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]14.8 13.4 5 36.1 9 1.56 3 24.2 3 35.7 8 2.60 5 18.4 25 30.4 9 1.43 3 59.2 20 68.4 57 41.6 18 79.1 15 87.3 8 43.1 27 36.4 17 66.6 21 25.0 27 31.7 13 63.5 11 4.66 20 38.9 11 78.4 10 3.01 9
PH-Flow [101]16.8 13.7 24 37.1 36 1.77 30 24.3 6 35.5 7 2.58 3 18.5 28 30.6 12 1.54 16 58.8 2 66.8 6 41.6 18 79.0 8 87.2 6 42.9 15 36.3 10 67.1 60 24.6 9 31.6 3 63.7 20 4.64 12 39.0 19 78.6 19 3.10 35
NN-field [71]18.0 13.5 10 36.9 30 1.67 12 24.2 3 35.4 6 2.54 1 18.7 41 30.6 12 1.52 13 59.3 31 68.5 62 41.7 26 79.1 15 87.3 8 43.2 46 36.4 17 66.2 7 25.0 27 31.6 3 63.6 14 4.64 12 38.9 11 78.1 7 3.05 17
MDP-Flow2 [68]20.3 13.3 4 35.1 5 1.62 6 24.6 14 36.5 16 2.63 10 18.5 28 30.5 10 1.42 2 59.0 10 67.8 30 41.4 5 79.1 15 87.3 8 43.4 72 36.5 23 66.4 12 25.0 27 32.0 52 63.9 26 4.64 12 39.3 48 78.7 25 3.08 27
PMMST [114]21.0 13.4 5 35.0 4 1.70 18 25.1 35 37.1 28 2.73 20 18.5 28 30.5 10 1.39 1 58.9 5 67.4 15 41.5 12 79.2 36 87.4 15 43.4 72 36.3 10 66.2 7 24.9 18 31.8 23 63.8 22 4.67 23 39.2 41 78.7 25 3.09 31
COFM [59]21.7 13.6 18 36.0 7 1.89 55 24.6 14 36.4 14 2.71 18 18.5 28 30.3 7 1.59 27 58.8 2 66.8 6 41.1 3 79.0 8 87.4 15 42.6 9 35.8 4 67.2 69 24.1 3 31.2 2 61.6 2 4.89 98 38.5 4 78.1 7 3.34 101
Layers++ [37]22.2 14.0 57 37.5 48 1.91 59 24.3 6 35.3 5 2.75 22 18.3 23 31.0 22 1.56 21 59.2 20 67.5 20 41.7 26 79.2 36 87.4 15 43.1 27 36.4 17 66.5 18 25.0 27 31.6 3 63.2 5 4.60 2 38.7 7 77.7 6 3.12 41
HAST [109]23.4 13.7 24 36.2 14 1.93 65 24.7 22 37.0 26 2.77 31 18.8 44 32.2 47 1.66 42 59.1 14 67.9 38 41.4 5 79.0 8 87.4 15 42.6 9 36.3 10 66.9 39 24.6 9 31.6 3 63.3 7 4.71 40 39.0 19 78.4 10 3.06 20
AGIF+OF [85]23.4 13.9 47 37.5 48 1.67 12 24.6 14 36.5 16 2.68 14 18.1 18 31.0 22 1.61 32 58.9 5 66.9 8 41.4 5 79.2 36 87.5 45 43.1 27 36.6 35 67.2 69 25.0 27 31.8 23 63.6 14 4.60 2 39.0 19 78.6 19 2.98 5
Sparse-NonSparse [56]23.9 13.8 34 37.3 41 1.81 34 24.4 9 36.0 10 2.61 6 18.0 16 31.2 27 1.52 13 59.0 10 67.1 11 42.0 50 79.2 36 87.4 15 43.1 27 36.7 52 66.7 25 25.3 69 31.7 13 63.6 14 4.63 7 38.9 11 78.5 17 3.08 27
nLayers [57]24.4 13.9 47 36.7 25 1.85 45 24.5 11 36.1 11 2.76 25 17.7 9 30.0 6 1.44 4 59.2 20 67.6 22 41.6 18 79.3 62 87.5 45 43.3 55 36.4 17 66.8 34 25.1 42 31.7 13 63.2 5 4.72 47 38.7 7 77.6 4 3.03 12
ProbFlowFields [128]27.4 13.5 10 36.6 19 1.82 36 24.4 9 36.4 14 2.68 14 18.5 28 31.2 27 1.49 8 59.2 20 67.2 12 42.1 55 79.3 62 87.5 45 43.6 99 36.5 23 67.0 49 25.2 53 31.6 3 63.5 11 4.64 12 39.0 19 78.4 10 3.06 20
2DHMM-SAS [92]28.7 14.1 67 38.9 97 1.82 36 25.5 56 38.0 42 2.77 31 17.2 5 30.9 19 1.56 21 58.9 5 66.5 3 41.7 26 79.1 15 87.4 15 42.9 15 36.5 23 66.6 21 24.9 18 31.7 13 63.9 26 4.68 31 39.2 41 79.0 40 3.07 23
LSM [39]28.9 13.9 47 38.0 66 1.78 32 24.6 14 36.5 16 2.61 6 18.1 18 32.0 41 1.55 19 59.2 20 67.6 22 42.1 55 79.2 36 87.4 15 43.1 27 36.7 52 66.9 39 25.3 69 31.7 13 63.6 14 4.65 19 38.9 11 78.6 19 3.07 23
OFLAF [77]29.0 13.5 10 36.1 9 1.62 6 24.3 6 35.8 9 2.62 9 18.7 41 31.5 34 1.47 6 59.1 14 67.8 30 41.2 4 79.3 62 87.4 15 43.4 72 36.6 35 67.4 85 25.0 27 31.9 38 64.3 38 4.79 75 38.9 11 78.7 25 3.10 35
FGIK [136]29.6 13.9 47 36.8 28 2.59 112 26.6 91 39.4 80 5.00 124 10.0 3 24.3 3 1.92 81 60.9 113 67.4 15 40.1 1 76.4 1 85.1 1 39.6 1 33.0 1 59.9 1 22.7 1 31.0 1 60.0 1 4.23 1 37.1 1 76.4 1 2.77 1
FMOF [94]30.7 14.2 77 38.6 83 1.91 59 24.5 11 36.2 12 2.70 17 18.4 25 31.2 27 1.77 62 59.5 42 68.0 41 41.5 12 79.2 36 87.4 15 43.1 27 36.6 35 66.8 34 25.0 27 31.6 3 63.3 7 4.61 5 39.1 29 78.4 10 3.11 40
CombBMOF [113]32.4 13.6 18 36.4 16 1.71 21 24.5 11 36.9 25 2.58 3 18.1 18 31.5 34 1.81 70 59.5 42 68.2 47 41.6 18 79.1 15 87.3 8 43.0 21 36.8 64 66.5 18 25.0 27 33.9 138 65.2 91 4.68 31 39.1 29 78.4 10 2.92 3
ComponentFusion [96]32.6 13.4 5 36.1 9 1.72 24 24.6 14 36.8 24 2.57 2 18.9 51 32.9 61 1.69 44 59.1 14 67.8 30 41.4 5 79.2 36 87.4 15 43.6 99 36.5 23 66.3 9 25.1 42 32.0 52 64.8 65 4.76 70 39.1 29 78.7 25 3.10 35
IROF++ [58]34.0 13.8 34 37.8 58 1.72 24 24.6 14 36.6 21 2.61 6 18.6 37 31.3 30 1.64 39 58.8 2 66.7 5 41.8 34 79.0 8 87.3 8 42.7 12 36.5 23 66.6 21 25.0 27 32.0 52 65.0 73 4.74 61 39.5 75 79.2 56 3.30 96
