33.1 61 1.99 75 59.6 42 67.7 21 42.2 59 79.4 82 87.5 37 43.7 98 36.1 7 65.9 3 24.8 13 31.7 11 64.5 45 4.80 72 38.9 9 78.9 29 3.19 47
Efficient-NL [60]47.5 14.3 76 38.7 76 1.77 23 25.2 34 37.6 31 2.76 24 19.0 51 31.8 33 2.08 80 59.8 58 68.7 72 41.4 4 79.1 11 87.4 12 43.0 16 36.9 63 68.4 110 24.6 7 32.1 60 64.7 52 4.69 31 40.1 96 79.8 84 3.14 35
SVFilterOh [111]47.8 14.1 56 37.3 34 1.96 56 24.7 21 36.6 18 2.87 46 18.3 19 30.8 13 1.63 33 59.9 67 68.5 54 43.1 99 79.5 107 87.7 94 44.5 115 36.6 31 66.7 20 25.3 60 31.6 2 62.8 3 5.05 98 38.6 4 78.2 7 3.37 90
TC-Flow [46]48.1 13.7 19 36.9 25 1.91 49 25.3 39 38.5 50 3.05 60 19.3 78 34.1 85 1.73 46 59.2 18 67.8 25 42.2 59 79.3 54 87.5 37 43.5 67 37.1 78 68.0 100 25.6 78 31.9 34 64.3 35 4.71 36 39.0 17 79.0 33 3.13 33
Second-order prior [8]49.9 14.0 46 37.1 29 2.11 70 26.2 71 39.3 65 2.93 50 19.4 83 35.1 99 2.16 90 59.4 32 67.8 25 41.8 32 79.1 11 87.3 5 43.1 21 36.5 20 66.7 20 25.0 21 32.3 79 65.4 86 4.74 53 39.5 66 79.6 76 3.19 47
AggregFlow [97]49.9 14.5 85 38.3 66 2.20 79 25.7 62 38.5 50 3.23 73 18.6 32 30.8 13 1.44 4 59.7 49 68.4 49 41.7 25 79.4 82 87.6 69 43.8 105 37.5 94 66.9 32 26.4 107 31.8 20 64.2 32 4.70 35 38.9 9 78.4 8 3.08 18
EPPM w/o HM [88]50.2 13.4 3 36.6 16 1.61 3 25.5 49 39.3 65 2.76 24 19.4 83 35.7 105 1.99 75 59.6 42 69.3 91 41.9 37 79.2 30 87.4 12 43.1 21 37.0 72 67.5 79 25.3 60 32.8 100 65.0 64 4.85 80 39.4 53 79.0 33 3.04 9
IROF-TV [53]50.5 14.0 46 38.1 60 1.99 59 24.7 21 36.5 13 2.65 11 19.1 61 34.2 86 1.78 54 59.1 13 67.4 13 42.4 74 79.4 82 87.7 94 43.6 84 36.0 4 66.4 9 24.4 5 32.1 60 64.6 48 4.75 57 39.8 85 79.9 88 3.35 86
DeepFlow2 [108]50.9 13.9 39 36.6 16 2.07 67 25.6 57 38.4 47 3.08 62 19.1 61 33.6 68 1.70 40 59.6 42 68.5 54 41.9 37 79.4 82 87.5 37 43.7 98 36.7 44 66.3 6 25.4 70 31.9 34 64.7 52 4.67 21 39.4 53 79.4 61 3.26 73
TF+OM [100]51.0 13.7 19 36.5 15 2.17 72 25.2 34 37.4 29 3.76 86 17.9 10 32.7 51 1.76 52 59.8 58 68.5 54 42.3 67 79.3 54 87.5 37 43.7 98 36.9 63 66.7 20 25.7 87 31.8 20 64.3 35 4.79 66 39.3 42 79.3 53 3.47 102
CPM-Flow [116]51.5 13.8 28 37.8 50 1.87 44 25.1 31 38.2 45 2.93 50 19.0 51 33.4 67 1.61 29 59.6 42 68.7 72 42.1 48 79.3 54 87.5 37 43.5 67 36.8 56 66.9 32 25.5 73 32.0 48 65.2 80 4.68 28 39.5 66 79.5 69 3.25 69
TriFlow [95]52.3 14.2 64 39.0 88 2.20 79 26.6 79 39.3 65 4.59 100 19.0 51 33.7 71 1.71 45 59.9 67 68.7 72 41.4 4 79.2 30 87.5 37 43.5 67 36.7 44 67.1 50 25.2 44 31.8 20 63.9 24 4.69 31 39.1 26 79.0 33 3.23 65
EpicFlow [102]52.6 13.8 28 37.6 44 1.87 44 25.5 49 38.9 58 2.96 52 18.9 46 33.7 71 1.64 35 59.5 37 68.5 54 42.3 67 79.4 82 87.6 69 43.5 67 36.5 20 67.5 79 24.9 15 32.0 48 65.1 71 4.74 53 39.4 53 79.4 61 3.22 60
