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
PyrWarp [159]1.7 3.51 1 6.06 1 1.73 1 5.80 1 8.76 2 2.00 1 2.38 1 4.00 2 1.73 1 7.00 1 8.58 1 4.55 1 12.4 1 16.1 1 4.24 1 6.48 3 16.6 3 3.46 4 6.98 2 25.5 2 2.45 4 11.2 2 16.9 2 2.16 1
DAIN [158]9.6 3.92 5 7.44 6 2.08 71 6.45 8 9.88 6 2.16 69 2.83 3 5.10 3 1.73 1 7.85 5 10.7 6 4.65 2 13.5 3 17.9 3 4.43 3 7.07 5 17.3 4 3.42 3 7.87 5 30.9 7 2.38 1 12.1 5 18.2 6 2.16 1
MEMC-Net+ [155]13.3 4.24 9 7.59 9 2.16 102 6.93 32 10.3 11 2.16 69 3.11 4 5.69 5 1.73 1 8.29 12 10.3 5 4.65 2 14.8 7 19.8 7 4.43 3 7.62 6 18.1 6 3.37 1 8.08 7 30.1 5 2.38 1 12.4 7 18.5 7 2.16 1
PMMST [114]14.9 5.00 14 9.68 23 2.00 6 6.88 29 11.0 20 2.08 2 5.69 14 9.00 12 1.73 1 8.21 10 12.0 14 5.07 9 17.4 14 23.4 14 5.07 21 9.29 17 22.6 14 3.74 32 8.66 16 37.1 22 2.45 4 13.9 25 21.3 24 2.16 1
CFRF [156]17.1 4.00 6 7.33 4 1.73 1 6.95 35 10.7 15 2.16 69 3.37 6 5.35 4 2.00 93 7.77 4 9.61 3 5.07 9 14.4 6 19.1 6 4.65 6 6.86 4 17.7 5 3.70 6 7.59 4 27.9 4 2.45 4 11.8 4 17.9 4 2.31 109
MDP-Flow2 [68]17.6 4.97 13 9.42 18 2.00 6 6.68 15 11.0 20 2.08 2 5.69 14 9.04 17 1.73 1 8.19 6 12.0 14 5.10 34 17.5 16 23.5 17 5.07 21 9.95 48 24.7 46 3.74 32 8.60 12 36.4 14 2.45 4 13.9 25 21.5 26 2.16 1
InterpCNN [160]19.3 4.20 7 7.51 7 2.65 154 6.40 4 9.75 5 2.52 132 3.56 8 5.69 5 2.00 93 8.19 6 10.9 7 4.69 4 13.8 4 18.2 5 4.24 1 6.45 2 16.5 2 3.37 1 7.05 3 27.0 3 2.45 4 11.5 3 17.4 3 2.16 1
CtxSyn [136]25.7 3.87 2 7.35 5 1.83 4 5.80 1 8.96 3 2.08 2 3.11 4 5.69 5 2.00 93 7.33 2 9.95 4 4.97 6 17.1 12 22.5 10 4.93 11 8.70 11 20.9 9 3.74 32 10.2 127 33.7 12 2.52 117 12.6 9 18.8 8 2.38 128
CyclicGen [153]26.6 4.20 7 6.86 3 2.45 149 6.06 3 8.29 1 3.42 157 4.36 9 7.62 11 2.00 93 8.74 58 11.6 9 5.26 114 13.4 2 17.4 2 4.69 7 5.35 1 11.3 1 3.70 6 6.24 1 19.7 1 2.38 1 8.89 1 13.0 1 2.16 1
NNF-Local [87]26.7 5.07 22 10.1 37 2.00 6 6.40 4 10.0 9 2.08 2 5.69 14 9.00 12 1.73 1 8.66 46 14.5 91 5.10 34 17.6 19 23.8 26 5.07 21 10.4 82 25.8 78 3.74 32 8.66 16 37.5 28 2.45 4 13.9 25 21.6 30 2.16 1
PH-Flow [101]27.2 5.20 51 10.7 67 2.00 6 6.45 8 10.3 11 2.08 2 5.69 14 9.38 23 1.73 1 8.19 6 11.9 11 5.07 9 17.7 32 24.0 37 5.03 17 10.6 97 26.5 98 3.70 6 8.68 20 38.8 65 2.45 4 14.0 32 21.7 34 2.16 1
NN-field [71]28.0 5.07 22 10.4 53 2.00 6 6.45 8 10.0 9 2.08 2 5.97 62 9.00 12 1.73 1 8.76 62 15.0 104 5.10 34 17.6 19 23.7 22 5.07 21 10.1 60 25.0 55 3.74 32 8.54 10 36.9 19 2.45 4 13.9 25 21.6 30 2.16 1
OFRI [161]29.0 3.87 2 6.61 2 2.16 102 6.40 4 9.70 4 2.45 125 2.71 2 3.79 1 1.73 1 7.39 3 9.20 2 4.69 4 13.8 4 18.1 4 4.43 3 7.87 7 19.9 7 3.51 5 10.2 127 30.7 6 2.58 142 12.2 6 17.9 4 2.38 128
MPRN [157]29.8 4.43 12 8.35 11 2.08 71 7.39 60 10.8 17 2.16 69 6.06 107 10.4 90 2.00 93 8.70 53 12.4 19 4.97 6 16.7 8 22.2 8 4.83 9 8.23 8 20.5 8 3.70 6 8.81 28 33.2 10 2.45 4 12.4 7 18.9 9 2.16 1
NNF-EAC [103]30.4 5.35 87 10.0 33 2.08 71 7.05 41 11.6 34 2.08 2 6.00 63 9.35 20 1.73 1 8.35 15 12.4 19 5.23 97 17.7 32 23.9 34 5.07 21 9.47 18 22.9 15 3.70 6 8.83 32 37.0 21 2.45 4 14.0 32 21.6 30 2.16 1
IROF++ [58]32.0 5.23 71 10.8 76 2.00 6 6.88 29 11.5 32 2.08 2 6.00 63 10.0 40 1.73 1 8.19 6 11.9 11 5.07 9 17.9 54 24.4 61 5.10 41 9.49 20 24.2 37 3.74 32 9.09 65 37.2 25 2.45 4 14.0 32 22.1 49 2.16 1
SepConv-v1 [127]33.5 3.87 2 8.50 12 1.73 1 7.05 41 11.4 27 2.16 69 3.46 7 6.56 9 2.00 93 8.58 40 12.6 29 5.26 114 17.5 16 23.6 18 4.97 12 8.35 10 22.4 13 3.70 6 8.08 7 33.3 11 2.52 117 12.8 11 19.1 10 2.38 128
SuperSlomo [132]35.7 4.24 9 7.53 8 2.16 102 7.14 47 11.4 27 2.71 141 4.36 9 6.45 8 2.00 93 8.27 11 11.3 8 5.10 34 16.7 8 22.2 8 4.80 8 8.29 9 21.0 10 3.74 32 8.60 12 32.7 9 2.52 117 12.6 9 19.1 10 2.38 128
DF-Auto [115]37.1 5.03 19 8.87 13 2.16 102 7.72 80 13.1 76 2.38 112 5.69 14 9.20 19 1.73 1 8.68 49 12.5 24 5.10 34 17.4 14 23.4 14 5.16 68 9.47 18 24.0 29 3.74 32 8.98 46 38.4 52 2.45 4 14.0 32 21.8 38 2.16 1
DeepFlow2 [108]37.2 5.07 22 9.85 28 2.08 71 7.53 74 13.1 76 2.16 69 5.69 14 10.0 40 1.73 1 8.83 81 13.4 57 5.10 34 17.6 19 23.7 22 5.20 78 9.24 15 23.0 16 3.74 32 9.00 49 37.9 40 2.45 4 13.9 25 21.5 26 2.16 1
TOF-M [154]37.3 4.24 9 8.10 10 1.91 5 7.33 53 11.6 34 2.52 132 4.36 9 6.95 10 2.00 93 8.43 31 11.7 10 5.07 9 16.9 11 22.6 12 4.97 12 8.74 12 21.2 11 3.74 32 9.47 98 31.8 8 2.58 142 13.2 12 19.7 12 2.38 128
COFM [59]38.2 5.07 22 10.7 67 2.00 6 6.86 28 11.4 27 2.08 2 5.69 14 9.75 31 1.73 1 8.35 15 12.5 24 5.07 9 18.1 77 24.7 80 5.03 17 11.0 123 27.5 126 3.70 6 8.06 6 39.1 69 2.45 4 14.4 83 22.7 78 2.16 1
WLIF-Flow [93]39.0 5.10 42 10.2 43 2.00 6 7.00 40 11.9 46 2.08 2 5.69 14 9.68 26 1.73 1 8.29 12 12.2 16 5.23 97 17.8 42 24.0 37 5.10 41 10.6 97 26.6 102 3.83 116 8.83 32 37.5 28 2.45 4 14.1 46 21.9 45 2.16 1
