Optical flow evaluation results Statistics:     Average   SD   R0.5   R1.0   R2.0   A50   A75   A95  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
R0.5
endpoint
error
avg. Army
(Hidden texture)
GT   im0   im1
Mequon
(Hidden texture)
GT   im0   im1
Schefflera
(Hidden texture)
GT   im0   im1
Wooden
(Hidden texture)
GT   im0   im1
Grove
(Synthetic)
GT   im0   im1
Urban
(Synthetic)
GT   im0   im1
Yosemite
(Synthetic)
GT   im0   im1
Teddy
(Stereo)
GT   im0   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
OFLAF [77]12.5 1.67 4 9.54 5 0.81 12 4.12 7 23.1 5 2.26 16 3.43 1 11.8 1 1.47 8 2.31 10 15.3 6 0.67 9 18.1 2 27.2 3 8.68 5 12.6 38 27.0 11 6.93 30 0.78 26 1.08 37 3.37 33 11.6 9 25.9 3 16.2 19
MDP-Flow2 [68]14.4 1.76 8 9.93 9 0.86 14 3.26 2 20.6 2 1.44 3 4.04 3 13.6 3 1.26 6 3.09 29 21.8 34 0.88 21 22.4 17 32.2 13 14.3 16 9.15 13 23.6 3 5.83 11 2.18 52 0.32 18 4.78 48 10.8 5 26.3 4 15.0 11
NNF-Local [87]14.9 1.75 7 9.66 6 0.87 15 4.56 14 27.6 16 2.46 20 4.52 4 15.6 7 2.18 18 2.57 18 18.4 18 0.86 18 18.8 5 29.2 5 8.22 3 9.37 16 24.2 6 5.22 8 0.95 29 2.02 74 1.90 19 10.6 4 31.8 26 8.21 2
NN-field [71]17.5 2.01 20 11.0 21 1.10 29 5.74 28 30.7 33 3.21 29 4.57 5 15.7 8 2.22 20 1.81 3 15.7 8 0.54 6 19.0 6 29.4 6 8.42 4 10.5 22 20.3 1 3.83 1 1.43 36 2.03 75 3.72 35 10.1 2 31.1 21 6.81 1
PMMST [114]19.8 1.43 2 8.08 2 0.38 1 6.05 34 28.6 20 4.40 43 6.13 19 19.1 18 4.02 42 2.21 6 11.7 2 1.09 31 21.2 9 30.5 9 13.2 12 9.59 18 23.8 4 5.71 10 2.28 55 1.95 69 4.36 42 11.8 10 29.1 8 13.1 8
WLIF-Flow [93]23.2 1.80 10 9.97 10 0.94 17 6.24 37 28.7 22 4.52 45 5.74 13 18.5 13 3.13 27 3.03 28 19.9 25 1.01 28 21.9 10 32.0 12 14.1 14 12.4 35 27.2 12 6.44 14 3.40 76 0.07 9 8.69 74 11.4 7 26.8 5 15.7 15
ComponentFusion [96]23.8 1.73 6 9.92 8 0.77 9 3.75 5 22.3 4 2.27 17 5.02 9 17.1 10 2.21 19 2.87 22 19.3 23 0.93 22 24.1 21 35.1 24 18.6 39 12.4 35 39.0 76 8.29 61 2.41 56 0.13 16 4.73 47 11.9 12 30.0 17 15.5 14
Correlation Flow [75]24.6 1.96 17 10.9 19 0.66 6 4.21 9 25.5 12 1.35 2 6.69 31 20.7 26 0.94 2 1.68 2 13.3 3 0.48 5 25.4 30 36.9 31 16.3 27 13.5 56 32.5 36 7.88 52 2.82 65 1.63 54 10.8 82 11.3 6 29.7 12 9.89 5
NNF-EAC [103]26.4 1.95 16 10.5 15 1.10 29 4.29 11 25.1 10 2.20 13 5.06 10 16.6 9 1.81 12 3.94 57 23.4 44 1.63 57 22.5 18 32.5 16 14.7 18 11.3 27 25.8 8 6.81 24 2.71 62 2.13 77 4.63 46 12.4 16 30.2 19 16.5 20
Layers++ [37]27.1 1.85 13 10.1 11 1.03 24 6.26 38 27.9 19 4.58 47 4.88 8 15.2 5 3.65 36 2.26 8 14.4 4 0.68 11 17.8 1 25.4 1 12.2 8 13.3 49 28.3 16 6.81 24 4.53 86 2.71 95 7.34 65 13.2 25 29.7 12 19.2 45
LME [70]27.5 1.89 15 10.6 16 0.75 7 3.53 3 21.3 3 1.83 8 7.04 43 18.6 16 8.24 76 3.10 31 23.0 41 0.86 18 24.8 27 35.5 26 17.9 36 10.1 20 30.1 27 6.46 15 2.67 61 1.51 50 5.54 53 12.8 18 30.9 20 17.7 31
RNLOD-Flow [121]29.5 1.68 5 9.49 4 0.75 7 5.76 29 30.6 32 3.18 27 6.58 28 21.1 30 2.92 24 2.61 19 17.5 15 0.74 13 22.0 11 32.8 17 14.9 21 11.5 29 28.0 15 7.37 39 5.53 100 4.17 109 15.2 106 11.8 10 27.7 7 15.1 12
nLayers [57]29.8 1.40 1 7.64 1 0.64 4 8.47 72 30.5 31 7.07 84 6.80 37 20.0 22 5.79 67 2.13 5 14.7 5 0.78 16 18.3 3 26.0 2 12.2 8 12.9 44 25.6 7 6.84 26 1.93 48 2.24 81 3.35 32 14.5 37 32.0 29 20.9 54
HAST [109]31.0 1.57 3 8.65 3 0.60 2 5.82 32 24.9 9 3.84 35 3.85 2 12.5 2 0.41 1 2.82 21 18.8 20 0.58 7 18.7 4 27.9 4 8.00 1 15.9 93 32.6 37 9.69 84 9.89 126 4.87 119 36.9 135 8.55 1 22.0 1 9.33 3
FC-2Layers-FF [74]31.8 1.81 11 9.71 7 1.07 27 6.99 46 33.9 47 4.71 48 4.71 6 15.0 4 3.63 35 2.67 20 18.3 17 0.87 20 20.6 8 29.7 7 14.5 17 13.3 49 28.4 17 7.26 36 5.67 104 1.82 64 14.9 102 12.9 22 29.4 9 18.4 39
ProFlow_ROB [147]32.0 2.91 66 15.3 67 1.30 44 5.38 20 30.3 30 3.10 24 8.14 55 26.3 56 3.45 33 3.50 40 23.3 43 0.98 27 29.0 54 42.5 59 17.0 31 8.52 9 33.1 41 4.71 5 0.00 1 0.02 1 0.00 1 12.1 14 36.2 42 12.3 6
SVFilterOh [111]32.8 2.18 31 11.4 26 0.78 10 5.94 33 29.2 24 3.13 25 4.85 7 15.2 5 2.01 15 2.35 11 17.4 13 0.63 8 20.4 7 30.1 8 8.12 2 14.7 84 29.5 23 8.51 68 10.3 127 3.98 107 31.3 126 12.0 13 26.9 6 13.4 9
TC/T-Flow [76]33.2 2.19 33 11.8 33 1.21 39 5.00 17 29.4 25 1.89 10 5.57 12 18.5 13 1.28 7 3.63 46 23.7 47 1.24 38 24.1 21 35.4 25 15.2 24 7.02 2 25.8 8 5.43 9 3.79 81 2.13 77 19.3 115 14.6 40 36.2 42 17.9 34
