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        
SD
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
MDP-Flow2 [68]21.8 8.94 31 13.9 29 1.56 1 7.36 7 9.57 9 2.68 3 15.9 34 20.5 73 16.3 74 13.4 15 18.2 29 8.87 28 24.1 7 27.3 7 12.1 17 17.6 28 25.0 33 6.01 20 22.8 11 34.9 12 7.11 4 20.9 17 26.2 17 7.78 16
CBF [12]22.1 8.02 2 12.4 2 1.75 38 8.18 48 10.3 31 4.84 73 13.2 5 15.5 14 9.17 18 11.5 1 15.0 2 7.94 17 22.8 1 25.8 1 12.2 28 16.2 9 22.9 10 6.24 37 23.4 21 35.8 21 8.06 50 21.2 22 26.7 24 8.24 55
PMMST [114]24.2 8.93 27 14.0 36 1.57 2 7.21 3 9.34 4 2.66 1 14.1 17 16.2 25 11.0 35 15.6 76 21.2 87 14.7 114 24.1 7 27.3 7 12.1 17 16.3 11 23.0 11 5.91 11 22.6 9 34.5 9 7.52 19 19.9 4 25.0 4 8.18 44
SepConv-v1 [127]26.5 8.19 4 12.5 3 5.08 127 7.89 24 9.09 3 8.08 125 20.8 89 12.1 1 18.4 89 12.5 7 14.8 1 11.7 83 23.5 4 26.6 4 9.13 2 14.1 2 19.9 2 5.12 1 21.1 1 32.2 1 8.37 56 17.2 1 21.5 1 6.71 5
DeepFlow [86]27.2 8.76 16 13.7 19 1.59 3 8.08 42 10.4 41 4.72 64 13.8 12 18.1 47 7.83 11 12.1 2 15.2 4 8.41 22 28.8 59 32.7 59 12.1 17 17.0 22 24.1 24 5.99 18 21.6 3 33.0 4 7.45 12 23.0 66 28.9 67 7.80 18
DeepFlow2 [108]31.0 8.59 11 13.4 12 1.64 8 8.06 40 10.4 41 4.45 56 13.8 12 18.6 51 8.12 13 12.4 4 16.1 6 10.6 50 28.5 53 32.3 52 12.3 39 16.7 14 23.6 14 5.92 13 23.0 15 35.0 13 7.49 15 22.6 53 28.4 54 8.47 105
SuperFlow [81]31.5 8.83 20 13.8 21 1.68 12 8.19 49 10.3 31 5.04 79 16.0 36 16.6 28 10.9 33 14.9 55 15.1 3 7.67 11 23.0 3 26.0 2 12.5 45 18.0 40 25.5 42 6.55 61 23.6 25 35.8 21 9.80 82 20.7 12 26.0 13 8.12 33
CLG-TV [48]34.5 8.34 8 12.9 7 1.98 83 8.74 70 10.8 62 4.75 69 14.0 15 16.0 20 9.23 19 12.4 4 16.1 6 9.95 41 29.7 82 33.7 82 12.0 14 16.8 15 23.9 18 5.46 2 22.2 5 32.9 3 8.02 46 21.8 38 27.4 39 8.33 79
SIOF [67]35.1 8.78 18 13.5 14 1.80 56 8.97 81 11.2 87 4.51 58 16.7 49 23.2 94 11.6 39 13.2 11 17.7 20 9.61 37 23.7 6 26.8 6 11.8 8 17.8 33 25.2 36 5.98 17 23.4 21 35.9 24 7.33 7 22.1 41 27.8 43 8.15 37
AdaConv-v1 [126]36.1 9.51 65 14.1 43 4.99 126 9.04 84 9.51 8 9.70 127 18.8 76 13.8 3 18.3 88 14.5 44 16.5 11 15.2 118 25.9 19 29.4 19 7.81 1 13.1 1 18.4 1 5.63 5 21.4 2 32.7 2 7.45 12 17.4 2 21.8 2 6.73 7
Aniso. Huber-L1 [22]36.7 8.22 5 12.7 5 1.84 66 9.12 94 11.1 82 5.11 81 13.6 9 16.3 27 7.58 9 12.2 3 16.1 6 9.16 31 29.8 88 33.8 87 12.7 50 16.9 18 23.9 18 5.57 4 23.2 18 35.5 18 7.30 6 21.8 38 27.4 39 8.32 78
CombBMOF [113]37.8 9.74 79 14.3 51 3.85 122 7.82 19 10.2 23 3.81 35 16.2 38 19.1 59 12.8 53 13.8 24 18.5 34 10.2 46 26.5 20 30.0 20 12.2 28 17.8 33 25.2 36 6.09 28 23.1 16 35.2 16 7.64 26 21.3 25 26.7 24 8.21 52
MDP-Flow [26]38.0 8.27 6 12.8 6 1.74 33 7.26 5 9.42 5 3.90 38 17.2 57 16.1 24 15.0 69 13.6 19 18.0 25 10.9 57 28.8 59 32.7 59 15.3 93 17.9 39 25.2 36 7.36 88 23.6 25 36.1 26 12.2 101 20.6 9 25.9 10 8.07 23
LME [70]38.4 8.97 33 14.0 36 1.62 5 8.07 41 10.5 48 3.69 28 16.9 52 17.7 40 9.29 21 14.5 44 19.6 57 9.68 38 29.2 76 33.1 76 15.3 93 18.1 42 25.7 44 6.15 30 22.7 10 34.7 10 7.37 9 21.0 19 26.4 20 8.20 49
NN-field [71]38.9 9.03 39 14.1 43 1.74 33 7.01 2 9.05 2 2.74 8 18.3 71 19.1 59 12.6 51 16.8 101 22.7 106 15.8 120 24.2 9 27.5 9 12.1 17 17.8 33 25.1 34 6.07 25 23.1 16 35.4 17 7.69 30 20.6 9 25.9 10 8.36 89
WLIF-Flow [93]39.0 8.64 12 13.4 12 1.69 17 7.89 24 10.2 23 3.94 39 17.0 53 22.0 83 14.5 65 13.7 22 18.4 32 11.5 74 26.7 23 30.3 23 12.3 39 19.8 95 28.0 96 8.12 111 22.4 7 34.2 7 7.58 23 21.1 21 26.4 20 7.62 14
NNF-Local [87]39.4 8.84 22 13.8 21 1.61 4 7.25 4 9.44 6 2.76 9 14.6 23 19.3 64 14.5 65 16.0 89 21.6 94 15.8 120 24.2 9 27.5 9 12.2 28 18.4 50 26.0 52 6.42 53 24.2 32 37.1 36 9.54 75 20.3 7 25.4 7 8.27 67