LME [70]40.3 5.07 22 10.1 37 2.00 6 7.05 41 12.0 49 2.16 69 5.69 14 10.7 94 1.73 1 8.35 15 12.8 38 5.10 34 18.0 64 24.4 61 5.29 152 10.2 68 25.3 64 3.74 32 8.70 21 36.4 14 2.45 4 14.0 32 21.7 34 2.16 1
Layers++ [37]40.5 5.10 42 10.1 37 2.08 71 6.45 8 9.88 6 2.08 2 5.69 14 10.0 40 1.73 1 8.37 22 12.7 34 5.10 34 18.1 77 24.9 103 5.10 41 10.7 108 28.3 139 3.74 32 8.76 22 38.0 44 2.45 4 14.1 46 21.9 45 2.16 1
DeepFlow [86]41.0 5.07 22 9.63 22 2.08 71 7.44 70 13.0 70 2.16 69 5.74 55 10.0 40 1.73 1 8.96 94 13.0 41 5.20 66 17.6 19 23.8 26 5.20 78 9.15 14 23.2 18 3.87 127 8.81 28 35.6 13 2.45 4 13.7 16 21.1 18 2.16 1
ProbFlowFields [128]41.0 5.03 19 10.7 67 2.00 6 6.68 15 11.3 24 2.08 2 5.69 14 9.47 24 1.73 1 8.52 37 13.3 56 5.20 66 18.2 101 24.9 103 5.23 134 10.5 87 26.2 93 3.74 32 8.60 12 37.7 35 2.45 4 13.8 20 21.6 30 2.16 1
CombBMOF [113]41.0 5.35 87 10.5 59 2.00 6 6.83 26 11.4 27 2.08 2 5.80 58 10.0 40 1.73 1 8.83 81 14.4 86 5.10 34 17.9 54 24.3 55 5.07 21 9.88 41 24.1 33 3.70 6 10.7 139 38.3 47 2.45 4 14.0 32 21.9 45 2.16 1
nLayers [57]41.1 5.16 49 10.5 59 2.00 6 6.66 14 10.9 18 2.08 2 5.69 14 9.00 12 1.73 1 8.49 36 13.0 41 5.10 34 18.3 111 25.2 122 5.20 78 10.4 82 25.6 71 3.74 32 8.66 16 38.5 57 2.45 4 14.2 62 22.4 65 2.16 1
SuperFlow [81]42.1 5.00 14 9.35 15 2.16 102 7.85 86 13.1 76 2.38 112 6.00 63 9.47 24 2.00 93 8.70 53 12.7 34 5.20 66 17.6 19 23.7 22 5.20 78 9.27 16 23.9 27 3.70 6 8.81 28 37.6 31 2.45 4 13.8 20 21.2 21 2.16 1
IROF-TV [53]42.7 5.20 51 10.7 67 2.08 71 7.05 41 11.9 46 2.08 2 6.00 63 10.3 69 1.73 1 8.37 22 12.6 29 5.16 57 17.8 42 24.1 45 5.23 134 10.1 60 25.0 55 3.70 6 9.04 58 39.1 69 2.45 4 13.7 16 21.0 16 2.16 1
FMOF [94]42.7 5.42 108 11.0 86 2.00 6 6.76 21 11.0 20 2.08 2 6.00 63 10.3 69 1.73 1 8.83 81 14.1 78 5.10 34 17.8 42 24.1 45 5.07 21 10.0 58 25.6 71 3.74 32 8.58 11 37.7 35 2.45 4 14.3 71 22.4 65 2.16 1
Sparse-NonSparse [56]42.8 5.20 51 10.7 67 2.00 6 6.78 22 11.6 34 2.08 2 5.69 14 10.0 40 1.73 1 8.43 31 12.5 24 5.07 9 18.1 77 24.7 80 5.10 41 10.5 87 26.7 105 3.74 32 8.76 22 42.1 113 2.45 4 14.3 71 23.0 94 2.16 1
Aniso. Huber-L1 [22]43.2 5.26 73 10.0 33 2.08 71 8.81 116 14.5 119 2.16 69 6.00 63 9.75 31 1.73 1 8.72 57 13.0 41 5.16 57 17.6 19 23.8 26 5.10 41 9.87 40 23.2 18 3.70 6 9.26 79 37.8 37 2.45 4 13.8 20 21.0 16 2.16 1
Brox et al. [5]43.6 5.20 51 9.83 25 2.00 6 7.62 79 12.6 58 2.16 69 6.00 63 10.2 65 2.00 93 8.76 62 12.6 29 5.07 9 17.5 16 23.6 18 5.16 68 10.1 60 25.3 64 3.74 32 9.00 49 40.1 82 2.45 4 13.8 20 21.3 24 2.16 1
FlowFields [110]43.7 5.10 42 11.1 96 2.00 6 6.88 29 11.5 32 2.08 2 5.69 14 10.0 40 1.73 1 8.76 62 14.9 100 5.20 66 18.0 64 24.4 61 5.16 68 10.3 75 25.8 78 3.74 32 8.76 22 37.8 37 2.45 4 14.1 46 22.5 70 2.16 1
TV-L1-MCT [64]44.0 5.48 125 11.4 109 2.00 6 7.35 56 13.1 76 2.08 2 5.48 12 10.3 69 1.73 1 8.35 15 12.4 19 5.07 9 18.3 111 25.3 127 5.10 41 9.49 20 23.5 22 3.79 95 8.81 28 39.2 73 2.45 4 13.7 16 21.1 18 2.16 1
ComponentFusion [96]44.7 5.07 22 11.2 102 2.00 6 6.81 25 11.6 34 2.08 2 5.72 54 9.81 35 1.73 1 8.37 22 13.2 53 5.07 9 18.1 77 24.7 80 5.10 41 9.90 42 24.9 52 3.74 32 9.20 76 44.1 132 2.45 4 14.2 62 23.3 109 2.16 1
MDP-Flow [26]45.5 5.03 19 9.95 31 2.00 6 6.68 15 11.3 24 2.08 2 5.69 14 9.04 17 1.73 1 8.89 89 13.7 64 5.20 66 17.8 42 24.2 53 5.20 78 11.3 136 27.9 133 3.74 32 9.27 83 39.3 75 2.45 4 14.1 46 22.3 61 2.16 1
JOF [140]45.8 5.35 87 10.8 76 2.08 71 6.68 15 10.9 18 2.08 2 5.69 14 9.68 26 1.73 1 8.39 27 12.5 24 5.20 66 18.1 77 24.7 80 5.20 78 10.6 97 27.1 115 3.74 32 8.66 16 37.6 31 2.45 4 14.3 71 22.5 70 2.16 1
PGM-C [120]48.2 5.07 22 10.9 83 2.00 6 6.93 32 11.6 34 2.08 2 6.00 63 10.3 69 1.73 1 8.76 62 15.2 109 5.16 57 18.0 64 24.7 80 5.20 78 9.97 53 24.8 50 3.74 32 9.00 49 40.1 82 2.45 4 14.1 46 22.7 78 2.16 1
2DHMM-SAS [92]48.2 5.42 108 11.2 102 2.00 6 7.90 91 13.7 95 2.08 2 5.60 13 9.85 36 1.73 1 8.35 15 12.2 16 5.10 34 18.0 64 24.6 78 5.10 41 9.93 46 25.7 75 3.74 32 8.96 41 39.8 80 2.45 4 14.4 83 23.0 94 2.16 1
FlowFields+ [130]48.5 5.10 42 11.1 96 2.00 6 6.78 22 11.3 24 2.08 2 5.69 14 10.0 40 1.73 1 8.70 53 14.9 100 5.16 57 18.2 101 24.9 103 5.20 78 10.4 82 26.3 96 3.74 32 8.79 26 38.6 61 2.45 4 14.1 46 22.7 78 2.16 1
CLG-TV [48]49.0 5.20 51 9.49 19 2.08 71 8.43 106 14.3 113 2.16 69 6.00 63 10.1 61 2.00 93 8.76 62 13.1 49 5.20 66 17.6 19 23.8 26 5.10 41 9.59 28 23.1 17 3.74 32 9.20 76 38.4 52 2.45 4 14.0 32 21.5 26 2.16 1
CPM-Flow [116]49.5 5.07 22 10.9 83 2.00 6 6.95 35 11.6 34 2.08 2 5.80 58 10.0 40 1.73 1 9.00 100 15.9 124 5.20 66 18.1 77 24.7 80 5.20 78 9.81 32 24.3 38 3.79 95 9.26 79 38.3 47 2.45 4 14.0 32 22.2 55 2.16 1