AGIF+OF [85]33.5 1.99 19 10.9 19 1.16 34 8.96 77 37.8 69 6.95 79 6.31 22 20.4 23 3.86 40 2.89 23 19.1 21 0.93 22 22.1 12 32.4 14 14.8 19 12.9 44 28.6 19 6.79 23 3.48 79 0.08 14 8.67 73 12.8 18 29.9 15 17.5 27
3DFlow [135]34.2 1.97 18 10.7 17 0.63 3 5.21 18 29.9 28 1.88 9 5.17 11 17.4 11 1.02 3 1.00 1 9.03 1 0.18 1 22.3 16 32.8 17 13.2 12 19.1 114 42.2 96 12.7 104 11.7 134 1.61 52 31.8 129 11.5 8 29.9 15 9.34 4
TC-Flow [46]34.4 2.04 21 11.0 21 0.94 17 3.69 4 23.4 6 1.68 5 5.96 18 19.9 21 1.06 4 3.73 49 23.6 46 1.24 38 25.7 34 38.0 37 14.8 19 8.99 12 34.6 47 5.03 7 2.82 65 2.47 88 15.9 110 16.0 49 38.1 50 22.0 58
HBM-GC [105]34.8 2.10 26 10.8 18 0.94 17 7.69 60 31.9 40 6.10 71 6.21 21 18.5 13 3.82 38 2.22 7 15.5 7 0.78 16 22.1 12 31.8 10 14.2 15 13.3 49 24.1 5 7.49 43 8.91 123 1.87 65 21.4 119 12.7 17 31.1 21 16.7 23
IIOF-NLDP [131]36.4 2.63 54 13.9 53 1.09 28 7.53 57 38.0 72 3.28 30 6.98 42 22.1 39 1.85 13 2.28 9 15.7 8 0.95 25 25.2 28 37.6 36 12.5 10 13.4 54 35.9 56 8.72 71 0.78 26 0.39 23 3.57 34 15.4 47 37.7 47 15.1 12
ALD-Flow [66]36.7 2.22 35 11.8 33 1.02 23 4.33 12 24.7 7 2.04 12 6.35 24 20.9 27 1.56 9 3.67 47 24.0 51 1.10 32 25.8 35 37.5 35 15.8 26 8.24 5 32.7 39 4.68 3 3.06 70 2.62 94 16.6 112 15.6 48 39.3 53 19.8 49
ProbFlowFields [128]38.3 3.29 74 17.1 77 1.88 89 6.54 40 29.8 26 5.50 59 7.69 50 23.8 48 6.90 70 3.09 29 17.1 11 1.28 40 27.8 42 39.5 43 19.2 45 6.56 1 27.2 12 5.00 6 0.09 4 0.03 4 0.86 12 17.1 56 39.4 54 17.5 27
IROF++ [58]39.0 2.18 31 11.5 29 1.33 47 7.91 61 36.5 64 5.96 66 6.71 33 21.7 36 4.85 60 3.62 45 22.8 37 1.63 57 24.2 24 34.9 23 17.1 33 13.3 49 33.4 43 7.82 50 0.55 22 1.09 38 1.01 14 12.8 18 32.9 33 16.7 23
FESL [72]39.9 1.86 14 10.2 12 0.99 20 10.4 94 39.3 81 7.94 92 6.79 36 21.2 32 4.35 49 2.39 13 16.2 10 0.76 15 24.2 24 34.7 21 19.2 45 12.6 38 27.7 14 7.10 35 3.35 74 2.20 80 8.03 69 14.5 37 31.2 23 17.6 30
FMOF [94]40.7 2.09 24 11.2 25 1.44 61 9.20 80 37.9 70 6.96 80 6.14 20 19.5 19 3.82 38 2.52 16 17.4 13 0.73 12 24.1 21 34.8 22 17.7 35 13.5 56 28.4 17 6.99 32 4.64 89 1.63 54 14.5 98 14.5 37 32.7 31 17.2 26
Classic+CPF [83]41.0 2.16 29 11.6 30 1.42 59 8.04 64 36.6 65 5.76 63 6.70 32 21.8 38 3.86 40 3.02 27 21.2 32 1.14 34 23.6 20 34.2 20 17.0 31 13.4 54 29.1 20 7.03 34 4.58 88 1.50 49 13.6 95 12.9 22 29.7 12 17.5 27
MLDP_OF [89]41.2 2.46 47 13.6 50 1.14 33 4.43 13 27.8 18 1.99 11 6.80 37 21.7 36 1.89 14 2.52 16 19.6 24 0.75 14 28.2 43 40.4 46 19.2 45 11.8 31 29.6 24 9.40 80 8.30 121 2.15 79 31.7 128 13.3 26 33.4 36 15.9 16
PH-Flow [101]42.0 2.30 40 12.2 37 1.45 63 7.61 58 35.2 52 5.81 64 5.92 17 19.0 17 4.67 58 3.52 41 22.1 35 1.49 50 23.4 19 33.9 19 16.3 27 12.4 35 29.4 22 6.87 27 4.88 93 2.25 83 14.0 96 12.2 15 30.1 18 16.6 21
Efficient-NL [60]43.2 2.41 45 11.8 33 1.55 74 8.28 68 35.4 55 5.90 65 6.72 34 20.9 27 3.78 37 2.95 26 19.1 21 1.20 36 22.1 12 32.4 14 15.3 25 14.6 82 31.0 31 8.05 56 3.32 72 2.40 87 7.02 61 13.6 30 29.6 10 18.2 36
PMF [73]43.5 2.30 40 12.8 43 1.01 21 5.64 27 31.4 37 2.51 21 6.83 39 22.5 44 1.72 11 3.26 32 21.1 29 0.94 24 24.3 26 36.7 30 9.56 6 14.4 78 40.0 83 8.40 65 7.45 118 8.62 137 24.8 120 10.4 3 25.6 2 12.7 7
OAR-Flow [125]44.1 2.96 67 15.1 66 1.58 76 6.72 43 31.3 36 4.10 40 9.12 63 27.1 60 4.72 59 3.73 49 23.9 49 1.17 35 28.3 45 40.8 48 17.6 34 8.30 6 33.5 45 4.69 4 0.25 13 0.17 17 2.56 27 17.5 60 40.5 56 22.6 61
Aniso-Texture [82]44.2 1.84 12 10.4 14 0.81 12 4.68 15 24.7 7 3.74 33 8.07 54 23.8 48 3.23 30 2.10 4 18.4 18 0.46 3 29.0 54 41.0 51 22.9 61 12.7 41 32.7 39 8.37 64 6.63 113 5.87 128 14.8 101 16.4 50 35.2 40 24.2 70
Sparse-NonSparse [56]45.4 2.11 27 11.7 31 1.39 53 7.47 56 35.1 51 5.75 62 6.48 26 21.2 32 4.34 47 3.52 41 22.9 38 1.38 45 26.1 38 37.3 34 19.6 52 13.5 56 31.2 33 7.42 40 5.02 97 1.18 42 13.5 94 13.5 28 31.7 24 18.8 43
JOF [141]45.8 2.08 22 11.0 21 1.19 36 7.97 63 35.7 61 6.06 70 5.84 15 18.1 12 4.57 56 3.34 36 21.1 29 1.52 52 22.1 12 31.9 11 15.0 23 14.2 72 29.3 21 8.17 57 10.6 130 4.81 117 30.7 125 12.8 18 29.6 10 17.7 31
OFH [38]46.0 2.82 61 13.9 53 2.01 90 4.91 16 28.6 20 2.33 18 8.97 62 28.0 65 2.88 23 4.00 60 27.0 61 1.43 48 31.0 66 44.5 72 22.7 59 10.5 22 41.8 94 6.88 28 0.03 2 0.02 1 0.27 6 17.1 56 46.4 75 19.2 45