SimpleFlow [49]52.8 14.1 56 38.9 84 1.92 53 25.5 49 37.9 35 2.85 44 19.0 51 32.3 44 2.26 95 59.2 18 67.3 11 42.4 74 79.2 30 87.5 37 43.2 37 36.7 44 67.6 85 25.1 35 32.0 48 66.1 100 5.29 111 39.3 42 79.2 46 3.15 38
SRR-TVOF-NL [91]52.9 14.2 64 37.6 44 2.07 67 26.1 68 39.8 78 3.30 77 19.4 83 33.9 78 1.82 61 59.8 58 68.6 66 41.0 1 79.1 11 87.5 37 42.9 11 36.0 4 66.9 32 24.1 2 32.9 103 64.8 56 4.81 74 39.6 73 79.4 61 3.22 60
DeepFlow [86]53.1 13.7 19 35.7 4 2.03 64 25.6 57 38.2 45 3.30 77 19.2 71 33.9 78 1.74 50 59.7 49 68.0 35 42.2 59 79.4 82 87.5 37 43.7 98 37.3 89 66.4 9 26.2 102 31.8 20 64.8 56 4.63 6 39.3 42 79.3 53 3.26 73
CostFilter [40]54.0 13.6 14 37.4 38 1.63 8 25.5 49 39.7 76 2.75 21 19.0 51 36.0 108 1.79 56 59.4 32 68.8 78 42.0 44 79.4 82 87.6 69 43.7 98 38.6 111 67.1 50 28.1 120 31.9 34 64.6 48 4.81 74 39.0 17 78.5 14 3.00 4
OFH [38]54.1 14.1 56 38.2 65 2.03 64 25.6 57 38.4 47 3.01 56 19.4 83 35.1 99 1.79 56 59.5 37 68.8 78 42.3 67 79.1 11 87.4 12 43.1 21 36.7 44 67.6 85 25.2 44 32.1 60 65.1 71 4.79 66 39.2 36 79.2 46 3.15 38
Complementary OF [21]54.5 13.7 19 37.8 50 1.71 15 25.2 34 38.6 53 2.81 39 19.8 104 33.7 71 2.38 100 59.9 67 69.2 90 42.8 86 79.2 30 87.5 37 43.1 21 36.6 31 67.4 72 25.2 44 32.3 79 65.4 86 4.79 66 38.8 8 78.9 29 3.29 77
RFlow [90]54.7 13.8 28 37.8 50 2.02 62 26.0 65 39.1 63 2.85 44 19.0 51 33.1 61 1.86 64 59.7 49 68.4 49 42.2 59 79.2 30 87.6 69 43.4 60 36.1 7 66.8 27 24.5 6 32.2 73 65.1 71 4.82 79 39.7 79 79.8 84 3.34 83
DPOF [18]55.0 14.2 64 39.1 90 2.19 78 24.8 24 37.0 23 2.80 37 19.3 78 31.9 34 2.01 77 60.2 82 69.5 99 42.3 67 79.1 11 87.4 12 43.1 21 36.7 44 67.1 50 24.6 7 32.4 85 65.3 84 4.81 74 39.5 66 79.5 69 3.18 44
Aniso. Huber-L1 [22]55.1 14.3 76 38.5 70 2.17 72 26.6 79 39.5 74 3.21 72 19.2 71 32.5 49 1.83 63 59.7 49 68.7 72 41.9 37 79.2 30 87.4 12 43.2 37 36.3 9 67.1 50 24.6 7 32.2 73 64.9 62 4.71 36 39.7 79 79.6 76 3.24 68
OAR-Flow [125]55.6 14.0 46 36.9 25 2.05 66 25.3 39 38.1 40 3.11 65 19.1 61 34.0 84 1.70 40 59.2 18 68.6 66 41.9 37 79.4 82 87.6 69 43.5 67 36.9 63 67.8 92 25.3 60 32.0 48 65.1 71 4.75 57 39.3 42 79.3 53 3.18 44
TC/T-Flow [76]56.0 14.3 76 38.8 78 1.84 33 25.3 39 38.6 53 2.81 39 18.9 46 32.4 48 1.58 22 59.9 67 69.5 99 42.1 48 79.3 54 87.5 37 43.5 67 37.1 78 68.0 100 25.2 44 32.1 60 65.2 80 4.81 74 39.2 36 79.4 61 3.00 4
Brox et al. [5]56.0 14.0 46 37.4 38 1.90 47 26.4 76 40.1 85 3.08 62 19.3 78 35.0 98 1.97 72 59.7 49 68.2 40 41.7 25 79.4 82 87.6 69 43.6 84 36.6 31 66.9 32 25.1 35 31.9 34 64.8 56 4.73 45 39.4 53 79.5 69 3.15 38
