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]15.6 4.93 6 13.9 5 0.13 6 8.97 30 17.1 15 0.43 10 6.00 13 13.4 7 0.27 1 17.6 4 26.2 8 5.24 22 43.0 18 57.7 12 5.17 25 10.3 8 39.1 11 0.87 17 9.75 19 41.0 19 0.44 22 21.5 36 51.9 43 0.47 18
MDP-Flow2 [68]16.6 4.89 5 14.4 7 0.12 5 8.58 12 16.9 13 0.39 3 5.95 10 13.6 9 0.28 3 17.7 5 26.7 16 5.32 40 42.9 10 57.6 8 5.13 19 10.6 24 40.1 30 0.92 26 9.75 19 41.0 19 0.43 13 21.6 48 51.9 43 0.46 12
CtxSyn [137]17.2 3.42 2 9.96 1 0.08 1 6.79 1 13.5 1 0.50 31 2.17 1 5.94 1 0.43 63 15.1 1 23.3 1 4.57 1 42.2 4 56.7 4 4.54 4 10.0 5 36.5 4 0.63 3 13.5 149 44.0 113 0.40 5 21.1 7 49.2 4 0.43 5
SepConv-v1 [127]18.1 3.41 1 11.0 3 0.08 1 8.39 8 16.7 12 1.04 112 2.81 2 7.63 2 0.74 116 18.0 19 25.2 3 5.82 112 42.9 10 57.4 5 4.74 5 9.03 2 34.1 2 0.60 2 9.34 3 38.6 2 0.42 7 20.1 2 48.6 2 0.35 1
SuperSlomo [132]18.5 3.75 3 10.1 2 0.19 64 8.96 29 16.5 8 1.31 128 3.32 3 8.42 3 0.29 7 17.7 5 24.1 2 5.32 40 41.4 2 55.9 2 4.24 2 9.50 3 35.3 3 0.67 4 10.8 117 40.3 6 0.37 2 20.4 3 48.7 3 0.42 3
NNF-Local [87]21.3 5.11 19 15.7 31 0.11 4 8.18 3 15.8 5 0.39 3 6.01 16 13.5 8 0.27 1 18.3 36 28.3 57 5.29 31 43.0 18 57.6 8 5.11 17 10.8 47 40.9 62 1.01 53 9.67 11 40.7 12 0.46 38 21.2 8 51.2 11 0.46 12
NN-field [71]21.5 5.14 23 16.1 54 0.13 6 8.21 4 15.7 4 0.38 2 6.39 49 13.6 9 0.30 8 18.4 39 28.7 74 5.33 45 42.9 10 57.6 8 5.08 14 10.7 32 40.2 36 0.94 35 9.62 8 40.5 9 0.44 22 21.2 8 51.2 11 0.45 6
FGIK [136]25.0 4.55 4 14.6 9 0.09 3 10.5 84 19.3 47 1.09 116 3.51 4 9.66 4 0.67 113 20.6 127 28.7 74 5.10 3 37.5 1 51.1 1 4.02 1 7.84 1 30.4 1 0.49 1 8.54 1 35.1 1 0.32 1 19.5 1 47.3 1 0.37 2
Layers++ [37]25.7 5.25 37 15.9 40 0.17 45 8.27 5 15.5 3 0.37 1 6.16 26 14.3 16 0.38 42 18.0 19 26.9 21 5.32 40 43.1 30 57.9 25 5.24 44 10.7 32 40.6 55 0.97 47 9.70 12 40.7 12 0.39 3 21.3 15 51.3 14 0.48 32
PH-Flow [101]28.5 5.32 50 16.4 66 0.16 34 8.28 6 15.9 6 0.44 13 6.12 23 13.9 12 0.33 17 17.5 2 25.8 4 5.15 9 42.8 8 57.5 6 5.03 11 11.0 73 41.6 94 1.09 77 9.71 13 41.0 19 0.46 38 21.3 15 51.4 17 0.50 70
nLayers [57]30.6 5.26 40 15.8 37 0.16 34 8.54 10 16.6 10 0.45 16 5.89 7 13.1 5 0.30 8 18.1 25 27.1 26 5.35 51 43.3 59 58.0 37 5.36 78 10.8 47 40.9 62 1.11 82 9.65 10 40.1 4 0.48 63 21.2 8 51.1 9 0.45 6
COFM [59]30.6 5.08 16 15.1 16 0.19 64 8.86 21 17.4 20 0.48 25 6.37 45 14.2 15 0.40 50 17.7 5 26.2 8 5.11 4 42.9 10 57.8 16 5.02 10 10.9 59 41.6 94 1.11 82 9.24 2 38.8 3 0.50 79 21.5 36 51.9 43 0.46 12
Sparse-NonSparse [56]31.0 5.31 49 16.3 64 0.17 45 8.74 16 17.2 19 0.48 25 6.19 27 14.7 28 0.34 22 17.9 14 26.3 10 5.23 19 43.1 30 57.8 16 5.25 47 11.0 73 41.2 72 1.04 61 9.71 13 40.9 16 0.46 38 21.2 8 51.3 14 0.47 18
IROF++ [58]32.7 5.37 61 16.8 82 0.14 13 8.87 23 17.4 20 0.45 16 6.41 55 14.6 25 0.43 63 17.5 2 25.8 4 5.22 14 42.9 10 57.8 16 5.19 30 10.5 15 39.4 17 0.87 17 10.0 60 42.4 69 0.47 56 21.4 27 51.5 19 0.50 70
TV-L1-MCT [64]33.5 5.74 118 18.1 121 0.18 56 9.50 47 19.1 44 0.58 44 5.73 5 14.5 23 0.38 42 17.8 10 26.0 7 5.28 29 43.0 18 57.9 25 5.22 38 10.4 10 39.1 11 0.94 35 9.78 25 41.1 25 0.44 22 21.2 8 51.1 9 0.48 32
HAST [109]34.4 5.12 20 15.2 18 0.16 34 8.74 16 17.1 15 0.43 10 6.62 81 15.3 52 0.39 46 17.7 5 26.4 12 4.98 2 43.0 18 58.0 37 5.05 12 11.0 73 41.4 82 1.06 69 9.53 4 40.4 7 0.42 7 22.0 95 52.8 92 0.47 18
ComponentFusion [96]35.9 5.15 24 16.1 54 0.14 13 8.86 21 17.9 28 0.41 6 6.38 46 15.4 53 0.33 17 17.8 10 27.0 24 5.15 9 43.2 49 58.0 37 5.24 44 10.6 24 39.8 21 0.94 35 10.0 60 42.7 88 0.57 108 21.5 36 51.8 36 0.47 18
ProbFlowFields [128]36.5 5.03 11 15.6 28 0.17 45 8.55 11 17.1 15 0.41 6 6.00 13 14.4 19 0.32 14 18.1 25 27.1 26 5.38 56 43.3 59 58.1 55 5.49 124 10.9 59 41.2 72 1.20 100 9.61 7 40.7 12 0.47 56 21.0 6 50.8 7 0.49 50
FMOF [94]36.8 5.62 104 17.2 94 0.21 76 8.71 15 17.0 14 0.44 13 6.38 46 14.7 28 0.46 72 18.6 54 28.0 44 5.31 37 43.1 30 57.9 25 5.15 23 10.8 47 40.5 51 0.87 17 9.60 6 40.4 7 0.40 5 21.5 36 51.7 28 0.46 12
2DHMM-SAS [92]40.0 5.62 104 17.6 111 0.18 56 10.1 71 19.7 61 0.64 60 5.73 5 14.4 19 0.37 40 17.7 5 25.9 6 5.30 34 43.0 18 57.8 16 5.26 50 10.7 32 40.0 28 0.82 9 9.83 31 41.3 28 0.48 63 21.6 48 52.0 48 0.47 18
CombBMOF [113]40.5 5.46 76 16.2 62 0.22 88 8.89 24 18.0 30 0.45 16 6.29 34 14.7 28 0.40 50 18.5 48 28.0 44 5.24 22 43.0 18 57.7 12 5.08 14 10.8 47 40.2 36 0.82 9 11.7 140 42.9 95 0.47 56 21.2 8 50.9 8 0.45 6
LSM [39]41.0 5.49 81 17.4 104 0.18 56 8.93 26 17.7 25 0.48 25 6.32 38 15.4 53 0.35 31 18.1 25 27.1 26 5.22 14 43.1 30 57.9 25 5.28 60 11.0 73 41.3 78 1.03 59 9.72 15 40.9 16 0.46 38 21.4 27 51.7 28 0.48 32
Ramp [62]42.8 5.46 76 17.1 91 0.18 56 8.84 19 17.4 20 0.58 44 6.14 24 14.7 28 0.34 22 17.8 10 26.4 12 5.23 19 43.2 49 58.0 37 5.27 55 11.2 97 42.0 105 1.15 90 9.72 15 40.9 16 0.42 7 21.6 48 52.1 55 0.48 32
