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        
R5.0
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]1.9 2.88 1 7.22 1 0.04 1 6.64 1 12.4 1 0.42 8 0.90 1 3.03 2 0.14 1 13.6 1 19.3 1 3.09 1 32.1 1 44.8 1 2.91 2 7.09 3 27.5 2 0.25 1 8.62 2 34.3 3 0.28 2 17.7 2 43.0 2 0.35 5
DAIN [158]9.4 3.36 3 10.3 7 0.06 2 8.05 6 15.2 6 1.00 112 1.92 4 5.22 3 0.33 19 15.5 4 22.3 4 3.63 3 35.4 4 49.1 3 3.27 4 7.85 5 30.7 5 0.32 2 9.40 6 38.3 6 0.28 2 19.5 6 47.1 7 0.31 3
InterpCNN [160]12.8 3.63 8 10.4 8 0.09 8 7.97 5 14.6 5 0.90 97 2.48 6 6.05 7 0.51 88 18.1 32 24.7 8 3.76 5 35.2 2 48.7 2 2.88 1 7.06 2 27.7 3 0.32 2 9.00 3 33.4 2 0.32 5 18.2 3 44.3 3 0.30 2
CFRF [156]13.3 3.42 5 9.91 3 0.19 73 8.57 17 15.4 8 1.01 115 1.87 3 5.64 4 0.32 15 16.5 5 21.3 3 5.04 9 36.8 6 50.3 6 3.71 6 7.67 4 29.0 4 0.49 6 9.49 7 34.7 4 0.32 5 18.3 4 44.4 4 0.33 4
MEMC-Net+ [155]17.6 3.74 9 11.2 10 0.07 4 8.90 31 16.1 13 0.99 111 2.59 7 6.01 6 0.69 122 17.0 6 22.7 5 3.61 2 37.5 7 51.6 7 3.22 3 8.61 6 33.4 6 0.32 2 9.86 40 37.8 5 0.30 4 19.3 5 47.0 6 0.35 5
OFRI [161]19.6 3.15 2 8.69 2 0.09 8 7.77 4 13.9 4 0.98 110 1.45 2 2.88 1 0.33 19 14.9 2 20.8 2 3.70 4 35.3 3 49.1 3 3.31 5 8.88 7 33.4 6 0.44 5 15.2 160 39.3 9 0.50 87 20.4 9 46.6 5 0.43 11
CtxSyn [136]22.4 3.42 5 9.96 5 0.08 5 6.79 2 13.5 3 0.50 32 2.17 5 5.94 5 0.43 67 15.1 3 23.3 6 4.57 6 42.2 12 56.7 12 4.54 11 10.0 12 36.5 11 0.63 9 13.5 158 44.0 122 0.40 11 21.1 14 49.2 11 0.43 11
PMMST [114]22.6 4.93 14 13.9 14 0.13 12 8.97 38 17.1 23 0.43 11 6.00 20 13.4 14 0.27 2 17.6 9 26.2 17 5.24 30 43.0 26 57.7 20 5.17 32 10.3 16 39.1 19 0.87 26 9.75 23 41.0 26 0.44 29 21.5 43 51.9 52 0.47 27
CyclicGen [153]23.0 3.50 7 9.95 4 0.13 12 7.67 3 12.9 2 1.52 151 3.74 10 10.6 11 0.48 83 19.1 103 25.7 11 5.85 123 36.7 5 49.3 5 3.80 7 5.69 1 21.5 1 0.50 7 7.53 1 30.4 1 0.26 1 13.5 1 33.4 1 0.28 1
MDP-Flow2 [68]23.6 4.89 13 14.4 16 0.12 11 8.58 18 16.9 21 0.39 3 5.95 17 13.6 16 0.28 4 17.7 10 26.7 25 5.32 47 42.9 18 57.6 16 5.13 27 10.6 33 40.1 39 0.92 35 9.75 23 41.0 26 0.43 19 21.6 56 51.9 52 0.46 21
SepConv-v1 [127]24.2 3.41 4 11.0 9 0.08 5 8.39 13 16.7 19 1.04 121 2.81 8 7.63 8 0.74 125 18.0 25 25.2 10 5.82 120 42.9 18 57.4 13 4.74 13 9.03 8 34.1 8 0.60 8 9.34 5 38.6 7 0.42 13 20.1 8 48.6 9 0.35 5
SuperSlomo [132]24.8 3.75 10 10.1 6 0.19 73 8.96 37 16.5 15 1.31 137 3.32 9 8.42 9 0.29 8 17.7 10 24.1 7 5.32 47 41.4 8 55.9 8 4.24 8 9.50 10 35.3 10 0.67 10 10.8 124 40.3 12 0.37 8 20.4 9 48.7 10 0.42 9
NNF-Local [87]28.4 5.11 27 15.7 39 0.11 10 8.18 8 15.8 11 0.39 3 6.01 23 13.5 15 0.27 2 18.3 44 28.3 67 5.29 39 43.0 26 57.6 16 5.11 25 10.8 57 40.9 72 1.01 62 9.67 15 40.7 18 0.46 45 21.2 16 51.2 20 0.46 21
NN-field [71]28.5 5.14 31 16.1 63 0.13 12 8.21 9 15.7 10 0.38 2 6.39 56 13.6 16 0.30 9 18.4 48 28.7 84 5.33 52 42.9 18 57.6 16 5.08 22 10.7 41 40.2 45 0.94 44 9.62 12 40.5 15 0.44 29 21.2 16 51.2 20 0.45 14
Layers++ [37]32.6 5.25 45 15.9 48 0.17 52 8.27 10 15.5 9 0.37 1 6.16 33 14.3 23 0.38 47 18.0 25 26.9 30 5.32 47 43.1 37 57.9 33 5.24 51 10.7 41 40.6 65 0.97 56 9.70 16 40.7 18 0.39 9 21.3 23 51.3 23 0.48 41
MPRN [157]32.7 4.10 12 11.9 12 0.06 2 9.67 64 16.8 20 0.78 81 7.31 127 18.6 137 0.47 80 18.0 25 25.8 12 4.76 7 41.6 10 56.1 9 4.34 10 9.29 9 34.9 9 0.68 11 10.3 96 40.9 22 0.34 7 20.0 7 48.5 8 0.36 8
TOF-M [154]33.8 3.92 11 11.5 11 0.08 5 8.90 31 17.4 28 1.19 131 3.87 11 8.82 10 0.52 94 17.9 19 25.1 9 5.20 18 42.1 11 56.6 11 4.68 12 10.0 12 36.7 12 0.69 12 12.8 157 41.1 32 0.47 63 21.8 82 50.8 14 0.45 14
PH-Flow [101]35.5 5.32 58 16.4 75 0.16 41 8.28 11 15.9 12 0.44 14 6.12 30 13.9 19 0.33 19 17.5 7 25.8 12 5.15 16 42.8 16 57.5 14 5.03 19 11.0 83 41.6 104 1.09 86 9.71 17 41.0 26 0.46 45 21.3 23 51.4 26 0.50 79
nLayers [57]37.8 5.26 48 15.8 45 0.16 41 8.54 15 16.6 17 0.45 17 5.89 14 13.1 12 0.30 9 18.1 32 27.1 35 5.35 58 43.3 68 58.0 45 5.36 88 10.8 57 40.9 72 1.11 91 9.65 14 40.1 10 0.48 71 21.2 16 51.1 18 0.45 14
COFM [59]37.8 5.08 24 15.1 24 0.19 73 8.86 27 17.4 28 0.48 26 6.37 52 14.2 22 0.40 55 17.7 10 26.2 17 5.11 10 42.9 18 57.8 24 5.02 18 10.9 69 41.6 104 1.11 91 9.24 4 38.8 8 0.50 87 21.5 43 51.9 52 0.46 21
Sparse-NonSparse [56]38.2 5.31 57 16.3 73 0.17 52 8.74 22 17.2 27 0.48 26 6.19 34 14.7 35 0.34 26 17.9 19 26.3 19 5.23 27 43.1 37 57.8 24 5.25 54 11.0 83 41.2 82 1.04 70 9.71 17 40.9 22 0.46 45 21.2 16 51.3 23 0.47 27