p-harmonic [29]39.5 8.89 25 13.9 29 1.68 12 8.86 75 10.9 69 5.20 87 13.4 6 17.5 37 6.45 3 13.7 22 17.9 24 10.0 43 28.9 64 32.8 65 12.8 51 17.6 28 24.9 30 6.53 60 22.9 12 35.0 13 8.88 61 22.5 50 28.3 52 8.10 29
IROF-TV [53]39.9 8.93 27 13.9 29 1.82 62 8.15 46 10.6 53 4.01 42 13.9 14 17.6 38 8.70 16 13.3 12 18.0 25 9.04 29 28.5 53 32.3 52 15.3 93 18.5 54 26.2 56 6.57 62 24.7 46 37.8 48 6.81 3 22.2 45 28.0 48 6.71 5
Second-order prior [8]40.0 8.06 3 12.5 3 1.93 76 8.80 71 11.0 73 4.80 72 12.8 2 16.2 25 7.51 8 12.6 8 16.7 12 6.25 4 28.9 64 32.8 65 12.2 28 18.1 42 25.7 44 6.10 29 23.3 19 35.5 18 9.35 72 22.7 57 28.6 61 8.45 103
OAR-Flow [125]41.3 9.14 47 14.0 36 1.71 23 7.90 26 10.1 17 4.04 44 14.3 20 18.8 54 5.59 1 16.6 98 22.6 103 6.23 3 27.7 40 31.4 40 15.3 93 15.9 5 22.4 5 6.89 73 24.2 32 36.4 29 7.80 36 22.9 64 28.8 65 8.15 37
ALD-Flow [66]41.4 10.4 96 16.0 94 1.76 40 7.99 34 10.3 31 3.78 33 14.1 17 19.3 64 6.64 4 16.1 91 21.9 98 5.92 2 26.5 20 30.0 20 14.0 66 16.9 18 23.9 18 6.23 36 22.5 8 34.4 8 7.50 17 23.2 74 29.2 79 8.09 26
Ad-TV-NDC [36]41.7 9.09 43 13.8 21 2.24 104 9.50 110 11.1 82 6.94 121 14.2 19 15.4 13 6.85 5 14.5 44 18.6 35 9.51 36 27.4 33 31.1 33 12.3 39 18.2 47 25.8 50 6.40 52 22.9 12 34.7 10 7.43 10 20.6 9 25.8 9 8.26 63
IROF++ [58]42.8 8.58 10 13.3 10 1.68 12 7.99 34 10.4 41 3.84 36 17.3 58 18.5 49 12.5 49 12.4 4 16.7 12 9.15 30 28.4 52 32.3 52 15.3 93 19.5 88 27.6 89 6.06 23 23.3 19 35.6 20 8.55 60 23.4 82 29.4 86 7.79 17
DF-Auto [115]43.3 9.30 57 14.4 60 1.99 84 8.37 56 10.6 53 4.99 75 15.5 31 22.3 85 8.88 17 13.3 12 17.6 19 9.86 40 25.7 16 29.1 16 13.9 65 18.1 42 25.7 44 5.96 16 25.2 53 38.6 58 10.8 93 20.7 12 25.9 10 8.09 26
Modified CLG [34]44.0 7.87 1 12.2 1 1.68 12 8.96 79 10.7 59 5.94 115 16.8 50 16.7 30 15.9 73 13.3 12 16.4 10 12.6 102 27.6 38 31.3 38 11.9 9 18.8 65 26.6 66 6.50 58 22.3 6 34.0 6 7.67 28 22.2 45 27.9 45 8.64 109
Brox et al. [5]44.1 9.33 59 14.7 65 1.62 5 7.86 22 10.1 17 4.14 47 15.9 34 16.0 20 10.4 29 13.5 18 17.7 20 8.77 26 26.8 24 30.4 24 11.9 9 19.1 76 27.0 77 9.52 124 28.6 103 43.6 101 23.0 129 19.9 4 25.0 4 8.05 22
NNF-EAC [103]46.5 9.00 36 14.0 36 1.99 84 7.79 17 10.2 23 2.85 12 17.5 62 25.1 109 19.2 93 15.4 69 20.6 75 11.6 78 29.9 92 33.9 92 12.1 17 16.5 12 23.4 12 5.99 18 22.9 12 35.1 15 7.51 18 20.9 17 26.2 17 8.42 100
Local-TV-L1 [65]49.2 8.65 13 13.3 10 1.90 72 9.07 88 11.0 73 5.04 79 13.1 4 15.3 12 8.62 15 12.8 9 17.0 14 7.89 16 30.8 119 35.0 119 15.5 120 18.4 50 26.0 52 6.98 77 23.9 29 36.5 31 7.66 27 21.4 28 26.9 28 8.40 96
F-TV-L1 [15]49.5 10.4 96 16.2 96 1.94 78 9.02 82 11.2 87 4.72 64 14.6 23 16.7 30 11.0 35 14.2 33 18.9 44 10.3 47 27.5 35 31.2 36 12.3 39 16.0 6 22.6 6 6.38 50 23.9 29 36.6 32 9.23 68 21.3 25 26.7 24 10.2 122
PH-Flow [101]50.5 9.30 57 14.3 51 1.70 21 7.70 14 10.1 17 2.82 11 14.9 27 20.6 76 14.8 67 14.3 37 19.4 53 11.5 74 25.0 13 28.3 13 12.2 28 21.6 124 30.7 125 9.38 123 25.0 51 38.3 53 7.76 34 22.6 53 28.4 54 8.15 37
FMOF [94]51.3 9.22 53 13.9 29 1.96 80 7.58 11 9.87 14 2.87 13 19.5 79 22.4 86 17.7 83 15.3 65 20.6 75 12.5 101 24.5 11 27.7 11 13.7 61 19.3 84 27.3 85 6.05 22 24.6 44 37.7 46 6.64 2 23.4 82 29.4 86 6.98 8
Filter Flow [19]52.2 9.35 61 14.5 61 1.79 52 9.19 96 11.1 82 5.50 104 17.6 65 16.8 33 12.2 43 14.0 29 18.0 25 11.3 64 24.6 12 27.9 12 12.2 28 18.4 50 26.0 52 7.54 94 24.8 47 37.9 50 7.77 35 21.5 30 27.0 31 8.40 96
CRTflow [80]54.3 8.75 15 13.6 16 2.04 88 9.27 100 11.5 108 5.28 88 16.2 38 22.5 88 9.27 20 12.8 9 17.0 14 11.5 74 27.0 26 30.6 26 15.3 93 17.6 28 24.9 30 6.06 23 27.8 91 42.7 94 7.62 25 23.4 82 29.4 86 8.16 42