Ramp [62]36.1 14.1 67 38.7 88 1.92 63 24.6 14 36.6 21 2.69 16 17.9 13 31.0 22 1.47 6 58.9 5 67.0 10 41.9 40 79.2 36 87.5 45 43.1 27 37.0 82 67.4 85 25.5 84 31.6 3 63.5 11 4.63 7 39.1 29 78.9 34 3.19 59
SepConv-v1 [127]36.2 9.23 1 28.0 2 1.08 1 20.5 2 32.4 2 3.35 90 8.95 2 20.5 2 2.08 99 60.8 111 66.9 8 44.2 126 79.1 15 87.1 4 43.2 46 35.6 2 62.4 2 25.1 42 32.2 81 62.3 3 5.34 134 37.6 2 76.4 1 3.28 92
S2F-IF [123]36.8 13.5 10 36.6 19 1.70 18 24.9 29 37.9 38 2.77 31 18.8 44 32.7 57 1.54 16 59.1 14 67.7 26 41.6 18 79.3 62 87.5 45 43.3 55 36.5 23 67.1 60 25.0 27 31.9 38 64.7 60 4.74 61 39.3 48 79.1 50 3.10 35
TV-L1-MCT [64]38.1 14.5 100 39.7 120 1.86 49 25.2 38 37.8 36 2.78 34 17.3 6 31.1 26 1.59 27 58.9 5 66.6 4 41.6 18 79.1 15 87.4 15 42.9 15 36.8 64 66.4 12 25.6 90 31.8 23 64.0 32 4.73 51 39.1 29 79.0 40 3.20 66
FlowFields+ [130]38.5 13.5 10 37.0 33 1.69 17 25.0 32 38.2 48 2.78 34 18.9 51 33.3 73 1.55 19 59.1 14 67.6 22 41.9 40 79.3 62 87.5 45 43.3 55 36.6 35 67.2 69 25.1 42 31.8 23 64.5 51 4.67 23 39.3 48 79.2 56 3.07 23
RNLOD-Flow [121]38.8 13.9 47 37.9 63 1.86 49 25.2 38 37.9 38 2.78 34 19.0 58 32.1 43 1.78 64 59.2 20 67.8 30 41.5 12 79.1 15 87.4 15 43.1 27 36.7 52 66.8 34 25.2 53 31.9 38 64.2 35 4.75 66 39.2 41 79.0 40 3.06 20
FC-2Layers-FF [74]39.8 14.0 57 38.6 83 1.84 41 24.2 3 35.1 3 2.82 44 17.9 13 31.3 30 1.51 11 59.3 31 67.7 26 42.1 55 79.3 62 87.6 82 43.3 55 36.7 52 67.4 85 25.3 69 31.6 3 63.6 14 4.67 23 39.1 29 78.7 25 3.19 59
Classic+NL [31]40.6 14.2 77 38.8 91 1.98 68 24.6 14 36.5 16 2.65 12 17.7 9 30.9 19 1.51 11 59.2 20 67.5 20 42.2 68 79.2 36 87.5 45 43.3 55 37.0 82 67.1 60 25.5 84 31.7 13 63.6 14 4.67 23 39.2 41 79.0 40 3.18 56
Classic+CPF [83]41.2 14.1 67 38.3 77 1.74 27 24.9 29 37.1 28 2.73 20 17.6 8 31.4 32 1.60 30 59.0 10 67.3 13 41.4 5 79.3 62 87.6 82 43.3 55 36.9 72 67.9 113 25.2 53 31.9 38 64.3 38 4.64 12 39.3 48 79.2 56 3.04 14
FlowFields [110]41.6 13.6 18 37.1 36 1.74 27 25.0 32 38.1 43 2.75 22 18.8 44 33.2 71 1.53 15 59.4 36 68.0 41 42.3 76 79.3 62 87.5 45 43.2 46 36.5 23 67.0 49 25.0 27 31.8 23 64.7 60 4.69 34 39.4 62 79.3 64 3.13 43
NNF-EAC [103]44.2 14.2 77 37.3 41 2.09 81 25.3 44 37.6 34 2.76 25 18.9 51 30.6 12 1.61 32 59.8 66 68.5 62 43.3 117 79.1 15 87.3 8 43.1 27 36.5 23 66.5 18 25.0 27 32.1 65 64.3 38 4.73 51 39.4 62 79.0 40 3.14 45
LME [70]44.5 13.5 10 36.1 9 1.62 6 25.3 44 37.8 36 3.44 96 19.0 58 32.8 59 1.63 37 59.0 10 67.8 30 41.5 12 79.7 134 87.9 128 44.4 134 36.5 23 67.0 49 24.9 18 32.0 52 64.2 35 4.66 20 39.0 19 78.6 19 3.09 31
CtxSyn [137]44.8 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 1 42.5 90 79.0 8 87.1 4 43.0 21 37.9 120 65.3 5 25.7 101 38.4 150 67.7 129 5.17 123 42.3 146 78.4 10 3.48 121
S2D-Matching [84]45.2 14.2 77 38.9 97 1.96 66 25.3 44 37.9 38 2.76 25 17.5 7 31.0 22 1.60 30 59.3 31 67.4 15 42.8 99 79.2 36 87.5 45 43.2 46 36.9 72 67.3 79 25.4 79 31.8 23 63.8 22 4.64 12 39.1 29 78.6 19 3.21 72
WLIF-Flow [93]45.4 13.8 34 37.4 45 1.73 26 24.9 29 37.1 28 2.81 41 18.5 28 30.9 19 1.49 8 59.4 36 67.8 30 42.5 90 79.2 36 87.4 15 43.8 124 37.2 97 67.5 92 25.9 109 31.8 23 63.9 26 4.64 12 39.4 62 78.9 34 3.14 45
FESL [72]48.0 14.4 94 39.1 103 1.83 39 25.0 32 37.4 32 2.76 25 18.2 22 31.6 36 1.70 46 59.7 54 68.5 62 41.7 26 79.3 62 87.6 82 43.3 55 36.9 72 67.9 113 25.2 53 31.8 23 63.8 22 4.61 5 39.3 48 78.8 31 3.04 14
FF++_ROB [146]50.0 13.5 10 36.6 19 1.68 15 25.4 53 38.6 59 2.89 54 19.1 70 33.5 76 1.74 56 59.3 31 68.0 41 41.8 34 79.3 62 87.5 45 43.4 72 37.1 89 66.9 39 25.9 109 31.7 13 64.3 38 4.73 51 39.3 48 79.1 50 3.20 66
JOF [141]50.2 14.4 94 39.1 103 2.17 84 24.7 22 36.3 13 2.87 51 18.1 18 30.6 12 1.54 16 59.7 54 67.9 38 43.2 115 79.3 62 87.5 45 43.6 99 36.9 72 67.0 49 25.4 79 31.6 3 63.4 10 4.66 20 39.1 29 78.7 25 3.29 93
PGM-C [120]52.3 13.8 34 37.7 57 1.85 45 25.1 35 38.1 43 2.90 55 19.1 70 33.6 77 1.59 27 59.3 31 68.2 47 41.9 40 79.3 62 87.5 45 43.5 82 36.6 35 67.2 69 25.2 53 31.9 38 64.8 65 4.67 23 39.5 75 79.4 73 3.22 74
PMF [73]52.8 13.7 24 37.1 36 1.66 11 25.5 56 39.3 73 2.71 18 19.0 58 34.9 107 1.74 56 59.4 36 68.4 57 41.8 34 79.4 96 87.6 82 43.3 55 37.3 101 66.9 39 26.2 119 31.9 38 64.3 38 4.73 51 39.3 48 78.8 31 2.93 4