IROF++ [58]39.9 5.37 70 16.8 91 0.14 20 8.87 29 17.4 28 0.45 17 6.41 62 14.6 32 0.43 67 17.5 7 25.8 12 5.22 22 42.9 18 57.8 24 5.19 37 10.5 23 39.4 25 0.87 26 10.0 66 42.4 77 0.47 63 21.4 35 51.5 28 0.50 79
TV-L1-MCT [64]40.8 5.74 126 18.1 129 0.18 65 9.50 55 19.1 53 0.58 45 5.73 12 14.5 30 0.38 47 17.8 15 26.0 16 5.28 37 43.0 26 57.9 33 5.22 45 10.4 18 39.1 19 0.94 44 9.78 29 41.1 32 0.44 29 21.2 16 51.1 18 0.48 41
HAST [109]41.7 5.12 28 15.2 26 0.16 41 8.74 22 17.1 23 0.43 11 6.62 89 15.3 60 0.39 51 17.7 10 26.4 21 4.98 8 43.0 26 58.0 45 5.05 20 11.0 83 41.4 92 1.06 78 9.53 8 40.4 13 0.42 13 22.0 104 52.8 101 0.47 27
ComponentFusion [96]43.2 5.15 32 16.1 63 0.14 20 8.86 27 17.9 37 0.41 6 6.38 53 15.4 61 0.33 19 17.8 15 27.0 33 5.15 16 43.2 58 58.0 45 5.24 51 10.6 33 39.8 29 0.94 44 10.0 66 42.7 96 0.57 117 21.5 43 51.8 45 0.47 27
ProbFlowFields [128]43.6 5.03 19 15.6 36 0.17 52 8.55 16 17.1 23 0.41 6 6.00 20 14.4 26 0.32 15 18.1 32 27.1 35 5.38 63 43.3 68 58.1 63 5.49 134 10.9 69 41.2 82 1.20 109 9.61 11 40.7 18 0.47 63 21.0 13 50.8 14 0.49 59
FMOF [94]44.2 5.62 112 17.2 103 0.21 86 8.71 21 17.0 22 0.44 14 6.38 53 14.7 35 0.46 76 18.6 63 28.0 53 5.31 44 43.1 37 57.9 33 5.15 30 10.8 57 40.5 61 0.87 26 9.60 10 40.4 13 0.40 11 21.5 43 51.7 37 0.46 21
2DHMM-SAS [92]47.5 5.62 112 17.6 120 0.18 65 10.1 81 19.7 70 0.64 61 5.73 12 14.4 26 0.37 45 17.7 10 25.9 15 5.30 41 43.0 26 57.8 24 5.26 57 10.7 41 40.0 37 0.82 17 9.83 35 41.3 36 0.48 71 21.6 56 52.0 56 0.47 27
CombBMOF [113]48.2 5.46 85 16.2 71 0.22 98 8.89 30 18.0 39 0.45 17 6.29 41 14.7 35 0.40 55 18.5 57 28.0 53 5.24 30 43.0 26 57.7 20 5.08 22 10.8 57 40.2 45 0.82 17 11.7 147 42.9 104 0.47 63 21.2 16 50.9 16 0.45 14
LSM [39]48.6 5.49 90 17.4 113 0.18 65 8.93 34 17.7 34 0.48 26 6.32 45 15.4 61 0.35 35 18.1 32 27.1 35 5.22 22 43.1 37 57.9 33 5.28 67 11.0 83 41.3 88 1.03 68 9.72 19 40.9 22 0.46 45 21.4 35 51.7 37 0.48 41
Ramp [62]50.1 5.46 85 17.1 100 0.18 65 8.84 25 17.4 28 0.58 45 6.14 31 14.7 35 0.34 26 17.8 15 26.4 21 5.23 27 43.2 58 58.0 45 5.27 62 11.2 106 42.0 115 1.15 99 9.72 19 40.9 22 0.42 13 21.6 56 52.1 63 0.48 41
DeepFlow [86]51.2 5.06 23 14.6 18 0.19 73 9.80 71 19.5 60 0.75 78 6.45 65 16.6 97 0.35 35 18.7 73 27.6 46 5.41 72 43.4 85 58.0 45 5.37 91 10.3 16 38.3 15 0.99 58 9.83 35 41.8 54 0.43 19 21.3 23 51.6 35 0.48 41
NNF-EAC [103]51.5 5.52 94 15.7 39 0.34 140 9.27 48 18.1 41 0.48 26 6.53 72 13.8 18 0.40 55 18.2 40 27.0 33 5.71 109 43.0 26 57.7 20 5.11 25 10.4 18 39.1 19 0.83 20 9.89 45 41.6 48 0.52 102 21.7 69 52.2 71 0.49 59
DeepFlow2 [108]51.9 5.16 33 14.9 23 0.21 86 9.81 72 19.7 70 0.65 63 6.38 53 16.3 86 0.34 26 18.6 63 28.1 58 5.29 39 43.4 85 58.0 45 5.37 91 10.2 15 38.4 16 0.85 23 9.96 61 42.1 70 0.44 29 21.4 35 51.8 45 0.49 59
LME [70]52.0 5.13 30 15.8 45 0.14 20 9.15 45 18.4 50 0.51 33 6.32 45 15.7 69 0.34 26 17.9 19 27.1 35 5.34 54 43.8 138 58.8 136 5.79 152 10.8 57 41.2 82 0.93 39 9.86 40 41.3 36 0.43 19 21.3 23 51.5 28 0.47 27
FlowFields+ [130]52.3 5.23 44 16.6 83 0.15 28 8.91 33 18.3 44 0.45 17 6.28 40 15.9 73 0.34 26 18.2 40 28.1 58 5.34 54 43.4 85 58.2 75 5.35 84 10.9 69 41.6 104 1.10 89 9.79 30 41.5 43 0.46 45 21.3 23 51.5 28 0.48 41
SuperFlow [81]52.4 4.99 18 14.3 15 0.22 98 10.3 88 19.9 75 0.90 97 6.61 82 15.5 65 0.51 88 18.5 57 27.2 40 5.52 91 43.3 68 58.1 63 5.37 91 10.1 14 38.0 14 0.73 14 9.73 22 41.4 41 0.46 45 21.3 23 51.5 28 0.46 21
WLIF-Flow [93]52.4 5.25 45 16.0 56 0.15 28 9.14 44 18.1 41 0.59 51 6.29 41 14.3 23 0.34 26 17.9 19 26.3 19 5.65 105 43.1 37 57.9 33 5.26 57 11.2 106 41.9 114 1.22 115 9.82 34 41.3 36 0.44 29 21.7 69 52.2 71 0.49 59
PGM-C [120]52.6 5.18 36 16.0 56 0.15 28 8.97 38 18.2 43 0.46 23 6.51 68 16.4 92 0.33 19 18.4 48 28.5 75 5.36 60 43.4 85 58.1 63 5.40 107 10.7 41 40.5 61 0.96 53 9.92 50 41.9 58 0.45 37 21.4 35 51.8 45 0.48 41
EAI-Flow [151]53.0 5.33 64 15.9 48 0.17 52 9.73 69 19.6 66 0.71 71 6.61 82 16.3 86 0.36 40 18.3 44 28.1 58 5.11 10 43.1 37 57.9 33 5.31 70 10.7 41 39.9 33 0.98 57 10.1 76 42.7 96 0.51 97 21.1 14 50.9 16 0.44 13
FlowFields [110]53.3 5.22 42 16.5 78 0.16 41 8.95 35 18.3 44 0.42 8 6.29 41 15.9 73 0.35 35 18.4 48 28.5 75 5.41 72 43.4 85 58.1 63 5.33 74 10.9 69 41.3 88 1.08 82 9.79 30 41.5 43 0.45 37 21.3 23 51.6 35 0.49 59
Classic+NL [31]53.7 5.56 102 17.4 113 0.22 98 8.99 40 17.6 33 0.54 37 6.02 24 14.7 35 0.36 40 18.1 32 26.8 26 5.41 72 43.1 37 58.0 45 5.23 48 11.1 101 41.5 98 1.06 78 9.72 19 41.0 26 0.46 45 21.6 56 52.0 56 0.47 27