Sparse Occlusion [54]57.2 14.2 64 38.6 72 1.99 59 25.8 64 39.2 64 2.78 33 19.3 78 32.3 44 1.80 59 59.8 58 68.8 78 41.7 25 79.3 54 87.5 37 43.2 37 37.1 78 68.4 110 25.3 60 32.1 60 64.4 44 4.60 1 39.7 79 79.6 76 3.15 38
ComplOF-FED-GPU [35]57.5 14.0 46 38.0 58 1.91 49 25.3 39 38.5 50 2.90 48 20.2 108 34.6 92 2.16 90 59.5 37 68.5 54 42.5 79 79.2 30 87.4 12 43.2 37 36.6 31 67.4 72 25.0 21 32.2 73 65.4 86 4.75 57 39.7 79 79.8 84 3.19 47
Aniso-Texture [82]57.7 13.6 14 36.6 16 1.82 28 26.2 71 39.3 65 3.20 71 19.6 93 33.0 58 1.96 71 59.7 49 68.5 54 42.6 82 79.4 82 87.6 69 43.6 84 37.0 72 68.4 110 25.7 87 31.9 34 63.8 20 4.63 6 39.4 53 79.3 53 3.16 42
GraphCuts [14]57.9 15.1 101 39.3 94 2.68 97 26.4 76 39.4 72 4.50 98 19.2 71 30.7 12 2.69 106 60.7 92 68.6 66 42.8 86 79.0 5 87.4 12 42.5 5 35.6 1 66.7 20 23.7 1 32.0 48 65.0 64 5.04 97 39.0 17 79.2 46 3.48 103
Fusion [6]58.6 13.8 28 38.4 69 1.84 33 25.3 39 38.1 40 2.88 47 19.1 61 32.2 42 1.90 67 60.9 96 69.8 103 41.8 32 79.1 11 87.9 108 42.1 2 36.0 4 67.8 92 24.1 2 32.7 98 66.3 104 4.88 83 39.5 66 80.4 107 3.26 73
DF-Auto [115]59.2 14.2 64 36.7 21 2.25 83 26.5 78 39.0 61 4.23 92 18.8 39 31.4 28 1.58 22 60.1 78 69.3 91 41.6 17 79.3 54 87.5 37 43.6 84 36.6 31 67.0 40 25.1 35 32.3 79 65.1 71 4.81 74 39.9 86 80.1 96 3.22 60
Classic++ [32]59.3 14.0 46 38.1 60 2.17 72 25.7 62 38.8 56 2.96 52 19.3 78 33.9 78 1.93 68 59.7 49 67.9 33 42.8 86 79.2 30 87.5 37 43.3 46 37.4 93 67.0 40 26.6 109 31.8 20 64.3 35 4.78 65 39.4 53 79.5 69 3.36 87
Steered-L1 [118]59.5 13.7 19 37.5 41 1.84 33 25.5 49 38.9 58 3.17 70 19.7 100 33.1 61 2.40 101 60.2 82 68.5 54 42.8 86 79.4 82 87.7 94 43.5 67 36.6 31 67.0 40 25.6 78 31.8 20 64.6 48 4.96 91 38.6 4 79.0 33 3.36 87
ALD-Flow [66]60.4 14.1 56 37.9 55 2.17 72 25.4 47 38.4 47 3.14 67 19.1 61 33.9 78 1.73 46 59.6 42 69.0 86 42.6 82 79.4 82 87.6 69 43.6 84 37.0 72 67.5 79 25.6 78 31.7 11 64.0 29 4.69 31 39.4 53 79.5 69 3.20 54
p-harmonic [29]60.8 13.5 8 36.7 21 1.85 37 26.7 86 39.9 82 3.25 75 19.4 83 35.2 101 2.10 83 60.1 78 68.7 72 42.2 59 79.3 54 87.5 37 43.3 46 36.7 44 66.7 20 25.3 60 32.6 94 65.8 94 4.76 61 39.4 53 79.5 69 3.17 43
Shiralkar [42]63.7 14.2 64 39.0 88 2.02 62 26.8 87 40.3 89 2.98 54 18.5 23 38.0 120 2.48 104 60.1 78 67.7 21 41.8 32 78.8 2 87.2 3 42.3 4 37.7 100 67.2 59 26.2 102 33.2 109 67.1 108 4.94 88 39.4 53 79.3 53 3.10 26
HBM-GC [105]66.7 14.7 91 39.4 99 2.41 92 25.4 47 38.1 40 3.07 61 18.0 13 29.8 2 1.56 19 59.8 58 68.2 40 42.8 86 80.1 119 88.0 114 45.9 122 37.5 94 68.2 106 26.1 100 31.9 34 63.3 6 4.99 93 39.3 42 79.1 43 3.30 79