Ramp [62]46.4 2.21 34 12.1 36 1.45 63 7.45 55 35.5 58 5.63 61 6.33 23 20.6 25 4.23 44 3.43 37 22.5 36 1.38 45 25.8 35 37.0 32 19.3 49 13.5 56 30.3 28 7.45 41 4.89 94 1.97 71 15.1 105 13.1 24 31.9 27 18.0 35
NL-TV-NCC [25]46.5 2.25 37 11.7 31 0.78 10 6.94 45 35.5 58 2.54 22 6.48 26 21.1 30 1.08 5 2.48 15 21.5 33 0.46 3 31.5 69 46.7 86 16.7 29 17.3 100 41.0 92 10.2 88 4.41 85 0.10 15 10.1 79 18.4 61 43.2 62 18.2 36
LSM [39]46.6 2.24 36 12.4 39 1.39 53 7.37 53 35.4 55 5.47 58 6.61 29 21.6 35 4.24 45 3.46 39 23.8 48 1.30 42 25.8 35 37.0 32 19.3 49 13.7 62 32.1 35 7.36 38 5.34 99 1.11 40 14.5 98 13.7 33 32.3 30 18.2 36
Sparse Occlusion [54]47.5 2.14 28 11.4 26 1.03 24 7.32 51 31.0 34 6.11 72 7.29 47 22.9 46 2.48 22 3.29 33 22.9 38 1.03 29 26.9 40 39.4 41 14.9 21 13.0 46 33.3 42 7.63 46 7.80 119 8.76 140 12.2 90 14.8 42 34.8 39 16.9 25
Classic+NL [31]47.8 2.08 22 11.4 26 1.35 49 7.33 52 35.9 62 5.30 55 6.47 25 21.0 29 4.53 54 3.59 43 22.9 38 1.49 50 25.4 30 36.3 28 19.4 51 13.8 65 31.1 32 7.57 44 5.78 106 2.32 86 15.0 103 13.5 28 31.9 27 18.7 42
IROF-TV [53]49.8 2.51 50 13.5 48 1.41 57 8.08 65 38.7 78 6.19 75 6.97 41 22.3 41 4.43 51 4.23 63 28.8 69 1.72 62 28.3 45 39.9 44 22.6 58 13.8 65 40.0 83 8.01 54 0.23 11 0.39 23 0.67 10 13.7 33 33.6 37 17.8 33
RFlow [90]50.6 2.42 46 13.5 48 1.16 34 3.98 6 25.2 11 1.81 7 8.89 61 27.5 62 3.13 27 3.45 38 26.8 59 1.60 55 30.5 64 43.6 63 24.5 69 14.2 72 38.1 70 7.94 53 3.36 75 1.65 57 8.47 72 16.9 55 42.3 58 20.5 53
TV-L1-MCT [64]50.8 2.09 24 11.1 24 1.39 53 9.67 82 39.0 80 7.35 85 7.11 45 22.3 41 4.27 46 2.94 25 20.7 28 1.13 33 28.4 47 39.4 41 25.8 76 16.0 95 35.0 50 9.27 77 1.27 34 0.57 27 7.24 63 14.8 42 33.2 35 23.3 67
COFM [59]51.2 2.51 50 13.9 53 1.42 59 5.54 23 28.9 23 3.40 31 7.79 52 23.6 47 4.53 54 2.90 24 18.2 16 0.95 25 29.1 56 40.8 48 25.4 73 15.5 90 30.7 30 9.39 79 4.69 90 1.23 43 15.4 109 16.8 54 37.1 44 21.8 57
S2D-Matching [84]51.4 2.39 43 13.0 44 1.52 71 7.22 49 35.6 60 5.13 53 7.63 49 24.4 51 4.38 50 3.30 34 20.5 27 1.35 44 25.3 29 36.0 27 19.2 45 14.1 69 31.5 34 7.77 49 6.21 110 2.24 81 16.9 113 13.6 30 31.7 24 19.3 47
Occlusion-TV-L1 [63]53.1 2.47 48 13.1 45 1.12 31 6.32 39 32.2 42 4.45 44 9.86 68 28.3 66 4.44 52 3.86 55 26.7 58 1.43 48 31.9 75 44.3 69 27.1 82 11.3 27 35.3 54 10.4 91 0.47 20 1.16 41 0.67 10 19.8 68 46.6 77 22.9 65
Complementary OF [21]53.3 2.69 58 15.0 64 1.33 47 4.19 8 26.9 14 1.70 6 7.15 46 24.4 51 3.09 26 3.86 55 26.1 55 1.41 47 33.2 81 44.6 74 29.7 94 13.3 49 40.7 91 7.00 33 0.74 25 0.03 4 7.12 62 23.9 91 53.1 98 33.9 101
CostFilter [40]53.9 2.65 55 14.9 62 1.01 21 5.51 22 31.6 38 2.23 15 7.39 48 24.1 50 3.06 25 3.82 53 26.1 55 1.08 30 25.4 30 38.9 40 10.2 7 15.1 87 42.7 98 8.52 69 8.99 124 10.3 142 29.5 124 14.4 36 37.2 45 16.1 18
MDP-Flow [26]54.0 2.33 42 13.4 47 1.20 37 5.61 26 26.9 14 4.88 50 6.76 35 22.6 45 5.72 66 4.13 61 29.5 74 1.92 66 28.7 50 40.8 48 23.2 64 12.8 43 36.7 60 8.04 55 2.54 58 2.96 97 4.43 44 19.4 67 44.6 68 26.0 79
ACK-Prior [27]54.2 2.16 29 12.4 39 0.64 4 4.26 10 25.9 13 1.33 1 5.91 16 20.4 23 1.67 10 2.39 13 20.4 26 0.33 2 30.0 60 41.1 52 24.4 68 19.2 115 40.3 88 12.2 102 14.4 138 6.30 131 40.9 138 21.0 74 43.6 64 27.5 84
PWC-Net_ROB [148]55.8 4.13 97 21.0 97 2.11 92 8.97 78 40.1 83 6.18 74 10.7 73 31.8 76 8.37 77 2.38 12 17.1 11 0.67 9 34.8 94 50.7 106 21.3 54 11.8 31 39.2 78 6.97 31 0.15 7 1.43 46 0.07 3 14.9 44 38.2 51 15.9 16
2DHMM-SAS [92]56.1 2.28 39 12.3 38 1.46 65 8.45 71 38.1 73 6.02 69 8.34 57 24.4 51 5.21 62 3.73 49 23.4 44 1.62 56 25.5 33 36.6 29 18.8 40 14.5 79 33.4 43 8.46 67 5.07 98 2.05 76 15.3 107 13.3 26 32.9 33 18.5 41
SimpleFlow [49]56.5 2.39 43 12.6 42 1.60 78 9.03 79 38.3 74 7.38 86 8.52 59 25.7 55 5.41 63 4.36 68 25.5 54 2.48 75 26.8 39 38.0 37 21.6 55 14.0 68 29.7 25 7.65 47 2.77 64 1.97 71 6.48 58 14.3 35 32.8 32 19.7 48
Steered-L1 [118]57.6 1.78 9 10.2 12 0.92 16 2.76 1 19.0 1 1.44 3 5.78 14 19.7 20 2.10 16 3.99 59 27.5 64 1.53 54 31.3 68 43.3 61 27.6 84 14.6 82 39.2 78 9.88 85 14.6 139 5.70 126 47.1 139 22.4 81 48.1 80 29.3 90
AggregFlow [97]59.1 3.49 82 17.6 81 1.74 80 10.4 94 42.0 93 6.99 81 11.4 79 30.6 71 9.73 85 3.75 52 21.1 29 1.52 52 28.9 53 41.8 56 18.2 37 7.46 3 22.8 2 4.30 2 1.95 49 2.54 90 4.24 40 20.5 70 42.7 61 25.8 77