JOF [140]54.8 5.53 98 16.9 95 0.21 86 8.65 19 16.6 17 0.48 26 6.08 26 14.0 20 0.34 26 18.1 32 26.8 26 5.59 98 43.4 85 58.2 75 5.45 123 11.1 101 41.4 92 1.04 70 9.64 13 40.6 16 0.43 19 21.6 56 52.0 56 0.48 41
DF-Auto [115]55.5 5.03 19 13.8 13 0.17 52 10.2 82 19.3 56 0.79 83 6.09 27 14.4 26 0.34 26 18.7 73 28.1 58 5.24 30 43.2 58 57.9 33 5.31 70 10.4 18 39.3 22 0.93 39 10.1 76 42.3 74 0.49 77 21.9 95 52.9 108 0.53 117
FC-2Layers-FF [74]55.7 5.40 75 17.0 98 0.17 52 8.15 7 15.3 7 0.42 8 6.14 31 14.9 43 0.35 35 18.1 32 27.2 40 5.31 44 43.3 68 58.2 75 5.36 88 11.2 106 42.2 119 1.20 109 9.75 23 41.0 26 0.49 77 21.7 69 52.1 63 0.48 41
S2F-IF [123]55.7 5.22 42 16.5 78 0.15 28 8.84 25 18.0 39 0.44 14 6.27 39 15.7 69 0.33 19 18.3 44 28.3 67 5.14 15 43.4 85 58.2 75 5.41 111 11.0 83 41.5 98 1.11 91 9.91 49 41.9 58 0.47 63 21.3 23 51.5 28 0.51 93
AGIF+OF [85]55.9 5.60 108 17.4 113 0.15 28 8.95 35 17.7 34 0.59 51 6.20 36 14.5 30 0.43 67 17.9 19 26.6 24 5.22 22 43.4 85 58.3 99 5.38 98 11.1 101 42.0 115 1.01 62 9.87 44 40.7 18 0.42 13 21.5 43 52.0 56 0.48 41
OFLAF [77]56.5 5.16 33 15.9 48 0.14 20 8.28 11 16.1 13 0.40 5 6.34 50 14.9 43 0.30 9 18.0 25 27.3 42 5.11 10 43.3 68 58.1 63 5.39 100 11.2 106 42.4 121 1.21 112 10.1 76 42.4 77 0.60 125 21.9 95 52.6 90 0.45 14
MDP-Flow [26]57.9 5.03 19 15.4 28 0.14 20 8.68 20 17.4 28 0.47 24 5.97 18 14.3 23 0.32 15 18.9 90 28.5 75 5.50 88 43.2 58 58.0 45 5.39 100 11.2 106 42.6 124 1.31 126 10.3 96 43.1 111 0.49 77 21.4 35 51.7 37 0.47 27
S2D-Matching [84]58.6 5.56 102 17.3 107 0.18 65 9.96 77 19.9 75 0.66 65 5.99 19 14.7 35 0.41 60 17.9 19 26.4 21 5.40 69 43.2 58 58.0 45 5.17 32 11.2 106 42.0 115 1.17 104 9.93 53 41.1 32 0.43 19 21.5 43 51.8 45 0.48 41
TF+OM [100]60.3 4.98 16 14.6 18 0.20 80 9.03 42 17.9 37 0.55 39 6.29 41 16.2 82 0.39 51 18.5 57 28.0 53 5.50 88 43.3 68 58.1 63 5.47 129 10.6 33 39.8 29 1.03 68 9.86 40 42.0 64 0.51 97 21.7 69 52.3 76 0.52 107
Brox et al. [5]60.6 5.33 64 15.4 28 0.19 73 10.2 82 20.1 80 0.64 61 6.61 82 17.2 112 0.46 76 18.7 73 28.2 63 5.21 19 43.4 85 58.1 63 5.27 62 10.7 41 40.1 39 0.99 58 9.90 47 42.0 64 0.45 37 21.6 56 52.1 63 0.47 27
ProFlow_ROB [146]60.8 5.09 25 15.4 28 0.17 52 9.40 54 19.3 56 0.55 39 6.34 50 15.4 61 0.33 19 18.4 48 28.7 84 5.39 67 43.5 112 58.3 99 5.41 111 10.4 18 39.3 22 0.79 15 10.2 88 42.9 104 0.49 77 21.8 82 52.6 90 0.49 59
ALD-Flow [66]61.0 5.37 70 16.1 63 0.23 106 9.53 56 19.2 55 0.57 43 6.51 68 16.7 101 0.34 26 18.2 40 27.9 49 5.32 47 43.4 85 58.3 99 5.46 126 10.7 41 39.9 33 0.99 58 9.76 28 41.2 35 0.44 29 21.8 82 52.7 97 0.47 27
CPM-Flow [116]61.5 5.20 41 16.1 63 0.16 41 8.99 40 18.3 44 0.47 24 6.42 63 16.0 78 0.30 9 18.8 82 29.2 107 5.43 79 43.4 85 58.2 75 5.44 121 10.6 33 40.1 39 1.02 64 10.0 66 42.6 88 0.45 37 21.4 35 51.8 45 0.53 117
DMF_ROB [139]62.0 5.30 55 15.8 45 0.20 80 10.2 82 20.5 88 0.73 74 7.26 122 18.0 128 0.75 126 18.9 90 28.8 89 5.40 69 43.1 37 57.9 33 5.34 80 10.5 23 39.8 29 0.92 35 9.98 64 41.5 43 0.43 19 21.3 23 51.4 26 0.47 27
SVFilterOh [111]62.0 5.32 58 15.7 39 0.21 86 8.78 24 17.1 23 0.49 31 6.40 59 14.6 32 0.38 47 18.4 48 27.1 35 5.80 118 43.8 138 58.6 130 5.65 146 10.9 69 41.0 78 1.04 70 9.54 9 40.1 10 0.43 19 21.7 69 52.2 71 0.50 79
AggregFlow [97]62.2 5.64 115 17.2 103 0.22 98 9.81 72 19.5 60 0.59 51 6.11 29 14.4 26 0.28 4 18.9 90 29.0 98 5.30 41 43.4 85 58.2 75 5.33 74 10.7 41 40.2 45 0.96 53 9.89 45 41.7 51 0.50 87 21.4 35 51.7 37 0.50 79
RNLOD-Flow [121]63.4 5.32 58 16.6 83 0.16 41 9.70 66 19.6 66 0.60 55 6.57 76 15.5 65 0.51 88 18.2 40 27.4 43 5.22 22 43.1 37 58.0 45 5.28 67 11.0 83 41.4 92 1.08 82 9.85 38 41.3 36 0.50 87 21.9 95 52.7 97 0.49 59
Second-order prior [8]64.9 5.29 53 15.3 27 0.27 123 10.8 102 21.1 98 0.78 81 7.14 115 17.8 126 0.62 116 18.6 63 28.3 67 5.21 19 42.9 18 57.7 20 5.16 31 10.5 23 39.6 27 0.93 39 10.2 88 42.8 101 0.44 29 21.6 56 52.3 76 0.49 59
IROF-TV [53]65.5 5.35 69 16.6 83 0.21 86 9.10 43 17.8 36 0.57 43 6.61 82 16.8 103 0.44 71 17.8 15 26.9 30 5.37 62 43.5 112 58.4 114 5.50 136 10.5 23 40.1 39 0.90 32 9.98 64 42.2 72 0.46 45 21.6 56 52.1 63 0.51 93
DPOF [18]66.3 5.51 93 17.9 127 0.22 98 8.45 14 16.5 15 0.43 11 6.87 99 15.1 53 0.59 107 18.9 90 29.5 113 5.43 79 42.9 18 57.8 24 5.05 20 11.0 83 40.9 72 0.84 22 10.3 96 42.5 84 0.45 37 21.9 95 52.8 101 0.48 41
TC-Flow [46]68.1 5.19 37 15.9 48 0.21 86 9.57 57 19.6 66 0.63 58 6.78 97 17.0 109 0.36 40 18.1 32 27.4 43 5.61 101 43.3 68 58.2 75 5.46 126 11.0 83 41.6 104 1.18 105 9.93 53 41.7 51 0.45 37 21.5 43 52.0 56 0.49 59