FlowNet2 [122]66.7 15.9 113 41.4 112 2.76 100 27.1 91 40.2 87 4.29 94 19.6 93 34.3 88 1.88 65 60.0 72 70.2 107 42.0 44 79.4 82 87.7 94 43.3 46 36.4 14 66.3 6 24.9 15 32.1 60 64.5 45 4.71 36 39.6 73 79.2 46 3.08 18
SIOF [67]67.8 14.7 91 39.5 101 2.23 82 27.1 91 40.3 89 4.25 93 19.1 61 32.9 55 1.82 61 59.8 58 68.6 66 42.1 48 79.1 11 87.4 12 43.0 16 37.1 78 67.1 50 25.5 73 32.4 85 64.9 62 4.79 66 40.1 96 79.9 88 3.40 94
CLG-TV [48]67.9 14.3 76 38.8 78 2.17 72 26.6 79 39.8 78 3.24 74 19.5 90 33.9 78 2.11 85 60.0 72 69.0 86 42.4 74 79.3 54 87.6 69 43.5 67 36.6 31 66.9 32 25.1 35 32.1 60 65.1 71 4.71 36 39.9 86 80.0 92 3.20 54
MLDP_OF [89]68.8 13.9 39 38.1 60 1.81 26 25.6 57 38.9 58 2.80 37 18.8 39 32.3 44 1.61 29 59.6 42 68.3 46 42.3 67 79.3 54 87.6 69 43.9 108 39.6 123 68.7 115 28.5 122 33.0 107 65.3 84 5.09 101 39.6 73 79.2 46 3.51 105
Local-TV-L1 [65]70.7 14.9 96 37.3 34 3.21 112 27.3 96 39.5 74 4.67 101 18.9 46 32.3 44 1.70 40 61.3 107 68.6 66 47.1 121 79.3 54 87.6 69 43.6 84 39.0 115 66.7 20 28.9 124 31.7 11 64.3 35 4.79 66 39.3 42 79.1 43 3.41 97
F-TV-L1 [15]71.2 15.0 97 39.3 94 2.88 107 27.2 94 40.2 87 3.69 85 19.2 71 34.5 91 2.19 92 59.7 49 68.4 49 42.8 86 78.9 3 87.4 12 42.7 9 37.3 89 67.0 40 25.6 78 32.1 60 64.5 45 4.89 84 40.1 96 80.0 92 3.42 98
IAOF [50]71.2 15.5 109 39.2 93 2.93 109 29.4 111 43.0 113 5.18 110 17.8 8 33.0 58 2.04 78 60.8 94 68.9 82 42.2 59 79.2 30 87.4 12 43.3 46 36.8 56 67.2 59 25.1 35 32.7 98 65.6 93 4.67 21 40.0 90 80.0 92 3.20 54
TCOF [69]72.2 14.4 81 39.3 94 1.83 31 27.3 96 40.9 99 3.35 79 18.7 36 32.1 39 1.50 10 60.2 82 70.2 107 42.1 48 79.3 54 87.6 69 43.2 37 36.9 63 68.5 113 24.8 13 33.3 110 65.8 94 4.72 41 41.2 118 81.4 120 3.46 100
BriefMatch [124]73.3 14.0 46 37.0 28 2.17 72 25.6 57 38.8 56 3.98 90 19.7 100 33.0 58 2.69 106 61.1 103 69.0 86 46.4 118 79.3 54 87.6 69 43.8 105 40.5 126 67.9 97 30.6 126 31.8 20 64.0 29 4.94 88 39.0 17 78.8 26 3.34 83
Adaptive [20]74.5 14.5 85 39.6 103 2.31 87 27.1 91 40.4 92 3.35 79 18.6 32 33.7 71 1.98 73 59.6 42 68.2 40 42.4 74 79.4 82 87.6 69 43.4 60 37.1 78 67.5 79 25.7 87 32.4 85 64.8 56 4.73 45 40.0 90 80.1 96 3.38 92
CNN-flow-warp+ref [117]74.6 13.8 28 36.0 5 2.35 89 26.6 79 39.8 78 3.83 87 20.0 106 35.5 104 2.34 97 60.9 96 68.9 82 43.0 97 79.4 82 87.6 69 43.7 98 36.8 56 67.0 40 25.6 78 32.1 60 66.2 102 4.94 88 39.4 53 79.5 69 3.19 47
FlowNetS+ft+v [112]75.4 14.7 91 38.1 60 2.80 103 27.5 98 40.6 96 4.81 104 19.6 93 34.9 96 2.07 79 60.1 78 69.5 99 42.2 59 79.4 82 87.7 94 43.4 60 36.6 31 67.1 50 25.2 44 32.0 48 65.4 86 4.73 45 39.6 73 79.7 82 3.21 58
