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
PMMST [114]13.1 4.93 4 13.9 4 0.13 4 8.97 28 17.1 13 0.43 10 6.00 11 13.4 5 0.27 1 17.6 3 26.2 7 5.24 20 43.0 15 57.7 9 5.17 21 10.3 6 39.1 9 0.87 13 9.75 17 41.0 17 0.44 18 21.5 28 51.9 36 0.47 16
MDP-Flow2 [68]14.0 4.89 3 14.4 6 0.12 3 8.58 11 16.9 11 0.39 3 5.95 8 13.6 7 0.28 3 17.7 4 26.7 15 5.32 35 42.9 7 57.6 6 5.13 16 10.6 20 40.1 26 0.92 22 9.75 17 41.0 17 0.43 11 21.6 40 51.9 36 0.46 10
SepConv-v1 [127]15.6 3.41 1 11.0 2 0.08 1 8.39 7 16.7 10 1.04 101 2.81 1 7.63 1 0.74 103 18.0 18 25.2 2 5.82 101 42.9 7 57.4 3 4.74 3 9.03 1 34.1 1 0.60 1 9.34 2 38.6 1 0.42 5 20.1 1 48.6 1 0.35 1
SuperSlomo [132]16.0 3.75 2 10.1 1 0.19 54 8.96 27 16.5 7 1.31 114 3.32 2 8.42 2 0.29 7 17.7 4 24.1 1 5.32 35 41.4 1 55.9 1 4.24 1 9.50 2 35.3 2 0.67 2 10.8 106 40.3 5 0.37 1 20.4 2 48.7 2 0.42 2
NNF-Local [87]18.6 5.11 16 15.7 27 0.11 2 8.18 2 15.8 4 0.39 3 6.01 14 13.5 6 0.27 1 18.3 34 28.3 55 5.29 27 43.0 15 57.6 6 5.11 14 10.8 42 40.9 56 1.01 47 9.67 9 40.7 10 0.46 34 21.2 5 51.2 8 0.46 10
NN-field [71]18.8 5.14 20 16.1 49 0.13 4 8.21 3 15.7 3 0.38 2 6.39 44 13.6 7 0.30 8 18.4 36 28.7 72 5.33 40 42.9 7 57.6 6 5.08 12 10.7 27 40.2 31 0.94 30 9.62 7 40.5 8 0.44 18 21.2 5 51.2 8 0.45 4
Layers++ [37]22.3 5.25 33 15.9 35 0.17 36 8.27 4 15.5 2 0.37 1 6.16 23 14.3 13 0.38 40 18.0 18 26.9 19 5.32 35 43.1 26 57.9 22 5.24 39 10.7 27 40.6 49 0.97 42 9.70 10 40.7 10 0.39 2 21.3 11 51.3 10 0.48 29
PH-Flow [101]25.0 5.32 45 16.4 60 0.16 26 8.28 5 15.9 5 0.44 13 6.12 20 13.9 10 0.33 17 17.5 1 25.8 3 5.15 7 42.8 5 57.5 4 5.03 9 11.0 67 41.6 85 1.09 69 9.71 11 41.0 17 0.46 34 21.3 11 51.4 12 0.50 63
COFM [59]26.8 5.08 14 15.1 14 0.19 54 8.86 19 17.4 18 0.48 25 6.37 40 14.2 12 0.40 47 17.7 4 26.2 7 5.11 2 42.9 7 57.8 13 5.02 8 10.9 53 41.6 85 1.11 72 9.24 1 38.8 2 0.50 72 21.5 28 51.9 36 0.46 10
nLayers [57]27.0 5.26 36 15.8 33 0.16 26 8.54 9 16.6 9 0.45 16 5.89 5 13.1 3 0.30 8 18.1 24 27.1 24 5.35 46 43.3 52 58.0 31 5.36 72 10.8 42 40.9 56 1.11 72 9.65 8 40.1 3 0.48 58 21.2 5 51.1 6 0.45 4
Sparse-NonSparse [56]27.5 5.31 44 16.3 58 0.17 36 8.74 14 17.2 17 0.48 25 6.19 24 14.7 25 0.34 21 17.9 13 26.3 9 5.23 17 43.1 26 57.8 13 5.25 42 11.0 67 41.2 65 1.04 55 9.71 11 40.9 14 0.46 34 21.2 5 51.3 10 0.47 16
IROF++ [58]28.8 5.37 56 16.8 76 0.14 8 8.87 21 17.4 18 0.45 16 6.41 50 14.6 22 0.43 58 17.5 1 25.8 3 5.22 12 42.9 7 57.8 13 5.19 26 10.5 12 39.4 14 0.87 13 10.0 55 42.4 63 0.47 51 21.4 20 51.5 13 0.50 63
TV-L1-MCT [64]29.5 5.74 105 18.1 111 0.18 46 9.50 43 19.1 41 0.58 39 5.73 3 14.5 20 0.38 40 17.8 9 26.0 6 5.28 25 43.0 15 57.9 22 5.22 33 10.4 8 39.1 9 0.94 30 9.78 23 41.1 23 0.44 18 21.2 5 51.1 6 0.48 29
HAST [109]30.4 5.12 17 15.2 16 0.16 26 8.74 14 17.1 13 0.43 10 6.62 75 15.3 49 0.39 44 17.7 4 26.4 11 4.98 1 43.0 15 58.0 31 5.05 10 11.0 67 41.4 74 1.06 62 9.53 3 40.4 6 0.42 5 22.0 82 52.8 79 0.47 16
ComponentFusion [96]31.8 5.15 21 16.1 49 0.14 8 8.86 19 17.9 26 0.41 6 6.38 41 15.4 50 0.33 17 17.8 9 27.0 22 5.15 7 43.2 42 58.0 31 5.24 39 10.6 20 39.8 18 0.94 30 10.0 55 42.7 82 0.57 98 21.5 28 51.8 29 0.47 16
ProbFlowFields [128]32.3 5.03 9 15.6 25 0.17 36 8.55 10 17.1 13 0.41 6 6.00 11 14.4 16 0.32 14 18.1 24 27.1 24 5.38 51 43.3 52 58.1 48 5.49 109 10.9 53 41.2 65 1.20 90 9.61 6 40.7 10 0.47 51 21.0 4 50.8 4 0.49 45
FMOF [94]32.4 5.62 93 17.2 87 0.21 64 8.71 13 17.0 12 0.44 13 6.38 41 14.7 25 0.46 65 18.6 49 28.0 42 5.31 32 43.1 26 57.9 22 5.15 19 10.8 42 40.5 45 0.87 13 9.60 5 40.4 6 0.40 4 21.5 28 51.7 21 0.46 10
2DHMM-SAS [92]35.5 5.62 93 17.6 104 0.18 46 10.1 65 19.7 56 0.64 55 5.73 3 14.4 16 0.37 38 17.7 4 25.9 5 5.30 29 43.0 15 57.8 13 5.26 45 10.7 27 40.0 24 0.82 6 9.83 29 41.3 26 0.48 58 21.6 40 52.0 40 0.47 16