DeepFlow [86]43.3 5.06 15 14.6 9 0.19 64 9.80 61 19.5 52 0.75 76 6.45 58 16.6 88 0.35 31 18.7 64 27.6 37 5.41 65 43.4 76 58.0 37 5.37 81 10.3 8 38.3 7 0.99 48 9.83 31 41.8 45 0.43 13 21.3 15 51.6 26 0.48 32
NNF-EAC [103]43.8 5.52 85 15.7 31 0.34 130 9.27 40 18.1 32 0.48 25 6.53 65 13.8 11 0.40 50 18.2 32 27.0 24 5.71 101 43.0 18 57.7 12 5.11 17 10.4 10 39.1 11 0.83 12 9.89 40 41.6 40 0.52 93 21.7 61 52.2 62 0.49 50
DeepFlow2 [108]44.1 5.16 25 14.9 15 0.21 76 9.81 62 19.7 61 0.65 62 6.38 46 16.3 78 0.34 22 18.6 54 28.1 49 5.29 31 43.4 76 58.0 37 5.37 81 10.2 7 38.4 8 0.85 15 9.96 56 42.1 62 0.44 22 21.4 27 51.8 36 0.49 50
LME [70]44.3 5.13 22 15.8 37 0.14 13 9.15 37 18.4 41 0.51 32 6.32 38 15.7 61 0.34 22 17.9 14 27.1 26 5.34 47 43.8 128 58.8 126 5.79 142 10.8 47 41.2 72 0.93 30 9.86 36 41.3 28 0.43 13 21.3 15 51.5 19 0.47 18
SuperFlow [81]44.4 4.99 10 14.3 6 0.22 88 10.3 78 19.9 66 0.90 93 6.61 75 15.5 57 0.51 82 18.5 48 27.2 31 5.52 84 43.3 59 58.1 55 5.37 81 10.1 6 38.0 6 0.73 6 9.73 18 41.4 33 0.46 38 21.3 15 51.5 19 0.46 12
FlowFields+ [130]44.5 5.23 36 16.6 74 0.15 21 8.91 25 18.3 35 0.45 16 6.28 33 15.9 65 0.34 22 18.2 32 28.1 49 5.34 47 43.4 76 58.2 66 5.35 74 10.9 59 41.6 94 1.10 80 9.79 26 41.5 35 0.46 38 21.3 15 51.5 19 0.48 32
PGM-C [120]44.8 5.18 28 16.0 47 0.15 21 8.97 30 18.2 34 0.46 22 6.51 61 16.4 83 0.33 17 18.4 39 28.5 65 5.36 53 43.4 76 58.1 55 5.40 97 10.7 32 40.5 51 0.96 44 9.92 45 41.9 49 0.45 30 21.4 27 51.8 36 0.48 32
WLIF-Flow [93]45.0 5.25 37 16.0 47 0.15 21 9.14 36 18.1 32 0.59 50 6.29 34 14.3 16 0.34 22 17.9 14 26.3 10 5.65 97 43.1 30 57.9 25 5.26 50 11.2 97 41.9 104 1.22 106 9.82 30 41.3 28 0.44 22 21.7 61 52.2 62 0.49 50
FlowFields [110]45.6 5.22 34 16.5 69 0.16 34 8.95 27 18.3 35 0.42 8 6.29 34 15.9 65 0.35 31 18.4 39 28.5 65 5.41 65 43.4 76 58.1 55 5.33 65 10.9 59 41.3 78 1.08 73 9.79 26 41.5 35 0.45 30 21.3 15 51.6 26 0.49 50
Classic+NL [31]46.1 5.56 93 17.4 104 0.22 88 8.99 32 17.6 24 0.54 36 6.02 17 14.7 28 0.36 36 18.1 25 26.8 17 5.41 65 43.1 30 58.0 37 5.23 41 11.1 91 41.5 88 1.06 69 9.72 15 41.0 19 0.46 38 21.6 48 52.0 48 0.47 18
JOF [141]47.2 5.53 89 16.9 86 0.21 76 8.65 13 16.6 10 0.48 25 6.08 19 14.0 13 0.34 22 18.1 25 26.8 17 5.59 90 43.4 76 58.2 66 5.45 113 11.1 91 41.4 82 1.04 61 9.64 9 40.6 10 0.43 13 21.6 48 52.0 48 0.48 32
DF-Auto [115]47.7 5.03 11 13.8 4 0.17 45 10.2 72 19.3 47 0.79 80 6.09 20 14.4 19 0.34 22 18.7 64 28.1 49 5.24 22 43.2 49 57.9 25 5.31 63 10.4 10 39.3 14 0.93 30 10.1 70 42.3 66 0.49 69 21.9 86 52.9 99 0.53 109
S2F-IF [123]47.9 5.22 34 16.5 69 0.15 21 8.84 19 18.0 30 0.44 13 6.27 32 15.7 61 0.33 17 18.3 36 28.3 57 5.14 8 43.4 76 58.2 66 5.41 101 11.0 73 41.5 88 1.11 82 9.91 44 41.9 49 0.47 56 21.3 15 51.5 19 0.51 84
FC-2Layers-FF [74]48.4 5.40 66 17.0 89 0.17 45 8.15 2 15.3 2 0.42 8 6.14 24 14.9 36 0.35 31 18.1 25 27.2 31 5.31 37 43.3 59 58.2 66 5.36 78 11.2 97 42.2 110 1.20 100 9.75 19 41.0 19 0.49 69 21.7 61 52.1 55 0.48 32
AGIF+OF [85]48.4 5.60 100 17.4 104 0.15 21 8.95 27 17.7 25 0.59 50 6.20 29 14.5 23 0.43 63 17.9 14 26.6 15 5.22 14 43.4 76 58.3 90 5.38 88 11.1 91 42.0 105 1.01 53 9.87 39 40.7 12 0.42 7 21.5 36 52.0 48 0.48 32
OFLAF [77]49.3 5.16 25 15.9 40 0.14 13 8.28 6 16.1 7 0.40 5 6.34 43 14.9 36 0.30 8 18.0 19 27.3 33 5.11 4 43.3 59 58.1 55 5.39 90 11.2 97 42.4 112 1.21 103 10.1 70 42.4 69 0.60 116 21.9 86 52.6 81 0.45 6
MDP-Flow [26]50.2 5.03 11 15.4 20 0.14 13 8.68 14 17.4 20 0.47 23 5.97 11 14.3 16 0.32 14 18.9 80 28.5 65 5.50 81 43.2 49 58.0 37 5.39 90 11.2 97 42.6 115 1.31 117 10.3 89 43.1 102 0.49 69 21.4 27 51.7 28 0.47 18
S2D-Matching [84]51.0 5.56 93 17.3 98 0.18 56 9.96 67 19.9 66 0.66 64 5.99 12 14.7 28 0.41 55 17.9 14 26.4 12 5.40 62 43.2 49 58.0 37 5.17 25 11.2 97 42.0 105 1.17 95 9.93 48 41.1 25 0.43 13 21.5 36 51.8 36 0.48 32
TF+OM [100]52.4 4.98 8 14.6 9 0.20 70 9.03 34 17.9 28 0.55 38 6.29 34 16.2 74 0.39 46 18.5 48 28.0 44 5.50 81 43.3 59 58.1 55 5.47 119 10.6 24 39.8 21 1.03 59 9.86 36 42.0 56 0.51 88 21.7 61 52.3 67 0.52 98
Brox et al. [5]52.8 5.33 56 15.4 20 0.19 64 10.2 72 20.1 71 0.64 60 6.61 75 17.2 103 0.46 72 18.7 64 28.2 53 5.21 11 43.4 76 58.1 55 5.27 55 10.7 32 40.1 30 0.99 48 9.90 42 42.0 56 0.45 30 21.6 48 52.1 55 0.47 18
ALD-Flow [66]53.1 5.37 61 16.1 54 0.23 96 9.53 48 19.2 46 0.57 42 6.51 61 16.7 92 0.34 22 18.2 32 27.9 40 5.32 40 43.4 76 58.3 90 5.46 116 10.7 32 39.9 25 0.99 48 9.76 24 41.2 27 0.44 22 21.8 74 52.7 88 0.47 18
ProFlow_ROB [147]53.1 5.09 17 15.4 20 0.17 45 9.40 46 19.3 47 0.55 38 6.34 43 15.4 53 0.33 17 18.4 39 28.7 74 5.39 60 43.5 103 58.3 90 5.41 101 10.4 10 39.3 14 0.79 7 10.2 81 42.9 95 0.49 69 21.8 74 52.6 81 0.49 50