OAR-Flow [125]68.9 5.28 51 15.5 32 0.18 65 9.71 68 19.5 60 0.67 66 6.43 64 16.3 86 0.28 4 18.0 25 27.6 46 5.23 27 43.5 112 58.4 114 5.48 132 10.9 69 41.3 88 1.13 96 10.2 88 42.9 104 0.51 97 21.7 69 52.3 76 0.45 14
Aniso. Huber-L1 [22]68.9 5.41 77 16.0 56 0.23 106 11.2 113 21.1 98 0.90 97 6.72 92 15.4 61 0.46 76 18.5 57 28.1 58 5.39 67 43.0 26 57.8 24 5.23 48 10.5 23 40.1 39 0.81 16 10.2 88 42.6 88 0.46 45 21.9 95 52.7 97 0.52 107
EpicFlow [102]69.4 5.19 37 16.1 63 0.15 28 9.60 58 19.8 74 0.58 45 6.40 59 16.4 92 0.35 35 18.6 63 29.1 105 5.47 85 43.4 85 58.2 75 5.42 115 10.8 57 41.2 82 1.08 82 10.1 76 42.5 84 0.54 108 21.5 43 52.0 56 0.49 59
ComplOF-FED-GPU [35]69.7 5.30 55 16.1 63 0.19 73 9.39 52 19.3 56 0.58 45 7.21 119 16.9 106 0.66 119 18.4 48 28.6 81 5.32 47 43.1 37 58.0 45 5.27 62 10.8 57 40.9 72 0.99 58 10.1 76 42.8 101 0.47 63 21.8 82 52.3 76 0.50 79
FF++_ROB [145]70.6 5.19 37 16.1 63 0.13 12 9.36 51 19.0 52 0.51 33 6.52 71 16.2 82 0.46 76 18.6 63 28.8 89 5.41 72 43.4 85 58.2 75 5.44 121 11.3 114 41.2 82 1.71 151 9.85 38 41.8 54 0.49 77 21.3 23 51.5 28 0.57 145
FESL [72]71.0 5.65 118 17.3 107 0.17 52 9.18 46 18.3 44 0.55 39 6.22 37 15.0 49 0.44 71 18.8 82 28.4 70 5.38 63 43.4 85 58.2 75 5.41 111 11.3 114 42.8 128 1.19 107 9.92 50 41.5 43 0.42 13 21.8 82 52.3 76 0.48 41
Classic+CPF [83]71.7 5.59 107 17.3 107 0.16 41 9.22 47 18.3 44 0.58 45 6.00 20 14.9 43 0.40 55 18.0 25 26.8 26 5.22 22 43.5 112 58.5 123 5.38 98 11.4 121 43.0 137 1.15 99 10.1 76 41.9 58 0.45 37 22.0 104 53.1 115 0.49 59
PMF [73]72.4 5.32 58 16.6 83 0.14 20 9.67 64 19.9 75 0.45 17 6.89 104 18.2 132 0.49 85 18.4 48 27.9 49 5.21 19 43.5 112 58.4 114 5.22 45 11.0 83 40.5 61 1.27 122 9.86 40 41.8 54 0.46 45 22.1 113 53.1 115 0.50 79
RFlow [90]74.3 5.19 37 16.1 63 0.23 106 10.8 102 21.2 102 0.85 92 6.59 80 16.0 78 0.51 88 18.8 82 28.8 89 5.47 85 43.1 37 58.0 45 5.21 43 10.5 23 40.0 37 0.93 39 10.0 66 42.6 88 0.49 77 22.1 113 53.2 119 0.51 93
Local-TV-L1 [65]74.5 5.29 53 14.6 18 0.35 142 11.5 121 21.1 98 1.23 132 6.39 56 14.9 43 0.37 45 19.0 97 27.9 49 6.64 141 43.3 68 58.3 99 5.33 74 10.9 69 39.0 17 1.58 150 9.79 30 41.6 48 0.48 71 21.3 23 51.5 28 0.53 117
PWC-Net_ROB [147]75.3 5.47 88 18.4 135 0.13 12 9.99 78 20.9 95 0.53 35 6.74 93 17.5 120 0.41 60 18.3 44 28.8 89 5.25 34 43.5 112 58.3 99 5.45 123 11.2 106 41.0 78 1.22 115 9.93 53 41.8 54 0.46 45 21.3 23 51.3 23 0.51 93
CLG-TV [48]76.0 5.32 58 15.7 39 0.26 120 11.0 109 21.2 102 0.83 90 6.75 95 16.6 97 0.56 101 18.9 90 28.4 70 5.50 88 43.3 68 58.1 63 5.25 54 10.5 23 39.8 29 0.87 26 10.1 76 42.5 84 0.44 29 22.0 104 53.1 115 0.51 93
TriFlow [95]76.2 5.42 78 17.0 98 0.24 112 10.9 105 21.2 102 0.91 100 6.61 82 16.8 103 0.36 40 18.9 90 29.0 98 5.28 37 43.2 58 58.2 75 5.37 91 11.0 83 40.9 72 0.95 48 9.96 61 41.7 51 0.49 77 21.7 69 52.2 71 0.47 27
EPPM w/o HM [88]76.3 5.34 67 17.3 107 0.13 12 9.73 69 20.1 80 0.53 35 7.33 130 18.7 139 0.63 117 18.5 57 29.1 105 5.33 52 43.1 37 58.0 45 5.20 40 11.0 83 41.4 92 0.96 53 10.3 96 42.3 74 0.56 114 21.8 82 52.4 86 0.49 59
Classic++ [32]76.4 5.33 64 16.0 56 0.28 124 10.2 82 20.3 84 0.69 69 6.87 99 16.6 97 0.50 86 18.7 73 27.7 48 5.64 103 43.2 58 58.0 45 5.26 57 11.0 83 40.7 68 1.34 129 9.93 53 41.9 58 0.47 63 21.7 69 52.4 86 0.50 79
SIOF [67]77.2 5.64 115 16.5 78 0.28 124 11.3 115 21.6 114 0.91 100 6.32 45 15.9 73 0.42 62 18.7 73 28.4 70 5.36 60 43.0 26 57.9 33 5.17 32 10.7 41 40.2 45 0.95 48 10.1 76 42.4 77 0.50 87 22.2 123 53.2 119 0.53 117
Efficient-NL [60]77.8 5.54 100 17.1 100 0.16 41 9.60 58 18.9 51 0.56 42 6.99 110 15.1 53 0.75 126 18.8 82 28.2 63 5.26 35 43.1 37 57.9 33 5.25 54 11.6 127 43.4 145 1.04 70 10.1 76 42.5 84 0.48 71 22.6 135 53.8 133 0.48 41
LDOF [28]78.3 5.53 98 15.6 36 0.32 136 11.1 111 20.3 84 1.45 149 6.89 104 17.3 114 0.59 107 19.0 97 28.9 94 5.63 102 43.4 85 58.2 75 5.40 107 10.4 18 39.0 17 0.83 20 9.92 50 42.4 77 0.46 45 21.6 56 52.3 76 0.46 21
ContinualFlow_ROB [152]78.4 5.85 131 19.2 141 0.16 41 10.4 92 21.5 109 0.82 86 7.31 127 18.8 141 0.51 88 18.7 73 29.7 117 5.52 91 43.1 37 58.1 63 5.33 74 10.5 23 40.3 50 0.86 24 9.97 63 41.6 48 0.43 19 21.5 43 52.1 63 0.55 137
CostFilter [40]78.8 5.44 80 17.7 122 0.13 12 9.64 61 20.1 80 0.45 17 6.96 108 19.1 142 0.47 80 18.5 57 28.9 94 5.13 14 43.6 128 58.5 123 5.32 73 11.1 101 40.5 61 1.48 142 9.94 58 42.1 70 0.45 37 21.8 82 52.6 90 0.49 59