CombBMOF [113]36.2 5.46 70 16.2 56 0.22 75 8.89 22 18.0 28 0.45 16 6.29 31 14.7 25 0.40 47 18.5 43 28.0 42 5.24 20 43.0 15 57.7 9 5.08 12 10.8 42 40.2 31 0.82 6 11.7 128 42.9 87 0.47 51 21.2 5 50.9 5 0.45 4
LSM [39]37.0 5.49 74 17.4 97 0.18 46 8.93 24 17.7 23 0.48 25 6.32 35 15.4 50 0.35 29 18.1 24 27.1 24 5.22 12 43.1 26 57.9 22 5.28 55 11.0 67 41.3 70 1.03 53 9.72 13 40.9 14 0.46 34 21.4 20 51.7 21 0.48 29
Ramp [62]37.9 5.46 70 17.1 84 0.18 46 8.84 17 17.4 18 0.58 39 6.14 21 14.7 25 0.34 21 17.8 9 26.4 11 5.23 17 43.2 42 58.0 31 5.27 50 11.2 88 42.0 94 1.15 80 9.72 13 40.9 14 0.42 5 21.6 40 52.1 45 0.48 29
DeepFlow [86]38.8 5.06 13 14.6 8 0.19 54 9.80 57 19.5 47 0.75 68 6.45 53 16.6 83 0.35 29 18.7 58 27.6 35 5.41 57 43.4 69 58.0 31 5.37 74 10.3 6 38.3 5 0.99 43 9.83 29 41.8 42 0.43 11 21.3 11 51.6 19 0.48 29
NNF-EAC [103]39.2 5.52 78 15.7 27 0.34 116 9.27 38 18.1 30 0.48 25 6.53 59 13.8 9 0.40 47 18.2 30 27.0 22 5.71 90 43.0 15 57.7 9 5.11 14 10.4 8 39.1 9 0.83 8 9.89 37 41.6 37 0.52 83 21.7 52 52.2 52 0.49 45
DeepFlow2 [108]39.3 5.16 22 14.9 13 0.21 64 9.81 58 19.7 56 0.65 57 6.38 41 16.3 73 0.34 21 18.6 49 28.1 47 5.29 27 43.4 69 58.0 31 5.37 74 10.2 5 38.4 6 0.85 11 9.96 52 42.1 56 0.44 18 21.4 20 51.8 29 0.49 45
SuperFlow [81]39.4 4.99 8 14.3 5 0.22 75 10.3 71 19.9 61 0.90 84 6.61 69 15.5 53 0.51 72 18.5 43 27.2 29 5.52 75 43.3 52 58.1 48 5.37 74 10.1 4 38.0 4 0.73 4 9.73 16 41.4 31 0.46 34 21.3 11 51.5 13 0.46 10
LME [70]39.7 5.13 19 15.8 33 0.14 8 9.15 35 18.4 39 0.51 30 6.32 35 15.7 57 0.34 21 17.9 13 27.1 24 5.34 42 43.8 114 58.8 113 5.79 127 10.8 42 41.2 65 0.93 25 9.86 33 41.3 26 0.43 11 21.3 11 51.5 13 0.47 16
WLIF-Flow [93]40.1 5.25 33 16.0 42 0.15 15 9.14 34 18.1 30 0.59 45 6.29 31 14.3 13 0.34 21 17.9 13 26.3 9 5.65 86 43.1 26 57.9 22 5.26 45 11.2 88 41.9 93 1.22 96 9.82 28 41.3 26 0.44 18 21.7 52 52.2 52 0.49 45
FlowFields+ [130]40.3 5.23 32 16.6 68 0.15 15 8.91 23 18.3 33 0.45 16 6.28 30 15.9 61 0.34 21 18.2 30 28.1 47 5.34 42 43.4 69 58.2 59 5.35 68 10.9 53 41.6 85 1.10 71 9.79 24 41.5 33 0.46 34 21.3 11 51.5 13 0.48 29
PGM-C [120]40.4 5.18 25 16.0 42 0.15 15 8.97 28 18.2 32 0.46 22 6.51 56 16.4 78 0.33 17 18.4 36 28.5 63 5.36 48 43.4 69 58.1 48 5.40 90 10.7 27 40.5 45 0.96 39 9.92 42 41.9 44 0.45 26 21.4 20 51.8 29 0.48 29
FlowFields [110]41.0 5.22 30 16.5 63 0.16 26 8.95 25 18.3 33 0.42 8 6.29 31 15.9 61 0.35 29 18.4 36 28.5 63 5.41 57 43.4 69 58.1 48 5.33 60 10.9 53 41.3 70 1.08 65 9.79 24 41.5 33 0.45 26 21.3 11 51.6 19 0.49 45
Classic+NL [31]41.2 5.56 84 17.4 97 0.22 75 8.99 30 17.6 22 0.54 32 6.02 15 14.7 25 0.36 34 18.1 24 26.8 16 5.41 57 43.1 26 58.0 31 5.23 36 11.1 85 41.5 79 1.06 62 9.72 13 41.0 17 0.46 34 21.6 40 52.0 40 0.47 16
DF-Auto [115]42.6 5.03 9 13.8 3 0.17 36 10.2 66 19.3 44 0.79 72 6.09 17 14.4 16 0.34 21 18.7 58 28.1 47 5.24 20 43.2 42 57.9 22 5.31 58 10.4 8 39.3 12 0.93 25 10.1 65 42.3 60 0.49 64 21.9 74 52.9 85 0.53 99
FC-2Layers-FF [74]43.3 5.40 61 17.0 82 0.17 36 8.15 1 15.3 1 0.42 8 6.14 21 14.9 33 0.35 29 18.1 24 27.2 29 5.31 32 43.3 52 58.2 59 5.36 72 11.2 88 42.2 98 1.20 90 9.75 17 41.0 17 0.49 64 21.7 52 52.1 45 0.48 29
S2F-IF [123]43.4 5.22 30 16.5 63 0.15 15 8.84 17 18.0 28 0.44 13 6.27 29 15.7 57 0.33 17 18.3 34 28.3 55 5.14 6 43.4 69 58.2 59 5.41 94 11.0 67 41.5 79 1.11 72 9.91 41 41.9 44 0.47 51 21.3 11 51.5 13 0.51 77
AGIF+OF [85]43.5 5.60 90 17.4 97 0.15 15 8.95 25 17.7 23 0.59 45 6.20 26 14.5 20 0.43 58 17.9 13 26.6 14 5.22 12 43.4 69 58.3 81 5.38 81 11.1 85 42.0 94 1.01 47 9.87 36 40.7 10 0.42 5 21.5 28 52.0 40 0.48 29