SPSA-learn [13]76.1 14.8 95 37.8 50 2.72 99 27.6 99 40.1 85 4.71 102 20.5 110 33.7 71 2.97 113 60.4 86 67.6 18 41.5 11 79.3 54 87.5 37 43.5 67 36.8 56 67.2 59 25.2 44 33.4 112 70.8 129 6.21 128 39.7 79 79.6 76 3.19 47
AdaConv-v1 [126]76.8 16.5 117 42.3 115 4.36 119 30.4 117 43.8 116 9.06 125 20.6 113 36.3 112 4.45 125 64.5 123 71.3 121 45.3 113 78.4 1 86.7 1 42.2 3 36.3 9 64.9 2 25.4 70 32.5 90 63.7 18 5.53 121 38.0 2 77.4 2 3.53 107
LDOF [28]77.2 15.0 97 38.8 78 2.92 108 28.0 104 41.1 101 5.03 107 19.7 100 34.8 95 2.15 88 60.0 72 68.9 82 42.6 82 79.4 82 87.6 69 43.5 67 36.9 63 66.8 27 25.5 73 31.9 34 65.1 71 4.73 45 39.5 66 79.6 76 3.23 65
ROF-ND [107]77.6 15.1 101 37.9 55 1.86 40 26.3 74 40.5 95 3.12 66 19.6 93 32.8 53 1.68 38 60.9 96 71.1 120 41.9 37 79.3 54 87.5 37 43.5 67 37.0 72 68.2 106 24.9 15 34.3 126 68.3 117 5.28 110 40.5 112 80.5 110 3.25 69
HBpMotionGpu [43]77.8 15.8 112 40.2 108 3.66 117 29.5 112 42.8 112 6.27 115 18.5 23 31.9 34 1.73 46 61.3 107 69.9 104 43.9 105 79.1 11 87.6 69 43.0 16 37.6 99 67.6 85 25.9 94 32.0 48 64.3 35 4.67 21 40.0 90 79.9 88 3.75 116
CRTflow [80]77.8 14.4 81 38.9 84 2.38 90 26.0 65 39.0 61 3.14 67 20.2 108 36.2 111 2.37 99 60.5 89 69.5 99 44.1 106 79.3 54 87.5 37 43.4 60 37.1 78 67.3 67 25.7 87 32.0 48 64.6 48 4.85 80 39.6 73 79.6 76 3.45 99
Modified CLG [34]78.2 14.1 56 37.6 44 2.33 88 28.5 108 41.4 105 5.68 111 19.6 93 35.8 107 2.31 96 60.2 82 68.6 66 42.1 48 79.4 82 87.5 37 43.5 67 36.7 44 67.2 59 25.2 44 32.3 79 66.0 98 4.76 61 40.2 100 80.4 107 3.40 94
Occlusion-TV-L1 [63]78.2 14.3 76 39.1 90 2.21 81 26.6 79 40.0 83 3.14 67 19.2 71 34.2 86 2.15 88 60.0 72 68.5 54 42.8 86 79.3 54 87.5 37 43.6 84 37.5 94 67.0 40 26.2 102 32.9 103 65.1 71 5.16 105 40.0 90 79.8 84 3.30 79
CBF [12]79.4 13.7 19 37.2 33 2.15 71 26.0 65 39.4 72 3.28 76 19.1 61 32.1 39 1.79 56 61.0 101 70.0 106 45.8 115 79.6 110 87.8 107 44.9 118 36.8 56 67.4 72 25.2 44 32.2 73 65.5 90 5.22 107 40.0 90 80.2 103 3.99 121
TriangleFlow [30]81.2 14.7 91 40.0 107 2.29 86 26.6 79 40.8 97 3.03 58 19.4 83 33.3 66 2.10 83 60.4 86 69.9 104 42.8 86 79.0 5 87.4 12 42.6 6 37.7 100 68.3 109 25.3 60 33.1 108 67.8 112 5.24 109 40.4 108 80.6 112 3.32 82
2D-CLG [1]81.3 14.5 85 37.6 44 2.76 100 29.8 114 42.4 109 6.69 119 19.7 100 35.2 101 2.74 109 60.7 92 68.7 72 41.5 11 79.4 82 87.7 94 43.5 67 36.6 31 67.0 40 25.1 35 32.5 90 66.7 106 4.90 86 40.2 100 80.1 96 3.25 69
BlockOverlap [61]81.9 15.1 101 37.6 44 3.31 114 27.7 101 39.3 65 5.73 112 18.6 32 30.3 4 2.09 82 60.9 96 68.2 40 47.1 121 80.2 120 87.9 108 46.5 123 39.0 115 67.3 67 28.4 121 31.9 34 63.9 24 5.09 101 39.7 79 79.3 53 3.55 108
