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        
A95
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
PMMST [114]8.9 5.00 6 9.68 15 2.00 3 6.88 24 11.0 12 2.08 1 5.69 7 9.00 5 1.73 1 8.21 5 12.0 6 5.07 3 17.4 6 23.4 6 5.07 13 9.29 9 22.6 6 3.74 25 8.66 11 37.1 14 2.45 2 13.9 16 21.3 16 2.16 1
MDP-Flow2 [68]11.3 4.97 5 9.42 9 2.00 3 6.68 10 11.0 12 2.08 1 5.69 7 9.04 10 1.73 1 8.19 2 12.0 6 5.10 26 17.5 8 23.5 9 5.07 13 9.95 38 24.7 37 3.74 25 8.60 7 36.4 6 2.45 2 13.9 16 21.5 18 2.16 1
NNF-Local [87]20.5 5.07 14 10.1 29 2.00 3 6.40 2 10.0 4 2.08 1 5.69 7 9.00 5 1.73 1 8.66 39 14.5 83 5.10 26 17.6 11 23.8 18 5.07 13 10.4 72 25.8 69 3.74 25 8.66 11 37.5 20 2.45 2 13.9 16 21.6 21 2.16 1
CtxSyn [137]20.8 3.87 1 7.35 1 1.83 2 5.80 1 8.96 1 2.08 1 3.11 1 5.69 1 2.00 90 7.33 1 9.95 1 4.97 1 17.1 4 22.5 3 4.93 4 8.70 4 20.9 2 3.74 25 10.2 119 33.7 4 2.52 110 12.6 1 18.8 1 2.38 120
PH-Flow [101]21.3 5.20 43 10.7 59 2.00 3 6.45 4 10.3 6 2.08 1 5.69 7 9.38 16 1.73 1 8.19 2 11.9 3 5.07 3 17.7 24 24.0 29 5.03 9 10.6 88 26.5 89 3.70 2 8.68 15 38.8 56 2.45 2 14.0 23 21.7 25 2.16 1
NN-field [71]21.7 5.07 14 10.4 45 2.00 3 6.45 4 10.0 4 2.08 1 5.97 55 9.00 5 1.73 1 8.76 53 15.0 95 5.10 26 17.6 11 23.7 14 5.07 13 10.1 50 25.0 45 3.74 25 8.54 5 36.9 11 2.45 2 13.9 16 21.6 21 2.16 1
FGIK [136]23.6 4.73 4 9.49 10 2.16 96 7.85 76 11.9 37 2.45 118 4.00 3 7.39 4 1.73 1 9.88 122 14.4 77 5.07 3 14.2 1 19.1 1 4.76 1 7.14 1 19.1 1 3.56 1 7.05 1 27.6 1 2.38 1 12.6 1 19.4 4 2.16 1
NNF-EAC [103]24.1 5.35 78 10.0 25 2.08 67 7.05 34 11.6 26 2.08 1 6.00 56 9.35 13 1.73 1 8.35 9 12.4 11 5.23 89 17.7 24 23.9 26 5.07 13 9.47 10 22.9 7 3.70 2 8.83 26 37.0 13 2.45 2 14.0 23 21.6 21 2.16 1
IROF++ [58]25.9 5.23 62 10.8 68 2.00 3 6.88 24 11.5 24 2.08 1 6.00 56 10.0 33 1.73 1 8.19 2 11.9 3 5.07 3 17.9 46 24.4 53 5.10 34 9.49 12 24.2 28 3.74 25 9.09 60 37.2 17 2.45 2 14.0 23 22.1 40 2.16 1
SepConv-v1 [127]27.3 3.87 1 8.50 3 1.73 1 7.05 34 11.4 19 2.16 68 3.46 2 6.56 3 2.00 90 8.58 33 12.6 20 5.26 106 17.5 8 23.6 10 4.97 5 8.35 3 22.4 5 3.70 2 8.08 3 33.3 3 2.52 110 12.8 4 19.1 2 2.38 120
SuperSlomo [132]29.2 4.24 3 7.53 2 2.16 96 7.14 40 11.4 19 2.71 132 4.36 4 6.45 2 2.00 90 8.27 6 11.3 2 5.10 26 16.7 2 22.2 2 4.80 2 8.29 2 21.0 3 3.74 25 8.60 7 32.7 2 2.52 110 12.6 1 19.1 2 2.38 120
DF-Auto [115]30.1 5.03 11 8.87 4 2.16 96 7.72 70 13.1 67 2.38 104 5.69 7 9.20 12 1.73 1 8.68 42 12.5 15 5.10 26 17.4 6 23.4 6 5.16 61 9.47 10 24.0 21 3.74 25 8.98 40 38.4 43 2.45 2 14.0 23 21.8 29 2.16 1
DeepFlow2 [108]30.5 5.07 14 9.85 20 2.08 67 7.53 64 13.1 67 2.16 68 5.69 7 10.0 33 1.73 1 8.83 71 13.4 48 5.10 26 17.6 11 23.7 14 5.20 69 9.24 7 23.0 8 3.74 25 9.00 43 37.9 32 2.45 2 13.9 16 21.5 18 2.16 1
COFM [59]32.1 5.07 14 10.7 59 2.00 3 6.86 23 11.4 19 2.08 1 5.69 7 9.75 24 1.73 1 8.35 9 12.5 15 5.07 3 18.1 69 24.7 72 5.03 9 11.0 114 27.5 117 3.70 2 8.06 2 39.1 60 2.45 2 14.4 75 22.7 69 2.16 1
WLIF-Flow [93]32.5 5.10 34 10.2 35 2.00 3 7.00 33 11.9 37 2.08 1 5.69 7 9.68 19 1.73 1 8.29 7 12.2 8 5.23 89 17.8 34 24.0 29 5.10 34 10.6 88 26.6 93 3.83 107 8.83 26 37.5 20 2.45 2 14.1 37 21.9 36 2.16 1
LME [70]33.6 5.07 14 10.1 29 2.00 3 7.05 34 12.0 41 2.16 68 5.69 7 10.7 85 1.73 1 8.35 9 12.8 29 5.10 26 18.0 56 24.4 53 5.29 142 10.2 58 25.3 54 3.74 25 8.70 16 36.4 6 2.45 2 14.0 23 21.7 25 2.16 1
DeepFlow [86]34.2 5.07 14 9.63 14 2.08 67 7.44 60 13.0 61 2.16 68 5.74 48 10.0 33 1.73 1 8.96 84 13.0 32 5.20 59 17.6 11 23.8 18 5.20 69 9.15 6 23.2 10 3.87 117 8.81 23 35.6 5 2.45 2 13.7 8 21.1 10 2.16 1
Layers++ [37]34.4 5.10 34 10.1 29 2.08 67 6.45 4 9.88 2 2.08 1 5.69 7 10.0 33 1.73 1 8.37 16 12.7 25 5.10 26 18.1 69 24.9 95 5.10 34 10.7 99 28.3 130 3.74 25 8.76 17 38.0 36 2.45 2 14.1 37 21.9 36 2.16 1
CombBMOF [113]34.5 5.35 78 10.5 51 2.00 3 6.83 21 11.4 19 2.08 1 5.80 51 10.0 33 1.73 1 8.83 71 14.4 77 5.10 26 17.9 46 24.3 47 5.07 13 9.88 32 24.1 24 3.70 2 10.7 130 38.3 39 2.45 2 14.0 23 21.9 36 2.16 1
ProbFlowFields [128]34.5 5.03 11 10.7 59 2.00 3 6.68 10 11.3 16 2.08 1 5.69 7 9.47 17 1.73 1 8.52 30 13.3 47 5.20 59 18.2 93 24.9 95 5.23 124 10.5 77 26.2 84 3.74 25 8.60 7 37.7 27 2.45 2 13.8 11 21.6 21 2.16 1
