Optics and Precision Engineering, Volume. 29, Issue 10, 2504(2021)
Co-segmentation of three-dimensional shape clusters by shape similarity
Figures & Tables(8)
Table 1. Comparison of segmentation results between our algorithm and other algorithms
View tableView in ArticleTable 1. Comparison of segmentation results between our algorithm and other algorithms
Algorithms
mIoU/%
pIoU/%
PointNet［
5 ］80.4
83.6
PointASNL
［ 10］83.3
86.1 PointNet++［
19 ］81.9
85.1
MACL［
27 ］71.8
75.2
SPLATNet［
28 ］83.7 85.4
Ours
83.3
86.0
Table 2. Comparison of IoU of different algorithms on various shapes
View tableView in ArticleTable 2. Comparison of IoU of different algorithms on various shapes
Method Air.
（2 690）
Bag
（76）
Cap
（55）
Car
（898）
Chair
（3 758）
Ear.
（69）
Guitar
（787）
Knife
（392）
PointNet［ 5 ］83.4 78.7 82.5 74.9 89.6 73.0 91.5 85.9 PointASNL［ 10 ］84.1 84.7 87.9 79.7 92.2 73.7 91.0 87.2 PointNet++［ 19 ］82.4 79.0 87.7 77.3 90.8 71.8 91.0 85.9 MACL［ 27 ］75 74.5 74.0 54.5 81.3 66.5 88.4 84.4 SPLATNet［ 28 ］83.2 84.3 89.1 80.3 90.7 75.5 92.1 87.1 Ours 83.2 84.0 85.7 80.3 91.1 78.5 90.3 88.4 Method Lamp
（1 547）
Lap.
（451）
Motor.
（202）
Mug
（184）
Pistol
（283）
Rocket
（66）
Skate.
（152）
Table
（5 271）
PointNet［ 5 ］80.8 95.3 65.2 93.0 81.2 57.9 72.8 80.6 PointASNL［ 10 ］84.2 95.8 74.4 95.2 81.0 63.0 76.3 83.2 PointNet++［ 19 ］83.7 95.3 71.6 94.1 81.3 58.7 76.4 82.6 MACL［ 27 ］77.6 78.2 51.3 87.3 66.6 55.0 62.1 71.7 SPLATNet［ 28 ］83.9 96.3 75.6 95.8 83.8 64.0 75.5 81.8 Ours 85.7 95.6 73.7 95.4 81.9 60.0 76.1 83.3
Table 3. Comparison of segmentation time between our algorithm and other algorithms
View tableView in ArticleTable 3. Comparison of segmentation time between our algorithm and other algorithms
#points Input Time Training/min Test/ms PointNet［ 5 ］1 024 Coordinates 793 22 PointASNL［ 10 ］2 048 Coordinates - - PointNet++［ 19 ］1 024 Coordinates+Normals 1 266 47 MACL［ 27 ］2 048 Coordinates 976.8 60.7 SPLATNet［ 28 ］- - 943 60.4 Ours 1 024 Coordinates 859 41.9
Table 4. Effectiveness verification of different components for co-segmentation of 3D shape clusters
View tableView in ArticleTable 4. Effectiveness verification of different components for co-segmentation of 3D shape clusters
Sampling pIoU/% Shared MLP FA Conv kNN 67.5 85.2 Random-PiS 73.1 86.0
Tools
Get Citation
Copy Citation Text
Jun Yang, Min-min Zhang. Co-segmentation of three-dimensional shape clusters by shape similarity[J]. Optics and Precision Engineering, 2021, 29(10): 2504
Paper Information
Category: Information Sciences
Received: Apr. 25, 2021
Accepted: --
Published Online: Nov. 23, 2021
The Author Email: Yang Jun (yangj@mail.lzjtu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20