MDP-Flow [26]53.0 13.4 5 36.1 9 1.67 12 24.8 26 37.2 31 2.79 38 18.8 44 32.0 41 1.70 46 59.8 66 68.9 91 42.1 55 79.3 62 87.6 82 43.5 82 36.7 52 67.7 103 25.2 53 32.5 100 65.5 102 4.77 73 39.1 29 79.0 40 3.09 31
SuperFlow [81]54.6 13.8 34 36.2 14 2.27 98 26.3 85 38.7 62 4.39 112 19.1 70 33.1 68 1.99 91 59.6 47 67.7 26 42.2 68 79.4 96 87.5 45 43.7 115 36.1 8 65.9 6 24.8 15 31.7 13 64.5 51 4.80 83 38.9 11 78.9 34 3.19 59
Efficient-NL [60]55.2 14.3 89 38.7 88 1.77 30 25.2 38 37.6 34 2.76 25 19.0 58 31.8 37 2.08 99 59.8 66 68.7 80 41.4 5 79.1 15 87.4 15 43.0 21 36.9 72 68.4 128 24.6 9 32.1 65 64.7 60 4.69 34 40.1 111 79.8 101 3.14 45
TC-Flow [46]55.8 13.7 24 36.9 30 1.91 59 25.3 44 38.5 56 3.05 70 19.3 89 34.1 94 1.73 52 59.2 20 67.8 30 42.2 68 79.3 62 87.5 45 43.5 82 37.1 89 68.0 117 25.6 90 31.9 38 64.3 38 4.71 40 39.0 19 79.0 40 3.13 43
SVFilterOh [111]55.9 14.1 67 37.3 41 1.96 66 24.7 22 36.6 21 2.87 51 18.3 23 30.8 17 1.63 37 59.9 77 68.5 62 43.1 114 79.5 126 87.7 110 44.5 135 36.6 35 66.7 25 25.3 69 31.6 3 62.8 4 5.05 114 38.6 5 78.2 9 3.37 108
AggregFlow [97]57.9 14.5 100 38.3 77 2.20 92 25.7 69 38.5 56 3.23 84 18.6 37 30.8 17 1.44 4 59.7 54 68.4 57 41.7 26 79.4 96 87.6 82 43.8 124 37.5 107 66.9 39 26.4 124 31.8 23 64.2 35 4.70 38 38.9 11 78.4 10 3.08 27
DMF_ROB [140]58.0 13.9 47 37.0 33 1.98 68 25.8 71 39.0 68 2.96 59 19.8 121 35.0 109 2.12 105 59.7 54 68.2 47 41.9 40 79.3 62 87.4 15 43.7 115 36.3 10 66.4 12 25.0 27 32.1 65 64.4 48 4.93 101 39.2 41 79.1 50 3.07 23
EPPM w/o HM [88]58.2 13.4 5 36.6 19 1.61 4 25.5 56 39.3 73 2.76 25 19.4 96 35.7 123 1.99 91 59.6 47 69.3 104 41.9 40 79.2 36 87.4 15 43.1 27 37.0 82 67.5 92 25.3 69 32.8 111 65.0 73 4.85 92 39.4 62 79.0 40 3.04 14
Second-order prior [8]58.3 14.0 57 37.1 36 2.11 82 26.2 82 39.3 73 2.93 57 19.4 96 35.1 113 2.16 110 59.4 36 67.8 30 41.8 34 79.1 15 87.3 8 43.1 27 36.5 23 66.7 25 25.0 27 32.3 88 65.4 97 4.74 61 39.5 75 79.6 88 3.19 59
IROF-TV [53]58.7 14.0 57 38.1 68 1.99 70 24.7 22 36.5 16 2.65 12 19.1 70 34.2 95 1.78 64 59.1 14 67.4 15 42.4 84 79.4 96 87.7 110 43.6 99 36.0 5 66.4 12 24.4 6 32.1 65 64.6 56 4.75 66 39.8 96 79.9 106 3.35 104
DeepFlow2 [108]59.0 13.9 47 36.6 19 2.07 79 25.6 64 38.4 52 3.08 72 19.1 70 33.6 77 1.70 46 59.6 47 68.5 62 41.9 40 79.4 96 87.5 45 43.7 115 36.7 52 66.3 9 25.4 79 31.9 38 64.7 60 4.67 23 39.4 62 79.4 73 3.26 88
TF+OM [100]59.0 13.7 24 36.5 17 2.17 84 25.2 38 37.4 32 3.76 99 17.9 13 32.7 57 1.76 61 59.8 66 68.5 62 42.3 76 79.3 62 87.5 45 43.7 115 36.9 72 66.7 25 25.7 101 31.8 23 64.3 38 4.79 75 39.3 48 79.3 64 3.47 120
PWC-Net_ROB [148]59.0 13.7 24 38.1 68 1.70 18 25.8 71 39.7 86 2.83 46 19.3 89 35.0 109 1.75 59 59.4 36 69.1 101 42.1 55 79.3 62 87.6 82 43.4 72 37.0 82 66.7 25 25.5 84 32.0 52 64.4 48 4.74 61 39.3 48 78.9 34 2.98 5
CPM-Flow [116]59.2 13.8 34 37.8 58 1.87 53 25.1 35 38.2 48 2.93 57 19.0 58 33.4 75 1.61 32 59.6 47 68.7 80 42.1 55 79.3 62 87.5 45 43.5 82 36.8 64 66.9 39 25.5 84 32.0 52 65.2 91 4.68 31 39.5 75 79.5 81 3.25 84
SuperSlomo [132]59.3 12.3 3 30.3 3 2.92 125 24.8 26 35.2 4 6.60 139 13.6 4 25.5 4 2.01 93 60.5 103 65.5 2 43.9 123 78.3 2 86.6 2 41.9 3 37.4 105 64.3 3 26.4 124 35.3 148 63.9 26 5.33 133 40.3 120 77.6 4 3.51 124
ProFlow_ROB [147]59.9 13.6 18 36.5 17 1.85 45 25.3 44 38.4 52 2.96 59 18.9 51 32.9 61 1.62 36 59.7 54 69.6 120 42.5 90 79.4 96 87.6 82 43.4 72 36.6 35 66.7 25 25.1 42 32.1 65 65.1 81 4.71 40 39.7 89 79.7 97 3.20 66
TriFlow [95]60.9 14.2 77 39.0 101 2.20 92 26.6 91 39.3 73 4.59 116 19.0 58 33.7 80 1.71 51 59.9 77 68.7 80 41.4 5 79.2 36 87.5 45 43.5 82 36.7 52 67.1 60 25.2 53 31.8 23 63.9 26 4.69 34 39.1 29 79.0 40 3.23 80
LiteFlowNet [143]60.9 13.8 34 38.6 83 1.68 15 26.0 74 40.1 97 2.84 47 19.2 81 35.3 119 1.64 39 59.8 66 69.4 111 42.3 76 79.1 15 87.4 15 42.9 15 36.6 35 67.6 98 24.4 6 32.9 114 65.8 108 4.81 85 39.6 82 78.9 34 3.03 12
EpicFlow [102]61.0 13.8 34 37.6 52 1.87 53 25.5 56 38.9 65 2.96 59 18.9 51 33.7 80 1.64 39 59.5 42 68.5 62 42.3 76 79.4 96 87.6 82 43.5 82 36.5 23 67.5 92 24.9 18 32.0 52 65.1 81 4.74 61 39.4 62 79.4 73 3.22 74