nLayers [57]34.6 5.16 41 10.5 51 2.00 3 6.66 9 10.9 10 2.08 1 5.69 7 9.00 5 1.73 1 8.49 29 13.0 32 5.10 26 18.3 103 25.2 114 5.20 69 10.4 72 25.6 62 3.74 25 8.66 11 38.5 48 2.45 2 14.2 53 22.4 56 2.16 1
SuperFlow [81]35.2 5.00 6 9.35 6 2.16 96 7.85 76 13.1 67 2.38 104 6.00 56 9.47 17 2.00 90 8.70 46 12.7 25 5.20 59 17.6 11 23.7 14 5.20 69 9.27 8 23.9 19 3.70 2 8.81 23 37.6 23 2.45 2 13.8 11 21.2 13 2.16 1
FMOF [94]36.2 5.42 99 11.0 78 2.00 3 6.76 16 11.0 12 2.08 1 6.00 56 10.3 62 1.73 1 8.83 71 14.1 69 5.10 26 17.8 34 24.1 37 5.07 13 10.0 48 25.6 62 3.74 25 8.58 6 37.7 27 2.45 2 14.3 63 22.4 56 2.16 1
IROF-TV [53]36.2 5.20 43 10.7 59 2.08 67 7.05 34 11.9 37 2.08 1 6.00 56 10.3 62 1.73 1 8.37 16 12.6 20 5.16 50 17.8 34 24.1 37 5.23 124 10.1 50 25.0 45 3.70 2 9.04 52 39.1 60 2.45 2 13.7 8 21.0 8 2.16 1
Sparse-NonSparse [56]36.6 5.20 43 10.7 59 2.00 3 6.78 17 11.6 26 2.08 1 5.69 7 10.0 33 1.73 1 8.43 25 12.5 15 5.07 3 18.1 69 24.7 72 5.10 34 10.5 77 26.7 96 3.74 25 8.76 17 42.1 104 2.45 2 14.3 63 23.0 85 2.16 1
Aniso. Huber-L1 [22]36.7 5.26 64 10.0 25 2.08 67 8.81 106 14.5 109 2.16 68 6.00 56 9.75 24 1.73 1 8.72 49 13.0 32 5.16 50 17.6 11 23.8 18 5.10 34 9.87 31 23.2 10 3.70 2 9.26 73 37.8 29 2.45 2 13.8 11 21.0 8 2.16 1
Brox et al. [5]36.8 5.20 43 9.83 17 2.00 3 7.62 69 12.6 49 2.16 68 6.00 56 10.2 58 2.00 90 8.76 53 12.6 20 5.07 3 17.5 8 23.6 10 5.16 61 10.1 50 25.3 54 3.74 25 9.00 43 40.1 74 2.45 2 13.8 11 21.3 16 2.16 1
FlowFields [110]37.2 5.10 34 11.1 88 2.00 3 6.88 24 11.5 24 2.08 1 5.69 7 10.0 33 1.73 1 8.76 53 14.9 91 5.20 59 18.0 56 24.4 53 5.16 61 10.3 65 25.8 69 3.74 25 8.76 17 37.8 29 2.45 2 14.1 37 22.5 61 2.16 1
TV-L1-MCT [64]37.7 5.48 117 11.4 100 2.00 3 7.35 48 13.1 67 2.08 1 5.48 5 10.3 62 1.73 1 8.35 9 12.4 11 5.07 3 18.3 103 25.3 119 5.10 34 9.49 12 23.5 14 3.79 86 8.81 23 39.2 65 2.45 2 13.7 8 21.1 10 2.16 1
ComponentFusion [96]38.4 5.07 14 11.2 94 2.00 3 6.81 20 11.6 26 2.08 1 5.72 47 9.81 28 1.73 1 8.37 16 13.2 44 5.07 3 18.1 69 24.7 72 5.10 34 9.90 33 24.9 43 3.74 25 9.20 70 44.1 123 2.45 2 14.2 53 23.3 100 2.16 1
MDP-Flow [26]39.0 5.03 11 9.95 23 2.00 3 6.68 10 11.3 16 2.08 1 5.69 7 9.04 10 1.73 1 8.89 79 13.7 55 5.20 59 17.8 34 24.2 45 5.20 69 11.3 127 27.9 124 3.74 25 9.27 77 39.3 67 2.45 2 14.1 37 22.3 52 2.16 1
JOF [141]39.4 5.35 78 10.8 68 2.08 67 6.68 10 10.9 10 2.08 1 5.69 7 9.68 19 1.73 1 8.39 21 12.5 15 5.20 59 18.1 69 24.7 72 5.20 69 10.6 88 27.1 106 3.74 25 8.66 11 37.6 23 2.45 2 14.3 63 22.5 61 2.16 1
PGM-C [120]41.6 5.07 14 10.9 75 2.00 3 6.93 27 11.6 26 2.08 1 6.00 56 10.3 62 1.73 1 8.76 53 15.2 99 5.16 50 18.0 56 24.7 72 5.20 69 9.97 43 24.8 41 3.74 25 9.00 43 40.1 74 2.45 2 14.1 37 22.7 69 2.16 1
2DHMM-SAS [92]41.7 5.42 99 11.2 94 2.00 3 7.90 81 13.7 86 2.08 1 5.60 6 9.85 29 1.73 1 8.35 9 12.2 8 5.10 26 18.0 56 24.6 70 5.10 34 9.93 36 25.7 66 3.74 25 8.96 35 39.8 72 2.45 2 14.4 75 23.0 85 2.16 1
FlowFields+ [130]42.1 5.10 34 11.1 88 2.00 3 6.78 17 11.3 16 2.08 1 5.69 7 10.0 33 1.73 1 8.70 46 14.9 91 5.16 50 18.2 93 24.9 95 5.20 69 10.4 72 26.3 87 3.74 25 8.79 21 38.6 52 2.45 2 14.1 37 22.7 69 2.16 1
CLG-TV [48]42.2 5.20 43 9.49 10 2.08 67 8.43 97 14.3 103 2.16 68 6.00 56 10.1 54 2.00 90 8.76 53 13.1 40 5.20 59 17.6 11 23.8 18 5.10 34 9.59 20 23.1 9 3.74 25 9.20 70 38.4 43 2.45 2 14.0 23 21.5 18 2.16 1
CPM-Flow [116]42.8 5.07 14 10.9 75 2.00 3 6.95 29 11.6 26 2.08 1 5.80 51 10.0 33 1.73 1 9.00 89 15.9 114 5.20 59 18.1 69 24.7 72 5.20 69 9.81 24 24.3 29 3.79 86 9.26 73 38.3 39 2.45 2 14.0 23 22.2 46 2.16 1
ALD-Flow [66]43.3 5.20 43 10.7 59 2.08 67 7.35 48 12.9 56 2.16 68 6.00 56 10.1 54 1.73 1 8.39 21 13.0 32 5.16 50 17.9 46 24.3 47 5.20 69 9.56 17 23.5 14 3.79 86 8.79 21 36.8 10 2.45 2 14.5 86 23.0 85 2.16 1
HAST [109]44.5 5.07 14 10.5 51 2.00 3 6.68 10 10.7 9 2.08 1 6.00 56 10.3 62 1.73 1 8.29 7 12.4 11 5.00 2 18.4 115 25.3 119 5.03 9 11.0 114 30.7 143 3.70 2 8.60 7 41.8 97 2.45 2 14.9 116 23.9 117 2.16 1