Nguyen [33]81.9 15.6 110 38.5 70 3.62 116 30.1 116 43.2 114 6.04 113 19.6 93 36.3 112 2.25 94 61.1 103 69.4 96 42.0 44 79.2 30 87.5 37 43.1 21 36.4 14 67.2 59 24.7 12 34.3 126 67.4 111 5.00 94 40.2 100 80.3 104 3.29 77
SegOF [10]82.2 14.2 64 36.8 24 2.54 94 27.0 90 40.0 83 4.18 91 21.1 116 36.1 110 3.15 118 60.5 89 70.7 116 41.6 17 79.4 82 87.6 69 43.6 84 36.9 63 68.2 106 25.2 44 32.5 90 68.0 116 5.31 114 39.6 73 79.4 61 3.22 60
ACK-Prior [27]82.6 13.8 28 38.1 60 1.74 20 25.5 49 39.3 65 2.82 42 19.6 93 33.8 77 2.45 103 60.5 89 70.3 109 42.3 67 80.2 120 88.0 114 45.8 121 38.2 105 67.8 92 26.9 113 32.6 94 66.2 102 5.35 116 38.9 9 79.7 82 3.60 112
IAOF2 [51]83.2 15.6 110 41.3 111 2.58 96 27.6 99 41.4 105 4.29 94 17.8 8 33.6 68 1.94 69 61.2 106 70.8 117 42.8 86 79.4 82 87.7 94 43.3 46 37.2 85 67.5 79 25.6 78 32.3 79 65.0 64 4.63 6 40.6 113 80.4 107 3.40 94
StereoOF-V1MT [119]84.3 14.6 89 39.9 105 2.00 61 27.2 94 41.9 107 3.04 59 20.9 115 37.8 118 2.85 112 61.3 107 68.3 46 43.8 103 79.2 30 87.5 37 42.9 11 38.2 105 67.8 92 26.3 106 33.8 119 68.5 118 5.36 117 40.0 90 79.4 61 3.09 22
Dynamic MRF [7]84.7 13.9 39 38.6 72 1.90 47 26.1 68 40.4 92 3.08 62 20.0 106 37.7 117 2.73 108 61.3 107 69.3 91 44.6 108 79.1 11 87.6 69 43.0 16 37.7 100 68.0 100 25.9 94 32.6 94 67.2 109 5.08 100 40.4 108 80.5 110 3.49 104
TV-L1-improved [17]84.7 14.2 64 38.8 78 2.25 83 26.9 88 40.3 89 3.40 83 19.5 90 33.9 78 2.44 102 59.9 67 69.0 86 42.7 85 79.4 82 87.7 94 43.5 67 37.2 85 67.6 85 25.8 91 32.1 60 66.1 100 5.05 98 39.9 86 80.0 92 3.46 100
Correlation Flow [75]85.0 14.0 46 38.3 66 1.61 3 26.2 71 39.8 78 2.98 54 19.1 61 31.9 34 1.73 46 60.4 86 69.4 96 43.6 102 80.2 120 87.9 108 47.8 126 38.0 104 68.7 115 26.0 98 33.4 112 67.2 109 5.29 111 40.1 96 80.3 104 3.39 93
Black & Anandan [4]87.7 15.3 105 38.8 78 2.96 110 28.4 106 40.9 99 4.78 103 20.5 110 35.2 101 2.74 109 60.9 96 69.3 91 42.1 48 79.4 82 87.7 94 43.6 84 37.1 78 66.6 16 25.6 78 32.9 103 65.9 97 4.72 41 40.3 103 80.3 104 3.25 69
Rannacher [23]88.0 14.4 81 39.3 94 2.38 90 26.9 88 40.4 92 3.36 82 19.5 90 34.6 92 2.58 105 59.8 58 68.8 78 42.8 86 79.4 82 87.7 94 43.6 84 37.2 85 67.8 92 25.8 91 32.2 73 66.0 98 5.02 95 39.9 86 79.9 88 3.56 109
LocallyOriented [52]89.8 15.0 97 40.3 109 2.53 93 27.7 101 41.3 103 3.86 88 19.4 83 34.4 89 1.95 70 61.1 103 70.6 113 43.3 100 79.2 30 87.5 37 43.3 46 39.1 119 68.1 104 27.6 118 32.9 103 65.8 94 4.72 41 40.6 113 80.6 112 3.37 90