TF+OM [100]59.5 2.89 65 14.7 60 1.35 49 5.44 21 27.6 16 3.94 36 10.2 69 26.3 56 12.8 97 3.61 44 24.6 53 1.28 40 29.8 59 40.5 47 25.7 74 12.7 41 34.9 49 6.11 12 5.62 103 4.89 120 14.0 96 21.5 76 46.5 76 23.8 69
EPPM w/o HM [88]61.8 3.53 84 16.6 73 1.44 61 5.80 30 35.3 54 2.22 14 8.01 53 26.3 56 2.45 21 4.38 69 28.0 65 1.77 64 27.0 41 40.0 45 13.0 11 18.6 108 44.4 108 10.8 94 10.5 129 2.30 85 37.7 136 13.6 30 35.6 41 13.9 10
DeepFlow2 [108]61.9 3.18 72 16.9 76 1.48 67 6.68 42 33.7 46 4.15 41 10.7 73 31.1 72 7.69 73 5.96 89 31.1 83 3.33 87 28.5 48 41.3 53 19.1 42 9.45 17 34.7 48 6.60 18 1.60 41 1.66 60 10.4 80 23.5 86 47.9 79 30.2 93
Adaptive [20]62.3 2.49 49 13.2 46 1.13 32 7.17 47 34.5 50 4.97 51 10.2 69 28.7 68 4.34 47 4.31 67 28.2 66 1.66 59 34.5 89 48.1 93 28.2 86 14.3 76 36.1 57 8.24 58 4.04 83 4.49 115 7.32 64 14.7 41 34.7 38 18.9 44
CombBMOF [113]62.9 2.67 56 14.4 57 1.05 26 7.17 47 33.9 47 4.00 37 6.89 40 21.4 34 4.18 43 5.20 81 28.8 69 3.04 85 28.2 43 41.7 55 18.5 38 21.8 120 39.5 80 20.1 125 4.02 82 4.61 116 6.08 55 17.1 56 37.5 46 24.5 72
ComplOF-FED-GPU [35]65.2 2.87 64 15.6 69 1.35 49 6.14 35 33.6 45 3.15 26 8.26 56 27.4 61 3.30 31 4.29 64 28.2 66 1.71 61 33.1 80 47.9 92 24.1 67 14.7 84 45.7 111 9.19 76 3.33 73 1.48 48 15.0 103 18.8 64 48.4 82 22.0 58
TCOF [69]66.5 3.05 69 15.4 68 1.75 81 8.12 67 38.6 76 5.20 54 13.8 92 34.5 87 13.2 99 8.75 111 29.0 71 8.90 117 33.8 85 47.3 89 23.1 63 9.33 15 25.9 10 6.64 20 2.59 59 1.95 69 6.38 57 15.3 46 39.1 52 18.4 39
ROF-ND [107]66.9 3.29 74 14.7 60 1.29 43 7.42 54 31.8 39 2.42 19 7.10 44 22.1 39 2.13 17 3.68 48 23.2 42 2.87 82 31.1 67 43.7 64 23.6 66 19.3 118 38.5 72 10.7 93 8.90 122 2.99 98 24.8 120 21.9 78 48.6 83 22.7 63
DeepFlow [86]67.4 3.36 77 17.3 78 1.54 73 7.91 61 35.2 52 5.35 56 12.1 84 33.0 81 10.5 92 6.24 91 32.1 86 3.55 90 28.8 51 42.3 57 18.8 40 9.77 19 37.4 65 6.90 29 1.30 35 0.37 20 9.70 78 27.4 104 52.7 94 35.8 104
Classic++ [32]67.5 2.59 53 13.9 53 1.51 70 6.79 44 32.3 43 5.37 57 9.15 64 27.8 64 5.54 64 4.29 64 29.0 71 1.77 64 30.2 62 43.9 65 22.8 60 14.8 86 40.0 83 8.36 63 6.82 114 4.17 109 16.5 111 16.5 51 39.5 55 19.8 49
BriefMatch [124]67.5 2.27 38 12.5 41 1.23 41 6.23 36 32.1 41 3.54 32 6.68 30 22.3 41 3.16 29 3.32 35 23.9 49 1.23 37 30.8 65 43.3 61 26.8 79 23.9 124 43.6 102 21.0 127 11.0 133 4.44 114 33.1 132 21.5 76 44.8 69 29.2 89
TV-L1-improved [17]69.0 2.56 52 13.6 50 1.20 37 5.80 30 30.0 29 4.04 38 9.84 67 28.4 67 4.60 57 4.16 62 27.0 61 1.66 59 31.5 69 45.4 80 23.0 62 17.5 101 45.5 110 13.7 111 7.01 116 4.32 113 20.5 117 17.1 56 42.5 60 20.4 52
Bartels [41]70.2 3.26 73 16.7 75 1.37 52 5.33 19 29.8 26 3.18 27 8.40 58 26.9 59 4.45 53 4.40 70 26.9 60 2.16 69 32.7 77 45.4 80 28.4 90 14.3 76 38.1 70 12.9 105 8.20 120 3.82 105 31.3 126 18.4 61 43.7 66 23.3 67
S2F-IF [123]70.2 4.50 100 23.8 105 2.14 96 8.86 74 42.8 97 6.52 76 11.0 75 34.0 86 9.17 80 4.86 73 29.2 73 2.39 73 35.6 96 51.0 108 26.9 80 8.49 8 36.6 59 6.30 13 0.60 23 0.03 4 2.49 26 23.6 87 52.7 94 25.9 78
SIOF [67]71.2 2.67 56 13.6 50 1.23 41 7.65 59 37.9 70 4.78 49 14.2 95 32.9 80 15.4 101 6.36 92 34.7 93 3.84 93 34.0 86 45.8 83 33.2 99 13.5 56 35.7 55 10.5 92 1.99 50 0.99 35 4.21 39 20.5 70 45.6 71 30.7 95
DMF_ROB [140]72.3 3.59 89 19.4 91 1.80 85 8.09 66 35.4 55 5.96 66 11.6 80 33.7 84 7.90 75 5.84 87 32.4 87 3.42 89 33.7 83 47.0 87 28.7 92 12.6 38 37.5 67 8.25 60 0.50 21 0.35 19 2.46 25 26.5 98 52.6 93 32.2 99
F-TV-L1 [15]72.5 3.34 76 17.3 78 1.80 85 9.99 90 38.6 76 7.03 82 13.2 90 32.6 79 7.82 74 5.85 88 32.9 88 2.91 84 31.5 69 45.0 77 25.2 71 15.1 87 38.7 73 8.99 74 2.19 53 3.29 101 3.03 30 15.1 45 38.0 49 16.6 21
PGM-C [120]73.2 4.80 105 24.9 111 2.34 106 9.79 83 42.4 94 7.86 90 11.3 78 34.5 87 9.49 81 5.28 84 34.6 92 2.54 78 34.5 89 49.1 99 26.5 77 9.26 14 37.2 62 6.72 22 0.42 18 0.07 9 1.85 18 23.7 88 53.0 97 25.6 76
CRTflow [80]73.5 3.53 84 18.6 85 1.79 83 6.54 40 34.0 49 4.08 39 10.5 71 31.6 75 5.02 61 4.95 77 30.6 79 2.31 70 30.1 61 44.2 68 19.1 42 24.2 125 50.1 120 26.0 131 1.80 46 0.92 33 6.63 59 22.7 83 52.1 90 30.0 92