CPM-Flow [116]53.8 5.20 33 16.1 54 0.16 34 8.99 32 18.3 35 0.47 23 6.42 56 16.0 70 0.30 8 18.8 72 29.2 98 5.43 72 43.4 76 58.2 66 5.44 111 10.6 24 40.1 30 1.02 55 10.0 60 42.6 80 0.45 30 21.4 27 51.8 36 0.53 109
DMF_ROB [140]53.8 5.30 47 15.8 37 0.20 70 10.2 72 20.5 79 0.73 72 7.26 114 18.0 119 0.75 117 18.9 80 28.8 80 5.40 62 43.1 30 57.9 25 5.34 70 10.5 15 39.8 21 0.92 26 9.98 58 41.5 35 0.43 13 21.3 15 51.4 17 0.47 18
SVFilterOh [111]54.2 5.32 50 15.7 31 0.21 76 8.78 18 17.1 15 0.49 30 6.40 52 14.6 25 0.38 42 18.4 39 27.1 26 5.80 110 43.8 128 58.6 121 5.65 136 10.9 59 41.0 68 1.04 61 9.54 5 40.1 4 0.43 13 21.7 61 52.2 62 0.50 70
AggregFlow [97]54.4 5.64 107 17.2 94 0.22 88 9.81 62 19.5 52 0.59 50 6.11 22 14.4 19 0.28 3 18.9 80 29.0 89 5.30 34 43.4 76 58.2 66 5.33 65 10.7 32 40.2 36 0.96 44 9.89 40 41.7 42 0.50 79 21.4 27 51.7 28 0.50 70
RNLOD-Flow [121]55.6 5.32 50 16.6 74 0.16 34 9.70 57 19.6 58 0.60 54 6.57 69 15.5 57 0.51 82 18.2 32 27.4 34 5.22 14 43.1 30 58.0 37 5.28 60 11.0 73 41.4 82 1.08 73 9.85 34 41.3 28 0.50 79 21.9 86 52.7 88 0.49 50
Second-order prior [8]56.7 5.29 45 15.3 19 0.27 113 10.8 93 21.1 89 0.78 79 7.14 107 17.8 117 0.62 107 18.6 54 28.3 57 5.21 11 42.9 10 57.7 12 5.16 24 10.5 15 39.6 19 0.93 30 10.2 81 42.8 92 0.44 22 21.6 48 52.3 67 0.49 50
IROF-TV [53]57.7 5.35 60 16.6 74 0.21 76 9.10 35 17.8 27 0.57 42 6.61 75 16.8 94 0.44 67 17.8 10 26.9 21 5.37 55 43.5 103 58.4 105 5.50 126 10.5 15 40.1 30 0.90 23 9.98 58 42.2 64 0.46 38 21.6 48 52.1 55 0.51 84
DPOF [18]58.4 5.51 84 17.9 119 0.22 88 8.45 9 16.5 8 0.43 10 6.87 91 15.1 46 0.59 98 18.9 80 29.5 104 5.43 72 42.9 10 57.8 16 5.05 12 11.0 73 40.9 62 0.84 14 10.3 89 42.5 76 0.45 30 21.9 86 52.8 92 0.48 32
TC-Flow [46]60.2 5.19 29 15.9 40 0.21 76 9.57 49 19.6 58 0.63 57 6.78 89 17.0 100 0.36 36 18.1 25 27.4 34 5.61 93 43.3 59 58.2 66 5.46 116 11.0 73 41.6 94 1.18 96 9.93 48 41.7 42 0.45 30 21.5 36 52.0 48 0.49 50
Aniso. Huber-L1 [22]60.9 5.41 68 16.0 47 0.23 96 11.2 104 21.1 89 0.90 93 6.72 84 15.4 53 0.46 72 18.5 48 28.1 49 5.39 60 43.0 18 57.8 16 5.23 41 10.5 15 40.1 30 0.81 8 10.2 81 42.6 80 0.46 38 21.9 86 52.7 88 0.52 98
OAR-Flow [125]61.0 5.28 43 15.5 24 0.18 56 9.71 59 19.5 52 0.67 65 6.43 57 16.3 78 0.28 3 18.0 19 27.6 37 5.23 19 43.5 103 58.4 105 5.48 122 10.9 59 41.3 78 1.13 87 10.2 81 42.9 95 0.51 88 21.7 61 52.3 67 0.45 6
EpicFlow [102]61.5 5.19 29 16.1 54 0.15 21 9.60 50 19.8 65 0.58 44 6.40 52 16.4 83 0.35 31 18.6 54 29.1 96 5.47 78 43.4 76 58.2 66 5.42 105 10.8 47 41.2 72 1.08 73 10.1 70 42.5 76 0.54 99 21.5 36 52.0 48 0.49 50
ComplOF-FED-GPU [35]61.5 5.30 47 16.1 54 0.19 64 9.39 44 19.3 47 0.58 44 7.21 111 16.9 97 0.66 110 18.4 39 28.6 71 5.32 40 43.1 30 58.0 37 5.27 55 10.8 47 40.9 62 0.99 48 10.1 70 42.8 92 0.47 56 21.8 74 52.3 67 0.50 70
FF++_ROB [146]62.7 5.19 29 16.1 54 0.13 6 9.36 43 19.0 43 0.51 32 6.52 64 16.2 74 0.46 72 18.6 54 28.8 80 5.41 65 43.4 76 58.2 66 5.44 111 11.3 105 41.2 72 1.71 141 9.85 34 41.8 45 0.49 69 21.3 15 51.5 19 0.57 136
FESL [72]63.2 5.65 110 17.3 98 0.17 45 9.18 38 18.3 35 0.55 38 6.22 30 15.0 42 0.44 67 18.8 72 28.4 60 5.38 56 43.4 76 58.2 66 5.41 101 11.3 105 42.8 119 1.19 98 9.92 45 41.5 35 0.42 7 21.8 74 52.3 67 0.48 32
Classic+CPF [83]63.8 5.59 98 17.3 98 0.16 34 9.22 39 18.3 35 0.58 44 6.00 13 14.9 36 0.40 50 18.0 19 26.8 17 5.22 14 43.5 103 58.5 114 5.38 88 11.4 112 43.0 128 1.15 90 10.1 70 41.9 49 0.45 30 22.0 95 53.1 106 0.49 50
PMF [73]64.4 5.32 50 16.6 74 0.14 13 9.67 56 19.9 66 0.45 16 6.89 96 18.2 123 0.49 79 18.4 39 27.9 40 5.21 11 43.5 103 58.4 105 5.22 38 11.0 73 40.5 51 1.27 113 9.86 36 41.8 45 0.46 38 22.1 104 53.1 106 0.50 70
Local-TV-L1 [65]66.1 5.29 45 14.6 9 0.35 132 11.5 111 21.1 89 1.23 123 6.39 49 14.9 36 0.37 40 19.0 87 27.9 40 6.64 131 43.3 59 58.3 90 5.33 65 10.9 59 39.0 9 1.58 140 9.79 26 41.6 40 0.48 63 21.3 15 51.5 19 0.53 109
RFlow [90]66.3 5.19 29 16.1 54 0.23 96 10.8 93 21.2 93 0.85 88 6.59 73 16.0 70 0.51 82 18.8 72 28.8 80 5.47 78 43.1 30 58.0 37 5.21 36 10.5 15 40.0 28 0.93 30 10.0 60 42.6 80 0.49 69 22.1 104 53.2 110 0.51 84
PWC-Net_ROB [148]67.2 5.47 79 18.4 126 0.13 6 9.99 68 20.9 86 0.53 34 6.74 85 17.5 111 0.41 55 18.3 36 28.8 80 5.25 26 43.5 103 58.3 90 5.45 113 11.2 97 41.0 68 1.22 106 9.93 48 41.8 45 0.46 38 21.3 15 51.3 14 0.51 84
CLG-TV [48]67.7 5.32 50 15.7 31 0.26 110 11.0 100 21.2 93 0.83 86 6.75 87 16.6 88 0.56 92 18.9 80 28.4 60 5.50 81 43.3 59 58.1 55 5.25 47 10.5 15 39.8 21 0.87 17 10.1 70 42.5 76 0.44 22 22.0 95 53.1 106 0.51 84
TriFlow [95]67.7 5.42 69 17.0 89 0.24 102 10.9 96 21.2 93 0.91 95 6.61 75 16.8 94 0.36 36 18.9 80 29.0 89 5.28 29 43.2 49 58.2 66 5.37 81 11.0 73 40.9 62 0.95 39 9.96 56 41.7 42 0.49 69 21.7 61 52.2 62 0.47 18
EPPM w/o HM [88]68.1 5.34 58 17.3 98 0.13 6 9.73 60 20.1 71 0.53 34 7.33 120 18.7 130 0.63 108 18.5 48 29.1 96 5.33 45 43.1 30 58.0 37 5.20 33 11.0 73 41.4 82 0.96 44 10.3 89 42.3 66 0.56 105 21.8 74 52.4 77 0.49 50