CNN-flow-warp+ref [117]54.6 8.33 7 13.0 8 2.06 92 8.26 53 10.3 31 5.85 112 18.3 71 22.7 90 11.1 37 13.6 19 16.0 5 11.1 60 29.1 74 33.0 74 15.3 93 15.7 3 22.1 3 6.96 76 28.2 97 43.1 97 7.67 28 21.8 38 27.3 37 8.49 106
TC/T-Flow [76]55.0 9.42 63 14.6 64 2.39 108 8.67 68 11.2 87 4.00 40 13.6 9 16.0 20 8.03 12 17.5 112 23.5 115 10.8 54 27.3 31 31.0 31 15.3 93 17.4 26 24.6 26 5.89 10 25.8 67 37.8 48 9.59 77 22.8 60 28.7 63 8.13 35
ComplOF-FED-GPU [35]55.2 9.91 87 15.5 87 1.77 47 7.74 15 10.1 17 4.25 52 19.8 83 17.7 40 17.0 78 15.3 65 20.7 78 11.8 84 28.2 51 32.0 51 14.5 70 16.2 9 22.8 9 5.95 15 26.2 73 39.6 74 9.25 69 22.7 57 28.4 54 8.25 60
COFM [59]55.2 8.95 32 13.8 21 1.90 72 7.42 8 9.61 10 3.19 21 15.3 29 22.1 84 16.3 74 15.4 69 20.9 81 14.6 111 26.8 24 30.4 24 12.2 28 21.4 121 30.3 121 6.26 40 26.3 74 40.4 76 10.4 89 20.8 14 26.1 14 8.36 89
Sparse Occlusion [54]55.6 9.75 80 15.2 78 2.05 91 8.71 69 11.2 87 4.19 49 13.5 7 15.9 19 7.80 10 14.6 49 19.7 62 7.51 10 30.4 104 34.5 105 15.3 93 16.1 7 22.7 7 6.27 41 26.9 83 41.1 85 7.45 12 23.2 74 29.2 79 8.12 33
2DHMM-SAS [92]56.0 8.83 20 13.6 16 1.76 40 8.88 77 11.3 95 4.29 53 17.5 62 20.9 77 12.5 49 14.5 44 19.6 57 11.3 64 30.1 97 34.1 96 15.1 83 17.6 28 24.9 30 5.84 6 25.2 53 38.7 60 8.23 54 23.1 69 29.1 72 8.16 42
2D-CLG [1]56.4 8.51 9 13.2 9 1.76 40 8.84 74 10.4 41 5.71 110 19.4 78 15.6 16 15.0 69 14.2 33 16.3 9 14.0 107 31.1 123 35.3 123 20.9 130 16.1 7 22.7 7 6.34 46 27.7 90 42.3 89 8.19 53 21.4 28 26.9 28 8.13 35
LDOF [28]56.5 8.85 23 13.8 21 2.04 88 10.2 126 9.70 13 10.8 131 17.0 53 20.4 72 12.0 40 13.4 15 17.4 18 12.3 96 22.9 2 26.0 2 11.9 9 18.9 69 26.7 69 6.27 41 30.1 117 46.3 119 16.0 113 19.7 3 24.7 3 8.89 113
Horn & Schunck [3]56.8 8.92 26 13.6 16 1.73 26 9.79 119 11.4 99 6.31 118 24.1 107 18.7 52 18.6 91 15.8 85 19.4 53 11.1 60 28.0 45 31.8 46 10.4 5 17.8 33 25.2 36 5.54 3 25.3 58 38.4 56 9.70 79 22.1 41 27.7 42 8.27 67
PMF [73]56.9 9.35 61 14.5 61 1.77 47 7.80 18 10.1 17 2.68 3 24.0 106 28.7 118 22.5 114 15.3 65 20.6 75 11.6 78 25.7 16 29.2 17 12.1 17 19.1 76 27.0 77 5.92 13 27.6 88 42.4 91 9.09 66 23.1 69 29.0 71 6.47 1
CPM-Flow [116]57.0 9.82 84 15.4 86 1.69 17 7.60 12 9.90 15 3.04 18 15.6 33 15.7 17 7.43 7 16.9 103 23.0 110 12.0 89 27.6 38 31.3 38 15.3 93 18.5 54 26.2 56 7.13 83 23.4 21 35.8 21 9.99 84 23.8 98 29.9 100 8.37 91
FlowNetS+ft+v [112]57.4 9.02 38 14.1 43 2.07 95 10.0 124 11.0 73 9.60 126 16.3 41 14.4 4 13.5 58 13.8 24 17.7 20 13.3 105 29.7 82 33.8 87 15.3 93 16.8 15 23.8 16 6.25 39 27.8 91 42.6 92 7.83 40 20.4 8 25.5 8 8.24 55
Black & Anandan [4]57.8 9.24 55 14.1 43 1.95 79 9.65 117 11.4 99 5.28 88 28.3 116 24.2 100 20.2 102 14.8 53 18.7 39 10.5 49 27.7 40 31.5 41 9.57 4 19.0 73 27.0 77 6.35 48 24.2 32 36.7 33 8.42 58 21.0 19 26.3 19 6.55 2
TC-Flow [46]58.2 10.9 104 17.1 105 1.71 23 8.86 75 11.6 111 4.00 40 13.0 3 16.0 20 6.24 2 15.6 76 21.1 84 8.58 23 27.9 42 31.7 44 15.1 83 18.7 62 26.4 63 6.72 66 24.6 44 37.6 44 7.95 44 23.4 82 29.4 86 8.28 70
Fusion [6]58.3 8.82 19 13.8 21 2.62 111 7.96 32 10.1 17 4.47 57 16.5 44 13.6 2 17.3 82 14.0 29 18.1 28 9.97 42 29.8 88 33.8 87 12.8 51 19.4 85 27.4 86 10.1 127 26.4 75 40.4 76 8.14 51 21.7 34 27.2 35 10.1 121
OFLAF [77]58.7 9.70 74 15.0 73 1.69 17 7.94 31 10.4 41 2.73 7 14.3 20 15.0 9 10.2 25 13.8 24 18.6 35 8.40 21 30.0 94 34.0 94 15.4 113 17.0 22 23.9 18 6.73 67 30.1 117 46.1 117 13.9 108 23.4 82 29.3 83 9.45 117
MLDP_OF [89]58.8 9.06 40 14.1 43 1.83 65 8.81 72 11.3 95 4.78 71 14.0 15 17.6 38 8.56 14 15.5 73 20.3 71 15.8 120 29.7 82 33.7 82 13.6 57 19.1 76 27.0 77 5.86 8 23.8 27 36.3 27 8.15 52 23.2 74 29.1 72 8.25 60
PGM-C [120]59.0 9.70 74 15.2 78 1.69 17 7.84 21 10.2 23 3.70 29 21.2 91 17.2 35 12.3 46 17.4 109 23.6 116 8.69 24 28.0 45 31.8 46 15.3 93 16.6 13 23.4 12 6.17 31 26.4 75 40.5 80 8.04 48 24.3 113 30.5 115 8.34 82