SRR-TVOF-NL [91]61.4 14.2 77 37.6 52 2.07 79 26.1 78 39.8 89 3.30 88 19.4 96 33.9 87 1.82 71 59.8 66 68.6 74 41.0 2 79.1 15 87.5 45 42.9 15 36.0 5 66.9 39 24.1 3 32.9 114 64.8 65 4.81 85 39.6 82 79.4 73 3.22 74
SimpleFlow [49]61.5 14.1 67 38.9 97 1.92 63 25.5 56 37.9 38 2.85 49 19.0 58 32.3 49 2.26 115 59.2 20 67.3 13 42.4 84 79.2 36 87.5 45 43.2 46 36.7 52 67.6 98 25.1 42 32.0 52 66.1 115 5.29 129 39.3 48 79.2 56 3.15 48
DeepFlow [86]61.5 13.7 24 35.7 6 2.03 76 25.6 64 38.2 48 3.30 88 19.2 81 33.9 87 1.74 56 59.7 54 68.0 41 42.2 68 79.4 96 87.5 45 43.7 115 37.3 101 66.4 12 26.2 119 31.8 23 64.8 65 4.63 7 39.3 48 79.3 64 3.26 88
OFH [38]62.7 14.1 67 38.2 74 2.03 76 25.6 64 38.4 52 3.01 66 19.4 96 35.1 113 1.79 66 59.5 42 68.8 86 42.3 76 79.1 15 87.4 15 43.1 27 36.7 52 67.6 98 25.2 53 32.1 65 65.1 81 4.79 75 39.2 41 79.2 56 3.15 48
CostFilter [40]62.7 13.6 18 37.4 45 1.63 10 25.5 56 39.7 86 2.75 22 19.0 58 36.0 127 1.79 66 59.4 36 68.8 86 42.0 50 79.4 96 87.6 82 43.7 115 38.6 130 67.1 60 28.1 140 31.9 38 64.6 56 4.81 85 39.0 19 78.5 17 3.00 7
Complementary OF [21]63.2 13.7 24 37.8 58 1.71 21 25.2 38 38.6 59 2.81 41 19.8 121 33.7 80 2.38 120 59.9 77 69.2 102 42.8 99 79.2 36 87.5 45 43.1 27 36.6 35 67.4 85 25.2 53 32.3 88 65.4 97 4.79 75 38.8 9 78.9 34 3.29 93
Aniso. Huber-L1 [22]63.4 14.3 89 38.5 81 2.17 84 26.6 91 39.5 83 3.21 83 19.2 81 32.5 55 1.83 73 59.7 54 68.7 80 41.9 40 79.2 36 87.4 15 43.2 46 36.3 10 67.1 60 24.6 9 32.2 81 64.9 71 4.71 40 39.7 89 79.6 88 3.24 83
RFlow [90]63.4 13.8 34 37.8 58 2.02 73 26.0 74 39.1 71 2.85 49 19.0 58 33.1 68 1.86 74 59.7 54 68.4 57 42.2 68 79.2 36 87.6 82 43.4 72 36.1 8 66.8 34 24.5 8 32.2 81 65.1 81 4.82 91 39.7 89 79.8 101 3.34 101
DPOF [18]63.9 14.2 77 39.1 103 2.19 91 24.8 26 37.0 26 2.80 39 19.3 89 31.9 38 2.01 93 60.2 95 69.5 116 42.3 76 79.1 15 87.4 15 43.1 27 36.7 52 67.1 60 24.6 9 32.4 94 65.3 95 4.81 85 39.5 75 79.5 81 3.18 56
OAR-Flow [125]64.4 14.0 57 36.9 30 2.05 78 25.3 44 38.1 43 3.11 76 19.1 70 34.0 93 1.70 46 59.2 20 68.6 74 41.9 40 79.4 96 87.6 82 43.5 82 36.9 72 67.8 107 25.3 69 32.0 52 65.1 81 4.75 66 39.3 48 79.3 64 3.18 56
TC/T-Flow [76]64.7 14.3 89 38.8 91 1.84 41 25.3 44 38.6 59 2.81 41 18.9 51 32.4 54 1.58 25 59.9 77 69.5 116 42.1 55 79.3 62 87.5 45 43.5 82 37.1 89 68.0 117 25.2 53 32.1 65 65.2 91 4.81 85 39.2 41 79.4 73 3.00 7
Brox et al. [5]65.2 14.0 57 37.4 45 1.90 57 26.4 87 40.1 97 3.08 72 19.3 89 35.0 109 1.97 88 59.7 54 68.2 47 41.7 26 79.4 96 87.6 82 43.6 99 36.6 35 66.9 39 25.1 42 31.9 38 64.8 65 4.73 51 39.4 62 79.5 81 3.15 48
Sparse Occlusion [54]65.5 14.2 77 38.6 83 1.99 70 25.8 71 39.2 72 2.78 34 19.3 89 32.3 49 1.80 69 59.8 66 68.8 86 41.7 26 79.3 62 87.5 45 43.2 46 37.1 89 68.4 128 25.3 69 32.1 65 64.4 48 4.60 2 39.7 89 79.6 88 3.15 48
ComplOF-FED-GPU [35]67.0 14.0 57 38.0 66 1.91 59 25.3 44 38.5 56 2.90 55 20.2 128 34.6 103 2.16 110 59.5 42 68.5 62 42.5 90 79.2 36 87.4 15 43.2 46 36.6 35 67.4 85 25.0 27 32.2 81 65.4 97 4.75 66 39.7 89 79.8 101 3.19 59
LFNet_ROB [151]67.1 13.8 34 37.5 48 1.80 33 27.0 105 41.7 125 3.08 72 19.6 107 35.5 120 1.87 75 59.2 20 67.4 15 41.7 26 79.1 15 87.4 15 42.8 14 36.8 64 67.3 79 24.8 15 33.2 122 65.7 107 4.79 75 40.4 126 80.0 110 3.26 88
Aniso-Texture [82]67.2 13.6 18 36.6 19 1.82 36 26.2 82 39.3 73 3.20 82 19.6 107 33.0 65 1.96 87 59.7 54 68.5 62 42.6 95 79.4 96 87.6 82 43.6 99 37.0 82 68.4 128 25.7 101 31.9 38 63.8 22 4.63 7 39.4 62 79.3 64 3.16 52
GraphCuts [14]67.4 15.1 117 39.3 108 2.68 114 26.4 87 39.4 80 4.50 114 19.2 81 30.7 16 2.69 126 60.7 109 68.6 74 42.8 99 79.0 8 87.4 15 42.5 7 35.6 2 66.7 25 23.7 2 32.0 52 65.0 73 5.04 113 39.0 19 79.2 56 3.48 121
Fusion [6]68.1 13.8 34 38.4 80 1.84 41 25.3 44 38.1 43 2.88 53 19.1 70 32.2 47 1.90 79 60.9 113 69.8 121 41.8 34 79.1 15 87.9 128 42.1 4 36.0 5 67.8 107 24.1 3 32.7 108 66.3 119 4.88 97 39.5 75 80.4 127 3.26 88
DF-Auto [115]68.6 14.2 77 36.7 25 2.25 96 26.5 89 39.0 68 4.23 107 18.8 44 31.4 32 1.58 25 60.1 90 69.3 104 41.6 18 79.3 62 87.5 45 43.6 99 36.6 35 67.0 49 25.1 42 32.3 88 65.1 81 4.81 85 39.9 97 80.1 115 3.22 74
Classic++ [32]68.8 14.0 57 38.1 68 2.17 84 25.7 69 38.8 63 2.96 59 19.3 89 33.9 87 1.93 83 59.7 54 67.9 38 42.8 99 79.2 36 87.5 45 43.3 55 37.4 105 67.0 49 26.6 128 31.8 23 64.3 38 4.78 74 39.4 62 79.5 81 3.36 105