OFLAF [77]44.0 5.16 22 15.9 35 0.14 8 8.28 5 16.1 6 0.40 5 6.34 39 14.9 33 0.30 8 18.0 18 27.3 31 5.11 2 43.3 52 58.1 48 5.39 83 11.2 88 42.4 99 1.21 93 10.1 65 42.4 63 0.60 105 21.9 74 52.6 70 0.45 4
MDP-Flow [26]45.0 5.03 9 15.4 18 0.14 8 8.68 12 17.4 18 0.47 23 5.97 9 14.3 13 0.32 14 18.9 74 28.5 63 5.50 72 43.2 42 58.0 31 5.39 83 11.2 88 42.6 102 1.31 105 10.3 83 43.1 92 0.49 64 21.4 20 51.7 21 0.47 16
S2D-Matching [84]45.6 5.56 84 17.3 91 0.18 46 9.96 62 19.9 61 0.66 58 5.99 10 14.7 25 0.41 52 17.9 13 26.4 11 5.40 56 43.2 42 58.0 31 5.17 21 11.2 88 42.0 94 1.17 85 9.93 45 41.1 23 0.43 11 21.5 28 51.8 29 0.48 29
TF+OM [100]46.9 4.98 6 14.6 8 0.20 60 9.03 32 17.9 26 0.55 34 6.29 31 16.2 70 0.39 44 18.5 43 28.0 42 5.50 72 43.3 52 58.1 48 5.47 106 10.6 20 39.8 18 1.03 53 9.86 33 42.0 50 0.51 79 21.7 52 52.3 57 0.52 90
Brox et al. [5]47.5 5.33 51 15.4 18 0.19 54 10.2 66 20.1 66 0.64 55 6.61 69 17.2 98 0.46 65 18.7 58 28.2 51 5.21 9 43.4 69 58.1 48 5.27 50 10.7 27 40.1 26 0.99 43 9.90 39 42.0 50 0.45 26 21.6 40 52.1 45 0.47 16
ALD-Flow [66]47.6 5.37 56 16.1 49 0.23 83 9.53 44 19.2 43 0.57 37 6.51 56 16.7 87 0.34 21 18.2 30 27.9 38 5.32 35 43.4 69 58.3 81 5.46 104 10.7 27 39.9 21 0.99 43 9.76 22 41.2 25 0.44 18 21.8 63 52.7 75 0.47 16
SVFilterOh [111]48.4 5.32 45 15.7 27 0.21 64 8.78 16 17.1 13 0.49 29 6.40 47 14.6 22 0.38 40 18.4 36 27.1 24 5.80 99 43.8 114 58.6 109 5.65 121 10.9 53 41.0 62 1.04 55 9.54 4 40.1 3 0.43 11 21.7 52 52.2 52 0.50 63
CPM-Flow [116]48.4 5.20 29 16.1 49 0.16 26 8.99 30 18.3 33 0.47 23 6.42 51 16.0 66 0.30 8 18.8 66 29.2 90 5.43 63 43.4 69 58.2 59 5.44 102 10.6 20 40.1 26 1.02 49 10.0 55 42.6 74 0.45 26 21.4 20 51.8 29 0.53 99
AggregFlow [97]48.6 5.64 96 17.2 87 0.22 75 9.81 58 19.5 47 0.59 45 6.11 19 14.4 16 0.28 3 18.9 74 29.0 81 5.30 29 43.4 69 58.2 59 5.33 60 10.7 27 40.2 31 0.96 39 9.89 37 41.7 39 0.50 72 21.4 20 51.7 21 0.50 63
RNLOD-Flow [121]49.9 5.32 45 16.6 68 0.16 26 9.70 53 19.6 53 0.60 49 6.57 63 15.5 53 0.51 72 18.2 30 27.4 32 5.22 12 43.1 26 58.0 31 5.28 55 11.0 67 41.4 74 1.08 65 9.85 32 41.3 26 0.50 72 21.9 74 52.7 75 0.49 45
Second-order prior [8]50.6 5.29 41 15.3 17 0.27 100 10.8 82 21.1 81 0.78 71 7.14 98 17.8 107 0.62 96 18.6 49 28.3 55 5.21 9 42.9 7 57.7 9 5.16 20 10.5 12 39.6 16 0.93 25 10.2 76 42.8 84 0.44 18 21.6 40 52.3 57 0.49 45
IROF-TV [53]51.8 5.35 55 16.6 68 0.21 64 9.10 33 17.8 25 0.57 37 6.61 69 16.8 89 0.44 61 17.8 9 26.9 19 5.37 50 43.5 94 58.4 94 5.50 111 10.5 12 40.1 26 0.90 19 9.98 54 42.2 58 0.46 34 21.6 40 52.1 45 0.51 77
DPOF [18]52.3 5.51 77 17.9 109 0.22 75 8.45 8 16.5 7 0.43 10 6.87 82 15.1 43 0.59 88 18.9 74 29.5 96 5.43 63 42.9 7 57.8 13 5.05 10 11.0 67 40.9 56 0.84 10 10.3 83 42.5 70 0.45 26 21.9 74 52.8 79 0.48 29
TC-Flow [46]54.1 5.19 26 15.9 35 0.21 64 9.57 45 19.6 53 0.63 52 6.78 80 17.0 95 0.36 34 18.1 24 27.4 32 5.61 82 43.3 52 58.2 59 5.46 104 11.0 67 41.6 85 1.18 86 9.93 45 41.7 39 0.45 26 21.5 28 52.0 40 0.49 45
Aniso. Huber-L1 [22]54.7 5.41 63 16.0 42 0.23 83 11.2 92 21.1 81 0.90 84 6.72 77 15.4 50 0.46 65 18.5 43 28.1 47 5.39 55 43.0 15 57.8 13 5.23 36 10.5 12 40.1 26 0.81 5 10.2 76 42.6 74 0.46 34 21.9 74 52.7 75 0.52 90
OAR-Flow [125]54.8 5.28 39 15.5 21 0.18 46 9.71 55 19.5 47 0.67 59 6.43 52 16.3 73 0.28 3 18.0 18 27.6 35 5.23 17 43.5 94 58.4 94 5.48 107 10.9 53 41.3 70 1.13 77 10.2 76 42.9 87 0.51 79 21.7 52 52.3 57 0.45 4
EpicFlow [102]55.4 5.19 26 16.1 49 0.15 15 9.60 46 19.8 60 0.58 39 6.40 47 16.4 78 0.35 29 18.6 49 29.1 88 5.47 69 43.4 69 58.2 59 5.42 97 10.8 42 41.2 65 1.08 65 10.1 65 42.5 70 0.54 89 21.5 28 52.0 40 0.49 45
ComplOF-FED-GPU [35]55.5 5.30 43 16.1 49 0.19 54 9.39 41 19.3 44 0.58 39 7.21 102 16.9 92 0.66 98 18.4 36 28.6 69 5.32 35 43.1 26 58.0 31 5.27 50 10.8 42 40.9 56 0.99 43 10.1 65 42.8 84 0.47 51 21.8 63 52.3 57 0.50 63