ALD-Flow [66]49.8 5.20 51 10.7 67 2.08 71 7.35 56 12.9 65 2.16 69 6.00 63 10.1 61 1.73 1 8.39 27 13.0 41 5.16 57 17.9 54 24.3 55 5.20 78 9.56 25 23.5 22 3.79 95 8.79 26 36.8 18 2.45 4 14.5 94 23.0 94 2.16 1
HAST [109]50.5 5.07 22 10.5 59 2.00 6 6.68 15 10.7 15 2.08 2 6.00 63 10.3 69 1.73 1 8.29 12 12.4 19 5.00 8 18.4 123 25.3 127 5.03 17 11.0 123 30.7 152 3.70 6 8.60 12 41.8 106 2.45 4 14.9 124 23.9 125 2.16 1
S2F-IF [123]51.2 5.10 42 11.6 120 2.00 6 6.78 22 11.4 27 2.08 2 5.69 14 10.3 69 1.73 1 8.74 58 15.2 109 5.07 9 18.3 111 25.1 118 5.20 78 10.5 87 26.1 88 3.74 32 9.02 56 38.5 57 2.45 4 14.1 46 22.6 72 2.16 1
Ramp [62]51.7 5.29 80 10.8 76 2.00 6 6.83 26 11.6 34 2.08 2 5.69 14 10.1 61 1.73 1 8.35 15 12.2 16 5.07 9 18.1 77 24.7 80 5.10 41 10.9 118 27.8 132 3.79 95 8.83 32 43.0 124 2.45 4 14.5 94 23.2 103 2.16 1
Second-order prior [8]51.8 5.20 51 9.83 25 2.08 71 8.43 106 14.5 119 2.08 2 6.35 115 11.0 112 2.00 93 8.83 81 13.8 71 5.07 9 17.7 32 23.8 26 5.07 21 9.70 30 24.1 33 3.74 32 9.33 87 38.4 52 2.45 4 14.0 32 21.8 38 2.16 1
EAI-Flow [151]53.2 5.20 51 11.2 102 2.08 71 7.39 60 12.4 55 2.16 69 6.00 63 10.8 106 1.73 1 8.81 75 14.6 93 5.07 9 18.1 77 24.8 92 5.16 68 9.83 33 24.0 29 3.74 32 9.43 97 38.3 47 2.45 4 13.7 16 21.5 26 2.16 1
CBF [12]53.3 5.00 14 9.40 17 2.08 71 7.77 84 13.0 70 2.16 69 6.00 63 9.68 26 1.73 1 8.68 49 12.5 24 5.35 134 17.6 19 23.4 14 5.20 78 9.85 38 24.3 38 3.74 32 9.11 69 39.3 75 2.52 117 14.0 32 21.1 18 2.38 128
p-harmonic [29]54.1 5.07 22 9.98 32 2.00 6 8.68 112 14.4 115 2.16 69 6.00 63 10.7 94 1.91 88 9.20 111 13.7 64 5.20 66 17.8 42 24.0 37 5.10 41 9.90 42 23.7 25 3.74 32 9.61 109 38.5 57 2.45 4 14.0 32 21.7 34 2.16 1
Local-TV-L1 [65]54.2 5.20 51 9.38 16 2.16 102 8.96 122 14.5 119 2.38 112 5.69 14 9.35 20 1.73 1 8.70 53 13.0 41 5.45 141 17.6 19 23.8 26 5.16 68 9.54 24 24.0 29 4.08 152 8.76 22 37.2 25 2.45 4 13.6 15 20.9 15 2.31 109
SIOF [67]54.2 5.42 108 10.4 53 2.08 71 8.83 117 15.0 133 2.38 112 5.69 14 10.4 90 1.73 1 8.68 49 13.1 49 5.20 66 17.3 13 23.2 13 5.07 21 9.83 33 23.6 24 3.74 32 9.00 49 36.9 19 2.45 4 14.3 71 22.1 49 2.31 109
DPOF [18]54.8 5.35 87 11.7 122 2.08 71 6.56 13 10.4 13 2.08 2 6.00 63 9.71 30 1.91 88 8.76 62 14.4 86 5.20 66 17.7 32 24.1 45 5.07 21 10.3 75 26.7 105 3.70 6 9.33 87 39.1 69 2.45 4 14.4 83 22.8 84 2.16 1
ProFlow_ROB [146]55.3 5.07 22 10.9 83 2.00 6 7.33 53 12.7 60 2.16 69 5.69 14 9.98 39 1.73 1 8.60 43 14.1 78 5.20 66 18.3 111 25.2 122 5.20 78 9.52 23 23.4 21 3.70 6 9.49 103 42.0 111 2.45 4 14.5 94 23.6 119 2.16 1
LDOF [28]55.4 5.35 87 9.83 25 2.16 102 7.94 92 12.1 50 2.52 132 6.00 63 10.3 69 2.00 93 8.91 92 13.6 62 5.23 97 17.6 19 23.6 18 5.20 78 9.49 20 24.5 43 3.74 32 8.96 41 37.9 40 2.45 4 14.0 32 21.8 38 2.16 1
ComplOF-FED-GPU [35]55.8 5.20 51 11.1 96 2.00 6 7.19 51 12.6 58 2.08 2 6.35 115 10.0 40 2.00 93 8.68 49 14.0 77 5.10 34 17.9 54 24.5 69 5.10 41 9.97 53 25.1 58 3.74 32 9.40 92 38.8 65 2.45 4 14.5 94 23.2 103 2.16 1
LSM [39]56.0 5.35 87 11.5 114 2.00 6 6.98 37 11.9 46 2.08 2 5.80 58 10.7 94 1.73 1 8.58 40 13.4 57 5.07 9 18.1 77 24.9 103 5.10 41 10.6 97 27.1 115 3.74 32 8.83 32 42.2 115 2.45 4 14.4 83 23.0 94 2.16 1
AGIF+OF [85]56.0 5.42 108 11.1 96 2.00 6 6.98 37 11.8 43 2.08 2 5.69 14 10.0 40 1.73 1 8.43 31 12.8 38 5.07 9 18.5 131 25.2 122 5.20 78 10.8 114 27.6 127 3.74 32 8.98 46 37.9 40 2.45 4 14.7 112 23.4 113 2.16 1
OFLAF [77]56.3 5.07 22 10.6 64 2.00 6 6.48 12 10.5 14 2.08 2 5.69 14 10.0 40 1.73 1 8.37 22 12.6 29 5.07 9 18.4 123 25.4 134 5.20 78 10.9 118 27.4 124 3.74 32 9.59 108 44.9 138 2.45 4 15.1 130 24.1 127 2.16 1
FC-2Layers-FF [74]56.5 5.26 73 11.0 86 2.00 6 6.40 4 9.88 6 2.08 2 5.69 14 10.3 69 1.73 1 8.39 27 12.8 38 5.10 34 18.2 101 25.0 112 5.20 78 11.0 123 28.1 135 3.79 95 8.91 39 42.8 119 2.45 4 14.5 94 23.0 94 2.16 1
Classic+NL [31]56.7 5.35 87 11.0 86 2.08 71 6.98 37 11.7 41 2.08 2 5.69 14 10.2 65 1.73 1 8.43 31 12.4 19 5.20 66 18.1 77 24.8 92 5.10 41 10.6 97 26.8 108 3.79 95 8.83 32 42.9 120 2.45 4 14.4 83 22.9 91 2.16 1
RFlow [90]58.0 5.07 22 10.2 43 2.08 71 8.58 110 14.7 125 2.08 2 6.00 63 10.3 69 1.73 1 8.91 92 14.4 86 5.20 66 17.7 32 23.9 34 5.10 41 9.95 48 25.4 67 3.70 6 9.13 71 40.4 88 2.45 4 14.3 71 22.6 72 2.31 109
OAR-Flow [125]58.0 5.20 51 10.7 67 2.08 71 7.44 70 13.0 70 2.16 69 5.74 55 10.0 40 1.73 1 8.35 15 13.0 41 5.10 34 18.1 77 24.9 103 5.23 134 10.2 68 24.7 46 3.74 32 9.54 105 39.4 78 2.45 4 14.4 83 22.7 78 2.16 1
RNLOD-Flow [121]58.2 5.20 51 11.0 86 2.00 6 7.53 74 13.4 84 2.08 2 6.00 63 11.0 112 1.73 1 8.52 37 13.0 41 5.07 9 18.2 101 25.0 112 5.10 41 10.6 97 26.9 111 3.74 32 8.96 41 38.4 52 2.45 4 14.9 124 23.5 115 2.16 1
TF+OM [100]59.2 5.00 14 10.2 43 2.08 71 6.93 32 11.7 41 2.16 69 5.69 14 10.5 92 1.73 1 8.81 75 14.6 93 5.20 66 18.0 64 24.4 61 5.20 78 9.95 48 26.1 88 3.79 95 9.09 65 41.0 94 2.45 4 14.1 46 21.8 38 2.38 128