ALD-Flow [66]69.7 14.1 67 37.9 63 2.17 84 25.4 53 38.4 52 3.14 78 19.1 70 33.9 87 1.73 52 59.6 47 69.0 96 42.6 95 79.4 96 87.6 82 43.6 99 37.0 82 67.5 92 25.6 90 31.7 13 64.0 32 4.69 34 39.4 62 79.5 81 3.20 66
Steered-L1 [118]69.8 13.7 24 37.5 48 1.84 41 25.5 56 38.9 65 3.17 81 19.7 116 33.1 68 2.40 121 60.2 95 68.5 62 42.8 99 79.4 96 87.7 110 43.5 82 36.6 35 67.0 49 25.6 90 31.8 23 64.6 56 4.96 107 38.6 5 79.0 40 3.36 105
p-harmonic [29]70.6 13.5 10 36.7 25 1.85 45 26.7 99 39.9 93 3.25 86 19.4 96 35.2 115 2.10 102 60.1 90 68.7 80 42.2 68 79.3 62 87.5 45 43.3 55 36.7 52 66.7 25 25.3 69 32.6 104 65.8 108 4.76 70 39.4 62 79.5 81 3.17 53
ContFlow_ROB [150]73.7 14.4 94 39.3 108 2.02 73 26.8 100 41.2 117 4.10 105 19.8 121 35.9 126 1.90 79 59.9 77 69.3 104 41.9 40 79.2 36 87.4 15 43.1 27 36.6 35 67.8 107 24.9 18 33.0 119 64.7 60 4.70 38 39.1 29 79.6 88 3.17 53
Shiralkar [42]74.5 14.2 77 39.0 101 2.02 73 26.8 100 40.3 103 2.98 63 18.5 28 38.0 140 2.48 124 60.1 90 67.7 26 41.8 34 78.8 4 87.2 6 42.3 6 37.7 114 67.2 69 26.2 119 33.2 122 67.1 125 4.94 103 39.4 62 79.3 64 3.10 35
AugFNG_ROB [144]74.5 14.6 104 39.7 120 2.31 100 27.3 112 41.3 119 4.30 111 19.5 103 37.8 137 1.92 81 59.8 66 68.8 86 42.1 55 79.4 96 87.7 110 43.3 55 36.3 10 66.4 12 24.9 18 32.7 108 65.6 105 4.73 51 38.8 9 78.6 19 2.84 2
FlowNet2 [122]77.5 15.9 131 41.4 130 2.76 117 27.1 107 40.2 100 4.29 109 19.6 107 34.3 97 1.88 76 60.0 84 70.2 125 42.0 50 79.4 96 87.7 110 43.3 55 36.4 17 66.3 9 24.9 18 32.1 65 64.5 51 4.71 40 39.6 82 79.2 56 3.08 27
HBM-GC [105]77.6 14.7 107 39.4 115 2.41 106 25.4 53 38.1 43 3.07 71 18.0 16 29.8 5 1.56 21 59.8 66 68.2 47 42.8 99 80.1 140 88.0 134 45.9 144 37.5 107 68.2 124 26.1 117 31.9 38 63.3 7 4.99 109 39.3 48 79.1 50 3.30 96
SIOF [67]78.6 14.7 107 39.5 117 2.23 95 27.1 107 40.3 103 4.25 108 19.1 70 32.9 61 1.82 71 59.8 66 68.6 74 42.1 55 79.1 15 87.4 15 43.0 21 37.1 89 67.1 60 25.5 84 32.4 94 64.9 71 4.79 75 40.1 111 79.9 106 3.40 112
CLG-TV [48]78.7 14.3 89 38.8 91 2.17 84 26.6 91 39.8 89 3.24 85 19.5 103 33.9 87 2.11 104 60.0 84 69.0 96 42.4 84 79.3 62 87.6 82 43.5 82 36.6 35 66.9 39 25.1 42 32.1 65 65.1 81 4.71 40 39.9 97 80.0 110 3.20 66
EPMNet [133]78.9 15.7 129 42.3 134 2.55 109 26.9 102 39.5 83 4.05 104 19.6 107 34.3 97 1.88 76 60.1 90 70.4 131 42.0 50 79.4 96 87.7 110 43.3 55 36.5 23 66.9 39 24.9 18 32.1 65 64.5 51 4.71 40 40.0 104 79.3 64 3.05 17
MLDP_OF [89]79.3 13.9 47 38.1 68 1.81 34 25.6 64 38.9 65 2.80 39 18.8 44 32.3 49 1.61 32 59.6 47 68.3 54 42.3 76 79.3 62 87.6 82 43.9 128 39.6 143 68.7 135 28.5 142 33.0 119 65.3 95 5.09 117 39.6 82 79.2 56 3.51 124
Local-TV-L1 [65]82.0 14.9 112 37.3 41 3.21 131 27.3 112 39.5 83 4.67 117 18.9 51 32.3 49 1.70 46 61.3 125 68.6 74 47.1 142 79.3 62 87.6 82 43.6 99 39.0 135 66.7 25 28.9 144 31.7 13 64.3 38 4.79 75 39.3 48 79.1 50 3.41 115
F-TV-L1 [15]82.5 15.0 113 39.3 108 2.88 124 27.2 110 40.2 100 3.69 97 19.2 81 34.5 102 2.19 112 59.7 54 68.4 57 42.8 99 78.9 5 87.4 15 42.7 12 37.3 101 67.0 49 25.6 90 32.1 65 64.5 51 4.89 98 40.1 111 80.0 110 3.42 116
IAOF [50]82.8 15.5 125 39.2 107 2.93 127 29.4 130 43.0 132 5.18 128 17.8 11 33.0 65 2.04 96 60.8 111 68.9 91 42.2 68 79.2 36 87.4 15 43.3 55 36.8 64 67.2 69 25.1 42 32.7 108 65.6 105 4.67 23 40.0 104 80.0 110 3.20 66
3DFlow [135]83.0 14.1 67 38.7 88 1.71 21 25.2 38 38.2 48 2.84 47 19.0 58 32.3 49 1.69 44 59.9 77 69.0 96 42.4 84 79.6 130 87.6 82 45.1 140 37.7 114 69.2 142 25.4 79 33.7 133 66.7 122 4.86 95 39.9 97 79.8 101 3.12 41
OFRF [134]83.2 16.1 133 39.8 122 3.51 135 27.6 116 40.2 100 4.76 119 18.4 25 34.3 97 1.75 59 60.4 99 68.9 91 43.0 110 79.2 36 87.5 45 43.1 27 38.1 122 68.1 121 26.4 124 32.2 81 65.0 73 4.79 75 39.0 19 79.1 50 3.05 17
TCOF [69]83.7 14.4 94 39.3 108 1.83 39 27.3 112 40.9 114 3.35 90 18.7 41 32.1 43 1.50 10 60.2 95 70.2 125 42.1 55 79.3 62 87.6 82 43.2 46 36.9 72 68.5 131 24.8 15 33.3 124 65.8 108 4.72 47 41.2 137 81.4 140 3.46 118
BriefMatch [124]85.4 14.0 57 37.0 33 2.17 84 25.6 64 38.8 63 3.98 103 19.7 116 33.0 65 2.69 126 61.1 121 69.0 96 46.4 139 79.3 62 87.6 82 43.8 124 40.5 146 67.9 113 30.6 146 31.8 23 64.0 32 4.94 103 39.0 19 78.8 31 3.34 101