FlowFields [110]74.6 4.67 101 24.4 107 2.22 99 9.80 84 44.3 101 7.67 88 11.8 82 36.4 95 10.1 89 4.90 75 30.5 78 2.63 80 36.4 100 51.6 111 28.9 93 8.76 11 38.7 73 6.48 16 0.85 28 0.03 4 2.71 28 23.3 85 53.7 103 22.3 60
FlowFields+ [130]74.7 4.68 102 24.5 108 2.22 99 9.86 87 44.7 104 7.63 87 12.1 84 37.3 98 10.3 91 4.92 76 30.3 77 2.61 79 36.3 98 51.6 111 28.3 89 8.62 10 38.7 73 6.57 17 0.41 16 0.02 1 1.92 21 23.7 88 53.6 102 25.5 75
CPM-Flow [116]75.5 4.79 104 24.9 111 2.32 104 9.83 85 42.4 94 7.89 91 11.2 77 33.9 85 9.50 82 5.25 82 34.3 90 2.50 77 34.7 92 49.3 102 26.7 78 10.3 21 37.5 67 7.62 45 0.42 18 0.07 9 1.82 17 24.5 94 54.2 105 26.8 82
TriangleFlow [30]75.5 2.81 60 14.9 62 1.22 40 7.27 50 37.1 67 3.76 34 9.83 66 30.2 70 3.34 32 3.84 54 27.1 63 1.72 62 39.4 113 53.7 116 34.8 104 21.8 120 43.5 100 16.0 117 4.72 92 7.40 134 8.30 71 18.5 63 44.3 67 21.5 56
SRR-TVOF-NL [91]75.8 3.16 71 16.2 72 1.49 68 8.87 75 38.5 75 5.57 60 12.3 86 33.4 82 8.53 78 3.96 58 26.6 57 1.34 43 32.8 78 44.6 74 27.2 83 13.8 65 39.0 76 8.34 62 5.55 102 5.38 124 17.8 114 22.0 79 43.3 63 25.2 74
Rannacher [23]75.8 3.03 68 16.1 71 1.59 77 8.35 69 36.9 66 6.87 78 11.1 76 31.8 76 6.71 69 4.88 74 29.7 75 2.34 71 31.7 74 45.9 84 23.3 65 16.8 97 44.0 104 10.3 90 4.89 94 2.57 92 12.1 89 16.7 53 41.9 57 19.9 51
EpicFlow [102]76.0 4.80 105 24.9 111 2.33 105 9.90 88 42.9 98 7.95 93 11.8 82 35.7 93 9.56 83 5.26 83 34.4 91 2.49 76 34.6 91 49.2 101 27.0 81 10.8 25 37.5 67 7.33 37 0.41 16 0.07 9 1.80 16 24.1 92 53.5 100 26.4 80
LocallyOriented [52]76.0 4.06 93 20.2 94 1.87 88 12.1 98 47.6 107 8.49 96 15.9 100 39.1 105 11.1 94 5.10 79 28.6 68 2.84 81 34.0 86 47.4 90 25.7 74 11.8 31 32.6 37 7.84 51 1.10 30 1.51 50 6.95 60 20.3 69 46.8 78 23.1 66
Aniso. Huber-L1 [22]76.8 2.84 63 14.5 58 1.46 65 14.0 101 42.6 96 12.9 100 13.4 91 31.3 73 13.0 98 6.50 93 35.2 95 4.19 96 29.7 58 42.4 58 21.8 57 14.5 79 35.0 50 8.43 66 5.54 101 3.18 100 12.8 92 16.6 52 37.7 47 20.9 54
Dynamic MRF [7]78.4 3.39 78 18.9 88 1.30 44 5.60 25 33.5 44 2.81 23 9.67 65 31.3 73 3.54 34 4.64 72 33.7 89 2.39 73 38.0 106 51.2 109 34.9 105 19.2 115 51.8 124 15.2 115 3.41 77 0.37 20 20.9 118 25.1 96 52.2 91 31.7 97
FF++_ROB [146]79.5 4.95 108 25.8 117 2.27 101 10.3 93 44.5 102 7.95 93 13.1 89 37.6 102 12.4 96 5.12 80 31.4 84 2.87 82 36.3 98 52.0 115 28.2 86 10.9 26 36.9 61 7.65 47 1.46 37 0.96 34 4.19 38 20.8 73 49.0 84 22.6 61
DPOF [18]80.5 4.03 91 21.8 99 2.11 92 9.50 81 40.4 85 5.97 68 8.88 60 27.5 62 6.05 68 4.29 64 30.8 80 2.08 68 31.5 69 45.1 78 21.6 55 15.9 93 37.3 64 9.53 82 15.3 140 1.61 52 47.3 140 22.1 80 46.3 74 28.5 86
CBF [12]83.2 2.82 61 15.0 64 1.32 46 18.0 107 40.4 85 21.6 112 10.6 72 29.2 69 9.72 84 6.57 94 34.8 94 4.55 99 31.5 69 44.0 67 24.5 69 14.5 79 35.0 50 8.92 73 10.9 132 6.02 129 26.2 123 20.7 72 43.6 64 27.2 83
Brox et al. [5]83.5 3.55 87 18.8 87 1.64 79 10.1 92 39.6 82 8.97 97 11.7 81 33.4 82 8.96 79 6.57 94 36.4 97 3.41 88 38.2 108 47.6 91 45.3 127 13.5 56 42.4 97 9.63 83 0.27 14 0.99 35 0.47 9 31.0 111 56.4 111 43.3 118
Fusion [6]83.5 3.40 79 19.1 89 2.16 98 5.57 24 31.1 35 4.53 46 7.70 51 25.2 54 7.53 72 5.78 86 35.6 96 4.10 95 36.6 101 47.1 88 38.8 114 14.2 72 41.9 95 13.2 106 6.84 115 5.31 122 11.7 87 24.8 95 51.1 89 31.6 96
Local-TV-L1 [65]85.6 4.05 92 19.4 91 2.51 110 17.1 106 43.6 100 15.9 106 19.8 108 37.3 98 23.3 108 9.20 114 43.3 108 6.89 113 28.6 49 41.3 53 20.2 53 14.1 69 35.1 53 8.67 70 1.24 32 0.62 28 3.94 36 33.5 120 57.2 112 49.6 125
CLG-TV [48]85.7 2.80 59 14.6 59 1.41 57 14.0 101 40.7 88 14.1 103 12.7 87 32.0 78 11.0 93 8.13 104 47.7 118 5.99 109 32.0 76 45.2 79 25.2 71 14.1 69 40.1 87 10.9 95 6.45 111 5.82 127 10.4 80 19.0 65 42.4 59 26.6 81
LiteFlowNet [143]86.3 6.03 118 30.6 120 2.46 109 12.8 99 48.7 108 9.20 98 14.4 96 42.4 110 9.92 88 5.00 78 30.8 80 2.05 67 43.8 120 61.4 124 32.8 97 16.3 96 47.6 116 8.24 58 0.10 5 0.87 32 0.32 7 22.5 82 52.4 92 24.5 72
p-harmonic [29]87.9 3.47 81 19.1 89 2.29 102 8.40 70 35.9 62 6.80 77 12.8 88 34.6 89 9.84 87 9.04 112 47.6 117 6.72 111 37.1 103 48.7 97 39.6 115 13.1 47 44.0 104 11.2 96 3.43 78 2.50 89 6.33 56 21.2 75 45.2 70 30.5 94
LDOF [28]88.0 4.09 95 20.0 93 2.31 103 9.96 89 41.8 91 7.06 83 14.1 93 37.0 96 10.1 89 8.41 106 43.3 108 4.97 100 34.4 88 46.2 85 32.5 96 12.2 34 41.0 92 8.88 72 1.63 43 2.00 73 5.79 54 29.9 106 56.0 109 38.8 113