EpicFlow [102]59.0 9.69 73 15.2 78 1.67 11 7.90 26 10.2 23 4.37 55 16.0 36 14.5 5 9.75 23 19.1 121 25.8 123 12.3 96 27.9 42 31.6 42 15.3 93 16.9 18 23.9 18 6.21 35 24.9 49 38.0 51 10.3 88 24.6 118 30.9 119 8.30 74
TV-L1-MCT [64]60.3 9.18 50 14.2 49 1.78 49 8.53 62 11.1 82 3.70 29 17.7 67 23.3 97 13.6 59 14.4 41 19.5 56 11.6 78 30.5 110 34.6 108 13.8 62 18.1 42 25.7 44 6.02 21 25.8 67 39.5 72 15.0 111 21.7 34 27.3 37 7.99 20
AGIF+OF [85]60.7 9.07 41 14.0 36 1.78 49 7.93 30 10.3 31 3.78 33 14.4 22 17.8 42 12.4 47 14.9 55 20.2 68 11.4 69 28.9 64 32.8 65 15.3 93 20.0 97 28.3 97 6.98 77 25.5 61 39.0 63 7.74 32 23.9 105 30.1 109 8.28 70
Bartels [41]60.7 12.7 119 20.1 120 2.13 101 8.52 61 11.0 73 4.96 74 13.5 7 14.5 5 10.2 25 14.4 41 18.9 44 10.8 54 23.5 4 26.6 4 12.9 54 19.0 73 26.9 74 6.94 75 24.5 39 37.5 42 19.7 124 23.4 82 29.4 86 8.31 76
S2F-IF [123]62.0 10.3 94 16.3 98 1.79 52 7.83 20 10.2 23 2.90 15 17.0 53 20.0 69 13.9 62 16.1 91 21.6 94 6.69 5 29.2 76 33.2 77 15.3 93 16.8 15 23.7 15 6.34 46 24.9 49 38.2 52 10.7 91 23.9 105 30.0 107 8.35 87
BlockOverlap [61]62.4 9.09 43 14.3 51 2.04 88 8.96 79 10.9 69 5.37 98 18.1 69 15.5 14 18.0 86 14.2 33 17.2 16 14.0 107 28.9 64 32.8 65 13.8 62 18.8 65 26.7 69 7.92 105 24.8 47 37.2 37 21.0 126 20.0 6 25.1 6 8.38 92
OFH [38]63.2 9.54 67 15.0 73 1.74 33 8.49 60 10.6 53 5.13 82 18.1 69 24.9 107 10.4 29 17.4 109 23.7 118 5.72 1 28.7 57 32.5 55 14.6 73 17.6 28 24.8 28 5.85 7 26.0 71 39.2 67 10.2 86 22.7 57 28.5 59 14.1 128
nLayers [57]63.5 9.15 48 14.3 51 1.76 40 7.42 8 9.62 11 3.57 25 27.8 114 29.9 121 25.8 124 15.9 87 21.5 92 11.9 85 30.2 98 34.3 99 14.7 76 20.3 103 28.8 104 6.45 55 23.5 24 36.0 25 7.87 42 21.6 31 27.1 32 8.10 29
HAST [109]63.6 8.87 24 13.8 21 1.76 40 7.34 6 9.50 7 2.70 5 28.8 118 28.6 117 24.0 119 14.9 55 20.2 68 7.68 12 28.9 64 32.8 65 12.1 17 21.3 120 30.2 120 7.57 96 28.6 103 43.9 104 7.55 21 22.8 60 28.7 63 8.43 102
TCOF [69]63.9 9.34 60 14.3 51 1.89 69 9.50 110 11.7 117 5.42 99 16.2 38 21.7 81 10.3 27 13.8 24 18.6 35 9.45 35 30.4 104 34.6 108 13.6 57 18.2 47 25.7 44 6.20 34 28.5 100 43.5 100 7.54 20 22.9 64 28.8 65 8.18 44
Layers++ [37]64.5 8.93 27 14.0 36 1.76 40 6.74 1 8.61 1 2.71 6 18.3 71 25.8 111 19.3 94 15.3 65 20.8 79 11.3 64 33.1 128 37.6 128 19.8 127 21.6 124 30.6 124 8.73 117 24.4 37 37.4 40 7.81 38 21.6 31 27.1 32 8.09 26
DPOF [18]64.9 11.0 105 17.4 109 3.88 123 7.78 16 10.2 23 3.01 16 18.7 74 18.1 47 18.4 89 16.5 96 22.4 101 14.6 111 28.8 59 32.7 59 12.1 17 18.9 69 26.7 69 6.18 33 25.2 53 38.4 56 7.59 24 23.6 93 29.6 93 8.07 23
FlowFields [110]65.5 9.98 88 15.7 89 2.08 97 7.96 32 10.4 41 3.62 26 23.1 99 23.2 94 20.3 104 16.0 89 21.5 92 7.08 8 27.0 26 30.6 26 14.2 68 19.2 82 27.1 82 6.08 27 24.4 37 37.4 40 10.2 86 23.2 74 29.2 79 8.35 87
Classic++ [32]66.0 9.48 64 14.9 69 1.80 56 8.59 63 11.0 73 4.61 60 13.7 11 15.0 9 9.57 22 14.4 41 19.0 46 8.76 25 29.9 92 33.9 92 13.6 57 20.2 101 28.7 102 6.87 72 27.4 86 42.0 86 9.63 78 23.8 98 29.9 100 8.34 82
SRR-TVOF-NL [91]66.8 9.65 71 14.8 66 1.82 62 8.21 51 10.6 53 4.76 70 22.7 97 28.1 115 21.9 109 15.6 76 20.9 81 9.18 32 28.9 64 32.8 65 15.3 93 20.7 110 29.3 110 5.91 11 24.5 39 37.6 44 6.56 1 22.5 50 28.2 51 8.34 82
HBM-GC [105]67.1 9.25 56 14.5 61 1.81 60 9.08 90 11.9 123 3.75 32 17.3 58 18.7 52 17.9 84 14.3 37 19.2 48 8.85 27 30.0 94 34.0 94 15.5 120 21.5 122 30.4 122 8.27 114 27.4 86 42.1 88 7.15 5 20.8 14 26.1 14 7.05 10
NL-TV-NCC [25]67.6 9.19 52 14.3 51 2.18 102 9.02 82 11.6 111 4.13 46 14.8 25 16.7 30 10.9 33 20.8 125 28.1 126 8.19 19 26.5 20 30.0 20 13.1 55 18.9 69 26.7 69 6.43 54 26.6 79 40.4 76 15.1 112 23.7 97 29.7 97 8.29 73