Classic++ [32]68.2 5.33 56 16.0 47 0.28 114 10.2 72 20.3 75 0.69 68 6.87 91 16.6 88 0.50 80 18.7 64 27.7 39 5.64 95 43.2 49 58.0 37 5.26 50 11.0 73 40.7 58 1.34 120 9.93 48 41.9 49 0.47 56 21.7 61 52.4 77 0.50 70
SIOF [67]69.1 5.64 107 16.5 69 0.28 114 11.3 106 21.6 104 0.91 95 6.32 38 15.9 65 0.42 58 18.7 64 28.4 60 5.36 53 43.0 18 57.9 25 5.17 25 10.7 32 40.2 36 0.95 39 10.1 70 42.4 69 0.50 79 22.2 114 53.2 110 0.53 109
LDOF [28]69.8 5.53 89 15.6 28 0.32 126 11.1 102 20.3 75 1.45 140 6.89 96 17.3 105 0.59 98 19.0 87 28.9 85 5.63 94 43.4 76 58.2 66 5.40 97 10.4 10 39.0 9 0.83 12 9.92 45 42.4 69 0.46 38 21.6 48 52.3 67 0.46 12
Efficient-NL [60]69.8 5.54 91 17.1 91 0.16 34 9.60 50 18.9 42 0.56 41 6.99 102 15.1 46 0.75 117 18.8 72 28.2 53 5.26 27 43.1 30 57.9 25 5.25 47 11.6 118 43.4 136 1.04 61 10.1 70 42.5 76 0.48 63 22.6 126 53.8 124 0.48 32
p-harmonic [29]70.6 5.17 27 15.5 24 0.16 34 11.2 104 21.4 98 0.94 100 6.55 66 17.4 110 0.55 91 19.2 96 28.6 71 5.45 76 43.3 59 58.2 66 5.27 55 10.7 32 40.2 36 1.04 61 10.4 97 43.4 107 0.50 79 21.8 74 52.6 81 0.49 50
Complementary OF [21]70.7 5.28 43 16.7 80 0.15 21 9.39 44 19.5 52 0.58 44 7.53 125 16.3 78 1.10 136 18.7 64 29.0 89 5.35 51 43.2 49 58.2 66 5.26 50 10.9 59 41.2 72 1.16 93 10.3 89 43.4 107 0.55 102 21.5 36 52.2 62 0.51 84
CostFilter [40]70.8 5.44 71 17.7 113 0.13 6 9.64 53 20.1 71 0.45 16 6.96 100 19.1 132 0.47 76 18.5 48 28.9 85 5.13 7 43.6 119 58.5 114 5.32 64 11.1 91 40.5 51 1.48 132 9.94 53 42.1 62 0.45 30 21.8 74 52.6 81 0.49 50
F-TV-L1 [15]71.1 5.56 93 16.0 47 0.36 136 11.4 109 21.5 101 0.94 100 6.88 93 17.0 100 0.66 110 18.7 64 27.9 40 5.79 109 42.6 5 57.8 16 5.01 9 10.6 24 39.3 14 1.02 55 10.0 60 41.9 49 0.55 102 22.0 95 52.8 92 0.51 84
OFH [38]71.5 5.49 81 16.6 74 0.25 106 10.3 78 20.2 74 0.77 78 6.88 93 17.8 117 0.36 36 18.4 39 28.9 85 5.24 22 43.1 30 58.0 37 5.26 50 10.9 59 41.5 88 1.18 96 10.3 89 43.0 99 0.58 111 21.6 48 52.1 55 0.50 70
TC/T-Flow [76]72.4 5.73 116 17.3 98 0.22 88 9.66 55 19.7 61 0.63 57 6.24 31 14.9 36 0.32 14 18.6 54 28.7 74 5.38 56 43.5 103 58.4 105 5.50 126 11.0 73 41.4 82 0.89 22 10.2 81 43.0 99 0.58 111 21.9 86 53.0 104 0.45 6
CBF [12]72.5 4.98 8 14.8 14 0.18 56 10.2 72 19.9 66 0.71 70 6.63 82 15.2 50 0.42 58 19.0 87 28.5 65 6.39 127 43.4 76 58.3 90 5.49 124 10.7 32 40.4 46 0.95 39 10.1 70 42.6 80 0.50 79 22.3 119 53.5 120 0.53 109
HBM-GC [105]72.8 5.52 85 17.1 91 0.22 88 9.64 53 19.3 47 0.59 50 5.93 9 13.2 6 0.31 13 18.8 72 28.0 44 5.83 114 44.3 140 59.2 133 5.71 138 11.5 115 43.3 134 1.32 118 9.75 19 40.6 10 0.39 3 22.0 95 52.9 99 0.50 70
LFNet_ROB [151]72.8 5.45 73 17.6 111 0.13 6 10.4 82 21.2 93 0.73 72 6.75 87 18.1 121 0.47 76 18.4 39 28.7 74 5.27 28 43.1 30 58.0 37 5.20 33 11.1 91 41.8 102 1.10 80 10.4 97 42.7 88 0.50 79 21.7 61 52.0 48 0.60 139
Steered-L1 [118]73.0 5.12 20 16.0 47 0.17 45 9.62 52 19.5 52 0.88 90 7.15 108 15.6 59 1.00 128 19.4 103 28.5 65 6.39 127 43.5 103 58.5 114 5.19 30 10.8 47 40.8 61 1.20 100 9.95 55 42.6 80 0.52 93 21.7 61 52.6 81 0.48 32
GraphCuts [14]74.1 5.98 126 17.5 109 0.24 102 10.0 69 19.5 52 0.76 77 8.24 138 14.6 25 1.06 131 19.7 108 29.0 89 5.69 99 42.9 10 57.9 25 4.97 7 10.5 15 40.3 41 0.87 17 10.0 60 42.4 69 0.58 111 22.1 104 53.2 110 0.51 84
ContFlow_ROB [150]74.3 5.59 98 17.8 115 0.16 34 10.6 88 21.4 98 0.92 97 7.33 120 18.2 123 0.41 55 19.1 93 30.2 114 5.29 31 43.0 18 57.9 25 5.14 20 11.1 91 42.1 109 1.00 52 10.4 97 41.9 49 0.51 88 21.4 27 51.9 43 0.52 98
MLDP_OF [89]74.8 5.44 71 17.2 94 0.17 45 9.84 64 19.9 66 0.62 56 6.19 27 14.8 34 0.28 3 18.6 54 27.4 34 5.71 101 43.3 59 58.2 66 5.34 70 11.9 129 43.3 134 1.57 139 10.4 97 42.6 80 0.56 105 21.7 61 52.3 67 0.59 138
AdaConv-v1 [126]75.2 6.72 138 21.8 142 0.25 106 12.8 129 22.4 123 1.80 145 8.18 137 18.4 126 1.46 143 24.3 143 34.7 145 7.39 139 41.5 3 56.1 3 4.28 3 9.57 4 36.9 5 0.71 5 9.75 19 41.0 19 0.60 116 20.5 4 49.7 5 0.42 3
SRR-TVOF-NL [91]75.6 5.70 113 16.9 86 0.23 96 10.3 78 21.0 88 0.88 90 6.57 69 16.1 72 0.39 46 19.2 96 28.7 74 5.12 6 43.2 49 58.3 90 5.27 55 10.8 47 40.9 62 0.86 16 10.6 112 42.3 66 0.46 38 22.5 122 53.8 124 0.54 120
BlockOverlap [61]76.2 5.34 58 14.6 9 0.41 141 11.4 109 20.6 80 1.42 136 6.49 59 14.1 14 0.61 105 18.9 80 26.9 21 7.34 138 44.2 138 58.9 129 5.91 144 11.0 73 39.9 25 1.39 127 9.81 29 41.3 28 0.46 38 21.5 36 51.7 28 0.51 84
Sparse Occlusion [54]77.0 5.43 70 16.8 82 0.23 96 10.3 78 20.8 84 0.63 57 6.51 61 15.0 42 0.44 67 19.0 87 29.0 89 5.42 70 43.4 76 58.2 66 5.41 101 11.3 105 42.9 125 1.14 88 10.1 70 42.2 64 0.42 7 22.1 104 53.2 110 0.49 50