UnFlow [129]91.3 16.0 114 42.8 117 2.87 106 30.6 119 45.2 124 4.52 99 21.3 119 39.4 123 2.81 111 60.0 72 68.3 46 42.1 48 79.2 30 87.4 12 43.5 67 37.5 94 68.0 100 25.2 44 33.8 119 65.1 71 4.98 92 43.2 128 81.8 123 3.67 114
Filter Flow [19]95.0 15.0 97 39.4 99 2.78 102 28.4 106 40.8 97 6.31 116 18.5 23 32.9 55 2.14 86 61.7 111 69.3 91 45.3 113 79.7 113 88.0 114 44.5 115 37.3 89 67.7 89 26.1 100 32.1 60 65.2 80 4.93 87 40.3 103 80.7 115 3.97 120
StereoFlow [44]96.6 22.8 128 51.1 129 4.80 120 36.2 128 51.1 129 6.57 118 19.2 71 34.6 92 1.89 66 60.0 72 68.5 54 42.4 74 80.3 123 89.1 128 43.9 108 39.0 115 74.1 129 25.3 60 32.1 60 65.0 64 4.73 45 40.3 103 80.9 116 3.36 87
Ad-TV-NDC [36]100.0 17.2 119 39.9 105 5.26 122 29.6 113 42.1 108 6.18 114 19.2 71 33.7 71 1.98 73 62.4 113 70.3 109 45.2 112 79.6 110 87.9 108 43.9 108 38.3 108 67.3 67 27.2 117 32.3 79 65.5 90 4.80 72 40.3 103 80.1 96 3.58 111
Bartels [41]101.3 14.6 89 39.3 94 2.80 103 26.1 68 39.7 76 4.45 97 19.0 51 33.2 64 2.14 86 62.1 112 70.9 118 48.9 123 80.7 127 88.1 117 49.2 128 43.7 128 69.0 121 34.8 128 32.4 85 65.0 64 5.76 125 40.4 108 80.1 96 4.26 123
TI-DOFE [24]102.7 17.9 122 43.0 118 5.41 123 32.3 124 46.2 126 7.98 123 20.5 110 38.1 121 2.97 113 63.1 120 70.6 113 43.8 103 79.1 11 87.6 69 43.1 21 37.7 100 67.4 72 25.8 91 33.4 112 67.8 112 5.09 101 41.6 122 81.5 122 3.68 115
Horn & Schunck [3]103.6 15.3 105 40.4 110 2.69 98 29.0 109 42.7 110 5.10 108 21.1 116 37.9 119 3.33 119 62.5 115 70.3 109 43.0 97 79.3 54 87.7 94 43.6 84 37.5 94 67.3 67 25.9 94 33.9 123 68.5 118 5.03 96 41.2 118 81.2 119 3.57 110
GroupFlow [9]105.7 16.8 118 43.4 119 3.43 115 29.1 110 43.9 117 5.11 109 22.2 122 39.3 122 3.53 120 61.0 101 70.6 113 42.5 79 79.7 113 88.1 117 44.0 111 39.0 115 69.4 125 26.8 112 32.8 100 66.8 107 4.87 82 40.4 108 80.1 96 3.01 6
2bit-BM-tele [98]107.5 15.3 105 39.5 101 3.22 113 27.8 103 41.2 102 4.90 105 18.8 39 32.5 49 2.34 97 62.4 113 71.0 119 49.0 124 80.6 125 88.2 122 47.9 127 42.8 127 69.3 124 32.9 127 33.4 112 70.0 127 6.77 129 40.3 103 79.4 61 4.33 126
SLK [47]108.1 17.4 120 43.9 121 4.90 121 30.5 118 44.0 118 7.18 121 22.5 123 39.8 124 4.15 124 64.5 123 70.5 112 46.7 119 78.9 3 87.7 94 41.6 1 38.5 110 68.8 117 26.0 98 33.8 119 70.1 128 5.50 120 41.6 122 81.4 120 3.91 118
SILK [79]109.0 16.3 115 42.0 114 4.01 118 29.9 115 43.5 115 6.44 117 21.6 120 37.4 116 3.55 121 62.6 116 69.4 96 47.0 120 79.3 54 87.7 94 43.6 84 39.9 124 68.1 104 29.2 125 32.8 100 67.8 112 5.14 104 40.6 113 80.6 112 3.52 106