S2F-IF [123]44.6 5.10 34 11.6 111 2.00 3 6.78 17 11.4 19 2.08 1 5.69 7 10.3 62 1.73 1 8.74 50 15.2 99 5.07 3 18.3 103 25.1 110 5.20 69 10.5 77 26.1 79 3.74 25 9.02 50 38.5 48 2.45 2 14.1 37 22.6 63 2.16 1
Second-order prior [8]44.7 5.20 43 9.83 17 2.08 67 8.43 97 14.5 109 2.08 1 6.35 106 11.0 102 2.00 90 8.83 71 13.8 62 5.07 3 17.7 24 23.8 18 5.07 13 9.70 22 24.1 24 3.74 25 9.33 81 38.4 43 2.45 2 14.0 23 21.8 29 2.16 1
Ramp [62]45.4 5.29 71 10.8 68 2.00 3 6.83 21 11.6 26 2.08 1 5.69 7 10.1 54 1.73 1 8.35 9 12.2 8 5.07 3 18.1 69 24.7 72 5.10 34 10.9 109 27.8 123 3.79 86 8.83 26 43.0 115 2.45 2 14.5 86 23.2 94 2.16 1
CBF [12]46.0 5.00 6 9.40 8 2.08 67 7.77 74 13.0 61 2.16 68 6.00 56 9.68 19 1.73 1 8.68 42 12.5 15 5.35 124 17.6 11 23.4 6 5.20 69 9.85 29 24.3 29 3.74 25 9.11 64 39.3 67 2.52 110 14.0 23 21.1 10 2.38 120
Local-TV-L1 [65]46.8 5.20 43 9.38 7 2.16 96 8.96 112 14.5 109 2.38 104 5.69 7 9.35 13 1.73 1 8.70 46 13.0 32 5.45 131 17.6 11 23.8 18 5.16 61 9.54 16 24.0 21 4.08 142 8.76 17 37.2 17 2.45 2 13.6 7 20.9 7 2.31 102
SIOF [67]46.9 5.42 99 10.4 45 2.08 67 8.83 107 15.0 123 2.38 104 5.69 7 10.4 82 1.73 1 8.68 42 13.1 40 5.20 59 17.3 5 23.2 5 5.07 13 9.83 25 23.6 16 3.74 25 9.00 43 36.9 11 2.45 2 14.3 63 22.1 40 2.31 102
p-harmonic [29]47.1 5.07 14 9.98 24 2.00 3 8.68 103 14.4 105 2.16 68 6.00 56 10.7 85 1.91 85 9.20 101 13.7 55 5.20 59 17.8 34 24.0 29 5.10 34 9.90 33 23.7 17 3.74 25 9.61 101 38.5 48 2.45 2 14.0 23 21.7 25 2.16 1
LDOF [28]48.1 5.35 78 9.83 17 2.16 96 7.94 82 12.1 42 2.52 125 6.00 56 10.3 62 2.00 90 8.91 82 13.6 53 5.23 89 17.6 11 23.6 10 5.20 69 9.49 12 24.5 34 3.74 25 8.96 35 37.9 32 2.45 2 14.0 23 21.8 29 2.16 1
DPOF [18]48.2 5.35 78 11.7 113 2.08 67 6.56 8 10.4 7 2.08 1 6.00 56 9.71 23 1.91 85 8.76 53 14.4 77 5.20 59 17.7 24 24.1 37 5.07 13 10.3 65 26.7 96 3.70 2 9.33 81 39.1 60 2.45 2 14.4 75 22.8 75 2.16 1
ProFlow_ROB [147]48.9 5.07 14 10.9 75 2.00 3 7.33 46 12.7 51 2.16 68 5.69 7 9.98 32 1.73 1 8.60 36 14.1 69 5.20 59 18.3 103 25.2 114 5.20 69 9.52 15 23.4 13 3.70 2 9.49 95 42.0 102 2.45 2 14.5 86 23.6 111 2.16 1
ComplOF-FED-GPU [35]49.0 5.20 43 11.1 88 2.00 3 7.19 44 12.6 49 2.08 1 6.35 106 10.0 33 2.00 90 8.68 42 14.0 68 5.10 26 17.9 46 24.5 61 5.10 34 9.97 43 25.1 48 3.74 25 9.40 86 38.8 56 2.45 2 14.5 86 23.2 94 2.16 1
LSM [39]49.5 5.35 78 11.5 105 2.00 3 6.98 30 11.9 37 2.08 1 5.80 51 10.7 85 1.73 1 8.58 33 13.4 48 5.07 3 18.1 69 24.9 95 5.10 34 10.6 88 27.1 106 3.74 25 8.83 26 42.2 106 2.45 2 14.4 75 23.0 85 2.16 1
AGIF+OF [85]49.6 5.42 99 11.1 88 2.00 3 6.98 30 11.8 34 2.08 1 5.69 7 10.0 33 1.73 1 8.43 25 12.8 29 5.07 3 18.5 123 25.2 114 5.20 69 10.8 105 27.6 118 3.74 25 8.98 40 37.9 32 2.45 2 14.7 104 23.4 104 2.16 1
OFLAF [77]50.0 5.07 14 10.6 56 2.00 3 6.48 7 10.5 8 2.08 1 5.69 7 10.0 33 1.73 1 8.37 16 12.6 20 5.07 3 18.4 115 25.4 126 5.20 69 10.9 109 27.4 115 3.74 25 9.59 100 44.9 129 2.45 2 15.1 122 24.1 119 2.16 1
Classic+NL [31]50.2 5.35 78 11.0 78 2.08 67 6.98 30 11.7 32 2.08 1 5.69 7 10.2 58 1.73 1 8.43 25 12.4 11 5.20 59 18.1 69 24.8 85 5.10 34 10.6 88 26.8 99 3.79 86 8.83 26 42.9 111 2.45 2 14.4 75 22.9 82 2.16 1
FC-2Layers-FF [74]50.2 5.26 64 11.0 78 2.00 3 6.40 2 9.88 2 2.08 1 5.69 7 10.3 62 1.73 1 8.39 21 12.8 29 5.10 26 18.2 93 25.0 104 5.20 69 11.0 114 28.1 126 3.79 86 8.91 33 42.8 110 2.45 2 14.5 86 23.0 85 2.16 1
RFlow [90]51.1 5.07 14 10.2 35 2.08 67 8.58 101 14.7 115 2.08 1 6.00 56 10.3 62 1.73 1 8.91 82 14.4 77 5.20 59 17.7 24 23.9 26 5.10 34 9.95 38 25.4 57 3.70 2 9.13 66 40.4 80 2.45 2 14.3 63 22.6 63 2.31 102
OAR-Flow [125]51.2 5.20 43 10.7 59 2.08 67 7.44 60 13.0 61 2.16 68 5.74 48 10.0 33 1.73 1 8.35 9 13.0 32 5.10 26 18.1 69 24.9 95 5.23 124 10.2 58 24.7 37 3.74 25 9.54 97 39.4 70 2.45 2 14.4 75 22.7 69 2.16 1
RNLOD-Flow [121]51.5 5.20 43 11.0 78 2.00 3 7.53 64 13.4 75 2.08 1 6.00 56 11.0 102 1.73 1 8.52 30 13.0 32 5.07 3 18.2 93 25.0 104 5.10 34 10.6 88 26.9 102 3.74 25 8.96 35 38.4 43 2.45 2 14.9 116 23.5 106 2.16 1
TF+OM [100]52.1 5.00 6 10.2 35 2.08 67 6.93 27 11.7 32 2.16 68 5.69 7 10.5 83 1.73 1 8.81 66 14.6 85 5.20 59 18.0 56 24.4 53 5.20 69 9.95 38 26.1 79 3.79 86 9.09 60 41.0 86 2.45 2 14.1 37 21.8 29 2.38 120