CRTflow [80]78.1 5.48 80 16.5 69 0.34 130 10.7 91 20.7 81 0.86 89 7.25 113 18.6 129 0.60 103 18.8 72 28.8 80 5.98 119 43.4 76 58.2 66 5.43 108 10.7 32 40.4 46 0.95 39 9.93 48 42.0 56 0.49 69 21.7 61 52.3 67 0.49 50
LiteFlowNet [143]79.4 5.61 101 18.9 131 0.15 21 9.94 66 20.9 86 0.65 62 6.33 42 17.5 111 0.39 46 19.2 96 30.9 126 5.94 118 43.1 30 57.9 25 5.36 78 11.3 105 42.2 110 1.06 69 10.7 114 43.5 109 0.62 120 21.2 8 51.2 11 0.54 120
SimpleFlow [49]80.0 5.52 85 17.5 109 0.18 56 10.2 72 19.7 61 0.73 72 7.32 119 15.8 63 1.05 130 18.0 19 26.8 17 5.44 74 43.3 59 58.1 55 5.33 65 11.3 105 42.9 125 1.22 106 10.3 89 44.6 122 1.04 145 21.8 74 52.6 81 0.47 18
AugFNG_ROB [144]80.4 5.68 112 18.7 128 0.15 21 10.9 96 21.8 108 0.93 98 7.28 115 20.6 141 0.48 78 19.3 101 30.7 119 5.40 62 43.6 119 58.6 121 5.47 119 10.6 24 40.1 30 0.82 9 10.5 108 43.0 99 0.50 79 20.9 5 50.7 6 0.48 32
FlowNet2 [122]80.9 6.90 140 21.5 141 0.25 106 10.6 88 20.7 81 0.82 83 7.10 105 17.3 105 0.54 87 19.4 103 31.8 133 5.57 88 43.4 76 58.3 90 5.39 90 10.7 32 40.3 41 0.90 23 10.0 60 42.0 56 0.46 38 21.6 48 51.9 43 0.51 84
IAOF [50]81.8 5.97 125 16.8 82 0.29 119 14.1 144 24.8 144 1.41 135 6.05 18 16.2 74 0.61 105 20.1 116 29.5 104 5.47 78 43.0 18 57.8 16 5.19 30 10.7 32 40.3 41 0.94 35 10.4 97 43.3 105 0.46 38 22.0 95 52.8 92 0.54 120
Modified CLG [34]82.0 5.05 14 15.1 16 0.19 64 12.3 125 22.2 117 1.30 127 6.81 90 18.3 125 0.66 110 19.3 101 29.7 107 5.34 47 43.4 76 58.2 66 5.29 62 10.8 47 40.6 55 1.15 90 10.2 81 43.6 110 0.47 56 21.9 86 52.7 88 0.53 109
Aniso-Texture [82]83.4 5.09 17 15.7 31 0.15 21 11.1 102 21.7 105 1.00 105 7.30 118 15.9 65 0.59 98 18.7 64 28.6 71 5.90 115 43.6 119 58.4 105 5.53 129 11.6 118 44.0 141 1.44 130 9.90 42 41.4 33 0.43 13 22.1 104 53.1 106 0.49 50
FlowNetS+ft+v [112]83.8 5.40 66 15.5 24 0.29 119 11.7 117 21.7 105 1.62 142 6.88 93 17.1 102 0.56 92 19.0 87 29.2 98 5.73 105 43.5 103 58.4 105 5.56 131 10.5 15 39.9 25 0.95 39 10.1 70 42.9 95 0.52 93 21.8 74 52.5 80 0.48 32
Occlusion-TV-L1 [63]84.6 5.32 50 16.2 62 0.28 114 11.3 106 21.9 111 0.96 104 6.60 74 16.9 97 0.58 96 19.1 93 28.9 85 5.72 103 43.4 76 58.2 66 5.24 44 10.9 59 40.3 41 1.26 112 10.9 121 42.6 80 0.81 136 21.8 74 52.4 77 0.49 50
EPMNet [133]85.2 6.85 139 22.5 143 0.21 76 10.5 84 20.3 75 0.84 87 7.10 105 17.3 105 0.54 87 19.9 109 33.4 141 5.56 87 43.4 76 58.3 90 5.39 90 11.0 73 41.6 94 0.92 26 10.0 60 42.0 56 0.46 38 21.6 48 51.8 36 0.54 120
Shiralkar [42]86.5 5.73 116 18.1 121 0.21 76 11.6 113 22.0 113 0.88 90 6.74 85 19.9 136 0.73 115 20.3 119 30.1 113 5.46 77 42.6 5 57.5 6 4.99 8 11.3 105 41.5 88 1.35 121 11.0 124 44.9 125 0.67 123 21.5 36 51.7 28 0.48 32
TCOF [69]86.8 5.56 93 16.8 82 0.17 45 11.8 118 22.1 115 1.02 109 6.09 20 15.0 42 0.30 8 19.0 87 29.4 102 5.67 98 43.4 76 58.3 90 5.17 25 11.4 112 43.1 130 1.02 55 11.0 124 43.9 112 0.48 63 23.1 137 55.1 142 0.52 98
HBpMotionGpu [43]87.0 5.80 120 16.3 64 0.42 142 13.1 132 23.8 135 1.34 130 6.32 38 14.9 36 0.38 42 19.9 109 30.4 117 5.80 110 43.1 30 58.3 90 5.39 90 11.3 105 41.0 68 1.21 103 9.94 53 41.9 49 0.43 13 22.1 104 52.9 99 0.53 109
Adaptive [20]87.5 5.50 83 16.7 80 0.30 121 11.8 118 22.2 117 1.02 109 6.58 72 16.5 87 0.53 86 18.6 54 28.0 44 5.60 92 43.5 103 58.3 90 5.21 36 11.0 73 41.3 78 1.09 77 10.4 97 42.8 92 0.46 38 22.2 114 53.5 120 0.54 120
3DFlow [135]87.6 5.58 97 17.4 104 0.16 34 9.35 42 19.1 44 0.61 55 6.93 99 15.0 42 0.44 67 18.6 54 28.4 60 5.54 86 43.4 76 58.2 66 5.40 97 12.1 136 44.7 149 1.35 121 11.3 131 44.6 122 0.57 108 22.4 120 53.7 123 0.50 70
CNN-flow-warp+ref [117]87.8 4.95 7 14.4 7 0.22 88 10.9 96 21.2 93 1.23 123 7.43 123 18.0 119 0.79 120 20.9 130 29.8 109 6.84 134 43.5 103 58.3 90 5.57 132 10.7 32 40.3 41 1.22 106 10.3 89 44.4 120 0.67 123 21.6 48 52.1 55 0.47 18
Fusion [6]88.0 5.37 61 16.9 86 0.21 76 9.33 41 18.3 35 0.54 36 6.39 49 15.1 46 0.54 87 20.0 114 29.8 109 5.41 65 43.5 103 59.2 133 5.14 20 11.5 115 43.7 139 1.21 103 10.5 108 44.1 115 0.52 93 23.1 137 55.4 143 0.52 98
BriefMatch [124]90.0 5.45 73 16.5 69 0.31 125 9.84 64 19.6 58 1.43 137 7.55 127 15.6 59 1.08 133 20.3 119 29.2 98 7.97 146 43.3 59 58.3 90 5.43 108 12.0 133 41.5 88 2.37 147 9.84 33 41.5 35 0.56 105 21.4 27 51.7 28 0.52 98
ResPWCR_ROB [145]90.4 5.54 91 17.8 115 0.20 70 10.6 88 21.5 101 0.80 82 7.77 131 17.7 116 0.44 67 19.4 103 30.7 119 5.93 116 42.7 7 57.6 8 5.10 16 12.4 145 41.7 101 2.49 148 10.9 121 42.7 88 0.58 111 21.7 61 52.3 67 0.52 98
Nguyen [33]91.4 5.63 106 15.9 40 0.23 96 13.8 138 23.8 135 1.37 132 6.89 96 18.7 130 0.59 98 20.8 129 30.8 123 5.44 74 43.1 30 58.1 55 5.14 20 10.6 24 40.4 46 0.93 30 11.9 142 45.9 132 0.73 132 22.0 95 52.8 92 0.52 98
2D-CLG [1]93.2 5.27 42 15.7 31 0.21 76 13.1 132 22.8 125 1.37 132 7.29 116 17.3 105 0.94 126 20.3 119 30.2 114 5.34 47 43.5 103 58.4 105 5.37 81 10.8 47 40.7 58 1.22 106 10.5 108 44.3 118 0.59 115 22.0 95 52.3 67 0.50 70