TC/T-Flow [76]59.2 5.45 117 11.5 114 2.00 6 7.42 66 13.0 70 2.08 2 5.69 14 9.76 33 1.73 1 8.60 43 13.7 64 5.16 57 18.3 111 24.9 103 5.20 78 10.1 60 24.9 52 3.74 32 9.75 112 42.6 116 2.45 4 14.5 94 22.6 72 2.16 1
EpicFlow [102]60.2 5.07 22 11.0 86 2.00 6 7.39 60 12.9 65 2.08 2 5.80 58 10.3 69 1.73 1 8.85 87 15.5 117 5.20 66 18.1 77 24.8 92 5.20 78 10.2 68 25.1 58 3.74 32 9.33 87 40.4 88 2.45 4 14.5 94 24.1 127 2.16 1
DMF_ROB [139]60.7 5.20 51 10.8 76 2.08 71 7.85 86 13.4 84 2.08 2 6.35 115 11.6 125 2.00 93 9.02 101 14.5 91 5.16 57 17.8 42 24.4 61 5.20 78 9.83 33 24.3 38 3.74 32 9.04 58 38.3 47 2.45 4 14.1 46 22.4 65 2.16 1
F-TV-L1 [15]61.0 5.35 87 10.3 50 2.16 102 8.83 117 14.6 124 2.16 69 6.00 63 10.3 69 2.00 93 8.76 62 13.2 53 5.26 114 17.6 19 23.8 26 5.03 17 9.57 27 23.2 18 3.79 95 9.18 74 37.6 31 2.45 4 13.8 20 21.2 21 2.31 109
TC-Flow [46]61.2 5.07 22 10.8 76 2.00 6 7.39 60 13.2 82 2.16 69 6.00 63 10.3 69 1.73 1 8.66 46 13.7 64 5.23 97 18.2 101 25.0 112 5.20 78 10.2 68 24.5 43 3.79 95 9.04 58 38.1 45 2.45 4 14.5 94 23.5 115 2.16 1
S2D-Matching [84]61.5 5.35 87 11.2 102 2.00 6 7.75 83 13.5 88 2.08 2 5.69 14 10.0 40 1.73 1 8.37 22 12.6 29 5.20 66 18.3 111 25.2 122 5.07 21 11.0 123 27.7 131 3.79 95 9.09 65 40.3 86 2.45 4 14.4 83 23.0 94 2.16 1
Fusion [6]63.5 5.20 51 10.4 53 2.00 6 7.14 47 11.8 43 2.08 2 5.74 55 9.68 26 1.73 1 9.33 114 14.2 80 5.20 66 18.3 111 24.7 80 5.07 21 11.6 141 28.1 135 3.70 6 9.63 110 41.4 99 2.45 4 15.3 143 24.2 130 2.16 1
LFNet_ROB [149]65.0 5.35 87 13.4 140 2.00 6 7.72 80 12.9 65 2.16 69 6.00 63 11.3 119 1.73 1 8.98 99 15.9 124 5.07 9 18.1 77 24.8 92 5.10 41 11.0 123 28.1 135 3.74 32 9.09 65 37.6 31 2.45 4 14.0 32 22.4 65 2.16 1
Classic++ [32]65.7 5.20 51 10.3 50 2.08 71 7.94 92 13.8 98 2.08 2 6.00 63 10.1 61 1.73 1 8.89 89 13.7 64 5.23 97 18.0 64 24.5 69 5.10 41 10.3 75 25.8 78 3.87 127 9.13 71 40.1 82 2.45 4 14.2 62 22.2 55 2.31 109
Modified CLG [34]66.2 5.07 22 9.49 19 2.16 102 9.42 136 14.2 111 2.65 138 6.00 63 11.5 124 2.00 93 9.15 108 14.3 82 5.10 34 17.7 32 23.9 34 5.10 41 10.1 60 24.7 46 3.74 32 9.31 86 37.5 28 2.45 4 14.1 46 21.8 38 2.31 109
Sparse Occlusion [54]66.4 5.26 73 10.5 59 2.08 71 8.04 95 14.4 115 2.08 2 6.00 63 10.0 40 1.73 1 8.83 81 13.7 64 5.20 66 18.1 77 24.7 80 5.20 78 11.0 123 26.5 98 3.74 32 9.42 93 42.0 111 2.45 4 14.4 83 22.8 84 2.16 1
AggregFlow [97]66.7 5.45 117 13.8 144 2.08 71 7.44 70 13.1 76 2.16 69 5.69 14 9.95 38 1.73 1 9.15 108 16.1 126 5.10 34 18.0 64 24.5 69 5.20 78 9.90 42 24.6 45 3.83 116 8.98 46 40.7 91 2.45 4 14.4 83 23.0 94 2.16 1
FESL [72]67.1 5.42 108 11.0 86 2.00 6 7.05 41 11.8 43 2.08 2 5.69 14 10.7 94 1.73 1 8.81 75 13.5 60 5.20 66 18.4 123 25.1 118 5.20 78 11.0 123 27.0 114 3.74 32 9.06 63 42.9 120 2.45 4 14.8 118 23.7 120 2.16 1
PMF [73]67.4 5.20 51 11.4 109 2.00 6 7.35 56 12.4 55 2.08 2 6.00 63 12.0 134 1.73 1 8.76 62 14.4 86 5.07 9 18.4 123 25.0 112 5.10 41 10.2 68 25.8 78 3.87 127 9.04 58 41.3 98 2.45 4 15.2 139 24.5 134 2.16 1
Classic+CPF [83]67.9 5.35 87 11.3 107 2.00 6 7.07 46 12.1 50 2.08 2 5.69 14 10.5 92 1.73 1 8.43 31 12.7 34 5.07 9 18.7 143 25.7 144 5.20 78 11.2 133 28.7 142 3.74 32 9.42 93 42.9 120 2.45 4 15.1 130 24.2 130 2.16 1
FF++_ROB [145]68.8 5.07 22 11.5 114 2.00 6 7.16 50 12.2 52 2.08 2 6.00 63 10.3 69 1.73 1 8.96 94 16.4 131 5.20 66 18.6 137 25.7 144 5.20 78 10.6 97 26.8 108 3.92 142 9.00 49 39.1 69 2.45 4 14.2 62 22.9 91 2.16 1
TCOF [69]69.5 5.35 87 10.7 67 2.00 6 9.27 130 15.4 141 2.16 69 5.69 14 10.2 65 1.73 1 8.74 58 13.1 49 5.23 97 17.7 32 23.8 26 5.07 21 10.7 108 26.6 102 3.70 6 10.0 122 44.7 137 2.45 4 14.6 107 22.9 91 2.38 128
OFH [38]70.2 5.35 87 11.0 86 2.08 71 8.06 98 13.7 95 2.08 2 6.00 63 11.6 125 1.73 1 8.58 40 13.9 75 5.07 9 18.2 101 24.9 103 5.16 68 10.3 75 25.1 58 3.74 32 9.88 118 42.7 118 2.45 4 14.8 118 24.7 136 2.16 1
FlowNetS+ft+v [112]70.2 5.26 73 10.1 37 2.16 102 9.11 126 14.5 119 2.45 125 6.00 63 10.3 69 2.00 93 8.96 94 13.5 60 5.26 114 17.8 42 24.1 45 5.23 134 9.76 31 23.9 27 3.74 32 9.38 91 41.6 102 2.45 4 14.1 46 22.2 55 2.16 1
BlockOverlap [61]70.5 5.20 51 9.29 14 2.16 102 8.74 114 14.1 106 2.65 138 6.00 63 9.35 20 2.00 93 8.52 37 11.9 11 5.60 148 17.8 42 24.0 37 5.32 154 9.83 33 25.0 55 4.04 147 8.83 32 37.1 22 2.52 117 13.5 14 20.6 14 2.38 128
SVFilterOh [111]70.9 5.20 51 10.6 64 2.00 6 6.73 20 11.0 20 2.08 2 6.00 63 10.0 40 1.73 1 8.76 62 13.8 71 5.26 114 18.4 123 25.3 127 5.26 145 10.6 97 28.0 134 3.74 32 8.45 9 39.2 73 2.52 117 14.7 112 23.3 109 2.31 109
SRR-TVOF-NL [91]71.0 5.45 117 12.1 129 2.08 71 7.77 84 13.5 88 2.16 69 6.00 63 10.3 69 1.73 1 9.26 112 14.7 96 5.07 9 18.1 77 24.6 78 5.10 41 10.4 82 26.6 102 3.70 6 9.42 93 38.5 57 2.45 4 15.1 130 23.9 125 2.16 1