Complementary OF [21]78.8 5.28 51 16.7 89 0.15 28 9.39 52 19.5 60 0.58 45 7.53 134 16.3 86 1.10 145 18.7 73 29.0 98 5.35 58 43.2 58 58.2 75 5.26 57 10.9 69 41.2 82 1.16 102 10.3 96 43.4 116 0.55 111 21.5 43 52.2 71 0.51 93
p-harmonic [29]79.0 5.17 35 15.5 32 0.16 41 11.2 113 21.4 107 0.94 105 6.55 73 17.4 119 0.55 100 19.2 106 28.6 81 5.45 83 43.3 68 58.2 75 5.27 62 10.7 41 40.2 45 1.04 70 10.4 105 43.4 116 0.50 87 21.8 82 52.6 90 0.49 59
F-TV-L1 [15]79.6 5.56 102 16.0 56 0.36 146 11.4 119 21.5 109 0.94 105 6.88 101 17.0 109 0.66 119 18.7 73 27.9 49 5.79 117 42.6 13 57.8 24 5.01 17 10.6 33 39.3 22 1.02 64 10.0 66 41.9 58 0.55 111 22.0 104 52.8 101 0.51 93
OFH [38]79.7 5.49 90 16.6 83 0.25 116 10.3 88 20.2 83 0.77 80 6.88 101 17.8 126 0.36 40 18.4 48 28.9 94 5.24 30 43.1 37 58.0 45 5.26 57 10.9 69 41.5 98 1.18 105 10.3 96 43.0 108 0.58 120 21.6 56 52.1 63 0.50 79
TC/T-Flow [76]80.5 5.73 124 17.3 107 0.22 98 9.66 63 19.7 70 0.63 58 6.24 38 14.9 43 0.32 15 18.6 63 28.7 84 5.38 63 43.5 112 58.4 114 5.50 136 11.0 83 41.4 92 0.89 31 10.2 88 43.0 108 0.58 120 21.9 95 53.0 113 0.45 14
HBM-GC [105]80.6 5.52 94 17.1 100 0.22 98 9.64 61 19.3 56 0.59 51 5.93 16 13.2 13 0.31 14 18.8 82 28.0 53 5.83 122 44.3 150 59.2 143 5.71 148 11.5 124 43.3 143 1.32 127 9.75 23 40.6 16 0.39 9 22.0 104 52.9 108 0.50 79
CBF [12]80.7 4.98 16 14.8 22 0.18 65 10.2 82 19.9 75 0.71 71 6.63 90 15.2 57 0.42 62 19.0 97 28.5 75 6.39 137 43.4 85 58.3 99 5.49 134 10.7 41 40.4 56 0.95 48 10.1 76 42.6 88 0.50 87 22.3 128 53.5 129 0.53 117
LFNet_ROB [149]80.9 5.45 82 17.6 120 0.13 12 10.4 92 21.2 102 0.73 74 6.75 95 18.1 130 0.47 80 18.4 48 28.7 84 5.27 36 43.1 37 58.0 45 5.20 40 11.1 101 41.8 112 1.10 89 10.4 105 42.7 96 0.50 87 21.7 69 52.0 56 0.60 149
Steered-L1 [118]81.4 5.12 28 16.0 56 0.17 52 9.62 60 19.5 60 0.88 94 7.15 116 15.6 67 1.00 137 19.4 113 28.5 75 6.39 137 43.5 112 58.5 123 5.19 37 10.8 57 40.8 71 1.20 109 9.95 60 42.6 88 0.52 102 21.7 69 52.6 90 0.48 41
GraphCuts [14]82.5 5.98 136 17.5 118 0.24 112 10.0 79 19.5 60 0.76 79 8.24 147 14.6 32 1.06 140 19.7 119 29.0 98 5.69 107 42.9 18 57.9 33 4.97 15 10.5 23 40.3 50 0.87 26 10.0 66 42.4 77 0.58 120 22.1 113 53.2 119 0.51 93
MLDP_OF [89]82.8 5.44 80 17.2 103 0.17 52 9.84 74 19.9 75 0.62 57 6.19 34 14.8 41 0.28 4 18.6 63 27.4 43 5.71 109 43.3 68 58.2 75 5.34 80 11.9 138 43.3 143 1.57 149 10.4 105 42.6 88 0.56 114 21.7 69 52.3 76 0.59 148
AdaConv-v1 [126]83.5 6.72 148 21.8 152 0.25 116 12.8 139 22.4 133 1.80 155 8.18 146 18.4 134 1.46 153 24.3 153 34.7 155 7.39 149 41.5 9 56.1 9 4.28 9 9.57 11 36.9 13 0.71 13 9.75 23 41.0 26 0.60 125 20.5 11 49.7 12 0.42 9
SRR-TVOF-NL [91]83.9 5.70 121 16.9 95 0.23 106 10.3 88 21.0 97 0.88 94 6.57 76 16.1 80 0.39 51 19.2 106 28.7 84 5.12 13 43.2 58 58.3 99 5.27 62 10.8 57 40.9 72 0.86 24 10.6 119 42.3 74 0.46 45 22.5 131 53.8 133 0.54 128
BlockOverlap [61]84.9 5.34 67 14.6 18 0.41 151 11.4 119 20.6 89 1.42 145 6.49 66 14.1 21 0.61 114 18.9 90 26.9 30 7.34 148 44.2 148 58.9 139 5.91 154 11.0 83 39.9 33 1.39 136 9.81 33 41.3 36 0.46 45 21.5 43 51.7 37 0.51 93
Sparse Occlusion [54]85.1 5.43 79 16.8 91 0.23 106 10.3 88 20.8 93 0.63 58 6.51 68 15.0 49 0.44 71 19.0 97 29.0 98 5.42 77 43.4 85 58.2 75 5.41 111 11.3 114 42.9 134 1.14 97 10.1 76 42.2 72 0.42 13 22.1 113 53.2 119 0.49 59
CRTflow [80]86.7 5.48 89 16.5 78 0.34 140 10.7 100 20.7 90 0.86 93 7.25 121 18.6 137 0.60 112 18.8 82 28.8 89 5.98 129 43.4 85 58.2 75 5.43 118 10.7 41 40.4 56 0.95 48 9.93 53 42.0 64 0.49 77 21.7 69 52.3 76 0.49 59
LiteFlowNet [142]87.6 5.61 109 18.9 140 0.15 28 9.94 76 20.9 95 0.65 63 6.33 49 17.5 120 0.39 51 19.2 106 30.9 136 5.94 128 43.1 37 57.9 33 5.36 88 11.3 114 42.2 119 1.06 78 10.7 121 43.5 118 0.62 129 21.2 16 51.2 20 0.54 128
SimpleFlow [49]88.4 5.52 94 17.5 118 0.18 65 10.2 82 19.7 70 0.73 74 7.32 129 15.8 71 1.05 139 18.0 25 26.8 26 5.44 81 43.3 68 58.1 63 5.33 74 11.3 114 42.9 134 1.22 115 10.3 96 44.6 131 1.04 154 21.8 82 52.6 90 0.47 27
AugFNG_ROB [143]88.7 5.68 120 18.7 137 0.15 28 10.9 105 21.8 118 0.93 103 7.28 123 20.6 151 0.48 83 19.3 111 30.7 129 5.40 69 43.6 128 58.6 130 5.47 129 10.6 33 40.1 39 0.82 17 10.5 115 43.0 108 0.50 87 20.9 12 50.7 13 0.48 41
FlowNet2 [122]89.5 6.90 150 21.5 151 0.25 116 10.6 98 20.7 90 0.82 86 7.10 113 17.3 114 0.54 96 19.4 113 31.8 143 5.57 96 43.4 85 58.3 99 5.39 100 10.7 41 40.3 50 0.90 32 10.0 66 42.0 64 0.46 45 21.6 56 51.9 52 0.51 93