TC/T-Flow [76]52.4 5.45 109 11.5 105 2.00 3 7.42 56 13.0 61 2.08 1 5.69 7 9.76 26 1.73 1 8.60 36 13.7 55 5.16 50 18.3 103 24.9 95 5.20 69 10.1 50 24.9 43 3.74 25 9.75 104 42.6 107 2.45 2 14.5 86 22.6 63 2.16 1
EpicFlow [102]53.5 5.07 14 11.0 78 2.00 3 7.39 52 12.9 56 2.08 1 5.80 51 10.3 62 1.73 1 8.85 77 15.5 107 5.20 59 18.1 69 24.8 85 5.20 69 10.2 58 25.1 48 3.74 25 9.33 81 40.4 80 2.45 2 14.5 86 24.1 119 2.16 1
DMF_ROB [140]53.6 5.20 43 10.8 68 2.08 67 7.85 76 13.4 75 2.08 1 6.35 106 11.6 116 2.00 90 9.02 90 14.5 83 5.16 50 17.8 34 24.4 53 5.20 69 9.83 25 24.3 29 3.74 25 9.04 52 38.3 39 2.45 2 14.1 37 22.4 56 2.16 1
F-TV-L1 [15]53.7 5.35 78 10.3 42 2.16 96 8.83 107 14.6 114 2.16 68 6.00 56 10.3 62 2.00 90 8.76 53 13.2 44 5.26 106 17.6 11 23.8 18 5.03 9 9.57 19 23.2 10 3.79 86 9.18 69 37.6 23 2.45 2 13.8 11 21.2 13 2.31 102
TC-Flow [46]54.5 5.07 14 10.8 68 2.00 3 7.39 52 13.2 73 2.16 68 6.00 56 10.3 62 1.73 1 8.66 39 13.7 55 5.23 89 18.2 93 25.0 104 5.20 69 10.2 58 24.5 34 3.79 86 9.04 52 38.1 37 2.45 2 14.5 86 23.5 106 2.16 1
S2D-Matching [84]54.9 5.35 78 11.2 94 2.00 3 7.75 73 13.5 80 2.08 1 5.69 7 10.0 33 1.73 1 8.37 16 12.6 20 5.20 59 18.3 103 25.2 114 5.07 13 11.0 114 27.7 122 3.79 86 9.09 60 40.3 78 2.45 2 14.4 75 23.0 85 2.16 1
Fusion [6]57.0 5.20 43 10.4 45 2.00 3 7.14 40 11.8 34 2.08 1 5.74 48 9.68 19 1.73 1 9.33 104 14.2 71 5.20 59 18.3 103 24.7 72 5.07 13 11.6 132 28.1 126 3.70 2 9.63 102 41.4 91 2.45 2 15.3 134 24.2 122 2.16 1
LFNet_ROB [151]58.1 5.35 78 13.4 131 2.00 3 7.72 70 12.9 56 2.16 68 6.00 56 11.3 109 1.73 1 8.98 88 15.9 114 5.07 3 18.1 69 24.8 85 5.10 34 11.0 114 28.1 126 3.74 25 9.09 60 37.6 23 2.45 2 14.0 23 22.4 56 2.16 1
Modified CLG [34]58.3 5.07 14 9.49 10 2.16 96 9.42 126 14.2 101 2.65 129 6.00 56 11.5 115 2.00 90 9.15 98 14.3 73 5.10 26 17.7 24 23.9 26 5.10 34 10.1 50 24.7 37 3.74 25 9.31 80 37.5 20 2.45 2 14.1 37 21.8 29 2.31 102
Classic++ [32]58.5 5.20 43 10.3 42 2.08 67 7.94 82 13.8 89 2.08 1 6.00 56 10.1 54 1.73 1 8.89 79 13.7 55 5.23 89 18.0 56 24.5 61 5.10 34 10.3 65 25.8 69 3.87 117 9.13 66 40.1 74 2.45 2 14.2 53 22.2 46 2.31 102
Sparse Occlusion [54]59.5 5.26 64 10.5 51 2.08 67 8.04 86 14.4 105 2.08 1 6.00 56 10.0 33 1.73 1 8.83 71 13.7 55 5.20 59 18.1 69 24.7 72 5.20 69 11.0 114 26.5 89 3.74 25 9.42 87 42.0 102 2.45 2 14.4 75 22.8 75 2.16 1
AggregFlow [97]59.7 5.45 109 13.8 135 2.08 67 7.44 60 13.1 67 2.16 68 5.69 7 9.95 31 1.73 1 9.15 98 16.1 116 5.10 26 18.0 56 24.5 61 5.20 69 9.90 33 24.6 36 3.83 107 8.98 40 40.7 83 2.45 2 14.4 75 23.0 85 2.16 1
FESL [72]60.4 5.42 99 11.0 78 2.00 3 7.05 34 11.8 34 2.08 1 5.69 7 10.7 85 1.73 1 8.81 66 13.5 51 5.20 59 18.4 115 25.1 110 5.20 69 11.0 114 27.0 105 3.74 25 9.06 57 42.9 111 2.45 2 14.8 110 23.7 112 2.16 1
PMF [73]60.7 5.20 43 11.4 100 2.00 3 7.35 48 12.4 47 2.08 1 6.00 56 12.0 125 1.73 1 8.76 53 14.4 77 5.07 3 18.4 115 25.0 104 5.10 34 10.2 58 25.8 69 3.87 117 9.04 52 41.3 90 2.45 2 15.2 131 24.5 126 2.16 1
Classic+CPF [83]61.3 5.35 78 11.3 98 2.00 3 7.07 39 12.1 42 2.08 1 5.69 7 10.5 83 1.73 1 8.43 25 12.7 25 5.07 3 18.7 135 25.7 136 5.20 69 11.2 124 28.7 133 3.74 25 9.42 87 42.9 111 2.45 2 15.1 122 24.2 122 2.16 1
FF++_ROB [146]62.0 5.07 14 11.5 105 2.00 3 7.16 43 12.2 44 2.08 1 6.00 56 10.3 62 1.73 1 8.96 84 16.4 121 5.20 59 18.6 129 25.7 136 5.20 69 10.6 88 26.8 99 3.92 132 9.00 43 39.1 60 2.45 2 14.2 53 22.9 82 2.16 1
TCOF [69]62.4 5.35 78 10.7 59 2.00 3 9.27 120 15.4 131 2.16 68 5.69 7 10.2 58 1.73 1 8.74 50 13.1 40 5.23 89 17.7 24 23.8 18 5.07 13 10.7 99 26.6 93 3.70 2 10.0 114 44.7 128 2.45 2 14.6 99 22.9 82 2.38 120
BlockOverlap [61]62.5 5.20 43 9.29 5 2.16 96 8.74 105 14.1 96 2.65 129 6.00 56 9.35 13 2.00 90 8.52 30 11.9 3 5.60 138 17.8 34 24.0 29 5.32 144 9.83 25 25.0 45 4.04 137 8.83 26 37.1 14 2.52 110 13.5 6 20.6 6 2.38 120
FlowNetS+ft+v [112]62.8 5.26 64 10.1 29 2.16 96 9.11 116 14.5 109 2.45 118 6.00 56 10.3 62 2.00 90 8.96 84 13.5 51 5.26 106 17.8 34 24.1 37 5.23 124 9.76 23 23.9 19 3.74 25 9.38 85 41.6 94 2.45 2 14.1 37 22.2 46 2.16 1