TV-L1-improved [17]93.6 5.26 40 16.0 47 0.28 114 11.6 113 22.0 113 1.06 114 7.21 111 16.3 78 0.79 120 18.8 72 28.5 65 5.70 100 43.5 103 58.5 114 5.22 38 11.0 73 41.5 88 1.05 67 10.4 97 44.6 122 0.74 134 22.1 104 53.2 110 0.53 109
SPSA-learn [13]93.8 5.45 73 15.4 20 0.25 106 11.6 113 21.4 98 1.15 120 7.65 129 16.6 88 1.26 138 20.1 116 28.2 53 5.30 34 43.3 59 58.2 66 5.42 105 10.9 59 41.0 68 1.14 88 11.6 137 50.4 150 1.71 150 22.2 114 53.3 118 0.49 50
SegOF [10]94.6 5.25 37 15.9 40 0.20 70 10.9 96 20.8 84 0.82 83 8.07 136 18.4 126 1.18 137 20.0 114 32.3 135 5.52 84 43.3 59 58.2 66 5.35 74 11.4 112 43.1 130 1.38 126 10.7 114 46.3 133 0.96 142 21.5 36 51.7 28 0.53 109
IIOF-NLDP [131]95.3 5.65 110 17.8 115 0.15 21 10.5 84 21.5 101 0.72 71 6.98 101 15.2 50 0.42 58 19.5 106 29.3 101 6.15 123 43.1 30 58.0 37 5.20 33 12.2 140 44.1 143 1.54 136 11.9 142 49.2 148 1.34 149 22.2 114 53.0 104 0.50 70
TriangleFlow [30]96.8 5.85 122 18.2 123 0.26 110 11.0 100 21.8 108 0.79 80 7.17 109 16.3 78 0.58 96 19.6 107 30.7 119 5.74 106 42.8 8 57.8 16 4.95 6 11.6 118 42.8 119 1.05 67 10.8 117 45.8 130 0.73 132 22.8 131 54.3 136 0.51 84
Rannacher [23]97.4 5.39 64 16.6 74 0.30 121 11.6 113 22.2 117 1.01 107 7.17 109 16.9 97 0.92 125 18.6 54 28.4 60 5.74 106 43.6 119 58.5 114 5.33 65 11.0 73 41.6 94 1.11 82 10.4 97 44.3 118 0.72 131 21.9 86 52.8 92 0.54 120
Black & Anandan [4]98.0 5.71 114 15.5 24 0.35 132 12.7 128 22.3 121 1.12 117 7.89 132 18.1 121 1.06 131 20.5 125 30.3 116 5.42 70 43.6 119 58.6 121 5.35 74 10.6 24 39.7 20 0.91 25 10.9 121 44.1 115 0.50 79 22.2 114 52.9 99 0.53 109
ROF-ND [107]98.2 6.15 128 16.4 66 0.14 13 10.4 82 21.1 89 0.70 69 7.09 104 15.9 65 0.40 50 20.7 128 32.9 138 5.82 112 43.4 76 58.2 66 5.37 81 11.6 118 43.4 136 1.16 93 11.6 137 46.4 134 0.55 102 22.6 126 53.8 124 0.54 120
TVL1_ROB [139]99.0 5.72 115 15.6 28 0.35 132 13.7 137 23.8 135 1.40 134 6.64 83 17.6 113 0.60 103 20.5 125 29.7 107 5.58 89 43.6 119 58.5 114 5.42 105 10.8 47 40.4 46 1.09 77 10.5 108 44.5 121 0.65 121 21.9 86 52.6 81 0.49 50
OFRF [134]100.4 6.29 131 18.2 123 0.38 138 11.8 118 22.3 121 1.17 122 6.61 75 17.3 105 0.43 63 19.2 96 29.4 102 5.31 37 43.4 76 58.4 105 5.35 74 11.7 125 42.8 119 1.28 114 10.4 97 43.2 103 0.49 69 22.0 95 53.3 118 0.51 84
Ad-TV-NDC [36]100.7 6.08 127 15.9 40 0.60 144 13.0 130 22.8 125 1.36 131 6.55 66 16.4 83 0.56 92 20.9 130 30.6 118 6.29 125 44.1 134 59.0 131 5.43 108 10.7 32 39.4 17 1.11 82 10.4 97 43.3 105 0.51 88 22.1 104 52.9 99 0.53 109
IAOF2 [51]101.9 6.17 129 18.3 125 0.30 121 12.0 121 23.3 131 0.93 98 5.90 8 16.1 72 0.42 58 20.4 124 31.2 131 5.75 108 43.7 127 58.9 129 5.39 90 11.2 97 42.0 105 1.08 73 10.3 89 42.7 88 0.48 63 22.7 128 54.2 133 0.52 98
Correlation Flow [75]102.8 5.61 101 17.8 115 0.15 21 10.8 93 21.7 105 0.82 83 6.40 52 14.8 34 0.42 58 19.1 93 29.0 89 6.04 121 43.9 130 58.6 121 6.05 146 12.0 133 43.9 140 1.29 116 11.0 124 45.3 127 0.70 128 22.5 122 54.1 131 0.51 84
Filter Flow [19]103.5 5.64 107 16.4 66 0.32 126 12.2 124 22.2 117 1.08 115 6.61 75 16.2 74 0.57 95 20.3 119 29.0 89 6.32 126 44.1 134 59.1 132 5.74 140 10.9 59 40.7 58 1.04 61 10.2 81 43.2 103 0.54 99 22.7 128 54.3 136 0.54 120
Bartels [41]105.3 5.52 85 17.2 94 0.40 140 10.0 69 20.7 81 0.94 100 6.50 60 15.8 63 0.54 87 19.9 109 30.0 112 7.79 143 44.8 144 59.2 133 6.72 149 12.8 148 42.4 112 3.06 150 10.0 60 42.0 56 0.54 99 22.1 104 53.2 110 0.54 120
Dynamic MRF [7]106.8 5.39 64 17.4 104 0.20 70 10.5 84 21.8 108 0.74 75 7.60 128 20.3 140 0.99 127 21.3 133 31.1 129 7.06 136 43.0 18 58.1 55 5.34 70 11.6 118 43.0 128 1.49 133 10.7 114 45.8 130 0.85 137 22.5 122 53.2 110 0.55 129
LocallyOriented [52]106.8 5.79 119 17.9 119 0.26 110 12.1 123 23.2 129 1.01 107 7.05 103 17.6 113 0.51 82 19.9 109 30.9 126 5.72 103 43.3 59 58.2 66 5.23 41 11.9 129 42.6 115 1.52 135 10.8 117 44.0 113 0.53 97 22.5 122 54.0 129 0.52 98
ACK-Prior [27]110.3 5.46 76 17.7 113 0.15 21 9.70 57 20.3 75 0.67 65 7.76 130 16.4 83 1.08 133 19.9 109 31.0 128 6.01 120 44.7 143 59.6 140 5.78 141 12.1 136 44.2 145 1.33 119 10.6 112 44.2 117 0.53 97 23.4 142 56.1 147 0.52 98
StereoOF-V1MT [119]110.5 5.94 124 18.8 130 0.20 70 11.3 106 22.6 124 0.94 100 7.95 133 19.6 134 1.00 128 21.6 134 30.7 119 6.76 132 43.3 59 58.3 90 5.37 81 12.1 136 42.6 115 1.82 144 11.6 137 46.7 137 0.90 139 21.8 74 51.8 36 0.50 70
TI-DOFE [24]113.1 6.39 132 18.7 128 0.36 136 14.8 145 25.5 147 1.66 143 7.45 124 20.2 138 0.78 119 22.8 140 32.5 136 6.04 121 43.2 49 58.4 105 5.17 25 10.9 59 40.4 46 0.92 26 11.2 129 45.6 129 0.65 121 23.2 139 54.2 133 0.65 144
StereoFlow [44]113.2 10.4 150 27.1 150 0.35 132 16.3 149 28.4 150 1.03 111 6.55 66 16.8 94 0.50 80 18.8 72 28.2 53 5.38 56 45.7 149 62.1 149 5.58 133 13.6 149 50.3 150 1.28 114 10.0 60 42.4 69 0.49 69 23.0 133 55.5 144 0.56 134