IAOF [50]90.5 5.97 135 16.8 91 0.29 129 14.1 154 24.8 154 1.41 144 6.05 25 16.2 82 0.61 114 20.1 127 29.5 113 5.47 85 43.0 26 57.8 24 5.19 37 10.7 41 40.3 50 0.94 44 10.4 105 43.3 114 0.46 45 22.0 104 52.8 101 0.54 128
Modified CLG [34]90.8 5.05 22 15.1 24 0.19 73 12.3 135 22.2 127 1.30 136 6.81 98 18.3 133 0.66 119 19.3 111 29.7 117 5.34 54 43.4 85 58.2 75 5.29 69 10.8 57 40.6 65 1.15 99 10.2 88 43.6 119 0.47 63 21.9 95 52.7 97 0.53 117
Aniso-Texture [82]91.9 5.09 25 15.7 39 0.15 28 11.1 111 21.7 115 1.00 112 7.30 126 15.9 73 0.59 107 18.7 73 28.6 81 5.90 124 43.6 128 58.4 114 5.53 139 11.6 127 44.0 150 1.44 140 9.90 47 41.4 41 0.43 19 22.1 113 53.1 115 0.49 59
FlowNetS+ft+v [112]92.7 5.40 75 15.5 32 0.29 129 11.7 127 21.7 115 1.62 152 6.88 101 17.1 111 0.56 101 19.0 97 29.2 107 5.73 113 43.5 112 58.4 114 5.56 141 10.5 23 39.9 33 0.95 48 10.1 76 42.9 104 0.52 102 21.8 82 52.5 89 0.48 41
Occlusion-TV-L1 [63]93.2 5.32 58 16.2 71 0.28 124 11.3 115 21.9 121 0.96 109 6.60 81 16.9 106 0.58 105 19.1 103 28.9 94 5.72 111 43.4 85 58.2 75 5.24 51 10.9 69 40.3 50 1.26 121 10.9 128 42.6 88 0.81 145 21.8 82 52.4 86 0.49 59
EPMNet [133]94.0 6.85 149 22.5 153 0.21 86 10.5 95 20.3 84 0.84 91 7.10 113 17.3 114 0.54 96 19.9 120 33.4 151 5.56 95 43.4 85 58.3 99 5.39 100 11.0 83 41.6 104 0.92 35 10.0 66 42.0 64 0.46 45 21.6 56 51.8 45 0.54 128
Shiralkar [42]95.1 5.73 124 18.1 129 0.21 86 11.6 123 22.0 123 0.88 94 6.74 93 19.9 146 0.73 124 20.3 130 30.1 124 5.46 84 42.6 13 57.5 14 4.99 16 11.3 114 41.5 98 1.35 130 11.0 131 44.9 134 0.67 132 21.5 43 51.7 37 0.48 41
TCOF [69]95.2 5.56 102 16.8 91 0.17 52 11.8 128 22.1 125 1.02 118 6.09 27 15.0 49 0.30 9 19.0 97 29.4 111 5.67 106 43.4 85 58.3 99 5.17 32 11.4 121 43.1 139 1.02 64 11.0 131 43.9 121 0.48 71 23.1 147 55.1 152 0.52 107
HBpMotionGpu [43]95.5 5.80 128 16.3 73 0.42 152 13.1 142 23.8 145 1.34 139 6.32 45 14.9 43 0.38 47 19.9 120 30.4 127 5.80 118 43.1 37 58.3 99 5.39 100 11.3 114 41.0 78 1.21 112 9.94 58 41.9 58 0.43 19 22.1 113 52.9 108 0.53 117
3DFlow [135]95.8 5.58 106 17.4 113 0.16 41 9.35 50 19.1 53 0.61 56 6.93 107 15.0 49 0.44 71 18.6 63 28.4 70 5.54 94 43.4 85 58.2 75 5.40 107 12.1 145 44.7 158 1.35 130 11.3 138 44.6 131 0.57 117 22.4 129 53.7 132 0.50 79
Adaptive [20]96.4 5.50 92 16.7 89 0.30 131 11.8 128 22.2 127 1.02 118 6.58 79 16.5 96 0.53 95 18.6 63 28.0 53 5.60 100 43.5 112 58.3 99 5.21 43 11.0 83 41.3 88 1.09 86 10.4 105 42.8 101 0.46 45 22.2 123 53.5 129 0.54 128
Fusion [6]96.6 5.37 70 16.9 95 0.21 86 9.33 49 18.3 44 0.54 37 6.39 56 15.1 53 0.54 96 20.0 125 29.8 120 5.41 72 43.5 112 59.2 143 5.14 28 11.5 124 43.7 148 1.21 112 10.5 115 44.1 124 0.52 102 23.1 147 55.4 153 0.52 107
CNN-flow-warp+ref [117]96.8 4.95 15 14.4 16 0.22 98 10.9 105 21.2 102 1.23 132 7.43 132 18.0 128 0.79 129 20.9 140 29.8 120 6.84 144 43.5 112 58.3 99 5.57 142 10.7 41 40.3 50 1.22 115 10.3 96 44.4 129 0.67 132 21.6 56 52.1 63 0.47 27
ResPWCR_ROB [144]98.9 5.54 100 17.8 124 0.20 80 10.6 98 21.5 109 0.80 85 7.77 140 17.7 125 0.44 71 19.4 113 30.7 129 5.93 125 42.7 15 57.6 16 5.10 24 12.4 154 41.7 111 2.49 158 10.9 128 42.7 96 0.58 120 21.7 69 52.3 76 0.52 107
BriefMatch [124]98.9 5.45 82 16.5 78 0.31 135 9.84 74 19.6 66 1.43 146 7.55 136 15.6 67 1.08 142 20.3 130 29.2 107 7.97 156 43.3 68 58.3 99 5.43 118 12.0 142 41.5 98 2.37 157 9.84 37 41.5 43 0.56 114 21.4 35 51.7 37 0.52 107
Nguyen [33]100.2 5.63 114 15.9 48 0.23 106 13.8 148 23.8 145 1.37 141 6.89 104 18.7 139 0.59 107 20.8 139 30.8 133 5.44 81 43.1 37 58.1 63 5.14 28 10.6 33 40.4 56 0.93 39 11.9 149 45.9 141 0.73 141 22.0 104 52.8 101 0.52 107
2D-CLG [1]102.4 5.27 50 15.7 39 0.21 86 13.1 142 22.8 135 1.37 141 7.29 124 17.3 114 0.94 135 20.3 130 30.2 125 5.34 54 43.5 112 58.4 114 5.37 91 10.8 57 40.7 68 1.22 115 10.5 115 44.3 127 0.59 124 22.0 104 52.3 76 0.50 79
TV-L1-improved [17]102.5 5.26 48 16.0 56 0.28 124 11.6 123 22.0 123 1.06 123 7.21 119 16.3 86 0.79 129 18.8 82 28.5 75 5.70 108 43.5 112 58.5 123 5.22 45 11.0 83 41.5 98 1.05 76 10.4 105 44.6 131 0.74 143 22.1 113 53.2 119 0.53 117
SPSA-learn [13]103.0 5.45 82 15.4 28 0.25 116 11.6 123 21.4 107 1.15 128 7.65 138 16.6 97 1.26 148 20.1 127 28.2 63 5.30 41 43.3 68 58.2 75 5.42 115 10.9 69 41.0 78 1.14 97 11.6 144 50.4 159 1.71 160 22.2 123 53.3 127 0.49 59
SegOF [10]103.2 5.25 45 15.9 48 0.20 80 10.9 105 20.8 93 0.82 86 8.07 145 18.4 134 1.18 147 20.0 125 32.3 145 5.52 91 43.3 68 58.2 75 5.35 84 11.4 121 43.1 139 1.38 135 10.7 121 46.3 142 0.96 151 21.5 43 51.7 37 0.53 117