Adaptive [20]86.5 14.5 100 39.6 119 2.31 100 27.1 107 40.4 106 3.35 90 18.6 37 33.7 80 1.98 89 59.6 47 68.2 47 42.4 84 79.4 96 87.6 82 43.4 72 37.1 89 67.5 92 25.7 101 32.4 94 64.8 65 4.73 51 40.0 104 80.1 115 3.38 110
IIOF-NLDP [131]86.7 14.1 67 38.2 74 1.62 6 26.1 78 39.9 93 2.98 63 19.3 89 32.1 43 1.77 62 60.6 108 69.4 111 43.2 115 79.3 62 87.5 45 43.6 99 37.8 119 68.6 132 25.6 90 34.1 142 69.5 143 5.66 145 39.9 97 79.6 88 3.01 9
CNN-flow-warp+ref [117]86.8 13.8 34 36.0 7 2.35 103 26.6 91 39.8 89 3.83 100 20.0 126 35.5 120 2.34 117 60.9 113 68.9 91 43.0 110 79.4 96 87.6 82 43.7 115 36.8 64 67.0 49 25.6 90 32.1 65 66.2 117 4.94 103 39.4 62 79.5 81 3.19 59
FlowNetS+ft+v [112]87.7 14.7 107 38.1 68 2.80 120 27.5 115 40.6 111 4.81 121 19.6 107 34.9 107 2.07 98 60.1 90 69.5 116 42.2 68 79.4 96 87.7 110 43.4 72 36.6 35 67.1 60 25.2 53 32.0 52 65.4 97 4.73 51 39.6 82 79.7 97 3.21 72
SPSA-learn [13]88.7 14.8 111 37.8 58 2.72 116 27.6 116 40.1 97 4.71 118 20.5 130 33.7 80 2.97 133 60.4 99 67.6 22 41.5 12 79.3 62 87.5 45 43.5 82 36.8 64 67.2 69 25.2 53 33.4 126 70.8 150 6.21 149 39.7 89 79.6 88 3.19 59
AdaConv-v1 [126]89.7 16.5 137 42.3 134 4.36 140 30.4 136 43.8 136 9.06 146 20.6 133 36.3 131 4.45 145 64.5 143 71.3 141 45.3 134 78.4 3 86.7 3 42.2 5 36.3 10 64.9 4 25.4 79 32.5 100 63.7 20 5.53 140 38.0 3 77.4 3 3.53 127
ResPWCR_ROB [145]89.8 13.9 47 38.2 74 1.89 55 26.5 89 40.4 106 3.42 95 19.9 125 35.6 122 1.95 85 60.5 103 70.2 125 43.3 117 78.9 5 87.4 15 42.5 7 42.1 147 67.7 103 32.5 147 33.9 138 65.4 97 4.85 92 40.1 111 79.7 97 3.17 53
LDOF [28]89.8 15.0 113 38.8 91 2.92 125 28.0 123 41.1 116 5.03 125 19.7 116 34.8 106 2.15 108 60.0 84 68.9 91 42.6 95 79.4 96 87.6 82 43.5 82 36.9 72 66.8 34 25.5 84 31.9 38 65.1 81 4.73 51 39.5 75 79.6 88 3.23 80
ROF-ND [107]90.3 15.1 117 37.9 63 1.86 49 26.3 85 40.5 110 3.12 77 19.6 107 32.8 59 1.68 43 60.9 113 71.1 140 41.9 40 79.3 62 87.5 45 43.5 82 37.0 82 68.2 124 24.9 18 34.3 143 68.3 136 5.28 128 40.5 131 80.5 130 3.25 84
CRTflow [80]90.5 14.4 94 38.9 97 2.38 104 26.0 74 39.0 68 3.14 78 20.2 128 36.2 130 2.37 119 60.5 103 69.5 116 44.1 125 79.3 62 87.5 45 43.4 72 37.1 89 67.3 79 25.7 101 32.0 52 64.6 56 4.85 92 39.6 82 79.6 88 3.45 117
HBpMotionGpu [43]90.5 15.8 130 40.2 126 3.66 137 29.5 131 42.8 131 6.27 133 18.5 28 31.9 38 1.73 52 61.3 125 69.9 122 43.9 123 79.1 15 87.6 82 43.0 21 37.6 113 67.6 98 25.9 109 32.0 52 64.3 38 4.67 23 40.0 104 79.9 106 3.75 136
Occlusion-TV-L1 [63]90.8 14.3 89 39.1 103 2.21 94 26.6 91 40.0 95 3.14 78 19.2 81 34.2 95 2.15 108 60.0 84 68.5 62 42.8 99 79.3 62 87.5 45 43.6 99 37.5 107 67.0 49 26.2 119 32.9 114 65.1 81 5.16 122 40.0 104 79.8 101 3.30 96
Modified CLG [34]91.5 14.1 67 37.6 52 2.33 102 28.5 127 41.4 123 5.68 129 19.6 107 35.8 125 2.31 116 60.2 95 68.6 74 42.1 55 79.4 96 87.5 45 43.5 82 36.7 52 67.2 69 25.2 53 32.3 88 66.0 113 4.76 70 40.2 117 80.4 127 3.40 112
CBF [12]92.5 13.7 24 37.2 40 2.15 83 26.0 74 39.4 80 3.28 87 19.1 70 32.1 43 1.79 66 61.0 119 70.0 124 45.8 136 79.6 130 87.8 126 44.9 139 36.8 64 67.4 85 25.2 53 32.2 81 65.5 102 5.22 125 40.0 104 80.2 122 3.99 142
TriangleFlow [30]94.7 14.7 107 40.0 125 2.29 99 26.6 91 40.8 112 3.03 68 19.4 96 33.3 73 2.10 102 60.4 99 69.9 122 42.8 99 79.0 8 87.4 15 42.6 9 37.7 114 68.3 127 25.3 69 33.1 121 67.8 131 5.24 127 40.4 126 80.6 132 3.32 100
2D-CLG [1]95.1 14.5 100 37.6 52 2.76 117 29.8 133 42.4 128 6.69 140 19.7 116 35.2 115 2.74 129 60.7 109 68.7 80 41.5 12 79.4 96 87.7 110 43.5 82 36.6 35 67.0 49 25.1 42 32.5 100 66.7 122 4.90 100 40.2 117 80.1 115 3.25 84
Nguyen [33]95.8 15.6 126 38.5 81 3.62 136 30.1 135 43.2 133 6.04 131 19.6 107 36.3 131 2.25 114 61.1 121 69.4 111 42.0 50 79.2 36 87.5 45 43.1 27 36.4 17 67.2 69 24.7 14 34.3 143 67.4 128 5.00 110 40.2 117 80.3 123 3.29 93
SegOF [10]95.9 14.2 77 36.8 28 2.54 108 27.0 105 40.0 95 4.18 106 21.1 136 36.1 129 3.15 138 60.5 103 70.7 136 41.6 18 79.4 96 87.6 82 43.6 99 36.9 72 68.2 124 25.2 53 32.5 100 68.0 135 5.31 132 39.6 82 79.4 73 3.22 74