Nguyen [33]67.8 9.83 85 15.2 78 1.73 26 9.59 115 11.0 73 5.65 109 15.3 29 20.5 73 10.3 27 14.6 49 18.8 40 12.1 91 28.8 59 32.7 59 12.2 28 19.4 85 27.4 86 8.01 109 29.7 112 45.5 112 8.29 55 21.2 22 26.6 23 8.34 82
Efficient-NL [60]68.0 8.71 14 13.5 14 1.68 12 8.66 67 11.2 87 3.65 27 22.5 94 20.0 69 19.9 98 14.3 37 19.3 50 11.0 58 30.5 110 34.7 113 15.0 78 20.1 98 28.4 98 6.27 41 28.5 100 43.7 102 8.92 63 23.8 98 29.9 100 6.66 4
Complementary OF [21]68.3 11.4 111 18.1 114 1.70 21 9.23 99 12.1 124 4.19 49 31.6 123 19.0 58 23.6 116 19.5 124 26.5 124 6.72 6 28.1 49 31.8 46 14.6 73 17.3 25 24.4 25 6.38 50 26.1 72 39.0 63 8.92 63 22.3 47 27.9 45 7.57 13
AggregFlow [97]69.0 12.9 121 20.3 121 1.75 38 8.34 55 10.8 62 4.14 47 20.0 84 24.4 103 19.5 97 16.5 96 22.3 100 12.2 94 25.2 14 28.6 14 12.2 28 16.9 18 23.9 18 6.60 63 29.0 109 43.9 104 16.7 115 23.0 66 28.9 67 8.03 21
FESL [72]69.3 9.09 43 13.9 29 1.74 33 7.90 26 10.3 31 3.35 23 16.5 44 21.9 82 12.0 40 15.1 62 20.3 71 11.4 69 30.8 119 35.0 119 15.4 113 19.6 90 27.8 92 6.48 56 27.8 91 42.6 92 7.75 33 23.9 105 30.0 107 8.39 93
ProbFlowFields [128]69.4 10.1 89 16.0 94 1.78 49 8.04 38 10.5 48 3.08 20 25.8 113 28.8 119 24.3 120 14.5 44 19.6 57 11.4 69 27.2 29 30.9 30 15.3 93 17.4 26 24.6 26 8.78 118 27.3 85 42.0 86 18.8 122 22.4 49 28.1 49 8.39 93
StereoOF-V1MT [119]70.5 11.1 107 17.3 107 1.73 26 8.61 64 10.6 53 5.28 88 23.4 103 17.3 36 17.1 80 16.6 98 19.9 65 12.3 96 27.4 33 31.1 33 15.0 78 17.0 22 23.8 16 6.80 70 30.2 119 46.2 118 12.3 102 21.6 31 26.9 28 9.58 118
RNLOD-Flow [121]70.5 8.93 27 13.8 21 1.65 9 8.48 59 11.0 73 4.06 45 16.3 41 23.2 94 12.8 53 14.1 31 19.1 47 11.1 60 29.7 82 33.7 82 15.6 122 20.3 103 28.7 102 8.92 121 25.7 64 39.4 70 16.4 114 24.2 111 30.4 113 8.20 49
FlowFields+ [130]70.5 9.67 72 15.2 78 3.33 121 7.86 22 10.3 31 3.02 17 23.3 101 24.6 104 20.8 105 17.0 104 23.0 110 6.91 7 27.3 31 31.0 31 15.4 113 19.0 73 26.9 74 6.24 37 25.3 58 38.8 61 13.1 104 23.2 74 29.1 72 8.39 93
FlowNet2 [122]71.5 15.6 129 23.6 130 1.96 80 9.34 102 12.1 124 4.72 64 17.3 58 19.2 63 13.0 56 17.1 107 23.1 112 10.1 44 28.0 45 31.8 46 12.3 39 18.6 56 26.3 59 6.35 48 26.7 80 40.8 83 8.04 48 21.7 34 27.2 35 8.30 74
TI-DOFE [24]71.8 9.80 82 15.2 78 2.80 115 9.94 122 11.4 99 5.62 107 15.5 31 15.7 17 10.5 32 17.0 104 21.7 96 10.6 50 27.1 28 30.8 28 12.1 17 20.9 114 29.6 115 6.99 79 24.0 31 36.3 27 8.92 63 24.3 113 28.1 49 12.5 126
Sparse-NonSparse [56]71.9 9.18 50 14.3 51 1.73 26 8.14 45 10.6 53 3.31 22 16.6 47 22.9 92 13.8 61 14.8 53 19.8 64 11.3 64 30.5 110 34.6 108 15.0 78 20.1 98 28.5 100 7.48 92 28.5 100 43.7 102 9.49 73 23.5 91 29.5 91 8.24 55
LSM [39]72.9 9.10 46 14.2 49 1.73 26 8.33 54 10.9 69 3.40 24 16.6 47 22.7 90 12.2 43 15.0 61 20.3 71 11.0 58 30.5 110 34.7 113 15.1 83 20.7 110 29.4 111 6.17 31 28.1 96 43.0 96 11.5 97 23.8 98 29.9 100 8.27 67
ACK-Prior [27]73.0 9.81 83 15.1 76 2.07 95 8.01 37 10.4 41 3.86 37 25.1 110 19.1 59 22.0 111 15.1 62 20.1 67 10.1 44 30.4 104 34.4 102 15.4 113 19.1 76 26.9 74 7.57 96 25.8 67 39.3 68 19.5 123 22.3 47 27.9 45 7.73 15
Occlusion-TV-L1 [63]73.0 10.1 89 15.9 92 2.43 109 9.36 103 11.8 121 5.01 78 12.7 1 14.7 7 7.22 6 17.0 104 22.7 106 11.4 69 28.6 55 32.5 55 12.0 14 18.7 62 26.5 65 7.48 92 25.2 53 37.7 46 10.0 85 24.3 113 30.3 112 9.33 115
Classic+CPF [83]73.2 9.07 41 14.0 36 1.80 56 8.09 43 10.5 48 3.71 31 17.0 53 21.5 79 12.9 55 13.9 28 18.8 40 11.4 69 30.7 117 34.9 118 15.4 113 21.2 117 30.0 118 7.73 103 28.2 97 43.2 98 7.80 36 24.7 121 31.0 121 7.89 19