IIOF-NLDP [131]103.4 5.65 118 17.8 124 0.15 28 10.5 95 21.5 109 0.72 73 6.98 109 15.2 57 0.42 62 19.5 116 29.3 110 6.15 133 43.1 37 58.0 45 5.20 40 12.2 149 44.1 152 1.54 146 11.9 149 49.2 157 1.34 158 22.2 123 53.0 113 0.50 79
TriangleFlow [30]105.4 5.85 131 18.2 131 0.26 120 11.0 109 21.8 118 0.79 83 7.17 117 16.3 86 0.58 105 19.6 118 30.7 129 5.74 114 42.8 16 57.8 24 4.95 14 11.6 127 42.8 128 1.05 76 10.8 124 45.8 139 0.73 141 22.8 141 54.3 145 0.51 93
Rannacher [23]106.5 5.39 73 16.6 83 0.30 131 11.6 123 22.2 127 1.01 115 7.17 117 16.9 106 0.92 134 18.6 63 28.4 70 5.74 114 43.6 128 58.5 123 5.33 74 11.0 83 41.6 104 1.11 91 10.4 105 44.3 127 0.72 140 21.9 95 52.8 101 0.54 128
ROF-ND [107]106.6 6.15 138 16.4 75 0.14 20 10.4 92 21.1 98 0.70 70 7.09 112 15.9 73 0.40 55 20.7 138 32.9 148 5.82 120 43.4 85 58.2 75 5.37 91 11.6 127 43.4 145 1.16 102 11.6 144 46.4 143 0.55 111 22.6 135 53.8 133 0.54 128
Black & Anandan [4]106.8 5.71 122 15.5 32 0.35 142 12.7 138 22.3 131 1.12 125 7.89 141 18.1 130 1.06 140 20.5 136 30.3 126 5.42 77 43.6 128 58.6 130 5.35 84 10.6 33 39.7 28 0.91 34 10.9 128 44.1 124 0.50 87 22.2 123 52.9 108 0.53 117
TVL1_ROB [138]108.1 5.72 123 15.6 36 0.35 142 13.7 147 23.8 145 1.40 143 6.64 91 17.6 122 0.60 112 20.5 136 29.7 117 5.58 97 43.6 128 58.5 123 5.42 115 10.8 57 40.4 56 1.09 86 10.5 115 44.5 130 0.65 130 21.9 95 52.6 90 0.49 59
OFRF [134]109.1 6.29 141 18.2 131 0.38 148 11.8 128 22.3 131 1.17 130 6.61 82 17.3 114 0.43 67 19.2 106 29.4 111 5.31 44 43.4 85 58.4 114 5.35 84 11.7 134 42.8 128 1.28 123 10.4 105 43.2 112 0.49 77 22.0 104 53.3 127 0.51 93
Ad-TV-NDC [36]109.9 6.08 137 15.9 48 0.60 154 13.0 140 22.8 135 1.36 140 6.55 73 16.4 92 0.56 101 20.9 140 30.6 128 6.29 135 44.1 144 59.0 141 5.43 118 10.7 41 39.4 25 1.11 91 10.4 105 43.3 114 0.51 97 22.1 113 52.9 108 0.53 117
IAOF2 [51]110.7 6.17 139 18.3 134 0.30 131 12.0 131 23.3 141 0.93 103 5.90 15 16.1 80 0.42 62 20.4 135 31.2 141 5.75 116 43.7 137 58.9 139 5.39 100 11.2 106 42.0 115 1.08 82 10.3 96 42.7 96 0.48 71 22.7 138 54.2 142 0.52 107
Correlation Flow [75]111.2 5.61 109 17.8 124 0.15 28 10.8 102 21.7 115 0.82 86 6.40 59 14.8 41 0.42 62 19.1 103 29.0 98 6.04 131 43.9 140 58.6 130 6.05 156 12.0 142 43.9 149 1.29 125 11.0 131 45.3 136 0.70 137 22.5 131 54.1 140 0.51 93
Filter Flow [19]112.7 5.64 115 16.4 75 0.32 136 12.2 134 22.2 127 1.08 124 6.61 82 16.2 82 0.57 104 20.3 130 29.0 98 6.32 136 44.1 144 59.1 142 5.74 150 10.9 69 40.7 68 1.04 70 10.2 88 43.2 112 0.54 108 22.7 138 54.3 145 0.54 128
Bartels [41]114.3 5.52 94 17.2 103 0.40 150 10.0 79 20.7 90 0.94 105 6.50 67 15.8 71 0.54 96 19.9 120 30.0 123 7.79 153 44.8 154 59.2 143 6.72 159 12.8 158 42.4 121 3.06 160 10.0 66 42.0 64 0.54 108 22.1 113 53.2 119 0.54 128
LocallyOriented [52]115.6 5.79 127 17.9 127 0.26 120 12.1 133 23.2 139 1.01 115 7.05 111 17.6 122 0.51 88 19.9 120 30.9 136 5.72 111 43.3 68 58.2 75 5.23 48 11.9 138 42.6 124 1.52 145 10.8 124 44.0 122 0.53 106 22.5 131 54.0 138 0.52 107
Dynamic MRF [7]115.7 5.39 73 17.4 113 0.20 80 10.5 95 21.8 118 0.74 77 7.60 137 20.3 150 0.99 136 21.3 143 31.1 139 7.06 146 43.0 26 58.1 63 5.34 80 11.6 127 43.0 137 1.49 143 10.7 121 45.8 139 0.85 146 22.5 131 53.2 119 0.55 137
ACK-Prior [27]119.2 5.46 85 17.7 122 0.15 28 9.70 66 20.3 84 0.67 66 7.76 139 16.4 92 1.08 142 19.9 120 31.0 138 6.01 130 44.7 153 59.6 150 5.78 151 12.1 145 44.2 154 1.33 128 10.6 119 44.2 126 0.53 106 23.4 152 56.1 157 0.52 107
StereoOF-V1MT [119]119.6 5.94 134 18.8 139 0.20 80 11.3 115 22.6 134 0.94 105 7.95 142 19.6 144 1.00 137 21.6 144 30.7 129 6.76 142 43.3 68 58.3 99 5.37 91 12.1 145 42.6 124 1.82 154 11.6 144 46.7 146 0.90 148 21.8 82 51.8 45 0.50 79
StereoFlow [44]122.2 10.4 160 27.1 160 0.35 142 16.3 159 28.4 160 1.03 120 6.55 73 16.8 103 0.50 86 18.8 82 28.2 63 5.38 63 45.7 159 62.1 159 5.58 143 13.6 159 50.3 160 1.28 123 10.0 66 42.4 77 0.49 77 23.0 143 55.5 154 0.56 143
TI-DOFE [24]122.5 6.39 142 18.7 137 0.36 146 14.8 155 25.5 157 1.66 153 7.45 133 20.2 148 0.78 128 22.8 150 32.5 146 6.04 131 43.2 58 58.4 114 5.17 32 10.9 69 40.4 56 0.92 35 11.2 136 45.6 138 0.65 130 23.2 149 54.2 142 0.65 154
UnFlow [129]122.6 6.39 142 20.9 145 0.21 86 13.0 140 24.4 153 1.15 128 8.06 144 21.1 152 0.82 132 19.2 106 29.6 115 5.64 103 43.1 37 58.0 45 5.40 107 11.8 137 42.8 128 1.36 133 11.0 131 42.4 77 0.70 137 24.3 159 54.8 150 0.70 156