DF-Auto [115]88.2 4.71 103 22.2 100 2.11 92 21.1 112 49.4 110 21.6 112 20.3 109 39.8 107 31.0 114 7.62 101 37.5 99 5.08 102 33.6 82 43.9 65 33.3 100 8.36 7 29.8 26 7.48 42 2.60 60 5.21 121 2.22 22 32.4 115 53.1 98 43.2 117
TriFlow [95]89.2 3.53 84 17.9 82 1.77 82 11.0 97 37.3 68 10.6 99 16.7 103 35.8 94 25.3 110 4.44 71 30.9 82 2.34 71 35.0 95 44.3 69 35.7 106 10.7 24 30.4 29 6.68 21 33.4 143 9.63 141 90.0 145 30.3 109 55.2 108 36.8 108
FlowNetS+ft+v [112]91.7 3.75 90 18.5 84 2.13 95 10.0 91 38.8 79 8.25 95 16.3 101 37.5 101 20.0 102 7.89 102 37.0 98 5.17 103 36.9 102 48.2 94 35.7 106 11.6 30 40.0 83 9.13 75 4.56 87 4.02 108 14.6 100 23.8 90 51.0 87 31.9 98
Second-order prior [8]93.1 3.49 82 18.6 85 1.79 83 9.83 85 40.6 87 7.83 89 14.1 93 39.0 104 9.82 86 6.20 90 31.4 84 3.83 92 34.7 92 49.4 103 27.6 84 18.7 110 52.1 125 11.4 98 9.18 125 3.60 103 20.1 116 19.1 66 48.2 81 24.4 71
SuperFlow [81]93.5 3.40 79 16.6 73 1.81 87 15.3 103 41.5 89 15.9 106 17.0 104 35.2 92 27.6 111 10.0 117 43.1 107 8.60 116 36.1 97 44.3 69 46.7 129 13.1 47 39.8 82 11.3 97 2.49 57 4.24 112 4.26 41 30.0 107 54.7 106 40.8 115
Learning Flow [11]93.9 3.56 88 18.2 83 1.56 75 8.71 73 41.5 89 6.17 73 14.5 97 37.8 103 11.8 95 7.92 103 41.1 106 5.02 101 40.9 117 51.7 113 42.4 118 15.4 89 47.2 115 11.4 98 2.73 63 6.19 130 7.64 68 23.0 84 49.9 85 28.9 88
OFRF [134]94.0 3.10 70 15.9 70 1.40 56 21.2 113 45.4 105 20.7 111 18.7 107 34.6 89 22.6 107 7.09 96 30.2 76 5.59 106 30.2 62 44.8 76 16.7 29 18.6 108 43.5 100 10.2 88 6.14 109 3.78 104 25.5 122 34.2 121 53.5 100 54.4 130
CNN-flow-warp+ref [117]97.2 4.85 107 24.6 109 2.62 112 13.2 100 41.8 91 12.9 100 17.7 106 39.6 106 25.0 109 8.67 110 44.8 111 5.78 108 38.1 107 48.2 94 43.5 122 13.7 62 40.4 89 9.32 78 1.80 46 1.29 45 9.16 75 33.2 117 57.7 114 42.9 116
Ad-TV-NDC [36]97.6 10.3 128 20.2 94 18.1 139 38.1 126 53.0 117 43.3 130 28.0 122 45.6 114 35.7 118 20.6 124 48.9 121 23.8 125 29.1 56 42.5 59 19.1 42 13.7 62 36.1 57 9.46 81 2.03 51 1.43 46 4.38 43 41.4 130 65.3 126 57.0 132
WOLF_ROB [149]99.5 5.72 116 29.1 118 2.14 96 18.8 109 56.5 122 14.1 103 22.4 113 48.9 121 20.6 103 8.21 105 40.5 105 5.30 104 41.7 119 56.1 121 40.9 116 17.2 99 46.4 113 10.1 87 0.70 24 0.40 25 2.78 29 29.8 105 62.4 122 38.0 112
StereoOF-V1MT [119]99.8 4.08 94 23.0 101 1.49 68 10.4 94 53.3 118 4.35 42 16.3 101 49.5 122 5.71 65 7.37 99 48.5 119 4.03 94 46.7 124 62.9 127 42.9 121 21.9 122 64.7 134 17.0 118 1.58 40 1.87 65 9.43 77 33.2 117 66.2 127 36.5 106
BlockOverlap [61]101.4 4.14 99 17.3 78 3.50 116 23.3 114 43.1 99 25.5 116 21.0 110 37.2 97 27.8 112 13.1 118 39.0 102 13.7 120 28.8 51 38.6 39 28.2 86 18.7 110 37.2 62 13.3 107 12.6 136 6.40 133 40.8 137 26.8 102 45.8 72 43.3 118
Shiralkar [42]102.6 4.11 96 23.3 102 1.52 71 8.88 76 44.5 102 5.07 52 14.5 97 41.9 109 6.96 71 7.32 98 44.7 110 4.37 97 38.8 112 55.2 119 33.1 98 26.7 130 60.7 129 18.5 123 10.4 128 3.38 102 32.9 131 26.7 101 61.6 118 29.5 91
LFNet_ROB [151]102.8 8.75 125 41.6 136 3.69 121 18.9 110 59.4 123 15.2 105 24.3 115 60.8 134 21.2 104 8.64 109 49.0 122 5.67 107 50.3 129 66.9 132 46.2 128 17.8 102 52.5 126 12.5 103 0.17 8 0.05 8 1.03 15 26.6 99 61.9 120 27.8 85
SegOF [10]104.3 6.07 119 25.2 114 3.62 119 36.7 124 55.3 119 41.7 127 26.1 117 43.8 112 39.2 123 15.2 120 45.4 112 12.3 118 46.5 123 56.0 120 57.5 133 18.2 107 49.9 119 14.9 113 0.19 9 0.71 30 0.86 12 31.1 112 52.9 96 35.9 105
ContFlow_ROB [150]104.4 10.3 128 37.4 132 3.55 118 29.7 119 60.3 125 30.0 119 29.4 125 55.1 125 36.9 120 9.87 116 46.2 113 7.25 114 52.0 134 71.1 137 36.6 111 22.7 123 58.5 128 14.9 113 0.13 6 0.77 31 0.39 8 24.2 93 53.8 104 22.7 63
HBpMotionGpu [43]105.0 5.00 109 21.6 98 2.81 114 31.1 121 49.5 111 35.0 121 26.3 119 45.3 113 37.1 121 9.18 113 39.3 103 7.65 115 33.7 83 45.6 82 32.2 95 15.7 92 37.4 65 9.89 86 5.71 105 4.19 111 12.5 91 33.4 119 56.3 110 47.8 123
ResPWCR_ROB [145]105.1 5.84 117 29.6 119 2.83 115 15.8 104 51.1 113 13.4 102 21.2 111 48.5 120 21.2 104 8.43 107 47.3 116 5.39 105 41.2 118 57.0 122 37.4 112 19.2 115 53.0 127 15.6 116 1.16 31 1.66 60 5.49 52 31.6 113 62.2 121 34.6 103