FFV1MT [106]73.6 11.6 112 17.7 111 2.19 103 9.20 97 10.9 69 5.96 116 22.6 95 30.3 122 16.3 74 15.5 73 18.8 40 12.4 99 27.5 35 31.2 36 11.6 7 18.6 56 25.7 44 7.42 91 27.2 84 40.7 81 8.88 61 21.2 22 26.4 20 9.73 119
TriFlow [95]74.2 13.1 122 20.8 122 2.06 92 9.53 113 12.2 126 5.29 93 16.5 44 18.5 49 10.1 24 17.2 108 22.8 108 7.74 13 27.9 42 31.6 42 15.1 83 19.4 85 27.4 86 6.07 25 24.5 39 37.2 37 10.9 94 23.8 98 29.8 99 8.15 37
CostFilter [40]74.5 10.8 103 17.0 104 1.80 56 7.90 26 10.3 31 2.66 1 24.6 109 27.7 114 21.9 109 18.7 118 25.4 122 13.7 106 27.5 35 31.1 33 12.6 47 18.2 47 25.8 50 5.87 9 28.9 107 44.2 108 9.34 71 24.4 116 30.7 117 8.20 49
Ramp [62]74.8 9.22 53 14.3 51 1.73 26 8.19 49 10.7 59 4.24 51 21.9 93 28.8 119 21.1 108 14.2 33 19.2 48 11.6 78 30.6 115 34.8 116 14.8 77 20.4 106 29.0 108 7.40 89 28.0 95 42.9 95 7.57 22 23.0 66 28.9 67 8.28 70
TF+OM [100]74.8 11.8 114 18.7 116 3.19 118 8.23 52 10.8 62 4.54 59 15.1 28 19.7 66 10.4 29 16.3 94 21.9 98 7.87 15 28.9 64 32.8 65 19.1 126 18.6 56 26.3 59 6.68 65 26.5 78 40.7 81 11.5 97 23.8 98 29.9 100 8.23 54
IAOF2 [51]76.0 10.7 102 16.6 101 2.36 106 9.40 104 11.6 111 5.33 94 17.4 61 18.0 44 12.4 47 14.1 31 18.2 29 9.32 34 30.3 102 34.4 102 14.0 66 20.5 109 29.1 109 8.20 112 25.2 53 38.3 53 8.49 59 23.1 69 29.1 72 8.24 55
Heeger++ [104]76.3 14.5 126 21.7 125 4.63 125 9.50 110 11.0 73 5.73 111 25.4 112 23.5 99 14.4 64 15.5 73 18.8 40 12.4 99 28.7 57 32.5 55 15.2 90 15.8 4 22.2 4 6.73 67 27.6 88 39.8 75 9.28 70 22.1 41 27.6 41 8.34 82
SVFilterOh [111]77.0 10.5 99 16.4 99 1.97 82 7.65 13 9.98 16 3.05 19 28.0 115 30.4 123 25.4 122 15.6 76 21.2 87 14.7 114 28.9 64 32.7 59 15.4 113 20.1 98 28.4 98 6.61 64 25.8 67 39.5 72 7.84 41 22.5 50 28.3 52 8.49 106
Classic+NL [31]77.3 8.97 33 13.9 29 1.79 52 8.11 44 10.5 48 4.01 42 20.8 89 28.3 116 19.9 98 14.3 37 19.3 50 11.5 74 30.7 117 34.8 116 14.6 73 20.3 103 28.8 104 7.40 89 28.3 99 43.4 99 11.9 100 23.5 91 29.6 93 8.25 60
Dynamic MRF [7]77.4 10.1 89 15.9 92 1.81 60 8.42 58 10.8 62 4.73 68 19.5 79 19.1 59 12.2 43 15.6 76 19.3 50 12.8 104 27.2 29 30.8 28 15.2 90 18.6 56 26.3 59 7.28 86 28.8 106 44.1 107 12.4 103 24.6 118 30.7 117 9.73 119
TV-L1-improved [17]77.4 9.53 66 14.9 69 1.99 84 9.46 107 11.7 117 5.17 84 22.6 95 14.8 8 20.1 101 13.4 15 17.8 23 8.05 18 30.2 98 34.3 99 11.9 9 19.6 90 27.7 90 8.09 110 29.9 115 45.8 115 9.73 80 23.4 82 29.3 83 8.42 100
IAOF [50]77.8 11.1 107 16.6 101 5.32 128 10.6 128 12.3 127 5.87 113 23.3 101 24.2 100 19.4 95 15.4 69 19.7 62 12.0 89 28.9 64 32.8 65 12.1 17 18.8 65 26.6 66 7.26 85 25.6 63 39.1 66 7.35 8 22.1 41 27.8 43 8.26 63
ROF-ND [107]78.0 9.00 36 13.9 29 1.62 5 9.53 113 10.8 62 10.7 130 16.4 43 22.9 92 12.7 52 18.3 116 24.1 119 11.9 85 29.4 80 33.3 80 15.2 90 18.6 56 26.2 56 7.60 99 24.5 39 37.3 39 13.2 106 24.4 116 30.5 115 9.33 115
Steered-L1 [118]78.1 8.76 16 13.7 19 1.82 62 8.00 36 10.3 31 4.72 64 31.9 124 33.2 128 29.2 127 17.4 109 22.8 108 14.1 109 29.5 81 33.5 81 14.2 68 19.7 93 27.9 94 6.28 45 26.4 75 40.4 76 18.7 121 23.8 98 29.9 100 7.04 9
Adaptive [20]78.2 11.0 105 17.3 107 1.89 69 9.41 106 11.6 111 5.19 86 14.8 25 17.1 34 11.1 37 15.7 82 21.1 84 12.1 91 31.1 123 35.3 123 12.0 14 18.8 65 26.6 66 8.00 108 27.8 91 42.3 89 8.01 45 22.6 53 28.4 54 8.63 108
TriangleFlow [30]78.3 9.59 69 14.8 66 2.06 92 9.07 88 11.4 99 5.47 102 19.2 77 20.2 71 13.9 62 13.6 19 18.2 29 8.31 20 30.0 94 34.1 96 9.31 3 17.8 33 25.2 36 7.56 95 30.8 121 47.2 121 13.9 108 25.5 127 31.9 128 11.3 124
FOLKI [16]78.5 10.6 100 16.5 100 2.43 109 9.94 122 11.2 87 6.70 120 19.6 81 21.6 80 19.9 98 18.3 116 19.4 53 17.3 124 28.0 45 31.7 44 13.6 57 19.1 76 27.1 82 10.9 129 24.2 32 36.9 34 17.3 118 21.3 25 26.7 24 8.10 29