FESL [72]57.1 5.65 99 17.3 91 0.17 36 9.18 36 18.3 33 0.55 34 6.22 27 15.0 39 0.44 61 18.8 66 28.4 58 5.38 51 43.4 69 58.2 59 5.41 94 11.3 95 42.8 106 1.19 88 9.92 42 41.5 33 0.42 5 21.8 63 52.3 57 0.48 29
Classic+CPF [83]57.4 5.59 89 17.3 91 0.16 26 9.22 37 18.3 33 0.58 39 6.00 11 14.9 33 0.40 47 18.0 18 26.8 16 5.22 12 43.5 94 58.5 103 5.38 81 11.4 100 43.0 113 1.15 80 10.1 65 41.9 44 0.45 26 22.0 82 53.1 92 0.49 45
PMF [73]57.9 5.32 45 16.6 68 0.14 8 9.67 52 19.9 61 0.45 16 6.89 87 18.2 111 0.49 69 18.4 36 27.9 38 5.21 9 43.5 94 58.4 94 5.22 33 11.0 67 40.5 45 1.27 101 9.86 33 41.8 42 0.46 34 22.1 91 53.1 92 0.50 63
RFlow [90]59.4 5.19 26 16.1 49 0.23 83 10.8 82 21.2 85 0.85 79 6.59 67 16.0 66 0.51 72 18.8 66 28.8 75 5.47 69 43.1 26 58.0 31 5.21 31 10.5 12 40.0 24 0.93 25 10.0 55 42.6 74 0.49 64 22.1 91 53.2 96 0.51 77
Local-TV-L1 [65]59.5 5.29 41 14.6 8 0.35 118 11.5 99 21.1 81 1.23 110 6.39 44 14.9 33 0.37 38 19.0 80 27.9 38 6.64 116 43.3 52 58.3 81 5.33 60 10.9 53 39.0 7 1.58 127 9.79 24 41.6 37 0.48 58 21.3 11 51.5 13 0.53 99
CLG-TV [48]60.7 5.32 45 15.7 27 0.26 97 11.0 88 21.2 85 0.83 77 6.75 79 16.6 83 0.56 82 18.9 74 28.4 58 5.50 72 43.3 52 58.1 48 5.25 42 10.5 12 39.8 18 0.87 13 10.1 65 42.5 70 0.44 18 22.0 82 53.1 92 0.51 77
TriFlow [95]61.2 5.42 64 17.0 82 0.24 89 10.9 85 21.2 85 0.91 86 6.61 69 16.8 89 0.36 34 18.9 74 29.0 81 5.28 25 43.2 42 58.2 59 5.37 74 11.0 67 40.9 56 0.95 34 9.96 52 41.7 39 0.49 64 21.7 52 52.2 52 0.47 16
Classic++ [32]61.3 5.33 51 16.0 42 0.28 101 10.2 66 20.3 70 0.69 62 6.87 82 16.6 83 0.50 70 18.7 58 27.7 37 5.64 84 43.2 42 58.0 31 5.26 45 11.0 67 40.7 52 1.34 108 9.93 45 41.9 44 0.47 51 21.7 52 52.4 66 0.50 63
EPPM w/o HM [88]61.4 5.34 53 17.3 91 0.13 4 9.73 56 20.1 66 0.53 31 7.33 109 18.7 117 0.63 97 18.5 43 29.1 88 5.33 40 43.1 26 58.0 31 5.20 29 11.0 67 41.4 74 0.96 39 10.3 83 42.3 60 0.56 95 21.8 63 52.4 66 0.49 45
SIOF [67]62.1 5.64 96 16.5 63 0.28 101 11.3 94 21.6 93 0.91 86 6.32 35 15.9 61 0.42 53 18.7 58 28.4 58 5.36 48 43.0 15 57.9 22 5.17 21 10.7 27 40.2 31 0.95 34 10.1 65 42.4 63 0.50 72 22.2 100 53.2 96 0.53 99
LDOF [28]62.8 5.53 82 15.6 25 0.32 113 11.1 90 20.3 70 1.45 125 6.89 87 17.3 100 0.59 88 19.0 80 28.9 77 5.63 83 43.4 69 58.2 59 5.40 90 10.4 8 39.0 7 0.83 8 9.92 42 42.4 63 0.46 34 21.6 40 52.3 57 0.46 10
Efficient-NL [60]63.0 5.54 83 17.1 84 0.16 26 9.60 46 18.9 40 0.56 36 6.99 93 15.1 43 0.75 104 18.8 66 28.2 51 5.26 24 43.1 26 57.9 22 5.25 42 11.6 106 43.4 121 1.04 55 10.1 65 42.5 70 0.48 58 22.6 112 53.8 110 0.48 29
p-harmonic [29]63.5 5.17 24 15.5 21 0.16 26 11.2 92 21.4 89 0.94 89 6.55 60 17.4 105 0.55 81 19.2 88 28.6 69 5.45 67 43.3 52 58.2 59 5.27 50 10.7 27 40.2 31 1.04 55 10.4 91 43.4 97 0.50 72 21.8 63 52.6 70 0.49 45
Complementary OF [21]63.5 5.28 39 16.7 74 0.15 15 9.39 41 19.5 47 0.58 39 7.53 113 16.3 73 1.10 122 18.7 58 29.0 81 5.35 46 43.2 42 58.2 59 5.26 45 10.9 53 41.2 65 1.16 83 10.3 83 43.4 97 0.55 92 21.5 28 52.2 52 0.51 77
F-TV-L1 [15]63.7 5.56 84 16.0 42 0.36 121 11.4 97 21.5 91 0.94 89 6.88 84 17.0 95 0.66 98 18.7 58 27.9 38 5.79 98 42.6 3 57.8 13 5.01 7 10.6 20 39.3 12 1.02 49 10.0 55 41.9 44 0.55 92 22.0 82 52.8 79 0.51 77
CostFilter [40]64.1 5.44 66 17.7 105 0.13 4 9.64 49 20.1 66 0.45 16 6.96 91 19.1 119 0.47 68 18.5 43 28.9 77 5.13 5 43.6 108 58.5 103 5.32 59 11.1 85 40.5 45 1.48 120 9.94 49 42.1 56 0.45 26 21.8 63 52.6 70 0.49 45
OFH [38]64.4 5.49 74 16.6 68 0.25 93 10.3 71 20.2 69 0.77 70 6.88 84 17.8 107 0.36 34 18.4 36 28.9 77 5.24 20 43.1 26 58.0 31 5.26 45 10.9 53 41.5 79 1.18 86 10.3 83 43.0 90 0.58 101 21.6 40 52.1 45 0.50 63