OFH [38]63.4 5.35 78 11.0 78 2.08 67 8.06 89 13.7 86 2.08 1 6.00 56 11.6 116 1.73 1 8.58 33 13.9 66 5.07 3 18.2 93 24.9 95 5.16 61 10.3 65 25.1 48 3.74 25 9.88 110 42.7 109 2.45 2 14.8 110 24.7 128 2.16 1
SVFilterOh [111]63.9 5.20 43 10.6 56 2.00 3 6.73 15 11.0 12 2.08 1 6.00 56 10.0 33 1.73 1 8.76 53 13.8 62 5.26 106 18.4 115 25.3 119 5.26 135 10.6 88 28.0 125 3.74 25 8.45 4 39.2 65 2.52 110 14.7 104 23.3 100 2.31 102
CRTflow [80]64.4 5.29 71 10.5 51 2.16 96 8.43 97 14.5 109 2.16 68 6.35 106 11.1 108 2.00 90 8.64 38 13.0 32 5.29 115 18.0 56 24.5 61 5.20 69 9.68 21 23.8 18 3.74 25 9.00 43 40.9 85 2.45 2 14.1 37 22.2 46 2.31 102
SRR-TVOF-NL [91]64.4 5.45 109 12.1 120 2.08 67 7.77 74 13.5 80 2.16 68 6.00 56 10.3 62 1.73 1 9.26 102 14.7 87 5.07 3 18.1 69 24.6 70 5.10 34 10.4 72 26.6 93 3.70 2 9.42 87 38.5 48 2.45 2 15.1 122 23.9 117 2.16 1
Efficient-NL [60]64.6 5.35 78 10.7 59 2.00 3 7.42 56 13.0 61 2.08 1 6.35 106 10.7 85 2.00 90 8.81 66 13.4 48 5.10 26 18.1 69 24.7 72 5.10 34 11.2 124 27.6 118 3.70 2 9.47 91 43.6 121 2.45 2 15.1 122 23.8 115 2.16 1
EPPM w/o HM [88]64.6 5.23 62 12.6 123 2.00 3 7.39 52 13.0 61 2.08 1 6.35 106 14.0 142 1.91 85 8.83 71 15.3 103 5.10 26 18.0 56 24.5 61 5.10 34 10.5 77 27.6 118 3.74 25 9.11 64 41.9 98 2.45 2 14.5 86 23.2 94 2.16 1
MLDP_OF [89]65.8 5.32 75 11.1 88 2.00 3 7.55 67 13.6 83 2.08 1 5.69 7 10.0 33 1.73 1 8.76 53 13.1 40 5.26 106 18.0 56 24.5 61 5.20 69 11.0 114 26.9 102 4.08 142 9.26 73 38.2 38 2.52 110 14.4 75 22.6 63 2.38 120
ContFlow_ROB [150]66.1 5.42 99 13.2 129 2.08 67 8.00 85 13.4 75 2.38 104 6.35 106 11.3 109 1.73 1 9.11 94 16.7 122 5.10 26 18.1 69 24.7 72 5.07 13 10.5 77 25.4 57 3.70 2 9.06 57 39.1 60 2.45 2 14.2 53 23.5 106 2.16 1
3DFlow [135]66.1 5.42 99 11.5 105 2.00 3 7.14 40 12.3 45 2.08 1 6.22 105 10.0 33 1.73 1 8.66 39 13.6 53 5.23 89 17.9 46 24.5 61 5.20 69 12.3 147 29.0 135 3.79 86 10.6 128 41.7 95 2.45 2 14.8 110 23.2 94 2.16 1
PWC-Net_ROB [148]66.1 5.35 78 13.8 135 2.00 3 7.55 67 13.3 74 2.08 1 6.00 56 11.3 109 1.73 1 8.76 53 15.7 109 5.07 3 18.6 129 25.9 141 5.20 69 10.5 77 26.9 102 3.83 107 9.00 43 38.6 52 2.45 2 14.3 63 23.7 112 2.16 1
2D-CLG [1]66.2 5.16 41 10.0 25 2.16 96 9.90 132 14.2 101 2.83 139 6.35 106 10.7 85 2.00 90 10.0 124 15.2 99 5.10 26 17.7 24 24.1 37 5.20 69 10.1 50 24.1 24 3.74 25 9.81 105 43.6 121 2.45 2 14.1 37 21.8 29 2.16 1
Steered-L1 [118]66.2 5.07 14 9.81 16 2.00 3 7.35 48 12.8 55 2.16 68 6.35 106 10.3 62 2.00 90 9.31 103 14.3 73 5.35 124 18.2 93 24.7 72 5.07 13 10.2 58 25.7 66 3.79 86 9.33 81 40.4 80 2.45 2 14.6 99 22.8 75 2.31 102
IAOF [50]68.2 5.60 123 11.0 78 2.16 96 12.0 148 16.9 149 2.52 125 5.69 7 11.0 102 2.00 90 9.76 118 14.3 73 5.20 59 17.7 24 24.0 29 5.07 13 10.0 48 25.2 52 3.74 25 9.47 91 41.4 91 2.45 2 14.2 53 22.1 40 2.16 1
Occlusion-TV-L1 [63]68.2 5.20 43 10.2 35 2.08 67 8.89 109 15.3 129 2.16 68 6.00 56 10.3 62 2.00 90 9.15 98 15.4 104 5.26 106 17.6 11 23.7 14 5.10 34 9.98 45 25.5 60 3.87 117 10.3 122 39.3 67 2.52 110 14.1 37 22.3 52 2.16 1
Complementary OF [21]69.8 5.20 43 12.0 117 2.00 3 7.19 44 12.9 56 2.08 1 6.68 126 10.8 97 2.00 90 8.76 53 14.6 85 5.16 50 18.2 93 25.2 114 5.10 34 10.3 65 25.9 74 3.74 25 9.97 113 42.6 107 2.45 2 15.6 138 28.0 144 2.16 1
Adaptive [20]70.8 5.32 75 10.3 42 2.16 96 9.29 123 15.4 131 2.16 68 6.00 56 10.7 85 1.73 1 8.81 66 13.8 62 5.20 59 17.9 46 24.3 47 5.07 13 10.4 72 26.0 75 3.79 86 9.83 106 44.6 126 2.45 2 14.5 86 22.8 75 2.31 102
Ad-TV-NDC [36]71.2 5.66 125 9.88 21 2.52 143 10.1 136 15.1 124 2.71 132 6.00 56 10.7 85 1.73 1 9.49 113 14.2 71 5.35 124 17.7 24 24.0 29 5.20 69 9.56 17 24.0 21 3.87 117 9.56 98 38.6 52 2.45 2 13.9 16 21.2 13 2.38 120
CostFilter [40]72.4 5.32 75 13.2 129 2.00 3 7.33 46 12.3 45 2.08 1 6.06 99 13.5 141 1.73 1 8.96 84 16.1 116 5.07 3 18.6 129 25.6 135 5.16 61 9.98 45 24.8 41 4.04 137 9.20 70 43.5 120 2.45 2 15.1 122 24.9 131 2.16 1
Black & Anandan [4]73.0 5.45 109 10.1 29 2.16 96 10.2 139 15.3 129 2.45 118 6.68 126 11.3 109 2.00 90 10.2 126 15.6 108 5.20 59 17.8 34 24.0 29 5.16 61 9.83 25 24.7 37 3.74 25 10.2 119 41.9 98 2.45 2 14.2 53 21.8 29 2.16 1