SILK [79]80.2 9.72 78 15.1 76 2.69 112 10.2 126 11.4 99 7.82 124 39.2 130 32.9 127 28.5 126 14.6 49 18.4 32 9.73 39 29.0 73 32.9 73 10.4 5 21.2 117 30.0 118 7.00 80 24.5 39 37.5 42 8.03 47 23.1 69 28.9 67 8.31 76
LocallyOriented [52]80.3 10.1 89 15.7 89 1.79 52 9.46 107 11.6 111 5.28 88 23.1 99 24.2 100 20.9 107 19.3 123 23.2 113 7.35 9 30.4 104 34.6 108 12.6 47 18.9 69 26.8 73 6.27 41 25.7 64 38.6 58 7.89 43 23.6 93 29.6 93 8.19 47
S2D-Matching [84]81.9 9.57 68 14.9 69 1.76 40 8.37 56 10.8 62 4.36 54 20.1 86 24.9 107 18.2 87 15.7 82 21.3 91 15.7 119 28.8 59 32.7 59 14.5 70 21.5 122 30.4 122 11.0 130 25.7 64 39.3 68 11.5 97 23.1 69 29.1 72 8.75 112
GraphCuts [14]82.5 11.7 113 17.8 112 2.02 87 8.15 46 10.5 48 4.65 62 25.3 111 15.2 11 19.4 95 14.9 55 19.6 57 11.9 85 29.8 88 33.8 87 17.8 124 19.6 90 27.8 92 6.50 58 28.6 103 43.9 104 11.1 95 24.0 109 30.2 110 8.15 37
BriefMatch [124]82.5 9.89 86 15.5 87 2.11 99 8.05 39 10.2 23 5.90 114 23.5 104 18.0 44 22.7 115 18.2 115 18.6 35 18.7 127 28.1 49 31.9 50 13.8 62 19.5 88 27.7 90 7.05 81 26.7 80 39.4 70 21.6 127 23.4 82 29.3 83 14.3 130
RFlow [90]83.3 9.71 76 15.2 78 1.91 75 9.06 86 11.2 87 5.42 99 22.8 98 22.6 89 17.9 84 15.8 85 21.2 87 12.7 103 29.2 76 33.2 77 11.9 9 19.2 82 27.2 84 7.63 100 28.9 107 44.4 109 7.73 31 23.4 82 29.5 91 8.46 104
ComponentFusion [96]83.6 12.3 118 19.5 118 1.66 10 8.65 66 11.4 99 2.88 14 19.7 82 21.0 78 15.1 71 15.4 69 20.9 81 14.4 110 29.7 82 33.7 82 14.5 70 18.6 56 26.3 59 7.67 101 31.9 123 49.0 124 20.5 125 24.2 111 30.4 113 8.18 44
Learning Flow [11]84.1 8.99 35 14.1 43 1.85 68 9.10 92 11.3 95 4.99 75 40.2 131 42.5 131 31.6 131 14.9 55 17.2 16 12.2 94 30.8 119 35.0 119 15.1 83 18.7 62 26.4 63 7.58 98 25.1 52 38.3 53 11.4 96 25.5 127 31.7 126 8.24 55
Adaptive flow [45]84.5 10.3 94 14.8 66 2.37 107 9.87 121 11.5 108 5.57 105 18.0 68 17.9 43 17.1 80 16.4 95 20.0 66 14.8 116 32.3 126 36.7 126 16.6 123 21.1 116 29.8 116 8.41 115 23.8 27 36.4 29 13.1 104 21.7 34 27.1 32 7.17 11
Shiralkar [42]85.1 12.0 117 18.8 117 1.72 25 9.11 93 11.1 82 5.14 83 21.2 91 16.6 28 13.7 60 19.2 122 24.3 121 10.6 50 29.7 82 33.7 82 12.8 51 18.0 40 25.4 41 7.19 84 29.4 110 44.9 110 10.4 89 25.1 125 31.5 125 9.03 114
FC-2Layers-FF [74]85.1 9.71 76 14.9 69 2.11 99 7.51 10 9.66 12 4.67 63 20.5 87 25.1 109 20.2 102 15.6 76 21.1 84 11.9 85 30.5 110 34.6 108 15.3 93 20.8 112 29.4 111 7.31 87 29.7 112 45.6 114 9.76 81 23.6 93 29.7 97 8.22 53
SLK [47]85.2 9.63 70 15.0 73 1.90 72 9.14 95 10.3 31 5.63 108 34.7 126 19.7 66 22.4 113 18.9 119 24.2 120 20.4 130 29.8 88 33.8 87 12.2 28 18.1 42 25.5 42 6.93 74 31.9 123 48.8 123 9.12 67 22.8 60 28.5 59 14.2 129
EPPM w/o HM [88]86.2 10.4 96 16.2 96 2.97 117 8.62 65 11.3 95 2.76 9 29.0 119 27.4 113 22.2 112 16.8 101 22.6 103 10.8 54 25.8 18 29.2 17 12.1 17 20.2 101 28.6 101 6.49 57 29.8 114 45.8 115 18.0 119 24.0 109 30.2 110 8.72 111
UnFlow [129]86.8 13.4 123 21.2 124 2.71 114 8.81 72 10.7 59 6.35 119 18.7 74 18.9 55 14.8 67 14.6 49 19.6 57 7.77 14 31.8 125 36.1 125 15.0 78 22.2 127 31.4 127 7.79 104 24.2 32 37.0 35 7.49 15 28.1 131 33.7 131 11.6 125
Correlation Flow [75]88.9 9.75 80 15.3 85 1.84 66 9.28 101 11.6 111 5.17 84 17.5 62 18.9 55 15.2 72 16.1 91 21.7 96 11.3 64 30.2 98 34.3 99 12.5 45 21.2 117 29.9 117 8.24 113 31.3 122 47.8 122 9.82 83 24.9 123 31.3 124 6.61 3
HBpMotionGpu [43]90.5 12.7 119 19.5 118 2.69 112 9.65 117 11.7 117 5.48 103 20.0 84 23.3 97 17.0 78 17.6 113 23.4 114 10.6 50 30.8 119 35.0 119 25.1 131 20.4 106 28.9 107 7.95 106 22.0 4 33.7 5 7.44 11 23.2 74 29.1 72 8.40 96