UnFlow [129]113.5 6.39 132 20.9 135 0.21 76 13.0 130 24.4 143 1.15 120 8.06 135 21.1 142 0.82 123 19.2 96 29.6 106 5.64 95 43.1 30 58.0 37 5.40 97 11.8 128 42.8 119 1.36 124 11.0 124 42.4 69 0.70 128 24.3 149 54.8 140 0.70 146
Horn & Schunck [3]113.9 5.81 121 17.3 98 0.21 76 13.1 132 23.5 133 1.26 125 8.03 134 19.7 135 1.08 133 22.6 138 32.7 137 5.59 90 43.6 119 58.7 125 5.39 90 10.9 59 40.6 55 1.02 55 11.7 140 46.5 135 0.60 116 22.8 131 53.9 127 0.55 129
2bit-BM-tele [98]114.0 5.61 101 15.9 40 0.50 143 11.5 111 21.9 111 1.04 112 6.57 69 15.1 46 0.79 120 20.1 116 29.8 109 7.50 140 44.8 144 59.6 140 6.26 147 12.2 140 42.8 119 2.11 146 11.2 129 49.2 148 1.26 147 21.8 74 52.1 55 0.55 129
WOLF_ROB [149]125.0 6.71 137 21.0 136 0.32 126 12.5 126 23.2 129 1.12 117 7.54 126 17.6 113 0.65 109 20.3 119 33.1 140 6.43 129 43.6 119 58.8 126 5.47 119 11.9 129 42.8 119 1.56 137 12.1 145 46.5 135 0.71 130 22.1 104 52.8 92 0.58 137
NL-TV-NCC [25]127.3 6.44 134 20.3 134 0.24 102 10.7 91 22.1 115 0.68 67 7.38 122 17.2 103 0.59 98 22.2 137 34.7 145 6.82 133 45.5 148 60.2 147 6.68 148 12.3 144 44.6 147 1.19 98 14.4 150 48.1 144 0.67 123 24.0 148 56.4 148 0.55 129
Adaptive flow [45]128.1 7.18 144 19.2 132 0.69 145 15.0 146 25.0 145 2.11 147 7.29 116 16.7 92 0.87 124 22.6 138 31.3 132 7.85 145 44.8 144 60.2 147 5.63 135 11.7 125 43.4 136 1.36 124 10.4 97 43.7 111 0.57 108 23.0 133 54.7 139 0.50 70
SILK [79]128.2 6.21 130 19.3 133 0.39 139 13.8 138 24.0 138 1.73 144 8.85 141 20.2 138 1.41 140 21.8 135 31.1 129 7.10 137 43.5 103 58.5 114 5.45 113 11.9 129 41.4 82 2.03 145 10.8 117 45.5 128 0.77 135 22.4 120 53.2 110 0.60 139
HCIC-L [99]128.3 8.84 149 25.2 148 1.06 149 14.0 142 24.1 140 1.43 137 9.42 144 19.3 133 0.69 114 24.3 143 34.1 143 6.48 130 45.1 147 60.1 145 5.86 143 12.1 136 44.1 143 1.06 69 10.2 81 42.6 80 0.51 88 23.6 145 56.0 146 0.51 84
H+S_ROB [138]129.2 6.50 135 21.0 136 0.14 13 13.6 136 23.3 131 1.26 125 9.85 146 24.2 147 1.51 147 26.5 149 32.2 134 6.19 124 43.9 130 59.3 137 5.46 116 11.7 125 42.9 125 1.23 111 12.1 145 48.5 146 1.02 144 23.5 144 53.9 127 0.55 129
Learning Flow [11]131.6 5.91 123 18.6 127 0.30 121 12.0 121 22.9 127 1.00 105 8.30 139 20.0 137 1.33 139 21.9 136 32.9 138 6.94 135 44.5 142 59.7 143 5.97 145 11.5 115 42.6 115 1.35 121 11.3 131 46.8 138 0.69 127 23.7 146 55.9 145 0.62 142
GroupFlow [9]132.4 7.04 142 22.5 143 0.28 114 12.5 126 24.0 138 1.13 119 9.10 142 22.0 144 1.45 141 21.0 132 33.6 142 5.93 116 44.1 134 59.3 137 5.50 126 12.2 140 44.4 146 1.42 129 11.1 128 45.2 126 0.61 119 22.7 128 54.1 131 0.56 134
SLK [47]133.5 6.55 136 21.1 139 0.32 126 13.5 135 23.1 128 1.44 139 9.16 143 21.2 143 1.49 145 24.9 145 34.2 144 7.81 144 43.5 103 58.8 126 5.34 70 12.2 140 43.1 130 1.45 131 11.9 142 48.9 147 0.96 142 23.0 133 54.0 129 0.64 143
Heeger++ [104]135.8 7.79 147 25.2 148 0.17 45 13.9 141 24.2 141 1.33 129 11.8 148 28.7 149 1.49 145 23.4 141 30.8 123 7.63 141 44.4 141 59.9 144 5.62 134 12.6 147 43.1 130 1.77 143 12.6 148 46.9 139 0.87 138 23.2 139 53.5 120 0.60 139
FFV1MT [106]136.2 6.93 141 22.8 145 0.24 102 14.0 142 23.5 133 1.48 141 11.2 147 27.7 148 1.52 148 23.4 141 30.8 123 7.63 141 44.0 132 59.2 133 5.69 137 12.0 133 41.6 94 1.56 137 12.1 145 47.3 142 0.95 141 23.4 142 54.2 133 0.79 148
FOLKI [16]139.2 7.10 143 21.1 139 0.94 148 15.3 147 25.5 147 2.28 148 8.49 140 22.2 145 1.47 144 26.3 147 35.2 147 10.6 149 44.0 132 59.6 140 5.54 130 11.6 118 41.8 102 1.49 133 11.4 134 47.7 143 0.90 139 23.3 141 54.9 141 0.67 145
Pyramid LK [2]140.8 7.19 145 21.0 136 0.93 147 16.2 148 25.1 146 2.91 149 14.0 149 18.5 128 2.57 149 32.5 150 46.2 150 13.7 150 44.2 138 60.1 145 5.48 122 11.6 118 42.5 114 1.40 128 11.4 134 47.2 141 1.28 148 23.7 146 56.7 149 1.08 149
PGAM+LK [55]141.5 7.51 146 23.5 147 0.73 146 13.8 138 24.2 141 1.92 146 9.44 145 22.7 146 1.45 141 26.4 148 36.9 148 10.5 148 44.1 134 59.5 139 5.72 139 12.4 145 44.0 141 1.75 142 11.3 131 47.0 140 0.68 126 23.0 133 54.5 138 0.76 147
Periodicity [78]148.2 8.05 148 23.2 146 1.34 150 20.5 150 27.4 149 3.39 150 15.2 150 30.5 150 4.22 150 26.2 146 43.5 149 9.47 147 46.4 150 62.7 150 6.92 150 13.7 150 44.6 147 2.88 149 11.4 134 48.3 145 1.18 146 25.7 150 59.2 150 1.29 150
AVG_FLOW_ROB [142]151.0 30.2 151 60.4 151 6.56 151 42.6 151 49.8 151 9.03 151 34.7 151 42.2 151 9.09 151 57.3 151 72.3 151 20.9 151 51.6 151 69.0 151 7.96 151 25.2 151 71.8 151 4.67 151 39.2 151 64.3 151 3.36 151 43.7 151 66.4 151 8.60 151
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

Methodtime*framescolor Reference and notes
[1] 2D-CLG 844 2 gray The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences.