Efficient-NL [60]71.5 5.35 87 10.7 67 2.00 6 7.42 66 13.0 70 2.08 2 6.35 115 10.7 94 2.00 93 8.81 75 13.4 57 5.10 34 18.1 77 24.7 80 5.10 41 11.2 133 27.6 127 3.70 6 9.47 98 43.6 130 2.45 4 15.1 130 23.8 123 2.16 1
EPPM w/o HM [88]71.8 5.23 71 12.6 133 2.00 6 7.39 60 13.0 70 2.08 2 6.35 115 14.0 152 1.91 88 8.83 81 15.3 113 5.10 34 18.0 64 24.5 69 5.10 41 10.5 87 27.6 127 3.74 32 9.11 69 41.9 107 2.45 4 14.5 94 23.2 103 2.16 1
CRTflow [80]71.9 5.29 80 10.5 59 2.16 102 8.43 106 14.5 119 2.16 69 6.35 115 11.1 118 2.00 93 8.64 45 13.0 41 5.29 124 18.0 64 24.5 69 5.20 78 9.68 29 23.8 26 3.74 32 9.00 49 40.9 93 2.45 4 14.1 46 22.2 55 2.31 109
3DFlow [135]73.0 5.42 108 11.5 114 2.00 6 7.14 47 12.3 53 2.08 2 6.22 114 10.0 40 1.73 1 8.66 46 13.6 62 5.23 97 17.9 54 24.5 69 5.20 78 12.3 156 29.0 144 3.79 95 10.6 137 41.7 104 2.45 4 14.8 118 23.2 103 2.16 1
PWC-Net_ROB [147]73.2 5.35 87 13.8 144 2.00 6 7.55 77 13.3 83 2.08 2 6.00 63 11.3 119 1.73 1 8.76 62 15.7 119 5.07 9 18.6 137 25.9 149 5.20 78 10.5 87 26.9 111 3.83 116 9.00 49 38.6 61 2.45 4 14.3 71 23.7 120 2.16 1
MLDP_OF [89]73.3 5.32 84 11.1 96 2.00 6 7.55 77 13.6 92 2.08 2 5.69 14 10.0 40 1.73 1 8.76 62 13.1 49 5.26 114 18.0 64 24.5 69 5.20 78 11.0 123 26.9 111 4.08 152 9.26 79 38.2 46 2.52 117 14.4 83 22.6 72 2.38 128
Steered-L1 [118]73.6 5.07 22 9.81 24 2.00 6 7.35 56 12.8 64 2.16 69 6.35 115 10.3 69 2.00 93 9.31 113 14.3 82 5.35 134 18.2 101 24.7 80 5.07 21 10.2 68 25.7 75 3.79 95 9.33 87 40.4 88 2.45 4 14.6 107 22.8 84 2.31 109
2D-CLG [1]74.0 5.16 49 10.0 33 2.16 102 9.90 142 14.2 111 2.83 148 6.35 115 10.7 94 2.00 93 10.0 134 15.2 109 5.10 34 17.7 32 24.1 45 5.20 78 10.1 60 24.1 33 3.74 32 9.81 113 43.6 130 2.45 4 14.1 46 21.8 38 2.16 1
Occlusion-TV-L1 [63]75.7 5.20 51 10.2 43 2.08 71 8.89 119 15.3 139 2.16 69 6.00 63 10.3 69 2.00 93 9.15 108 15.4 114 5.26 114 17.6 19 23.7 22 5.10 41 9.98 55 25.5 69 3.87 127 10.3 131 39.3 75 2.52 117 14.1 46 22.3 61 2.16 1
IAOF [50]75.8 5.60 132 11.0 86 2.16 102 12.0 158 16.9 159 2.52 132 5.69 14 11.0 112 2.00 93 9.76 129 14.3 82 5.20 66 17.7 32 24.0 37 5.07 21 10.0 58 25.2 62 3.74 32 9.47 98 41.4 99 2.45 4 14.2 62 22.1 49 2.16 1
Complementary OF [21]76.8 5.20 51 12.0 126 2.00 6 7.19 51 12.9 65 2.08 2 6.68 135 10.8 106 2.00 93 8.76 62 14.6 93 5.16 57 18.2 101 25.2 122 5.10 41 10.3 75 25.9 83 3.74 32 9.97 121 42.6 116 2.45 4 15.6 147 28.0 153 2.16 1
Adaptive [20]78.3 5.32 84 10.3 50 2.16 102 9.29 133 15.4 141 2.16 69 6.00 63 10.7 94 1.73 1 8.81 75 13.8 71 5.20 66 17.9 54 24.3 55 5.07 21 10.4 82 26.0 84 3.79 95 9.83 114 44.6 135 2.45 4 14.5 94 22.8 84 2.31 109
CostFilter [40]79.3 5.32 84 13.2 139 2.00 6 7.33 53 12.3 53 2.08 2 6.06 107 13.5 151 1.73 1 8.96 94 16.1 126 5.07 9 18.6 137 25.6 143 5.16 68 9.98 55 24.8 50 4.04 147 9.20 76 43.5 129 2.45 4 15.1 130 24.9 139 2.16 1
Ad-TV-NDC [36]79.4 5.66 135 9.88 29 2.52 152 10.1 146 15.1 134 2.71 141 6.00 63 10.7 94 1.73 1 9.49 124 14.2 80 5.35 134 17.7 32 24.0 37 5.20 78 9.56 25 24.0 29 3.87 127 9.56 106 38.6 61 2.45 4 13.9 25 21.2 21 2.38 128
Black & Anandan [4]80.5 5.45 117 10.1 37 2.16 102 10.2 149 15.3 139 2.45 125 6.68 135 11.3 119 2.00 93 10.2 136 15.6 118 5.20 66 17.8 42 24.0 37 5.16 68 9.83 33 24.7 46 3.74 32 10.2 127 41.9 107 2.45 4 14.2 62 21.8 38 2.16 1
HBM-GC [105]80.5 5.35 87 10.6 64 2.16 102 7.42 66 13.4 84 2.16 69 5.69 14 9.00 12 1.73 1 8.74 58 13.2 53 5.26 114 18.6 137 25.5 140 5.26 145 11.8 148 31.5 156 3.83 116 8.83 32 41.1 96 2.45 4 14.3 71 22.2 55 2.31 109
BriefMatch [124]80.6 5.29 80 11.4 109 2.08 71 7.44 70 12.7 60 2.16 69 6.38 133 9.93 37 2.00 93 9.83 131 14.9 100 5.83 155 18.0 64 24.4 61 5.20 78 10.5 87 27.3 121 4.32 157 9.04 58 37.9 40 2.45 4 14.3 71 22.8 84 2.16 1
CNN-flow-warp+ref [117]81.4 5.00 14 9.59 21 2.16 102 8.35 104 13.6 92 2.16 69 6.35 115 11.8 133 2.00 93 10.6 141 15.4 114 5.48 145 17.8 42 24.3 55 5.23 134 9.95 48 24.3 38 3.83 116 9.83 114 44.6 135 2.45 4 14.2 62 22.3 61 2.16 1
LiteFlowNet [142]82.0 5.45 117 14.5 148 2.00 6 7.42 66 12.7 60 2.08 2 5.69 14 13.0 146 1.73 1 9.71 128 23.2 156 5.29 124 18.4 123 25.4 134 5.20 78 10.8 114 27.1 115 3.70 6 10.2 127 43.0 124 2.45 4 14.3 71 23.2 103 2.16 1
HBpMotionGpu [43]83.8 5.48 125 10.8 76 2.38 144 10.1 146 15.4 141 2.71 141 5.69 14 10.0 40 1.73 1 9.40 117 16.2 130 5.23 97 17.9 54 24.3 55 5.20 78 10.5 87 26.4 97 3.83 116 8.96 41 37.8 37 2.45 4 14.3 71 22.6 72 2.38 128
TriFlow [95]84.2 5.26 73 12.0 126 2.16 102 8.39 105 14.4 115 2.38 112 6.00 63 11.0 112 1.73 1 9.02 101 15.4 114 5.10 34 18.5 131 25.4 134 5.20 78 10.6 97 27.3 121 3.74 32 9.26 79 39.7 79 2.45 4 14.6 107 23.1 101 2.16 1