HBM-GC [105]65.1 5.52 78 17.1 84 0.22 75 9.64 49 19.3 44 0.59 45 5.93 7 13.2 4 0.31 13 18.8 66 28.0 42 5.83 103 44.3 125 59.2 119 5.71 123 11.5 103 43.3 119 1.32 106 9.75 17 40.6 9 0.39 2 22.0 82 52.9 85 0.50 63
TC/T-Flow [76]65.3 5.73 103 17.3 91 0.22 75 9.66 51 19.7 56 0.63 52 6.24 28 14.9 33 0.32 14 18.6 49 28.7 72 5.38 51 43.5 94 58.4 94 5.50 111 11.0 67 41.4 74 0.89 18 10.2 76 43.0 90 0.58 101 21.9 74 53.0 90 0.45 4
CBF [12]65.4 4.98 6 14.8 12 0.18 46 10.2 66 19.9 61 0.71 64 6.63 76 15.2 47 0.42 53 19.0 80 28.5 63 6.39 113 43.4 69 58.3 81 5.49 109 10.7 27 40.4 41 0.95 34 10.1 65 42.6 74 0.50 72 22.3 105 53.5 106 0.53 99
Steered-L1 [118]65.7 5.12 17 16.0 42 0.17 36 9.62 48 19.5 47 0.88 81 7.15 99 15.6 55 1.00 114 19.4 93 28.5 63 6.39 113 43.5 94 58.5 103 5.19 26 10.8 42 40.8 55 1.20 90 9.95 51 42.6 74 0.52 83 21.7 52 52.6 70 0.48 29
GraphCuts [14]66.2 5.98 113 17.5 102 0.24 89 10.0 63 19.5 47 0.76 69 8.24 124 14.6 22 1.06 117 19.7 97 29.0 81 5.69 88 42.9 7 57.9 22 4.97 5 10.5 12 40.3 36 0.87 13 10.0 55 42.4 63 0.58 101 22.1 91 53.2 96 0.51 77
AdaConv-v1 [126]67.1 6.72 123 21.8 127 0.25 93 12.8 116 22.4 111 1.80 130 8.18 123 18.4 113 1.46 129 24.3 129 34.7 130 7.39 124 41.5 2 56.1 2 4.28 2 9.57 3 36.9 3 0.71 3 9.75 17 41.0 17 0.60 105 20.5 3 49.7 3 0.42 2
MLDP_OF [89]67.5 5.44 66 17.2 87 0.17 36 9.84 60 19.9 61 0.62 51 6.19 24 14.8 31 0.28 3 18.6 49 27.4 32 5.71 90 43.3 52 58.2 59 5.34 65 11.9 116 43.3 119 1.57 126 10.4 91 42.6 74 0.56 95 21.7 52 52.3 57 0.59 124
BlockOverlap [61]68.2 5.34 53 14.6 8 0.41 126 11.4 97 20.6 74 1.42 121 6.49 54 14.1 11 0.61 94 18.9 74 26.9 19 7.34 123 44.2 123 58.9 115 5.91 129 11.0 67 39.9 21 1.39 115 9.81 27 41.3 26 0.46 34 21.5 28 51.7 21 0.51 77
SRR-TVOF-NL [91]68.4 5.70 101 16.9 80 0.23 83 10.3 71 21.0 80 0.88 81 6.57 63 16.1 68 0.39 44 19.2 88 28.7 72 5.12 4 43.2 42 58.3 81 5.27 50 10.8 42 40.9 56 0.86 12 10.6 102 42.3 60 0.46 34 22.5 108 53.8 110 0.54 110
Sparse Occlusion [54]69.5 5.43 65 16.8 76 0.23 83 10.3 71 20.8 78 0.63 52 6.51 56 15.0 39 0.44 61 19.0 80 29.0 81 5.42 61 43.4 69 58.2 59 5.41 94 11.3 95 42.9 111 1.14 78 10.1 65 42.2 58 0.42 5 22.1 91 53.2 96 0.49 45
CRTflow [80]70.4 5.48 73 16.5 63 0.34 116 10.7 80 20.7 75 0.86 80 7.25 104 18.6 116 0.60 93 18.8 66 28.8 75 5.98 106 43.4 69 58.2 59 5.43 99 10.7 27 40.4 41 0.95 34 9.93 45 42.0 50 0.49 64 21.7 52 52.3 57 0.49 45
SimpleFlow [49]72.0 5.52 78 17.5 102 0.18 46 10.2 66 19.7 56 0.73 66 7.32 108 15.8 59 1.05 116 18.0 18 26.8 16 5.44 65 43.3 52 58.1 48 5.33 60 11.3 95 42.9 111 1.22 96 10.3 83 44.6 109 1.04 130 21.8 63 52.6 70 0.47 16
FlowNet2 [122]72.7 6.90 125 21.5 126 0.25 93 10.6 79 20.7 75 0.82 74 7.10 96 17.3 100 0.54 77 19.4 93 31.8 120 5.57 79 43.4 69 58.3 81 5.39 83 10.7 27 40.3 36 0.90 19 10.0 55 42.0 50 0.46 34 21.6 40 51.9 36 0.51 77
IAOF [50]73.3 5.97 112 16.8 76 0.29 106 14.1 129 24.8 129 1.41 120 6.05 16 16.2 70 0.61 94 20.1 105 29.5 96 5.47 69 43.0 15 57.8 13 5.19 26 10.7 27 40.3 36 0.94 30 10.4 91 43.3 95 0.46 34 22.0 82 52.8 79 0.54 110
Modified CLG [34]73.5 5.05 12 15.1 14 0.19 54 12.3 113 22.2 105 1.30 113 6.81 81 18.3 112 0.66 98 19.3 92 29.7 99 5.34 42 43.4 69 58.2 59 5.29 57 10.8 42 40.6 49 1.15 80 10.2 76 43.6 99 0.47 51 21.9 74 52.7 75 0.53 99
Aniso-Texture [82]74.9 5.09 15 15.7 27 0.15 15 11.1 90 21.7 94 1.00 94 7.30 107 15.9 61 0.59 88 18.7 58 28.6 69 5.90 104 43.6 108 58.4 94 5.53 114 11.6 106 44.0 126 1.44 118 9.90 39 41.4 31 0.43 11 22.1 91 53.1 92 0.49 45
FlowNetS+ft+v [112]75.3 5.40 61 15.5 21 0.29 106 11.7 105 21.7 94 1.62 127 6.88 84 17.1 97 0.56 82 19.0 80 29.2 90 5.73 94 43.5 94 58.4 94 5.56 116 10.5 12 39.9 21 0.95 34 10.1 65 42.9 87 0.52 83 21.8 63 52.5 69 0.48 29