ACK-Prior [27]95.9 13.8 34 38.1 68 1.74 27 25.5 56 39.3 73 2.82 44 19.6 107 33.8 86 2.45 123 60.5 103 70.3 128 42.3 76 80.2 141 88.0 134 45.8 143 38.2 123 67.8 107 26.9 132 32.6 104 66.2 117 5.35 135 38.9 11 79.7 97 3.60 132
BlockOverlap [61]95.9 15.1 117 37.6 52 3.31 133 27.7 119 39.3 73 5.73 130 18.6 37 30.3 7 2.09 101 60.9 113 68.2 47 47.1 142 80.2 141 87.9 128 46.5 145 39.0 135 67.3 79 28.4 141 31.9 38 63.9 26 5.09 117 39.7 89 79.3 64 3.55 128
IAOF2 [51]96.9 15.6 126 41.3 129 2.58 111 27.6 116 41.4 123 4.29 109 17.8 11 33.6 77 1.94 84 61.2 124 70.8 137 42.8 99 79.4 96 87.7 110 43.3 55 37.2 97 67.5 92 25.6 90 32.3 88 65.0 73 4.63 7 40.6 132 80.4 127 3.40 112
TV-L1-improved [17]98.1 14.2 77 38.8 91 2.25 96 26.9 102 40.3 103 3.40 94 19.5 103 33.9 87 2.44 122 59.9 77 69.0 96 42.7 98 79.4 96 87.7 110 43.5 82 37.2 97 67.6 98 25.8 106 32.1 65 66.1 115 5.05 114 39.9 97 80.0 110 3.46 118
StereoOF-V1MT [119]98.8 14.6 104 39.9 123 2.00 72 27.2 110 41.9 126 3.04 69 20.9 135 37.8 137 2.85 132 61.3 125 68.3 54 43.8 121 79.2 36 87.5 45 42.9 15 38.2 123 67.8 107 26.3 123 33.8 134 68.5 137 5.36 136 40.0 104 79.4 73 3.09 31
Dynamic MRF [7]98.9 13.9 47 38.6 83 1.90 57 26.1 78 40.4 106 3.08 72 20.0 126 37.7 136 2.73 128 61.3 125 69.3 104 44.6 129 79.1 15 87.6 82 43.0 21 37.7 114 68.0 117 25.9 109 32.6 104 67.2 126 5.08 116 40.4 126 80.5 130 3.49 123
Correlation Flow [75]99.0 14.0 57 38.3 77 1.61 4 26.2 82 39.8 89 2.98 63 19.1 70 31.9 38 1.73 52 60.4 99 69.4 111 43.6 120 80.2 141 87.9 128 47.8 148 38.0 121 68.7 135 26.0 114 33.4 126 67.2 126 5.29 129 40.1 111 80.3 123 3.39 111
Rannacher [23]101.7 14.4 94 39.3 108 2.38 104 26.9 102 40.4 106 3.36 93 19.5 103 34.6 103 2.58 125 59.8 66 68.8 86 42.8 99 79.4 96 87.7 110 43.6 99 37.2 97 67.8 107 25.8 106 32.2 81 66.0 113 5.02 111 39.9 97 79.9 106 3.56 129
Black & Anandan [4]102.1 15.3 121 38.8 91 2.96 129 28.4 125 40.9 114 4.78 120 20.5 130 35.2 115 2.74 129 60.9 113 69.3 104 42.1 55 79.4 96 87.7 110 43.6 99 37.1 89 66.6 21 25.6 90 32.9 114 65.9 112 4.72 47 40.3 120 80.3 123 3.25 84
LocallyOriented [52]104.7 15.0 113 40.3 127 2.53 107 27.7 119 41.3 119 3.86 101 19.4 96 34.4 100 1.95 85 61.1 121 70.6 133 43.3 117 79.2 36 87.5 45 43.3 55 39.1 139 68.1 121 27.6 138 32.9 114 65.8 108 4.72 47 40.6 132 80.6 132 3.37 108
UnFlow [129]106.5 16.0 132 42.8 137 2.87 123 30.6 139 45.2 145 4.52 115 21.3 139 39.4 143 2.81 131 60.0 84 68.3 54 42.1 55 79.2 36 87.4 15 43.5 82 37.5 107 68.0 117 25.2 53 33.8 134 65.1 81 4.98 108 43.2 149 81.8 144 3.67 134
Filter Flow [19]110.8 15.0 113 39.4 115 2.78 119 28.4 125 40.8 112 6.31 134 18.5 28 32.9 61 2.14 106 61.7 131 69.3 104 45.3 134 79.7 134 88.0 134 44.5 135 37.3 101 67.7 103 26.1 117 32.1 65 65.2 91 4.93 101 40.3 120 80.7 135 3.97 141
TVL1_ROB [139]112.1 16.2 134 39.3 108 4.14 139 30.4 136 43.4 134 6.39 135 19.0 58 35.0 109 2.05 97 61.4 130 69.2 102 43.0 110 79.5 126 87.7 110 43.8 124 37.5 107 67.2 69 26.0 114 32.4 94 66.3 119 4.95 106 40.1 111 80.3 123 3.30 96
StereoFlow [44]112.2 22.8 149 51.1 150 4.80 141 36.2 149 51.1 150 6.57 137 19.2 81 34.6 103 1.89 78 60.0 84 68.5 62 42.4 84 80.3 144 89.1 149 43.9 128 39.0 135 74.1 150 25.3 69 32.1 65 65.0 73 4.73 51 40.3 120 80.9 136 3.36 105
WOLF_ROB [149]116.7 15.6 126 41.7 132 2.64 113 27.8 121 41.3 119 3.72 98 19.7 116 35.2 115 2.02 95 61.3 125 71.8 142 44.5 128 79.4 96 87.8 126 43.7 115 38.8 133 67.9 113 27.5 137 34.4 145 67.7 129 5.09 117 39.9 97 79.6 88 3.22 74
Ad-TV-NDC [36]117.0 17.2 140 39.9 123 5.26 143 29.6 132 42.1 127 6.18 132 19.2 81 33.7 80 1.98 89 62.4 133 70.3 128 45.2 133 79.6 130 87.9 128 43.9 128 38.3 126 67.3 79 27.2 136 32.3 88 65.5 102 4.80 83 40.3 120 80.1 115 3.58 131
Bartels [41]118.0 14.6 104 39.3 108 2.80 120 26.1 78 39.7 86 4.45 113 19.0 58 33.2 71 2.14 106 62.1 132 70.9 138 48.9 144 80.7 148 88.1 137 49.2 150 43.7 149 69.0 141 34.8 150 32.4 94 65.0 73 5.76 146 40.4 126 80.1 115 4.26 144
TI-DOFE [24]120.0 17.9 143 43.0 138 5.41 144 32.3 145 46.2 147 7.98 144 20.5 130 38.1 141 2.97 133 63.1 140 70.6 133 43.8 121 79.1 15 87.6 82 43.1 27 37.7 114 67.4 85 25.8 106 33.4 126 67.8 131 5.09 117 41.6 141 81.5 142 3.68 135