AdaConv-v1 [126]85.4 6.24 148 14.4 147 2.38 144 9.02 123 12.7 60 3.11 153 7.00 145 11.0 112 2.38 152 13.1 154 18.8 144 5.83 155 16.8 10 22.5 10 4.83 9 8.79 13 22.0 12 3.70 6 8.91 39 36.6 17 2.58 142 13.3 13 20.2 13 2.38 128
TVL1_ROB [138]85.6 5.45 117 9.93 30 2.38 144 10.9 152 15.8 154 2.71 141 6.00 63 10.9 109 2.00 93 9.85 132 15.0 104 5.20 66 17.8 42 24.1 45 5.20 78 10.1 60 25.8 78 3.83 116 9.87 117 44.1 132 2.45 4 14.0 32 21.9 45 2.16 1
Nguyen [33]86.0 5.42 108 10.0 33 2.38 144 10.9 152 15.1 134 2.65 138 6.00 63 12.0 134 2.00 93 10.4 140 16.1 126 5.20 66 17.8 42 24.1 45 5.07 21 9.98 55 25.3 64 3.70 6 10.9 143 46.9 144 2.52 117 14.1 46 22.1 49 2.16 1
Aniso-Texture [82]86.5 5.07 22 10.2 43 2.00 6 8.89 119 15.2 138 2.16 69 6.35 115 10.3 69 1.73 1 9.04 103 16.1 126 5.29 124 18.3 111 24.9 103 5.23 134 11.8 148 30.0 150 3.83 116 9.06 63 40.2 85 2.45 4 14.7 112 23.5 115 2.16 1
FlowNet2 [122]89.1 6.45 153 19.1 157 2.16 102 7.85 86 13.4 84 2.38 112 6.06 107 11.7 127 1.73 1 9.40 117 18.2 140 5.23 97 18.5 131 25.3 127 5.20 78 10.3 75 25.2 62 3.74 32 9.27 83 41.9 107 2.45 4 14.3 71 22.8 84 2.16 1
TV-L1-improved [17]89.2 5.10 42 10.2 43 2.08 71 9.20 129 15.4 141 2.16 69 6.35 115 10.3 69 2.00 93 8.85 87 13.8 71 5.23 97 18.0 64 24.4 61 5.10 41 10.6 97 26.5 98 3.79 95 9.93 120 46.9 144 2.52 117 14.3 71 22.7 78 2.38 128
ResPWCR_ROB [144]90.8 5.35 87 12.5 132 2.00 6 7.94 92 13.6 92 2.16 69 6.68 135 11.3 119 1.91 88 9.42 119 18.1 139 5.29 124 18.1 77 24.8 92 5.07 21 10.6 97 27.3 121 4.40 158 9.56 106 38.4 52 2.45 4 14.7 112 24.7 136 2.16 1
GraphCuts [14]91.1 5.66 135 11.9 125 2.16 102 7.53 74 12.5 57 2.38 112 7.68 152 10.2 65 2.00 93 9.47 122 14.9 100 5.23 97 18.1 77 24.5 69 5.00 14 10.1 60 25.7 75 3.70 6 9.02 56 42.1 113 2.52 117 15.1 130 24.1 127 2.31 109
SimpleFlow [49]91.2 5.35 87 11.0 86 2.00 6 8.04 95 13.9 101 2.08 2 6.56 134 11.3 119 2.00 93 8.41 30 12.7 34 5.20 66 18.4 123 25.4 134 5.20 78 11.4 139 28.9 143 3.74 32 10.1 124 53.7 155 2.52 117 15.3 143 26.5 147 2.16 1
Bartels [41]91.3 5.35 87 11.4 109 2.16 102 7.72 80 14.0 105 2.38 112 6.00 63 10.3 69 2.00 93 9.11 105 15.0 104 5.69 150 17.6 19 23.6 18 5.45 158 10.7 108 27.2 118 4.55 160 8.96 41 36.4 14 2.65 154 14.1 46 22.1 49 2.38 128
ContinualFlow_ROB [152]93.9 5.60 132 14.6 149 2.16 102 7.85 86 13.5 88 2.31 111 6.35 115 12.4 140 2.00 93 8.96 94 16.8 132 5.20 66 18.7 143 26.1 153 5.20 78 9.90 42 24.9 52 3.70 6 9.18 74 41.6 102 2.45 4 15.2 139 27.5 152 2.16 1
AugFNG_ROB [143]94.1 5.48 125 14.1 146 2.16 102 8.27 101 13.5 88 2.38 112 6.35 115 14.0 152 2.00 93 9.47 122 19.5 148 5.20 66 18.7 143 26.0 151 5.23 134 9.85 38 25.5 69 3.70 6 9.85 116 38.7 64 2.45 4 14.2 62 23.1 101 2.16 1
Filter Flow [19]94.7 5.42 108 10.2 43 2.16 102 9.40 135 14.7 125 2.71 141 6.00 63 10.7 94 2.00 93 9.49 124 13.9 75 5.35 134 18.1 77 24.3 55 5.26 145 10.2 68 25.6 71 3.83 116 9.52 104 41.4 99 2.45 4 14.6 107 22.3 61 2.38 128
ROF-ND [107]95.0 5.74 138 10.4 53 2.00 6 8.04 95 14.1 106 2.16 69 6.06 107 10.7 94 1.73 1 10.6 141 19.9 151 5.26 114 18.1 77 24.8 92 5.20 78 11.7 144 28.6 140 3.74 32 11.1 145 41.0 94 2.52 117 15.3 143 25.3 143 2.16 1
EPMNet [133]95.9 6.45 153 19.7 159 2.16 102 7.85 86 13.1 76 2.38 112 6.06 107 11.7 127 1.73 1 10.1 135 24.0 158 5.23 97 18.5 131 25.3 127 5.20 78 10.7 108 27.6 127 3.70 6 9.27 83 41.9 107 2.45 4 14.5 94 23.8 123 2.16 1
Shiralkar [42]96.5 5.48 125 12.7 134 2.08 71 9.06 125 14.7 125 2.08 2 6.00 63 12.8 144 2.00 93 10.7 143 19.7 149 5.20 66 18.1 77 24.8 92 5.00 14 10.8 114 26.1 88 3.87 127 10.8 142 47.5 149 2.45 4 14.9 124 25.8 145 2.16 1
IIOF-NLDP [131]97.3 5.45 117 12.0 126 2.00 6 8.12 99 14.7 125 2.08 2 6.06 107 10.0 40 1.73 1 9.13 106 14.8 99 5.32 131 18.1 77 24.8 92 5.10 41 12.2 153 29.1 145 3.87 127 12.0 153 59.6 159 2.65 154 15.2 139 24.6 135 2.16 1
TriangleFlow [30]97.5 5.60 132 11.6 120 2.16 102 8.50 109 14.4 115 2.08 2 6.35 115 10.7 94 2.00 93 9.42 119 15.8 121 5.23 97 18.0 64 24.5 69 5.00 14 11.1 132 27.2 118 3.74 32 10.4 132 47.2 148 2.52 117 15.6 147 26.7 148 2.16 1
Rannacher [23]97.6 5.26 73 10.8 76 2.16 102 9.27 130 15.5 148 2.16 69 6.35 115 10.9 109 2.00 93 8.76 62 14.4 86 5.23 97 17.9 54 24.4 61 5.20 78 10.5 87 26.7 105 3.79 95 9.90 119 45.9 141 2.52 117 14.4 83 23.5 115 2.38 128
Correlation Flow [75]97.9 5.42 108 11.7 122 2.00 6 8.58 110 15.4 141 2.08 2 5.69 14 9.80 34 1.73 1 8.89 89 14.7 96 5.32 131 18.1 77 24.8 92 5.32 154 12.3 156 30.3 151 3.83 116 10.5 135 48.8 151 2.52 117 14.8 118 23.7 120 2.31 109
IAOF2 [51]102.0 5.74 138 11.5 114 2.16 102 9.49 137 15.9 157 2.38 112 5.69 14 11.0 112 2.00 93 9.61 127 15.8 121 5.26 114 18.7 143 25.3 127 5.20 78 10.9 118 27.4 124 3.74 32 9.47 98 41.1 96 2.45 4 14.5 94 22.8 84 2.31 109