BriefMatch [124]73.2 5.29 71 11.4 100 2.08 67 7.44 60 12.7 51 2.16 68 6.38 124 9.93 30 2.00 90 9.83 120 14.9 91 5.83 145 18.0 56 24.4 53 5.20 69 10.5 77 27.3 112 4.32 147 9.04 52 37.9 32 2.45 2 14.3 63 22.8 75 2.16 1
HBM-GC [105]73.2 5.35 78 10.6 56 2.16 96 7.42 56 13.4 75 2.16 68 5.69 7 9.00 5 1.73 1 8.74 50 13.2 44 5.26 106 18.6 129 25.5 132 5.26 135 11.8 139 31.5 146 3.83 107 8.83 26 41.1 88 2.45 2 14.3 63 22.2 46 2.31 102
CNN-flow-warp+ref [117]73.8 5.00 6 9.59 13 2.16 96 8.35 95 13.6 83 2.16 68 6.35 106 11.8 124 2.00 90 10.6 131 15.4 104 5.48 135 17.8 34 24.3 47 5.23 124 9.95 38 24.3 29 3.83 107 9.83 106 44.6 126 2.45 2 14.2 53 22.3 52 2.16 1
LiteFlowNet [143]74.9 5.45 109 14.5 139 2.00 3 7.42 56 12.7 51 2.08 1 5.69 7 13.0 136 1.73 1 9.71 117 23.2 146 5.29 115 18.4 115 25.4 126 5.20 69 10.8 105 27.1 106 3.70 2 10.2 119 43.0 115 2.45 2 14.3 63 23.2 94 2.16 1
HBpMotionGpu [43]75.9 5.48 117 10.8 68 2.38 136 10.1 136 15.4 131 2.71 132 5.69 7 10.0 33 1.73 1 9.40 106 16.2 120 5.23 89 17.9 46 24.3 47 5.20 69 10.5 77 26.4 88 3.83 107 8.96 35 37.8 29 2.45 2 14.3 63 22.6 63 2.38 120
TriFlow [95]76.8 5.26 64 12.0 117 2.16 96 8.39 96 14.4 105 2.38 104 6.00 56 11.0 102 1.73 1 9.02 90 15.4 104 5.10 26 18.5 123 25.4 126 5.20 69 10.6 88 27.3 112 3.74 25 9.26 73 39.7 71 2.45 2 14.6 99 23.1 92 2.16 1
AdaConv-v1 [126]77.1 6.24 138 14.4 138 2.38 136 9.02 113 12.7 51 3.11 144 7.00 136 11.0 102 2.38 142 13.1 144 18.8 134 5.83 145 16.8 3 22.5 3 4.83 3 8.79 5 22.0 4 3.70 2 8.91 33 36.6 9 2.58 135 13.3 5 20.2 5 2.38 120
TVL1_ROB [139]77.7 5.45 109 9.93 22 2.38 136 10.9 142 15.8 144 2.71 132 6.00 56 10.9 99 2.00 90 9.85 121 15.0 95 5.20 59 17.8 34 24.1 37 5.20 69 10.1 50 25.8 69 3.83 107 9.87 109 44.1 123 2.45 2 14.0 23 21.9 36 2.16 1
Nguyen [33]78.0 5.42 99 10.0 25 2.38 136 10.9 142 15.1 124 2.65 129 6.00 56 12.0 125 2.00 90 10.4 130 16.1 116 5.20 59 17.8 34 24.1 37 5.07 13 9.98 45 25.3 54 3.70 2 10.9 134 46.9 135 2.52 110 14.1 37 22.1 40 2.16 1
Aniso-Texture [82]79.4 5.07 14 10.2 35 2.00 3 8.89 109 15.2 128 2.16 68 6.35 106 10.3 62 1.73 1 9.04 92 16.1 116 5.29 115 18.3 103 24.9 95 5.23 124 11.8 139 30.0 141 3.83 107 9.06 57 40.2 77 2.45 2 14.7 104 23.5 106 2.16 1
FlowNet2 [122]81.4 6.45 143 19.1 147 2.16 96 7.85 76 13.4 75 2.38 104 6.06 99 11.7 118 1.73 1 9.40 106 18.2 130 5.23 89 18.5 123 25.3 119 5.20 69 10.3 65 25.2 52 3.74 25 9.27 77 41.9 98 2.45 2 14.3 63 22.8 75 2.16 1
TV-L1-improved [17]81.5 5.10 34 10.2 35 2.08 67 9.20 119 15.4 131 2.16 68 6.35 106 10.3 62 2.00 90 8.85 77 13.8 62 5.23 89 18.0 56 24.4 53 5.10 34 10.6 88 26.5 89 3.79 86 9.93 112 46.9 135 2.52 110 14.3 63 22.7 69 2.38 120
Bartels [41]82.9 5.35 78 11.4 100 2.16 96 7.72 70 14.0 95 2.38 104 6.00 56 10.3 62 2.00 90 9.11 94 15.0 95 5.69 140 17.6 11 23.6 10 5.45 148 10.7 99 27.2 109 4.55 150 8.96 35 36.4 6 2.65 145 14.1 37 22.1 40 2.38 120
GraphCuts [14]83.1 5.66 125 11.9 116 2.16 96 7.53 64 12.5 48 2.38 104 7.68 142 10.2 58 2.00 90 9.47 111 14.9 91 5.23 89 18.1 69 24.5 61 5.00 6 10.1 50 25.7 66 3.70 2 9.02 50 42.1 104 2.52 110 15.1 122 24.1 119 2.31 102
ResPWCR_ROB [145]83.3 5.35 78 12.5 122 2.00 3 7.94 82 13.6 83 2.16 68 6.68 126 11.3 109 1.91 85 9.42 108 18.1 129 5.29 115 18.1 69 24.8 85 5.07 13 10.6 88 27.3 112 4.40 148 9.56 98 38.4 43 2.45 2 14.7 104 24.7 128 2.16 1
SimpleFlow [49]84.0 5.35 78 11.0 78 2.00 3 8.04 86 13.9 92 2.08 1 6.56 125 11.3 109 2.00 90 8.41 24 12.7 25 5.20 59 18.4 115 25.4 126 5.20 69 11.4 130 28.9 134 3.74 25 10.1 116 53.7 146 2.52 110 15.3 134 26.5 139 2.16 1
Filter Flow [19]86.4 5.42 99 10.2 35 2.16 96 9.40 125 14.7 115 2.71 132 6.00 56 10.7 85 2.00 90 9.49 113 13.9 66 5.35 124 18.1 69 24.3 47 5.26 135 10.2 58 25.6 62 3.83 107 9.52 96 41.4 91 2.45 2 14.6 99 22.3 52 2.38 120
AugFNG_ROB [144]86.5 5.48 117 14.1 137 2.16 96 8.27 92 13.5 80 2.38 104 6.35 106 14.0 142 2.00 90 9.47 111 19.5 138 5.20 59 18.7 135 26.0 143 5.23 124 9.85 29 25.5 60 3.70 2 9.85 108 38.7 55 2.45 2 14.2 53 23.1 92 2.16 1