Occlusion-TV-L1 [63]76.0 5.32 45 16.2 56 0.28 101 11.3 94 21.9 99 0.96 93 6.60 68 16.9 92 0.58 86 19.1 86 28.9 77 5.72 92 43.4 69 58.2 59 5.24 39 10.9 53 40.3 36 1.26 100 10.9 110 42.6 74 0.81 122 21.8 63 52.4 66 0.49 45
EPMNet [133]76.7 6.85 124 22.5 128 0.21 64 10.5 76 20.3 70 0.84 78 7.10 96 17.3 100 0.54 77 19.9 98 33.4 126 5.56 78 43.4 69 58.3 81 5.39 83 11.0 67 41.6 85 0.92 22 10.0 55 42.0 50 0.46 34 21.6 40 51.8 29 0.54 110
Shiralkar [42]77.2 5.73 103 18.1 111 0.21 64 11.6 101 22.0 101 0.88 81 6.74 78 19.9 123 0.73 102 20.3 108 30.1 104 5.46 68 42.6 3 57.5 4 4.99 6 11.3 95 41.5 79 1.35 109 11.0 112 44.9 112 0.67 110 21.5 28 51.7 21 0.48 29
TCOF [69]78.1 5.56 84 16.8 76 0.17 36 11.8 106 22.1 103 1.02 98 6.09 17 15.0 39 0.30 8 19.0 80 29.4 94 5.67 87 43.4 69 58.3 81 5.17 21 11.4 100 43.1 115 1.02 49 11.0 112 43.9 101 0.48 58 23.1 123 55.1 127 0.52 90
HBpMotionGpu [43]78.3 5.80 107 16.3 58 0.42 127 13.1 119 23.8 121 1.34 116 6.32 35 14.9 33 0.38 40 19.9 98 30.4 107 5.80 99 43.1 26 58.3 81 5.39 83 11.3 95 41.0 62 1.21 93 9.94 49 41.9 44 0.43 11 22.1 91 52.9 85 0.53 99
CNN-flow-warp+ref [117]78.3 4.95 5 14.4 6 0.22 75 10.9 85 21.2 85 1.23 110 7.43 111 18.0 109 0.79 106 20.9 116 29.8 100 6.84 119 43.5 94 58.3 81 5.57 117 10.7 27 40.3 36 1.22 96 10.3 83 44.4 108 0.67 110 21.6 40 52.1 45 0.47 16
Adaptive [20]79.2 5.50 76 16.7 74 0.30 108 11.8 106 22.2 105 1.02 98 6.58 66 16.5 82 0.53 76 18.6 49 28.0 42 5.60 81 43.5 94 58.3 81 5.21 31 11.0 67 41.3 70 1.09 69 10.4 91 42.8 84 0.46 34 22.2 100 53.5 106 0.54 110
3DFlow [135]79.3 5.58 88 17.4 97 0.16 26 9.35 40 19.1 41 0.61 50 6.93 90 15.0 39 0.44 61 18.6 49 28.4 58 5.54 77 43.4 69 58.2 59 5.40 90 12.1 122 44.7 134 1.35 109 11.3 119 44.6 109 0.57 98 22.4 106 53.7 109 0.50 63
Fusion [6]79.4 5.37 56 16.9 80 0.21 64 9.33 39 18.3 33 0.54 32 6.39 44 15.1 43 0.54 77 20.0 103 29.8 100 5.41 57 43.5 94 59.2 119 5.14 17 11.5 103 43.7 124 1.21 93 10.5 100 44.1 103 0.52 83 23.1 123 55.4 128 0.52 90
BriefMatch [124]81.2 5.45 68 16.5 63 0.31 112 9.84 60 19.6 53 1.43 122 7.55 114 15.6 55 1.08 119 20.3 108 29.2 90 7.97 131 43.3 52 58.3 81 5.43 99 12.0 119 41.5 79 2.37 133 9.84 31 41.5 33 0.56 95 21.4 20 51.7 21 0.52 90
Nguyen [33]81.4 5.63 95 15.9 35 0.23 83 13.8 123 23.8 121 1.37 118 6.89 87 18.7 117 0.59 88 20.8 115 30.8 111 5.44 65 43.1 26 58.1 48 5.14 17 10.6 20 40.4 41 0.93 25 11.9 130 45.9 119 0.73 118 22.0 82 52.8 79 0.52 90
2D-CLG [1]84.0 5.27 38 15.7 27 0.21 64 13.1 119 22.8 113 1.37 118 7.29 105 17.3 100 0.94 112 20.3 108 30.2 105 5.34 42 43.5 94 58.4 94 5.37 74 10.8 42 40.7 52 1.22 96 10.5 100 44.3 106 0.59 104 22.0 82 52.3 57 0.50 63
TV-L1-improved [17]84.4 5.26 36 16.0 42 0.28 101 11.6 101 22.0 101 1.06 103 7.21 102 16.3 73 0.79 106 18.8 66 28.5 63 5.70 89 43.5 94 58.5 103 5.22 33 11.0 67 41.5 79 1.05 60 10.4 91 44.6 109 0.74 120 22.1 91 53.2 96 0.53 99
SPSA-learn [13]84.5 5.45 68 15.4 18 0.25 93 11.6 101 21.4 89 1.15 107 7.65 116 16.6 83 1.26 124 20.1 105 28.2 51 5.30 29 43.3 52 58.2 59 5.42 97 10.9 53 41.0 62 1.14 78 11.6 125 50.4 135 1.71 135 22.2 100 53.3 104 0.49 45
SegOF [10]84.6 5.25 33 15.9 35 0.20 60 10.9 85 20.8 78 0.82 74 8.07 122 18.4 113 1.18 123 20.0 103 32.3 121 5.52 75 43.3 52 58.2 59 5.35 68 11.4 100 43.1 115 1.38 114 10.7 104 46.3 120 0.96 128 21.5 28 51.7 21 0.53 99
IIOF-NLDP [131]85.7 5.65 99 17.8 107 0.15 15 10.5 76 21.5 91 0.72 65 6.98 92 15.2 47 0.42 53 19.5 95 29.3 93 6.15 110 43.1 26 58.0 31 5.20 29 12.2 126 44.1 128 1.54 124 11.9 130 49.2 133 1.34 134 22.2 100 53.0 90 0.50 63
TriangleFlow [30]86.9 5.85 109 18.2 113 0.26 97 11.0 88 21.8 97 0.79 72 7.17 100 16.3 73 0.58 86 19.6 96 30.7 109 5.74 95 42.8 5 57.8 13 4.95 4 11.6 106 42.8 106 1.05 60 10.8 106 45.8 117 0.73 118 22.8 117 54.3 121 0.51 77