NL-TV-NCC [25]109.1 15.1 101 41.6 113 1.86 40 26.6 79 41.3 103 3.02 57 20.8 114 35.7 105 2.24 93 63.2 121 73.9 125 45.9 116 81.3 129 88.7 127 49.9 129 38.6 111 69.8 127 25.6 78 37.6 129 69.5 124 5.62 123 42.4 127 82.1 126 4.00 122
HCIC-L [99]110.4 23.2 129 49.0 128 11.0 129 32.1 123 44.4 119 9.93 126 23.2 125 36.4 114 3.02 115 64.4 122 72.1 122 44.9 109 80.6 125 88.5 125 46.6 124 39.1 119 68.9 119 27.1 115 32.4 85 65.0 64 5.53 121 39.1 26 79.3 53 3.65 113
Heeger++ [104]111.4 17.5 121 47.2 127 2.80 103 31.1 121 44.9 122 4.93 106 26.6 127 47.7 128 4.79 126 62.6 116 68.0 35 45.1 110 79.8 117 88.4 124 44.1 112 39.1 119 68.9 119 26.5 108 34.8 128 67.9 115 5.23 108 41.5 121 80.1 96 3.23 65
FFV1MT [106]113.5 16.4 116 44.7 123 3.13 111 31.9 122 44.7 120 7.15 120 25.4 126 45.6 127 5.04 127 62.6 116 68.0 35 45.1 110 79.6 110 87.9 108 44.1 112 38.9 114 67.7 89 27.1 115 34.0 125 68.5 118 5.29 111 41.8 125 81.0 117 4.48 128
Learning Flow [11]113.8 15.3 105 42.7 116 2.55 95 28.0 104 42.7 110 3.95 89 21.1 116 37.0 115 3.03 117 63.0 119 73.3 124 46.2 117 80.0 118 88.2 122 45.1 119 38.2 105 68.6 114 26.7 110 33.8 119 68.5 118 5.21 106 41.9 126 82.3 127 3.95 119
Adaptive flow [45]116.8 19.6 124 44.1 122 6.76 124 32.8 125 45.7 125 10.2 127 19.8 104 34.4 89 3.02 115 64.7 125 72.1 122 49.4 125 80.3 123 88.6 126 45.6 120 38.3 108 69.2 122 26.7 110 32.6 94 66.5 105 5.45 119 41.0 116 81.1 118 3.75 116
Pyramid LK [2]118.5 21.2 127 43.7 120 10.7 128 33.1 127 45.1 123 11.9 128 27.3 128 36.0 108 6.46 128 70.7 129 78.5 129 57.7 129 79.5 107 88.1 117 43.3 46 38.6 111 68.8 117 27.0 114 33.5 117 68.8 122 6.00 126 41.0 116 81.8 123 4.31 125
FOLKI [16]121.8 20.9 125 46.0 124 9.48 127 32.8 125 47.4 127 8.75 124 21.6 120 40.7 125 4.10 123 67.2 128 74.2 127 53.7 128 79.5 107 88.1 117 43.7 98 39.2 122 69.2 122 27.9 119 33.4 112 69.5 124 5.65 124 41.7 124 82.3 127 4.28 124
PGAM+LK [55]122.0 19.4 123 46.4 125 6.81 125 30.9 120 44.8 121 7.52 122 22.7 124 40.9 126 3.99 122 66.6 127 73.9 125 52.4 127 79.7 113 88.1 117 44.5 115 40.2 125 69.7 126 28.8 123 33.3 110 69.3 123 5.42 118 41.4 120 81.8 123 4.36 127
Periodicity [78]127.3 21.0 126 47.0 126 9.32 126 38.1 129 48.1 128 14.7 129 29.8 129 47.9 129 9.27 129 66.0 126 77.1 128 50.7 126 80.8 128 89.3 129 46.8 125 45.1 129 70.6 128 35.5 129 33.5 117 69.6 126 6.07 127 43.5 129 84.0 129 6.51 129
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 Anonymous. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015 submission 744.
[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. Submitted to TIP 2016.
[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.
* 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.