StereoFlow [44]106.1 28.4 144 55.1 145 37.7 144 81.1 145 92.6 145 77.8 144 65.0 143 82.9 145 51.1 139 69.6 144 90.7 145 65.5 141 52.7 135 67.5 133 44.9 126 8.13 4 33.5 45 6.60 18 0.05 3 0.37 20 0.17 4 32.2 114 54.8 107 40.4 114
2bit-BM-tele [98]106.2 5.17 111 23.4 103 3.54 117 16.3 105 40.3 84 16.7 108 15.2 99 34.6 89 14.2 100 8.49 108 37.6 100 6.75 112 32.8 78 44.5 72 28.6 91 24.3 126 43.9 103 22.5 129 15.6 141 8.72 139 50.0 142 26.2 97 50.8 86 37.5 110
SPSA-learn [13]106.9 5.52 113 25.3 116 4.12 122 25.2 117 50.0 112 26.8 117 25.1 116 45.7 115 36.7 119 19.0 121 54.2 124 20.8 122 38.6 109 48.4 96 44.4 124 17.9 105 45.3 109 17.6 120 1.60 41 0.54 26 5.27 51 39.6 127 57.9 115 53.3 128
FlowNet2 [122]108.0 7.84 122 30.7 121 2.58 111 41.4 130 65.2 130 44.4 131 29.6 126 48.0 118 46.8 132 5.31 85 24.0 51 3.06 86 47.8 125 64.8 130 36.3 109 17.8 102 44.3 106 13.4 108 2.93 68 8.71 138 5.22 49 30.2 108 61.7 119 28.8 87
IAOF2 [51]108.1 4.13 97 20.4 96 2.02 91 18.0 107 45.9 106 18.0 109 17.1 105 37.3 98 21.4 106 46.4 135 57.8 126 56.1 138 37.4 105 48.8 98 35.9 108 25.5 127 42.7 98 20.4 126 6.62 112 3.04 99 15.3 107 26.8 102 51.0 87 37.9 111
AugFNG_ROB [144]108.6 9.81 127 36.9 131 4.29 123 38.3 127 64.3 128 42.6 129 29.2 124 57.1 127 38.5 122 7.41 100 39.4 104 4.51 98 50.9 130 70.1 136 37.7 113 17.0 98 50.1 120 13.6 110 0.23 11 2.25 83 0.17 4 36.5 124 68.9 132 36.5 106
Filter Flow [19]109.1 5.13 110 23.5 104 2.40 108 20.5 111 51.3 114 19.6 110 23.3 114 42.6 111 35.3 117 27.2 127 48.8 120 28.3 127 39.4 113 49.1 99 44.6 125 17.9 105 40.5 90 11.8 101 7.39 117 7.67 136 11.5 86 26.6 99 46.0 73 33.9 101
EPMNet [133]109.1 7.68 121 33.7 125 2.38 107 39.6 128 72.0 139 40.0 126 27.9 121 46.4 116 44.6 130 7.12 97 38.7 101 3.78 91 47.8 125 64.8 130 36.3 109 17.8 102 44.3 106 13.4 108 1.56 39 5.60 125 2.27 23 33.0 116 70.0 133 32.3 100
Black & Anandan [4]110.0 5.52 113 25.2 114 4.71 125 24.4 116 52.8 115 24.4 115 26.8 120 48.3 119 34.4 116 20.9 125 60.4 127 22.4 124 38.7 111 49.7 104 42.8 120 18.9 112 49.4 117 17.1 119 1.78 45 2.57 92 3.30 31 36.0 122 57.3 113 49.5 124
Modified CLG [34]112.3 7.42 120 31.9 123 5.50 126 31.7 122 52.9 116 37.6 124 28.4 123 50.8 123 40.4 125 20.3 123 60.5 128 21.3 123 39.5 115 51.2 109 42.2 117 14.2 72 45.8 112 11.5 100 3.24 71 1.70 63 9.31 76 40.3 128 65.1 125 54.7 131
IAOF [50]113.1 5.70 115 24.0 106 3.65 120 30.0 120 48.7 108 33.9 120 26.2 118 47.8 117 29.5 113 28.0 128 51.3 123 32.9 128 37.3 104 50.2 105 34.4 103 26.2 128 50.9 123 18.0 122 5.85 107 1.63 54 11.7 87 36.3 123 59.4 117 51.9 126
TVL1_ROB [139]113.6 16.9 135 35.6 127 25.2 141 53.5 137 60.5 126 64.0 138 36.2 131 58.7 128 48.0 135 44.6 134 72.3 134 52.0 135 39.5 115 50.7 106 42.5 119 15.5 90 47.0 114 14.1 112 0.40 15 0.66 29 1.90 19 47.4 135 71.1 135 60.2 137
GraphCuts [14]114.8 5.45 112 24.7 110 2.64 113 24.3 115 55.8 121 21.9 114 21.4 112 40.8 108 32.4 115 9.25 115 46.4 114 6.31 110 38.6 109 51.7 113 33.8 101 28.8 133 39.7 81 18.7 124 12.1 135 2.87 96 35.1 134 38.5 125 58.4 116 53.9 129
2D-CLG [1]117.4 14.0 133 40.7 134 8.09 131 45.8 132 59.5 124 54.5 135 36.8 133 60.4 133 47.3 133 48.9 137 75.1 138 54.2 137 44.9 121 54.8 117 52.5 130 19.0 113 50.3 122 17.8 121 1.26 33 0.07 9 4.43 44 47.4 135 71.2 136 59.9 136
GroupFlow [9]117.9 8.95 126 33.2 124 7.07 128 43.6 131 70.7 135 45.5 132 32.7 128 59.8 132 42.4 128 13.2 119 46.6 115 12.4 119 51.1 131 70.0 135 34.2 102 30.8 135 62.8 131 33.8 136 1.54 38 2.56 91 4.14 37 39.0 126 67.0 129 47.4 122
UnFlow [129]119.2 22.1 142 43.6 138 7.44 130 52.6 136 73.8 140 54.3 134 47.7 139 74.9 142 47.5 134 26.4 126 68.7 132 24.7 126 64.5 140 75.5 142 65.6 140 28.5 132 67.0 138 27.1 133 0.19 9 1.87 65 0.05 2 30.4 110 62.4 122 36.8 108
Nguyen [33]119.7 8.19 123 31.4 122 4.40 124 54.9 138 55.7 120 70.2 140 33.6 130 54.6 124 43.3 129 43.5 133 60.9 129 50.5 134 45.1 122 54.9 118 54.2 131 21.1 119 49.4 117 21.0 127 2.92 67 1.87 65 7.39 66 44.7 133 66.2 127 58.5 134
Horn & Schunck [3]121.4 8.56 124 35.5 126 7.11 129 29.4 118 65.4 131 28.1 118 33.4 129 64.4 136 41.2 127 30.6 129 67.2 131 33.6 129 49.1 128 61.3 123 55.5 132 26.4 129 64.7 134 26.1 132 3.02 69 3.95 106 2.44 24 48.8 137 75.0 138 58.8 135
