HD-PointNet: point cloud processing in higher dimensions

Wenjuan Tang; Hainan Wang; Hua Shan; Yue Meng; Mei Wu

doi:10.1117/12.3009233

16 October 2023 HD-PointNet: point cloud processing in higher dimensions

Wenjuan Tang, Hainan Wang, Hua Shan, Yue Meng, Mei Wu

Proceedings Volume 12803, Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023); 128032P (2023) https://doi.org/10.1117/12.3009233
Event: 2023 5th International Conference on Artificial Intelligence and Computer Science (AICS 2023), 2023, Wuhan, China

Abstract

PointNet++ is a simple but effective network designed for point cloud processing. However, the accuracy of PointNet++ has been surpassed by many other methods, like DGCNN and Point Cloud Transformer. These methods are way heavier compared to PointNet++, which is not favorable for the deployment of real-world products. In this paper, we propose a module called HD projection layers that was inspired by nonlinear kernels used in support vector machines. The HD projection layers project the features of the point cloud into a higher dimension, increasing the linear separability and therefore relieving the burden on the classifier. Equipped with HD projection layers, we extended PointNet++ into a new network, HD-PointNet, which also involves many other improvements and better training techniques. Experiments show that the accuracy of HD-PointNet is competitive against other modern methods while using fewer computation resources.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Wenjuan Tang, Hainan Wang, Hua Shan, Yue Meng, and Mei Wu "HD-PointNet: point cloud processing in higher dimensions", Proc. SPIE 12803, Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023), 128032P (16 October 2023); https://doi.org/10.1117/12.3009233

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Point clouds

3D modeling

3D projection

Feature extraction

Machine learning

Support vector machines

Transformers

Show All Keywords

Keywords/Phrases

Search In:

Publication Years