Horn & Schunck [3]120.5 15.3 121 40.4 128 2.69 115 29.0 128 42.7 129 5.10 126 21.1 136 37.9 139 3.33 139 62.5 135 70.3 128 43.0 110 79.3 62 87.7 110 43.6 99 37.5 107 67.3 79 25.9 109 33.9 138 68.5 137 5.03 112 41.2 137 81.2 139 3.57 130
GroupFlow [9]123.6 16.8 139 43.4 139 3.43 134 29.1 129 43.9 137 5.11 127 22.2 142 39.3 142 3.53 140 61.0 119 70.6 133 42.5 90 79.7 134 88.1 137 44.0 131 39.0 135 69.4 146 26.8 131 32.8 111 66.8 124 4.87 96 40.4 126 80.1 115 3.01 9
2bit-BM-tele [98]125.2 15.3 121 39.5 117 3.22 132 27.8 121 41.2 117 4.90 122 18.8 44 32.5 55 2.34 117 62.4 133 71.0 139 49.0 145 80.6 146 88.2 142 47.9 149 42.8 148 69.3 145 32.9 148 33.4 126 70.0 147 6.77 150 40.3 120 79.4 73 4.33 147
SLK [47]126.1 17.4 141 43.9 142 4.90 142 30.5 138 44.0 138 7.18 142 22.5 143 39.8 144 4.15 144 64.5 143 70.5 132 46.7 140 78.9 5 87.7 110 41.6 2 38.5 128 68.8 137 26.0 114 33.8 134 70.1 149 5.50 139 41.6 141 81.4 140 3.91 139
SILK [79]127.0 16.3 135 42.0 133 4.01 138 29.9 134 43.5 135 6.44 136 21.6 140 37.4 135 3.55 141 62.6 136 69.4 111 47.0 141 79.3 62 87.7 110 43.6 99 39.9 144 68.1 121 29.2 145 32.8 111 67.8 131 5.14 121 40.6 132 80.6 132 3.52 126
NL-TV-NCC [25]127.4 15.1 117 41.6 131 1.86 49 26.6 91 41.3 119 3.02 67 20.8 134 35.7 123 2.24 113 63.2 141 73.9 146 45.9 137 81.3 150 88.7 148 49.9 151 38.6 130 69.8 148 25.6 90 37.6 149 69.5 143 5.62 143 42.4 147 82.1 147 4.00 143
HCIC-L [99]128.8 23.2 150 49.0 149 11.0 150 32.1 144 44.4 139 9.93 147 23.2 145 36.4 133 3.02 135 64.4 142 72.1 143 44.9 130 80.6 146 88.5 146 46.6 146 39.1 139 68.9 139 27.1 134 32.4 94 65.0 73 5.53 140 39.1 29 79.3 64 3.65 133
H+S_ROB [138]130.0 16.5 137 43.7 140 2.94 128 31.9 142 44.6 140 6.58 138 24.0 146 42.8 147 4.50 146 65.7 146 69.3 104 44.4 127 79.4 96 88.2 142 43.1 27 38.5 128 68.6 132 25.6 90 34.6 146 70.0 147 5.57 142 43.1 148 81.5 142 3.83 138
Heeger++ [104]130.5 17.5 142 47.2 148 2.80 120 31.1 141 44.9 143 4.93 123 26.6 148 47.7 149 4.79 147 62.6 136 68.0 41 45.1 131 79.8 138 88.4 145 44.1 132 39.1 139 68.9 139 26.5 127 34.8 147 67.9 134 5.23 126 41.5 140 80.1 115 3.23 80
Learning Flow [11]132.6 15.3 121 42.7 136 2.55 109 28.0 123 42.7 129 3.95 102 21.1 136 37.0 134 3.03 137 63.0 139 73.3 145 46.2 138 80.0 139 88.2 142 45.1 140 38.2 123 68.6 132 26.7 129 33.8 134 68.5 137 5.21 124 41.9 145 82.3 148 3.95 140
FFV1MT [106]132.6 16.4 136 44.7 144 3.13 130 31.9 142 44.7 141 7.15 141 25.4 147 45.6 148 5.04 148 62.6 136 68.0 41 45.1 131 79.6 130 87.9 128 44.1 132 38.9 134 67.7 103 27.1 134 34.0 141 68.5 137 5.29 129 41.8 144 81.0 137 4.48 149
Adaptive flow [45]136.0 19.6 145 44.1 143 6.76 145 32.8 146 45.7 146 10.2 148 19.8 121 34.4 100 3.02 135 64.7 145 72.1 143 49.4 146 80.3 144 88.6 147 45.6 142 38.3 126 69.2 142 26.7 129 32.6 104 66.5 121 5.45 138 41.0 135 81.1 138 3.75 136
Pyramid LK [2]138.1 21.2 148 43.7 140 10.7 149 33.1 148 45.1 144 11.9 149 27.3 149 36.0 127 6.46 149 70.7 150 78.5 150 57.7 150 79.5 126 88.1 137 43.3 55 38.6 130 68.8 137 27.0 133 33.5 131 68.8 141 6.00 147 41.0 135 81.8 144 4.31 146
FOLKI [16]141.8 20.9 146 46.0 145 9.48 148 32.8 146 47.4 148 8.75 145 21.6 140 40.7 145 4.10 143 67.2 149 74.2 148 53.7 149 79.5 126 88.1 137 43.7 115 39.2 142 69.2 142 27.9 139 33.4 126 69.5 143 5.65 144 41.7 143 82.3 148 4.28 145
PGAM+LK [55]142.1 19.4 144 46.4 146 6.81 146 30.9 140 44.8 142 7.52 143 22.7 144 40.9 146 3.99 142 66.6 148 73.9 146 52.4 148 79.7 134 88.1 137 44.5 135 40.2 145 69.7 147 28.8 143 33.3 124 69.3 142 5.42 137 41.4 139 81.8 144 4.36 148
Periodicity [78]148.1 21.0 147 47.0 147 9.32 147 38.1 150 48.1 149 14.7 150 29.8 150 47.9 150 9.27 150 66.0 147 77.1 149 50.7 147 80.8 149 89.3 150 46.8 147 45.1 150 70.6 149 35.5 151 33.5 131 69.6 146 6.07 148 43.5 150 84.0 150 6.51 150
AVG_FLOW_ROB [142]150.2 51.4 151 76.8 151 29.6 151 67.5 151 74.0 151 36.6 151 51.8 151 59.9 151 20.1 151 84.7 151 90.1 151 64.7 151 81.8 151 91.0 151 44.5 135 51.7 151 87.4 151 33.4 149 57.5 151 81.8 151 10.1 151 63.2 151 86.1 151 26.5 151
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] ContFlow_ROB 0.45 all color Anonymous. Continual Flow. ROB 2018 submission.
[151] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
* 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.