Black & Anandan [4]87.8 5.71 102 15.5 21 0.35 118 12.7 115 22.3 109 1.12 105 7.89 118 18.1 110 1.06 117 20.5 113 30.3 106 5.42 61 43.6 108 58.6 109 5.35 68 10.6 20 39.7 17 0.91 21 10.9 110 44.1 103 0.50 72 22.2 100 52.9 85 0.53 99
Rannacher [23]88.1 5.39 59 16.6 68 0.30 108 11.6 101 22.2 105 1.01 96 7.17 100 16.9 92 0.92 111 18.6 49 28.4 58 5.74 95 43.6 108 58.5 103 5.33 60 11.0 67 41.6 85 1.11 72 10.4 91 44.3 106 0.72 117 21.9 74 52.8 79 0.54 110
ROF-ND [107]88.6 6.15 115 16.4 60 0.14 8 10.4 75 21.1 81 0.70 63 7.09 95 15.9 61 0.40 47 20.7 114 32.9 124 5.82 101 43.4 69 58.2 59 5.37 74 11.6 106 43.4 121 1.16 83 11.6 125 46.4 121 0.55 92 22.6 112 53.8 110 0.54 110
Ad-TV-NDC [36]90.3 6.08 114 15.9 35 0.60 129 13.0 117 22.8 113 1.36 117 6.55 60 16.4 78 0.56 82 20.9 116 30.6 108 6.29 111 44.1 119 59.0 117 5.43 99 10.7 27 39.4 14 1.11 72 10.4 91 43.3 95 0.51 79 22.1 91 52.9 85 0.53 99
OFRF [134]90.9 6.29 118 18.2 113 0.38 123 11.8 106 22.3 109 1.17 109 6.61 69 17.3 100 0.43 58 19.2 88 29.4 94 5.31 32 43.4 69 58.4 94 5.35 68 11.7 113 42.8 106 1.28 102 10.4 91 43.2 93 0.49 64 22.0 82 53.3 104 0.51 77
IAOF2 [51]92.1 6.17 116 18.3 115 0.30 108 12.0 109 23.3 118 0.93 88 5.90 6 16.1 68 0.42 53 20.4 112 31.2 118 5.75 97 43.7 113 58.9 115 5.39 83 11.2 88 42.0 94 1.08 65 10.3 83 42.7 82 0.48 58 22.7 114 54.2 118 0.52 90
Correlation Flow [75]92.3 5.61 91 17.8 107 0.15 15 10.8 82 21.7 94 0.82 74 6.40 47 14.8 31 0.42 53 19.1 86 29.0 81 6.04 108 43.9 116 58.6 109 6.05 131 12.0 119 43.9 125 1.29 104 11.0 112 45.3 114 0.70 115 22.5 108 54.1 116 0.51 77
Filter Flow [19]93.3 5.64 96 16.4 60 0.32 113 12.2 112 22.2 105 1.08 104 6.61 69 16.2 70 0.57 85 20.3 108 29.0 81 6.32 112 44.1 119 59.1 118 5.74 125 10.9 53 40.7 52 1.04 55 10.2 76 43.2 93 0.54 89 22.7 114 54.3 121 0.54 110
Bartels [41]94.9 5.52 78 17.2 87 0.40 125 10.0 63 20.7 75 0.94 89 6.50 55 15.8 59 0.54 77 19.9 98 30.0 103 7.79 128 44.8 129 59.2 119 6.72 134 12.8 133 42.4 99 3.06 135 10.0 55 42.0 50 0.54 89 22.1 91 53.2 96 0.54 110
Dynamic MRF [7]95.9 5.39 59 17.4 97 0.20 60 10.5 76 21.8 97 0.74 67 7.60 115 20.3 127 0.99 113 21.3 119 31.1 116 7.06 121 43.0 15 58.1 48 5.34 65 11.6 106 43.0 113 1.49 121 10.7 104 45.8 117 0.85 123 22.5 108 53.2 96 0.55 118
LocallyOriented [52]96.1 5.79 106 17.9 109 0.26 97 12.1 111 23.2 117 1.01 96 7.05 94 17.6 106 0.51 72 19.9 98 30.9 114 5.72 92 43.3 52 58.2 59 5.23 36 11.9 116 42.6 102 1.52 123 10.8 106 44.0 102 0.53 87 22.5 108 54.0 114 0.52 90
StereoOF-V1MT [119]98.9 5.94 111 18.8 118 0.20 60 11.3 94 22.6 112 0.94 89 7.95 119 19.6 121 1.00 114 21.6 120 30.7 109 6.76 117 43.3 52 58.3 81 5.37 74 12.1 122 42.6 102 1.82 130 11.6 125 46.7 123 0.90 125 21.8 63 51.8 29 0.50 63
ACK-Prior [27]99.5 5.46 70 17.7 105 0.15 15 9.70 53 20.3 70 0.67 59 7.76 117 16.4 78 1.08 119 19.9 98 31.0 115 6.01 107 44.7 128 59.6 125 5.78 126 12.1 122 44.2 130 1.33 107 10.6 102 44.2 105 0.53 87 23.4 128 56.1 132 0.52 90
TI-DOFE [24]101.3 6.39 119 18.7 117 0.36 121 14.8 130 25.5 132 1.66 128 7.45 112 20.2 125 0.78 105 22.8 126 32.5 122 6.04 108 43.2 42 58.4 94 5.17 21 10.9 53 40.4 41 0.92 22 11.2 117 45.6 116 0.65 109 23.2 125 54.2 118 0.65 129
UnFlow [129]101.9 6.39 119 20.9 122 0.21 64 13.0 117 24.4 128 1.15 107 8.06 121 21.1 128 0.82 109 19.2 88 29.6 98 5.64 84 43.1 26 58.0 31 5.40 90 11.8 115 42.8 106 1.36 112 11.0 112 42.4 63 0.70 115 24.3 134 54.8 125 0.70 131
StereoFlow [44]102.2 10.4 135 27.1 135 0.35 118 16.3 134 28.4 135 1.03 100 6.55 60 16.8 89 0.50 70 18.8 66 28.2 51 5.38 51 45.7 134 62.1 134 5.58 118 13.6 134 50.3 135 1.28 102 10.0 55 42.4 63 0.49 64 23.0 119 55.5 129 0.56 122