PGAM+LK [55]91.7 11.9 116 18.0 113 7.26 131 9.48 109 10.8 62 7.62 122 31.5 122 39.9 130 31.4 130 19.0 120 23.6 116 16.3 123 29.1 74 33.0 74 12.6 47 18.4 50 26.0 52 6.80 70 25.5 61 39.0 63 14.8 110 22.6 53 28.4 54 8.41 99
2bit-BM-tele [98]92.5 11.1 107 17.2 106 2.34 105 9.40 104 11.7 117 5.36 96 28.5 117 37.1 129 31.0 129 15.7 82 20.8 79 9.18 32 28.6 55 32.5 55 15.0 78 22.0 126 31.1 126 9.53 125 39.1 131 59.9 131 26.9 131 20.8 14 26.1 14 8.11 32
StereoFlow [44]93.6 14.9 127 22.2 127 3.28 119 10.0 124 12.7 130 4.99 75 16.8 50 18.9 55 12.1 42 15.2 64 20.4 74 10.4 48 33.4 129 37.9 129 20.8 128 23.8 129 33.5 129 8.41 115 25.3 58 38.8 61 7.81 38 23.6 93 29.6 93 8.67 110
Rannacher [23]93.7 11.1 107 17.5 110 1.89 69 9.59 115 11.8 121 5.28 88 24.3 108 18.0 44 20.8 105 15.9 87 21.2 87 11.6 78 30.4 104 34.5 105 12.3 39 19.7 93 27.9 94 7.98 107 29.6 111 45.3 111 9.57 76 24.7 121 31.0 121 8.19 47
SimpleFlow [49]96.1 9.15 48 14.3 51 1.73 26 9.05 85 11.4 99 5.35 95 36.0 128 32.6 126 29.4 128 14.9 55 20.2 68 11.2 63 30.6 115 34.7 113 15.1 83 22.6 128 32.0 128 9.11 122 34.7 127 53.2 127 13.8 107 23.9 105 29.9 100 8.33 79
SegOF [10]97.0 11.8 114 18.2 115 5.53 129 8.88 77 11.4 99 4.62 61 31.1 121 20.5 73 23.7 117 25.8 130 34.8 131 18.2 126 30.2 98 34.2 98 15.3 93 19.1 76 27.0 77 7.08 82 32.5 125 49.7 125 16.8 116 22.8 60 28.6 61 8.08 25
Aniso-Texture [82]97.2 10.6 100 16.7 103 1.74 33 9.83 120 12.4 128 5.36 96 17.6 65 19.9 68 13.1 57 22.9 127 27.8 125 19.7 129 30.3 102 34.4 102 15.4 113 20.8 112 29.4 111 8.86 120 26.8 82 41.0 84 8.38 57 24.6 118 30.9 119 8.26 63
SPSA-learn [13]97.5 15.1 128 22.9 128 1.93 76 9.08 90 11.0 73 5.42 99 33.0 125 24.8 105 23.8 118 17.6 113 22.4 101 12.1 91 29.3 79 33.2 77 15.1 83 17.8 33 25.1 34 6.73 67 37.7 128 57.7 129 25.5 130 25.4 126 31.8 127 8.33 79
HCIC-L [99]101.9 14.3 125 20.9 123 2.86 116 11.2 129 13.3 131 7.62 122 23.9 105 31.6 125 25.6 123 21.0 126 28.2 127 14.8 116 25.6 15 29.0 15 12.2 28 24.0 130 33.9 130 10.5 128 30.5 120 46.8 120 18.5 120 23.3 80 29.2 79 7.37 12
IIOF-NLDP [131]103.8 10.2 93 15.8 91 2.10 98 9.06 86 11.2 87 5.60 106 20.6 88 24.8 105 16.9 77 16.7 100 22.6 103 14.6 111 30.4 104 34.5 105 20.8 128 20.4 106 28.8 104 8.81 119 37.7 128 57.6 128 16.8 116 24.9 123 31.2 123 8.26 63
GroupFlow [9]109.5 15.6 129 23.3 129 3.31 120 9.20 97 11.4 99 6.26 117 30.9 120 22.4 86 18.9 92 25.4 129 30.0 129 21.2 131 32.4 127 36.7 126 15.3 93 20.9 114 29.4 111 7.71 102 29.9 115 45.5 112 9.50 74 23.3 80 29.1 72 10.6 123
Pyramid LK [2]115.9 14.0 124 21.7 125 4.34 124 13.7 130 11.5 108 9.94 128 37.6 129 26.8 112 24.6 121 25.9 131 29.3 128 18.7 127 35.0 130 39.7 130 13.3 56 19.9 96 24.8 28 9.57 126 33.3 126 51.1 126 10.7 91 26.0 129 32.4 129 13.0 127
Periodicity [78]129.0 18.1 131 27.0 131 6.22 130 17.4 131 12.4 128 10.2 129 35.2 127 30.7 124 27.8 125 24.1 128 31.6 130 17.5 125 37.6 131 42.6 131 18.8 125 27.7 131 39.3 131 11.2 131 38.6 130 58.9 130 22.9 128 27.3 130 33.2 130 14.3 130
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. Submitted to TIP 2016.
[122] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[123] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[124] BriefMatch 0.068 2 gray G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62.
[125] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[126] AdaConv-v1 2.8 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[127] SepConv-v1 0.2 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[128] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[129] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[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-invariantdescriptors in variational optical flow estimation. ICIP 2017.
* 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.