Transformer enhanced hierarchical 3D point cloud semantic segmentation

Yaohua Liu; Yue Ma; Min Xu

doi:10.1117/12.2638832

17 May 2022 Transformer enhanced hierarchical 3D point cloud semantic segmentation

Yaohua Liu, Yue Ma, Min Xu

Proceedings Volume 12259, 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2022); 122590C (2022) https://doi.org/10.1117/12.2638832
Event: 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing, 2022, Kunming, China

Abstract

Point cloud can represent 3D geometry conveniently, but its challenging for computers to process it. In this work, we design a transformer enhanced hierarchical neural network for accurate large scale point cloud semantic segmentation. We use semantic space's transformer block to learn global feature correlation. In this way, we can expand the receptive field of network to the whole input point cloud. Experimental results on S3DIS 3d semantic segmentation dataset show that, compared with the traditional hierarchical 3d semantic segmentation model, our transformer-enhanced hierarchical model achieved higher performance on overall accuracy and mIoU.

Citation Download Citation

Yaohua Liu, Yue Ma, and Min Xu "Transformer enhanced hierarchical 3D point cloud semantic segmentation", Proc. SPIE 12259, 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2022), 122590C (17 May 2022); https://doi.org/10.1117/12.2638832

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