ROF-ND [107]87.7 5.74 128 10.4 45 2.00 3 8.04 86 14.1 96 2.16 68 6.06 99 10.7 85 1.73 1 10.6 131 19.9 141 5.26 106 18.1 69 24.8 85 5.20 69 11.7 135 28.6 131 3.74 25 11.1 136 41.0 86 2.52 110 15.3 134 25.3 135 2.16 1
EPMNet [133]88.5 6.45 143 19.7 149 2.16 96 7.85 76 13.1 67 2.38 104 6.06 99 11.7 118 1.73 1 10.1 125 24.0 148 5.23 89 18.5 123 25.3 119 5.20 69 10.7 99 27.6 118 3.70 2 9.27 77 41.9 98 2.45 2 14.5 86 23.8 115 2.16 1
Shiralkar [42]89.2 5.48 117 12.7 124 2.08 67 9.06 115 14.7 115 2.08 1 6.00 56 12.8 134 2.00 90 10.7 133 19.7 139 5.20 59 18.1 69 24.8 85 5.00 6 10.8 105 26.1 79 3.87 117 10.8 133 47.5 140 2.45 2 14.9 116 25.8 137 2.16 1
Rannacher [23]89.5 5.26 64 10.8 68 2.16 96 9.27 120 15.5 138 2.16 68 6.35 106 10.9 99 2.00 90 8.76 53 14.4 77 5.23 89 17.9 46 24.4 53 5.20 69 10.5 77 26.7 96 3.79 86 9.90 111 45.9 132 2.52 110 14.4 75 23.5 106 2.38 120
TriangleFlow [30]89.8 5.60 123 11.6 111 2.16 96 8.50 100 14.4 105 2.08 1 6.35 106 10.7 85 2.00 90 9.42 108 15.8 111 5.23 89 18.0 56 24.5 61 5.00 6 11.1 123 27.2 109 3.74 25 10.4 123 47.2 139 2.52 110 15.6 138 26.7 140 2.16 1
IIOF-NLDP [131]89.9 5.45 109 12.0 117 2.00 3 8.12 90 14.7 115 2.08 1 6.06 99 10.0 33 1.73 1 9.13 96 14.8 90 5.32 121 18.1 69 24.8 85 5.10 34 12.2 144 29.1 136 3.87 117 12.0 144 59.6 150 2.65 145 15.2 131 24.6 127 2.16 1
Correlation Flow [75]90.2 5.42 99 11.7 113 2.00 3 8.58 101 15.4 131 2.08 1 5.69 7 9.80 27 1.73 1 8.89 79 14.7 87 5.32 121 18.1 69 24.8 85 5.32 144 12.3 147 30.3 142 3.83 107 10.5 126 48.8 142 2.52 110 14.8 110 23.7 112 2.31 102
Horn & Schunck [3]93.8 5.48 117 10.4 45 2.16 96 10.5 141 15.4 131 2.52 125 6.68 126 12.0 125 2.00 90 11.5 139 17.6 128 5.23 89 17.9 46 24.0 29 5.20 69 9.93 36 24.1 24 3.79 86 11.1 136 42.9 111 2.52 110 14.5 86 22.2 46 2.38 120
IAOF2 [51]94.0 5.74 128 11.5 105 2.16 96 9.49 127 15.9 147 2.38 104 5.69 7 11.0 102 2.00 90 9.61 116 15.8 111 5.26 106 18.7 135 25.3 119 5.20 69 10.9 109 27.4 115 3.74 25 9.47 91 41.1 88 2.45 2 14.5 86 22.8 75 2.31 102
TI-DOFE [24]97.0 5.80 130 11.0 78 2.52 143 11.5 146 15.8 144 3.11 144 6.35 106 12.3 129 2.00 90 11.4 138 17.4 125 5.29 115 17.9 46 24.2 45 5.07 13 9.95 38 24.4 33 3.79 86 10.5 126 39.9 73 2.52 110 14.8 110 22.1 40 2.38 120
OFRF [134]97.6 5.80 130 13.7 133 2.16 96 9.15 118 15.1 124 2.45 118 6.00 56 11.7 118 1.73 1 9.13 96 15.1 98 5.10 26 18.7 135 25.9 141 5.16 61 11.3 127 29.1 136 3.87 117 10.1 116 44.5 125 2.45 2 15.4 137 24.9 131 2.16 1
LocallyOriented [52]97.7 5.45 109 11.2 94 2.16 96 9.49 127 15.7 142 2.16 68 6.06 99 11.7 118 1.91 85 9.42 108 17.0 123 5.23 89 18.2 93 24.8 85 5.07 13 11.0 114 26.5 89 4.04 137 10.4 123 43.0 115 2.45 2 14.8 110 23.4 104 2.31 102
SegOF [10]99.0 5.10 34 11.4 100 2.16 96 8.29 93 13.9 92 2.38 104 7.00 136 12.1 128 2.00 90 9.81 119 21.0 142 5.20 59 18.2 93 25.1 110 5.20 69 10.9 109 26.1 79 3.79 86 10.4 123 48.4 141 2.58 135 14.7 104 25.1 134 2.16 1
SPSA-learn [13]99.4 5.29 71 10.4 45 2.16 96 9.04 114 14.1 96 2.45 118 6.68 126 11.7 118 2.00 90 10.3 129 15.8 111 5.10 26 18.4 115 25.3 119 5.20 69 10.5 77 26.8 99 3.74 25 12.3 147 58.4 148 2.71 149 17.6 147 35.0 149 2.16 1
2bit-BM-tele [98]102.0 5.35 78 10.1 29 2.16 96 8.91 111 15.4 131 2.45 118 6.00 56 10.0 33 2.00 90 9.04 92 14.3 73 5.60 138 18.3 103 24.9 95 5.35 147 11.7 135 31.3 145 4.24 146 12.0 144 58.7 149 2.83 150 13.9 16 21.7 25 2.45 148
StereoOF-V1MT [119]102.5 5.69 127 13.0 127 2.08 67 8.68 103 14.1 96 2.08 1 6.73 135 12.4 131 2.00 90 11.6 140 19.1 137 5.45 131 18.5 123 25.4 126 5.20 69 11.3 127 26.1 79 3.92 132 11.2 138 44.9 129 2.58 135 14.2 53 22.6 63 2.16 1
ACK-Prior [27]103.3 5.35 78 11.7 113 2.00 3 7.39 52 12.9 56 2.08 1 6.68 126 10.8 97 2.00 90 9.54 115 15.7 109 5.32 121 18.7 135 25.5 132 5.29 142 11.9 142 29.5 138 3.87 117 10.1 116 41.7 95 2.52 110 16.1 142 24.8 130 2.38 120
StereoFlow [44]103.8 8.68 150 20.4 150 2.45 141 10.3 140 16.1 148 2.71 132 6.00 56 10.7 85 1.73 1 8.81 66 13.7 55 5.16 50 22.6 148 31.6 148 5.26 135 14.3 150 35.7 150 3.79 86 9.13 66 38.8 56 2.45 2 15.6 138 25.3 135 2.31 102
UnFlow [129]105.1 5.97 133 15.5 140 2.16 96 9.13 117 14.1 96 2.38 104 6.68 126 13.0 136 2.00 90 9.35 105 17.1 124 5.23 89 18.6 129 25.8 139 5.20 69 11.5 131 29.5 138 3.74 25 9.66 103 37.4 19 2.45 2 16.9 146 28.1 145 2.38 120