SILK [79]123.9 10.7 130 35.7 128 14.6 136 37.7 125 64.2 127 42.5 128 32.3 127 59.3 130 40.6 126 19.9 122 56.8 125 20.4 121 51.6 133 62.6 126 59.6 136 27.2 131 63.0 132 23.2 130 4.92 96 1.68 62 13.1 93 46.9 134 71.6 137 61.7 139
TI-DOFE [24]128.1 21.2 140 43.7 139 34.5 143 64.6 143 71.9 138 76.5 143 47.1 138 75.6 143 53.7 140 57.3 139 76.4 139 65.6 142 51.5 132 63.9 128 60.0 137 30.4 134 65.8 137 33.2 134 2.24 54 1.65 57 5.22 49 59.1 141 82.1 143 71.2 142
Periodicity [78]128.2 11.0 131 41.5 135 5.85 127 35.3 123 64.5 129 36.8 123 51.0 140 55.5 126 61.7 142 49.6 138 81.4 141 48.4 133 66.0 142 83.6 145 59.0 134 46.1 140 76.4 142 43.0 140 1.67 44 5.33 123 8.13 70 48.8 137 78.9 140 57.5 133
Heeger++ [104]129.4 24.4 143 45.8 140 9.72 133 47.8 134 85.9 144 37.8 125 66.2 144 69.8 139 75.2 143 59.7 141 88.6 144 56.9 139 66.6 143 80.3 144 62.4 139 65.6 145 87.3 145 67.1 145 4.14 84 1.26 44 7.39 66 41.9 131 68.8 130 43.4 120
SLK [47]132.2 17.8 137 50.1 143 21.7 140 62.2 142 77.8 142 74.7 142 40.4 136 72.7 141 48.1 136 66.2 142 73.9 136 76.1 144 60.9 138 71.2 138 72.9 144 33.1 136 68.3 140 35.4 138 5.99 108 1.09 38 11.4 85 60.5 143 81.9 142 75.0 143
FFV1MT [106]132.8 22.0 141 42.2 137 9.20 132 41.0 129 76.9 141 36.1 122 66.5 145 71.9 140 79.2 144 58.5 140 87.7 143 57.1 140 64.8 141 76.5 143 70.3 143 64.8 144 85.8 144 65.3 144 4.70 91 4.86 118 11.3 84 41.9 131 68.8 130 43.4 120
Adaptive flow [45]133.3 16.0 134 36.3 129 17.5 138 57.9 139 67.3 132 64.2 139 38.7 135 59.2 129 48.8 137 39.9 131 69.2 133 44.2 132 49.0 127 62.0 125 43.6 123 39.1 139 62.2 130 34.3 137 34.2 144 23.4 144 82.8 143 40.6 129 64.9 124 51.9 126
H+S_ROB [138]133.3 19.8 138 52.3 144 11.9 135 59.1 140 81.5 143 63.0 137 52.7 141 80.5 144 49.7 138 77.0 145 84.8 142 83.9 145 68.5 145 73.1 139 94.1 145 47.1 141 76.6 143 51.9 142 3.54 80 1.65 57 10.8 82 74.4 145 85.4 145 76.7 144
FOLKI [16]134.9 13.4 132 45.9 141 16.0 137 48.5 135 67.4 133 57.8 136 36.6 132 66.2 137 40.3 124 32.2 130 66.9 130 37.2 130 52.9 136 64.2 129 60.1 138 34.7 137 65.7 136 40.2 139 12.9 137 7.56 135 33.8 133 55.3 140 78.0 139 70.7 141
PGAM+LK [55]137.1 17.6 136 48.4 142 26.7 142 45.8 132 71.8 137 49.9 133 38.3 134 67.6 138 44.6 130 42.8 132 79.5 140 42.6 131 56.5 137 69.9 134 59.0 134 37.8 138 70.5 141 33.6 135 23.5 142 15.0 143 48.8 141 54.6 139 80.9 141 61.1 138
Pyramid LK [2]138.0 19.8 138 36.7 130 40.3 145 61.8 141 68.8 134 74.6 141 43.5 137 63.7 135 58.2 141 46.9 136 72.7 135 54.1 136 61.5 139 74.5 141 65.8 141 51.3 142 64.1 133 50.1 141 10.8 131 6.30 131 31.9 130 68.2 144 84.9 144 84.8 145
HCIC-L [99]140.8 29.6 145 37.7 133 11.4 134 77.3 144 71.7 136 90.9 145 63.0 142 59.4 131 83.6 145 66.9 143 74.8 137 69.8 143 68.1 144 74.1 140 66.1 142 54.4 143 67.4 139 52.5 143 58.9 145 43.5 145 89.4 144 59.4 142 70.0 133 67.4 140
AdaConv-v1 [126]146.5 82.5 146 78.4 146 94.0 147 98.6 146 99.3 146 97.9 146 99.9 146 99.9 146 99.9 146 97.4 147 96.9 147 99.7 147 100.0 147 99.9 147 99.8 147 93.4 146 95.5 147 93.4 146 86.5 147 85.7 147 99.4 147 99.9 146 99.9 146 99.9 146
SepConv-v1 [127]146.5 82.5 146 78.4 146 94.0 147 98.6 146 99.3 146 97.9 146 99.9 146 99.9 146 99.9 146 97.4 147 96.9 147 99.7 147 100.0 147 99.9 147 99.8 147 93.4 146 95.5 147 93.4 146 86.5 147 85.7 147 99.4 147 99.9 146 99.9 146 99.9 146
SuperSlomo [132]146.5 82.5 146 78.4 146 94.0 147 98.6 146 99.3 146 97.9 146 99.9 146 99.9 146 99.9 146 97.4 147 96.9 147 99.7 147 100.0 147 99.9 147 99.8 147 93.4 146 95.5 147 93.4 146 86.5 147 85.7 147 99.4 147 99.9 146 99.9 146 99.9 146
FGIK [136]146.5 82.5 146 78.4 146 94.0 147 98.6 146 99.3 146 97.9 146 99.9 146 99.9 146 99.9 146 97.4 147 96.9 147 99.7 147 100.0 147 99.9 147 99.8 147 93.4 146 95.5 147 93.4 146 86.5 147 85.7 147 99.4 147 99.9 146 99.9 146 99.9 146
CtxSyn [137]146.5 82.5 146 78.4 146 94.0 147 98.6 146 99.3 146 97.9 146 99.9 146 99.9 146 99.9 146 97.4 147 96.9 147 99.7 147 100.0 147 99.9 147 99.8 147 93.4 146 95.5 147 93.4 146 86.5 147 85.7 147 99.4 147 99.9 146 99.9 146 99.9 146
AVG_FLOW_ROB [142]147.9 93.7 151 89.5 151 90.8 146 99.0 151 99.4 151 98.5 151 99.9 146 99.9 146 99.9 146 95.9 146 91.8 146 95.9 146 99.8 146 99.7 146 99.7 146 96.8 151 95.1 146 94.6 151 85.8 146 76.3 146 97.8 146 100.0 151 100.0 151 99.9 146
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.