[2] Pyramid LK 12 2 color A modification of Bouguet's pyramidal implementation of Lucas-Kanade.
[3] Horn & Schunck 49 2 gray A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data.
[4] Black & Anandan 328 2 gray A modern Matlab implementation of the Black & Anandan method by Deqing Sun.
[5] Brox et al. 18 2 color T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.)
[6] Fusion 2,666 2 color V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008.
[7] Dynamic MRF 366 2 gray B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.)
[8] Second-order prior 14 2 gray W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[9] GroupFlow 600 2 gray X. Ren. Local Grouping for Optical Flow. CVPR 2008.
[10] SegOF 60 2 color L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available.
[11] Learning Flow 825 2 gray D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008.
[12] CBF 69 2 color W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[13] SPSA-learn 200 2 color Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008.
[14] GraphCuts 1,200 2 color T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008.
[15] F-TV-L1 8 2 gray A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008.
[16] FOLKI 1.4 2 gray G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005.
[17] TV-L1-improved 2.9 2 gray A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision.
[18] DPOF 287 2 color C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.)
[19] Filter Flow 34,000 2 color S. Seitz and S. Baker. Filter flow. ICCV 2009.
[20] Adaptive 9.2 2 gray A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009.
[21] Complementary OF 44 2 color H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[22] Aniso. Huber-L1 2 2 gray M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision.
[23] Rannacher 0.12 2 gray J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009.
[24] TI-DOFE 260 2 gray C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009.
[25] NL-TV-NCC 20 2 color M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010.
[26] MDP-Flow 188 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010.
[27] ACK-Prior 5872 2 color K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010.
[28] LDOF 122 2 color T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011.
[29] p-harmonic 565 2 gray J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010.
[30] TriangleFlow 4200 2 gray B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010.
[31] Classic+NL 972 2 color D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code.
[32] Classic++ 486 2 gray A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010.
[33] Nguyen 33 2 gray D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011.
[34] Modified CLG 133 2 gray R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010.
[35] ComplOF-FED-GPU 0.97 2 color P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010.
[36] Ad-TV-NDC 35 2 gray M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010.
[37] Layers++ 18206 2 color D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010.
[38] OFH 620 3 color H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011.
[39] LSM 1615 2 color K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011.
[40] CostFilter 55 2 color C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011.
[41] Bartels 0.15 2 gray C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU.
[42] Shiralkar 600 2 gray M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242.
[43] HBpMotionGpu 1000 5 gray S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.)
[44] StereoFlow 7200 2 color G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772.
[45] Adaptive flow 121 2 gray T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011.
[46] TC-Flow 2500 5 color S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011.
[47] SLK 300 2 gray T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011.
[48] CLG-TV 29 2 gray M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code.
[49] SimpleFlow 1.7 2 color M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012.
[50] IAOF 57 2 gray D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011.
[51] IAOF2 56 2 gray D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011.
[52] LocallyOriented 9541 2 gray Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012.
[53] IROF-TV 261 2 color H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop.
[54] Sparse Occlusion 2312 2 color A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011.
[55] PGAM+LK 0.37 2 gray A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010.
[56] Sparse-NonSparse 713 2 color L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013.
[57] nLayers 36150 4 color D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012.
[58] IROF++ 187 2 color H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013.
[59] COFM 600 3 color M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013.
[60] Efficient-NL 400 2 color P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012.
[61] BlockOverlap 2 2 gray M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to MMSP 2012.
[62] Ramp 1200 2 color A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012.
[63] Occlusion-TV-L1 538 3 gray C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012.
[64] TV-L1-MCT 90 2 color M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012.
[65] Local-TV-L1 500 2 gray L. Raket. Local smoothness for global optical flow. ICIP 2012.
[66] ALD-Flow 61 2 color M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012.
[67] SIOF 234 2 color L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012.
[68] MDP-Flow2 342 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available.
[69] TCOF 1421 all gray J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013.
[70] LME 476 2 color W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013.
[71] NN-field 362 2 color L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[72] FESL 3310 2 color W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013.
[73] PMF 35 2 color J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013.
[74] FC-2Layers-FF 2662 4 color D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013.
[75] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[76] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[77] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[78] Periodicity 8000 4 color G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013.
[79] SILK 572 2 gray P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP.
[80] CRTflow 13 3 color O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013.
[81] SuperFlow 178 2 color Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507.
[82] Aniso-Texture 300 2 color Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267.
[83] Classic+CPF 640 2 gray Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013.
[84] S2D-Matching 1200 2 color Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479.
[85] AGIF+OF 438 2 gray Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015.
[86] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[87] NNF-Local 673 2 color Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014.
[88] EPPM w/o HM 2.5 2 color L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014.
[89] MLDP_OF 165 2 gray M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014.
[90] RFlow 20 2 gray S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014.
[91] SRR-TVOF-NL 32 all color P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014.
[92] 2DHMM-SAS 157 2 color M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission.
[93] WLIF-Flow 700 2 color Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014.
[94] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[95] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[96] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[97] AggregFlow 1642 2 color D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759.
[98] 2bit-BM-tele 124 2 gray R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013.
[99] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[100] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[101] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[102] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[103] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[104] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[105] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[106] FFV1MT 358 5 gray F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015.
[107] ROF-ND 4 2 color S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015.
[108] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[109] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[110] FlowFields 15 2 color C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015.
[111] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[112] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[113] CombBMOF 51 2 color M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.)
[114] PMMST 182 2 color F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015.
[115] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[116] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[117] CNN-flow-warp+ref 1.4 3 color D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016.
[118] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[119] StereoOF-V1MT 343 2 gray Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132.
[120] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[121] RNLOD-Flow 1040 2 gray C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. IEEE TIP 26(8):4055-4067, 2017.
[122] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[123] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[124] BriefMatch 0.068 2 gray G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62.
[125] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[126] AdaConv-v1 2.8 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[127] SepConv-v1 0.2 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[128] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[129] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[130] FlowFields+ 10.5 2 color C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017.
[131] IIOF-NLDP 150 2 color D.-H. Trinh, W. Blondel, and C. Daul. A general form of illumination-invariant descriptors in variational optical flow estimation. ICIP 2017.
[132] SuperSlomo 0.5 2 color Anonymous. (Interpolation results only.) Super SloMo: High quality estimation of multiple intermediate frames for video interpolation. CVPR 2018 submission 325.
[133] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[134] OFRF 90 2 color T. Mai, M. Gouiffes, and S. Bouchafa. Optical Flow refinement using iterative propagation under color, proximity and flow reliability constraints. Submitted to Signal, Image and Video Processing 2017.
[135] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
[136] FGIK 0.18 2 color Anonymous. (Interpolation results only.) Learning flow-guided interpolation kernels for video frame synthesis. ECCV 2018 submission 433.
[137] CtxSyn 0.07 2 color S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[138] H+S_ROB 5 2 color ROB 2018 baseline submission, based on: E. Meinhardt-Llopis, J. Sanchez, and D. Kondermann. Horn-Schunck optical flow with a multi-scale strategy. Image Processing On Line 3:151–172, 2013.
[139] TVL1_ROB 1 2 color ROB 2018 baseline submission, based on: J. Sanchez, E. Meinhardt-Llopis, and G. Facciolo. TV-L1 optical flow estimation. Image Processing On Line 3:137-150, 2013.
[140] DMF_ROB 10 2 color ROB 2018 baseline submission, based on: P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[141] JOF 657 2 gray C. Zhang, L. Ge, Z. Chen, M. Li, W. Liu, and H. Chen. Refined TV-L1 optical flow estimation using joint filtering. Submitted to IEEE TMM, 2018.
[142] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[143] LiteFlowNet 0.06 2 color T.-W. Hui, X. Tang, and C. C. Loy. LiteFlowNet: A lightweight convolutional neural network for optical flow estimation. CVPR 2018.
[144] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[145] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[146] FF++_ROB 17.43 2 color R. Schuster, C. Bailer, O. Wasenmueller, D. Stricker. FlowFields++: Accurate optical flow correspondences meet robust interpolation. ICIP 2018. Submitted to ROB 2018.
[147] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[148] PWC-Net_ROB 0.069 2 color D. Sun, X. Yang, M.-Y. Liu, and J. Kautz. PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. CVPR 2018.
[149] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[150] ContFlow_ROB 0.45 all color Anonymous. Continual Flow. ROB 2018 submission.
[151] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
* The "time" column lists the reported runtime in seconds on the "Urban" sequence. Note that these runtimes are not normalized by processor speed or type.