2bit-BM-tele [98]102.2 5.61 91 15.9 35 0.50 128 11.5 99 21.9 99 1.04 101 6.57 63 15.1 43 0.79 106 20.1 105 29.8 100 7.50 125 44.8 129 59.6 125 6.26 132 12.2 126 42.8 106 2.11 132 11.2 117 49.2 133 1.26 132 21.8 63 52.1 45 0.55 118
Horn & Schunck [3]102.4 5.81 108 17.3 91 0.21 64 13.1 119 23.5 119 1.26 112 8.03 120 19.7 122 1.08 119 22.6 124 32.7 123 5.59 80 43.6 108 58.7 112 5.39 83 10.9 53 40.6 49 1.02 49 11.7 128 46.5 122 0.60 105 22.8 117 53.9 113 0.55 118
NL-TV-NCC [25]114.5 6.44 121 20.3 121 0.24 89 10.7 80 22.1 103 0.68 61 7.38 110 17.2 98 0.59 88 22.2 123 34.7 130 6.82 118 45.5 133 60.2 132 6.68 133 12.3 130 44.6 132 1.19 88 14.4 135 48.1 130 0.67 110 24.0 133 56.4 133 0.55 118
SILK [79]115.1 6.21 117 19.3 120 0.39 124 13.8 123 24.0 123 1.73 129 8.85 127 20.2 125 1.41 126 21.8 121 31.1 116 7.10 122 43.5 94 58.5 103 5.45 103 11.9 116 41.4 74 2.03 131 10.8 106 45.5 115 0.77 121 22.4 106 53.2 96 0.60 125
HCIC-L [99]115.3 8.84 134 25.2 133 1.06 134 14.0 127 24.1 125 1.43 122 9.42 130 19.3 120 0.69 101 24.3 129 34.1 128 6.48 115 45.1 132 60.1 130 5.86 128 12.1 122 44.1 128 1.06 62 10.2 76 42.6 74 0.51 79 23.6 130 56.0 131 0.51 77
Adaptive flow [45]115.3 7.18 129 19.2 119 0.69 130 15.0 131 25.0 130 2.11 132 7.29 105 16.7 87 0.87 110 22.6 124 31.3 119 7.85 130 44.8 129 60.2 132 5.63 120 11.7 113 43.4 121 1.36 112 10.4 91 43.7 100 0.57 98 23.0 119 54.7 124 0.50 63
Learning Flow [11]118.2 5.91 110 18.6 116 0.30 108 12.0 109 22.9 115 1.00 94 8.30 125 20.0 124 1.33 125 21.9 122 32.9 124 6.94 120 44.5 127 59.7 128 5.97 130 11.5 103 42.6 102 1.35 109 11.3 119 46.8 124 0.69 114 23.7 131 55.9 130 0.62 127
GroupFlow [9]118.8 7.04 127 22.5 128 0.28 101 12.5 114 24.0 123 1.13 106 9.10 128 22.0 130 1.45 127 21.0 118 33.6 127 5.93 105 44.1 119 59.3 123 5.50 111 12.2 126 44.4 131 1.42 117 11.1 116 45.2 113 0.61 108 22.7 114 54.1 116 0.56 122
SLK [47]120.1 6.55 122 21.1 124 0.32 113 13.5 122 23.1 116 1.44 124 9.16 129 21.2 129 1.49 131 24.9 131 34.2 129 7.81 129 43.5 94 58.8 113 5.34 65 12.2 126 43.1 115 1.45 119 11.9 130 48.9 132 0.96 128 23.0 119 54.0 114 0.64 128
Heeger++ [104]121.6 7.79 132 25.2 133 0.17 36 13.9 126 24.2 126 1.33 115 11.8 133 28.7 134 1.49 131 23.4 127 30.8 111 7.63 126 44.4 126 59.9 129 5.62 119 12.6 132 43.1 115 1.77 129 12.6 134 46.9 125 0.87 124 23.2 125 53.5 106 0.60 125
FFV1MT [106]122.2 6.93 126 22.8 130 0.24 89 14.0 127 23.5 119 1.48 126 11.2 132 27.7 133 1.52 133 23.4 127 30.8 111 7.63 126 44.0 117 59.2 119 5.69 122 12.0 119 41.6 85 1.56 125 12.1 133 47.3 128 0.95 127 23.4 128 54.2 118 0.79 133
FOLKI [16]125.1 7.10 128 21.1 124 0.94 133 15.3 132 25.5 132 2.28 133 8.49 126 22.2 131 1.47 130 26.3 133 35.2 132 10.6 134 44.0 117 59.6 125 5.54 115 11.6 106 41.8 92 1.49 121 11.4 122 47.7 129 0.90 125 23.3 127 54.9 126 0.67 130
Pyramid LK [2]126.5 7.19 130 21.0 123 0.93 132 16.2 133 25.1 131 2.91 134 14.0 134 18.5 115 2.57 134 32.5 135 46.2 135 13.7 135 44.2 123 60.1 130 5.48 107 11.6 106 42.5 101 1.40 116 11.4 122 47.2 127 1.28 133 23.7 131 56.7 134 1.08 134
PGAM+LK [55]127.0 7.51 131 23.5 132 0.73 131 13.8 123 24.2 126 1.92 131 9.44 131 22.7 132 1.45 127 26.4 134 36.9 133 10.5 133 44.1 119 59.5 124 5.72 124 12.4 131 44.0 126 1.75 128 11.3 119 47.0 126 0.68 113 23.0 119 54.5 123 0.76 132
Periodicity [78]133.4 8.05 133 23.2 131 1.34 135 20.5 135 27.4 134 3.39 135 15.2 135 30.5 135 4.22 135 26.2 132 43.5 134 9.47 132 46.4 135 62.7 135 6.92 135 13.7 135 44.6 132 2.88 134 11.4 122 48.3 131 1.18 131 25.7 135 59.2 135 1.29 135
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-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.
* 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.