Dynamic MRF [7]105.5 5.26 64 11.5 105 2.00 3 8.12 90 14.3 103 2.16 68 6.68 126 12.8 134 2.00 90 10.9 136 18.3 132 5.51 137 18.3 103 25.0 104 5.20 69 11.6 132 28.6 131 3.87 117 10.7 130 45.7 131 2.52 110 14.9 116 23.3 100 2.31 102
NL-TV-NCC [25]108.4 6.03 135 12.8 126 2.00 3 8.29 93 14.7 115 2.16 68 6.35 106 11.7 118 2.00 90 10.7 133 18.6 133 5.45 131 18.1 69 24.1 37 5.45 148 12.0 143 28.2 129 3.79 86 13.0 149 43.4 119 2.58 135 15.1 122 23.2 94 2.38 120
SILK [79]110.0 5.80 130 12.7 124 2.38 136 11.1 144 15.6 140 2.83 139 7.35 141 13.0 136 2.00 90 10.8 135 17.5 127 5.48 135 18.3 103 24.8 85 5.20 69 10.5 77 26.0 75 4.20 145 10.0 114 37.1 14 2.52 110 14.6 99 22.7 69 2.31 102
Learning Flow [11]111.7 5.57 122 11.1 88 2.16 96 9.27 120 15.1 124 2.16 68 7.00 136 13.3 139 2.00 90 10.2 126 15.2 99 5.45 131 18.5 123 25.1 110 5.32 144 10.7 99 26.2 84 3.87 117 10.6 128 40.8 84 2.52 110 15.1 122 23.3 100 2.38 120
H+S_ROB [138]117.0 6.00 134 13.0 127 2.16 96 9.63 129 13.7 86 2.71 132 8.00 146 13.3 139 2.38 142 13.7 146 17.4 125 5.35 124 18.3 103 24.7 72 5.20 69 10.8 105 25.6 62 3.79 86 11.7 141 47.1 138 2.58 135 15.0 121 24.9 131 2.38 120
FOLKI [16]119.9 6.14 137 12.4 121 3.11 147 11.5 146 15.5 138 3.32 147 7.00 136 14.7 145 2.38 142 13.5 145 18.2 130 6.27 148 18.6 129 25.0 104 5.23 124 10.3 65 25.1 48 4.04 137 11.0 135 38.3 39 2.58 135 14.7 104 22.4 56 2.38 120
Adaptive flow [45]120.2 6.24 138 11.3 98 2.71 145 11.2 145 15.7 142 3.42 148 6.35 106 10.9 99 2.00 90 10.2 126 14.7 87 5.72 141 18.7 135 25.4 126 5.23 124 11.7 135 30.8 144 3.87 117 9.42 87 38.8 56 2.58 135 14.9 116 24.3 124 2.38 120
WOLF_ROB [149]121.2 6.35 141 18.1 145 2.16 96 10.0 134 15.6 140 2.16 68 6.68 126 12.5 133 2.00 90 9.88 122 19.7 139 5.35 124 18.9 143 26.1 144 5.20 69 11.7 135 29.9 140 4.04 137 12.1 146 51.4 145 2.52 110 15.7 141 27.0 141 2.16 1
GroupFlow [9]122.7 6.56 145 19.6 148 2.16 96 9.38 124 14.7 115 2.52 125 7.68 142 16.8 148 2.00 90 11.1 137 23.5 147 5.29 115 20.7 147 29.3 147 5.23 124 12.4 149 32.8 148 3.87 117 11.3 140 49.6 144 2.45 2 16.8 145 30.4 148 2.16 1
Heeger++ [104]126.1 7.16 148 18.5 146 2.16 96 9.75 130 13.8 89 2.45 118 9.35 147 16.1 147 2.38 142 13.0 142 18.9 135 5.74 142 19.8 146 27.4 146 5.23 124 12.2 144 26.0 75 3.92 132 13.5 150 46.5 133 2.52 110 16.1 142 27.4 142 2.16 1
SLK [47]129.5 6.03 135 13.6 132 2.45 141 10.1 136 13.8 89 2.89 141 7.68 142 12.4 131 2.38 142 13.8 148 21.0 142 5.77 144 19.1 145 26.4 145 5.20 69 11.2 124 26.2 84 3.87 117 11.8 142 46.9 135 2.58 135 15.2 131 26.1 138 2.38 120
FFV1MT [106]131.7 6.40 142 16.8 142 2.16 96 9.87 131 13.9 92 2.89 141 9.35 147 18.7 149 2.52 148 13.0 142 18.9 135 5.74 142 18.8 141 25.7 136 5.26 135 10.9 109 26.0 75 3.92 132 12.8 148 46.5 133 2.52 110 16.2 144 27.4 142 2.45 148
HCIC-L [99]133.2 7.62 149 17.7 144 3.16 148 9.98 133 14.8 122 3.16 146 7.14 140 14.0 142 2.00 90 12.4 141 21.5 145 5.35 124 18.9 143 25.5 132 5.26 135 11.8 139 31.9 147 3.87 117 9.47 91 43.2 118 2.58 135 18.7 149 30.1 147 2.38 120
PGAM+LK [55]133.4 6.56 145 16.0 141 2.71 145 10.0 134 14.7 115 3.00 143 7.75 145 15.7 146 2.38 142 13.7 146 21.1 144 6.27 148 18.8 141 25.8 139 5.26 135 11.6 132 27.2 109 4.08 142 10.7 130 40.3 78 2.58 135 15.1 122 24.4 125 2.38 120
Pyramid LK [2]134.9 6.24 138 13.7 133 3.16 148 12.7 149 15.8 144 3.79 149 11.8 149 12.3 129 3.00 149 25.5 150 41.4 149 7.14 150 22.9 149 33.6 149 5.20 69 10.7 99 25.4 57 3.92 132 11.2 138 49.2 143 2.65 145 19.6 150 37.8 150 2.38 120
Periodicity [78]148.1 6.81 147 17.5 143 3.27 150 15.3 150 16.9 149 4.24 150 13.7 150 22.7 150 4.36 150 18.0 149 41.4 149 6.16 147 23.9 150 34.4 150 5.60 150 12.2 144 34.5 149 4.51 149 11.8 142 55.6 147 2.65 145 17.9 148 29.7 146 2.71 150
AVG_FLOW_ROB [142]151.0 31.4 151 43.5 151 5.60 151 24.2 151 24.5 151 6.45 151 24.3 151 27.7 151 8.43 151 44.7 151 55.2 151 16.9 151 38.9 151 51.5 151 6.24 151 31.3 151 72.3 151 4.83 151 34.9 151 63.2 151 3.65 151 35.1 151 43.8 151 6.73 151
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.