Horn & Schunck [3]102.2 5.48 125 10.4 53 2.16 102 10.5 151 15.4 141 2.52 132 6.68 135 12.0 134 2.00 93 11.5 149 17.6 138 5.23 97 17.9 54 24.0 37 5.20 78 9.93 46 24.1 33 3.79 95 11.1 145 42.9 120 2.52 117 14.5 94 22.2 55 2.38 128
OFRF [134]105.2 5.80 140 13.7 142 2.16 102 9.15 128 15.1 134 2.45 125 6.00 63 11.7 127 1.73 1 9.13 106 15.1 108 5.10 34 18.7 143 25.9 149 5.16 68 11.3 136 29.1 145 3.87 127 10.1 124 44.5 134 2.45 4 15.4 146 24.9 139 2.16 1
LocallyOriented [52]105.5 5.45 117 11.2 102 2.16 102 9.49 137 15.7 152 2.16 69 6.06 107 11.7 127 1.91 88 9.42 119 17.0 133 5.23 97 18.2 101 24.8 92 5.07 21 11.0 123 26.5 98 4.04 147 10.4 132 43.0 124 2.45 4 14.8 118 23.4 113 2.31 109
TI-DOFE [24]105.6 5.80 140 11.0 86 2.52 152 11.5 156 15.8 154 3.11 153 6.35 115 12.3 138 2.00 93 11.4 148 17.4 135 5.29 124 17.9 54 24.2 53 5.07 21 9.95 48 24.4 42 3.79 95 10.5 135 39.9 81 2.52 117 14.8 118 22.1 49 2.38 128
SegOF [10]107.0 5.10 42 11.4 109 2.16 102 8.29 102 13.9 101 2.38 112 7.00 145 12.1 137 2.00 93 9.81 130 21.0 152 5.20 66 18.2 101 25.1 118 5.20 78 10.9 118 26.1 88 3.79 95 10.4 132 48.4 150 2.58 142 14.7 112 25.1 142 2.16 1
SPSA-learn [13]107.6 5.29 80 10.4 53 2.16 102 9.04 124 14.1 106 2.45 125 6.68 135 11.7 127 2.00 93 10.3 139 15.8 121 5.10 34 18.4 123 25.3 127 5.20 78 10.5 87 26.8 108 3.74 32 12.3 156 58.4 157 2.71 159 17.6 156 35.0 159 2.16 1
StereoOF-V1MT [119]110.5 5.69 137 13.0 137 2.08 71 8.68 112 14.1 106 2.08 2 6.73 144 12.4 140 2.00 93 11.6 150 19.1 147 5.45 141 18.5 131 25.4 134 5.20 78 11.3 136 26.1 88 3.92 142 11.2 147 44.9 138 2.58 142 14.2 62 22.6 72 2.16 1
2bit-BM-tele [98]110.6 5.35 87 10.1 37 2.16 102 8.91 121 15.4 141 2.45 125 6.00 63 10.0 40 2.00 93 9.04 103 14.3 82 5.60 148 18.3 111 24.9 103 5.35 157 11.7 144 31.3 154 4.24 156 12.0 153 58.7 158 2.83 160 13.9 25 21.7 34 2.45 158
ACK-Prior [27]111.4 5.35 87 11.7 122 2.00 6 7.39 60 12.9 65 2.08 2 6.68 135 10.8 106 2.00 93 9.54 126 15.7 119 5.32 131 18.7 143 25.5 140 5.29 152 11.9 151 29.5 147 3.87 127 10.1 124 41.7 104 2.52 117 16.1 151 24.8 138 2.38 128
StereoFlow [44]112.0 8.68 160 20.4 160 2.45 149 10.3 150 16.1 158 2.71 141 6.00 63 10.7 94 1.73 1 8.81 75 13.7 64 5.16 57 22.6 158 31.6 158 5.26 145 14.3 160 35.7 160 3.79 95 9.13 71 38.8 65 2.45 4 15.6 147 25.3 143 2.31 109
UnFlow [129]113.3 5.97 143 15.5 150 2.16 102 9.13 127 14.1 106 2.38 112 6.68 135 13.0 146 2.00 93 9.35 115 17.1 134 5.23 97 18.6 137 25.8 147 5.20 78 11.5 140 29.5 147 3.74 32 9.66 111 37.4 27 2.45 4 16.9 155 28.1 154 2.38 128
Dynamic MRF [7]113.7 5.26 73 11.5 114 2.00 6 8.12 99 14.3 113 2.16 69 6.68 135 12.8 144 2.00 93 10.9 146 18.3 142 5.51 147 18.3 111 25.0 112 5.20 78 11.6 141 28.6 140 3.87 127 10.7 139 45.7 140 2.52 117 14.9 124 23.3 109 2.31 109
WRT [150]116.1 5.57 130 12.1 129 2.00 6 8.74 114 13.9 101 2.16 69 7.35 150 10.3 69 2.00 93 9.38 116 15.0 104 5.29 124 18.7 143 26.0 151 5.16 68 12.7 159 31.4 155 3.83 116 13.6 160 62.2 160 2.65 154 17.8 157 33.8 158 2.16 1
NL-TV-NCC [25]116.6 6.03 145 12.8 136 2.00 6 8.29 102 14.7 125 2.16 69 6.35 115 11.7 127 2.00 93 10.7 143 18.6 143 5.45 141 18.1 77 24.1 45 5.45 158 12.0 152 28.2 138 3.79 95 13.0 158 43.4 128 2.58 142 15.1 130 23.2 103 2.38 128
SILK [79]118.7 5.80 140 12.7 134 2.38 144 11.1 154 15.6 150 2.83 148 7.35 150 13.0 146 2.00 93 10.8 145 17.5 137 5.48 145 18.3 111 24.8 92 5.20 78 10.5 87 26.0 84 4.20 155 10.0 122 37.1 22 2.52 117 14.6 107 22.7 78 2.31 109
Learning Flow [11]119.9 5.57 130 11.1 96 2.16 102 9.27 130 15.1 134 2.16 69 7.00 145 13.3 149 2.00 93 10.2 136 15.2 109 5.45 141 18.5 131 25.1 118 5.32 154 10.7 108 26.2 93 3.87 127 10.6 137 40.8 92 2.52 117 15.1 130 23.3 109 2.38 128
H+S_ROB [137]126.0 6.00 144 13.0 137 2.16 102 9.63 139 13.7 95 2.71 141 8.00 156 13.3 149 2.38 152 13.7 156 17.4 135 5.35 134 18.3 111 24.7 80 5.20 78 10.8 114 25.6 71 3.79 95 11.7 150 47.1 147 2.58 142 15.0 129 24.9 139 2.38 128
Adaptive flow [45]128.9 6.24 148 11.3 107 2.71 155 11.2 155 15.7 152 3.42 157 6.35 115 10.9 109 2.00 93 10.2 136 14.7 96 5.72 151 18.7 143 25.4 134 5.23 134 11.7 144 30.8 153 3.87 127 9.42 93 38.8 65 2.58 142 14.9 124 24.3 132 2.38 128
FOLKI [16]129.2 6.14 147 12.4 131 3.11 157 11.5 156 15.5 148 3.32 156 7.00 145 14.7 155 2.38 152 13.5 155 18.2 140 6.27 158 18.6 137 25.0 112 5.23 134 10.3 75 25.1 58 4.04 147 11.0 144 38.3 47 2.58 142 14.7 112 22.4 65 2.38 128
WOLF_ROB [148]129.5 6.35 151 18.1 155 2.16 102 10.0 144 15.6 150 2.16 69 6.68 135 12.5 143 2.00 93 9.88 133 19.7 149 5.35 134 18.9 153 26.1 153 5.20 78 11.7 144 29.9 149 4.04 147 12.1 155 51.4 154 2.52 117 15.7 150 27.0 149 2.16 1