2bit-BM-tele [98]123.0 5.61 109 15.9 48 0.50 153 11.5 121 21.9 121 1.04 121 6.57 76 15.1 53 0.79 129 20.1 127 29.8 120 7.50 150 44.8 154 59.6 150 6.26 157 12.2 149 42.8 128 2.11 156 11.2 136 49.2 157 1.26 156 21.8 82 52.1 63 0.55 137
Horn & Schunck [3]123.1 5.81 129 17.3 107 0.21 86 13.1 142 23.5 143 1.26 134 8.03 143 19.7 145 1.08 142 22.6 148 32.7 147 5.59 98 43.6 128 58.7 134 5.39 100 10.9 69 40.6 65 1.02 64 11.7 147 46.5 144 0.60 125 22.8 141 53.9 136 0.55 137
WRT [150]126.2 5.83 130 18.2 131 0.17 52 11.3 115 21.5 109 0.92 102 8.29 148 15.2 57 1.12 146 19.5 116 29.6 115 5.93 125 43.6 128 58.7 134 5.31 70 12.4 154 45.8 159 1.43 139 12.1 152 51.8 160 1.66 159 22.6 135 54.6 148 0.58 146
WOLF_ROB [148]134.3 6.71 147 21.0 146 0.32 136 12.5 136 23.2 139 1.12 125 7.54 135 17.6 122 0.65 118 20.3 130 33.1 150 6.43 139 43.6 128 58.8 136 5.47 129 11.9 138 42.8 128 1.56 147 12.1 152 46.5 144 0.71 139 22.1 113 52.8 101 0.58 146
NL-TV-NCC [25]136.4 6.44 144 20.3 144 0.24 112 10.7 100 22.1 125 0.68 68 7.38 131 17.2 112 0.59 107 22.2 147 34.7 155 6.82 143 45.5 158 60.2 157 6.68 158 12.3 153 44.6 156 1.19 107 14.4 159 48.1 153 0.67 132 24.0 158 56.4 158 0.55 137
Adaptive flow [45]137.6 7.18 154 19.2 141 0.69 155 15.0 156 25.0 155 2.11 157 7.29 124 16.7 101 0.87 133 22.6 148 31.3 142 7.85 155 44.8 154 60.2 157 5.63 145 11.7 134 43.4 145 1.36 133 10.4 105 43.7 120 0.57 117 23.0 143 54.7 149 0.50 79
HCIC-L [99]137.8 8.84 159 25.2 158 1.06 159 14.0 152 24.1 150 1.43 146 9.42 154 19.3 143 0.69 122 24.3 153 34.1 153 6.48 140 45.1 157 60.1 155 5.86 153 12.1 145 44.1 152 1.06 78 10.2 88 42.6 88 0.51 97 23.6 155 56.0 156 0.51 93
SILK [79]137.8 6.21 140 19.3 143 0.39 149 13.8 148 24.0 148 1.73 154 8.85 151 20.2 148 1.41 150 21.8 145 31.1 139 7.10 147 43.5 112 58.5 123 5.45 123 11.9 138 41.4 92 2.03 155 10.8 124 45.5 137 0.77 144 22.4 129 53.2 119 0.60 149
H+S_ROB [137]138.6 6.50 145 21.0 146 0.14 20 13.6 146 23.3 141 1.26 134 9.85 156 24.2 157 1.51 157 26.5 159 32.2 144 6.19 134 43.9 140 59.3 147 5.46 126 11.7 134 42.9 134 1.23 120 12.1 152 48.5 155 1.02 153 23.5 154 53.9 136 0.55 137
Learning Flow [11]141.1 5.91 133 18.6 136 0.30 131 12.0 131 22.9 137 1.00 112 8.30 149 20.0 147 1.33 149 21.9 146 32.9 148 6.94 145 44.5 152 59.7 153 5.97 155 11.5 124 42.6 124 1.35 130 11.3 138 46.8 147 0.69 136 23.7 156 55.9 155 0.62 152
GroupFlow [9]141.8 7.04 152 22.5 153 0.28 124 12.5 136 24.0 148 1.13 127 9.10 152 22.0 154 1.45 151 21.0 142 33.6 152 5.93 125 44.1 144 59.3 147 5.50 136 12.2 149 44.4 155 1.42 138 11.1 135 45.2 135 0.61 128 22.7 138 54.1 140 0.56 143
SLK [47]143.0 6.55 146 21.1 149 0.32 136 13.5 145 23.1 138 1.44 148 9.16 153 21.2 153 1.49 155 24.9 155 34.2 154 7.81 154 43.5 112 58.8 136 5.34 80 12.2 149 43.1 139 1.45 141 11.9 149 48.9 156 0.96 151 23.0 143 54.0 138 0.64 153
Heeger++ [104]145.4 7.79 157 25.2 158 0.17 52 13.9 151 24.2 151 1.33 138 11.8 158 28.7 159 1.49 155 23.4 151 30.8 133 7.63 151 44.4 151 59.9 154 5.62 144 12.6 157 43.1 139 1.77 153 12.6 156 46.9 148 0.87 147 23.2 149 53.5 129 0.60 149
FFV1MT [106]145.9 6.93 151 22.8 155 0.24 112 14.0 152 23.5 143 1.48 150 11.2 157 27.7 158 1.52 158 23.4 151 30.8 133 7.63 151 44.0 142 59.2 143 5.69 147 12.0 142 41.6 104 1.56 147 12.1 152 47.3 151 0.95 150 23.4 152 54.2 142 0.79 158
FOLKI [16]149.0 7.10 153 21.1 149 0.94 158 15.3 157 25.5 157 2.28 158 8.49 150 22.2 155 1.47 154 26.3 157 35.2 157 10.6 159 44.0 142 59.6 150 5.54 140 11.6 127 41.8 112 1.49 143 11.4 141 47.7 152 0.90 148 23.3 151 54.9 151 0.67 155
Pyramid LK [2]150.4 7.19 155 21.0 146 0.93 157 16.2 158 25.1 156 2.91 159 14.0 159 18.5 136 2.57 159 32.5 160 46.2 160 13.7 160 44.2 148 60.1 155 5.48 132 11.6 127 42.5 123 1.40 137 11.4 141 47.2 150 1.28 157 23.7 156 56.7 159 1.08 159
PGAM+LK [55]151.1 7.51 156 23.5 157 0.73 156 13.8 148 24.2 151 1.92 156 9.44 155 22.7 156 1.45 151 26.4 158 36.9 158 10.5 158 44.1 144 59.5 149 5.72 149 12.4 154 44.0 150 1.75 152 11.3 138 47.0 149 0.68 135 23.0 143 54.5 147 0.76 157
Periodicity [78]157.9 8.05 158 23.2 156 1.34 160 20.5 160 27.4 159 3.39 160 15.2 160 30.5 160 4.22 160 26.2 156 43.5 159 9.47 157 46.4 160 62.7 160 6.92 160 13.7 160 44.6 156 2.88 159 11.4 141 48.3 154 1.18 155 25.7 160 59.2 160 1.29 160
AVG_FLOW_ROB [141]161.0 30.2 161 60.4 161 6.56 161 42.6 161 49.8 161 9.03 161 34.7 161 42.2 161 9.09 161 57.3 161 72.3 161 20.9 161 51.6 161 69.0 161 7.96 161 25.2 161 71.8 161 4.67 161 39.2 161 64.3 161 3.36 161 43.7 161 66.4 161 8.60 161
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.