GroupFlow [9]131.1 6.56 155 19.6 158 2.16 102 9.38 134 14.7 125 2.52 132 7.68 152 16.8 158 2.00 93 11.1 147 23.5 157 5.29 124 20.7 157 29.3 157 5.23 134 12.4 158 32.8 158 3.87 127 11.3 149 49.6 153 2.45 4 16.8 154 30.4 157 2.16 1
Heeger++ [104]135.0 7.16 158 18.5 156 2.16 102 9.75 140 13.8 98 2.45 125 9.35 157 16.1 157 2.38 152 13.0 152 18.9 145 5.74 152 19.8 156 27.4 156 5.23 134 12.2 153 26.0 84 3.92 142 13.5 159 46.5 142 2.52 117 16.1 151 27.4 150 2.16 1
SLK [47]138.7 6.03 145 13.6 141 2.45 149 10.1 146 13.8 98 2.89 150 7.68 152 12.4 140 2.38 152 13.8 158 21.0 152 5.77 154 19.1 155 26.4 155 5.20 78 11.2 133 26.2 93 3.87 127 11.8 151 46.9 144 2.58 142 15.2 139 26.1 146 2.38 128
FFV1MT [106]140.9 6.40 152 16.8 152 2.16 102 9.87 141 13.9 101 2.89 150 9.35 157 18.7 159 2.52 158 13.0 152 18.9 145 5.74 152 18.8 151 25.7 144 5.26 145 10.9 118 26.0 84 3.92 142 12.8 157 46.5 142 2.52 117 16.2 153 27.4 150 2.45 158
HCIC-L [99]142.3 7.62 159 17.7 154 3.16 158 9.98 143 14.8 132 3.16 155 7.14 149 14.0 152 2.00 93 12.4 151 21.5 155 5.35 134 18.9 153 25.5 140 5.26 145 11.8 148 31.9 157 3.87 127 9.47 98 43.2 127 2.58 142 18.7 159 30.1 156 2.38 128
PGAM+LK [55]142.7 6.56 155 16.0 151 2.71 155 10.0 144 14.7 125 3.00 152 7.75 155 15.7 156 2.38 152 13.7 156 21.1 154 6.27 158 18.8 151 25.8 147 5.26 145 11.6 141 27.2 118 4.08 152 10.7 139 40.3 86 2.58 142 15.1 130 24.4 133 2.38 128
Pyramid LK [2]144.5 6.24 148 13.7 142 3.16 158 12.7 159 15.8 154 3.79 159 11.8 159 12.3 138 3.00 159 25.5 160 41.4 159 7.14 160 22.9 159 33.6 159 5.20 78 10.7 108 25.4 67 3.92 142 11.2 147 49.2 152 2.65 154 19.6 160 37.8 160 2.38 128
Periodicity [78]157.9 6.81 157 17.5 153 3.27 160 15.3 160 16.9 159 4.24 160 13.7 160 22.7 160 4.36 160 18.0 159 41.4 159 6.16 157 23.9 160 34.4 160 5.60 160 12.2 153 34.5 159 4.51 159 11.8 151 55.6 156 2.65 154 17.9 158 29.7 155 2.71 160
AVG_FLOW_ROB [141]161.0 31.4 161 43.5 161 5.60 161 24.2 161 24.5 161 6.45 161 24.3 161 27.7 161 8.43 161 44.7 161 55.2 161 16.9 161 38.9 161 51.5 161 6.24 161 31.3 161 72.3 161 4.83 161 34.9 161 63.2 161 3.65 161 35.1 161 43.8 161 6.73 161
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] CtxSyn 0.07 2 color S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[137] 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.
[138] 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.
[139] 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.
[140] 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.
[141] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[142] 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.
[143] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[144] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[145] 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.
[146] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[147] 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.
[148] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[149] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
[150] WRT 9 2 color L. Mei, J. Lai, X. Xie, J. Zhu, and J. Chen. Illumination-invariance optical flow estimation using weighted regularization transform. Submitted to IEEE TCSVT 2018.
[151] EAI-Flow 2.1 2 color Anonymous. Hierarchical coherency sensitive hashing and interpolation with RANSAC for large displacement optical flow. CVIU 2018 submission 17-678.
[152] ContinualFlow_ROB 0.5 all color M Neoral, J. Sochman, and J. Matas. Continual occlusions and optical flow estimation. ACCV 2018.
[153] CyclicGen 0.088 2 color Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
[154] TOF-M 0.393 2 color T. Xue, B. Chen, J. Wu, D. Wei, and W. Freeman. Video enhancement with task-oriented flow. arXiv 1711.09078, 2017.
[155] MEMC-Net+ 0.16 2 color W. Bao, W.-S. Lai, X. Zhang, Z. Gao, and M.-H. Yang. (Interpolation results only.) MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement. Submitted to TPAMI 2018.
[156] CFRF 0.128 2 color Anonymous. (Interpolation results only.) Coarse-to-fine refinement framework for video frame interpolation. CVPR 2019 submission 1992.
[157] MPRN 0.32 4 color Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[158] DAIN 0.13 2 color Anonymous. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019 submission 1769.
[159] PyrWarp 0.14 2 color Anonymous. (Interpolation results only.) Feature pyramid warping for video frame interpolation. CVPR 2019 submission 868.
[160] InterpCNN 0.65 2 color Anonymous. (Interpolation results only.) Video frame interpolation with a stack of synthesis networks and intermediate optical flows. CVPR 2019 submission 6533.
[161] OFRI 0.31 2 color Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
* 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.