PCT: Point cloud transformer

Guo, Meng-Hao, Cai, Jun-Xiong, Liu, Zheng-Ning, Mu, Tai-Jiang, Martin, Ralph R. and Hu, Shi-Min 2021. PCT: Point cloud transformer. Computational Visual Media 7 (2) , 187–199. 10.1007/s41095-021-0229-5

PDF - Published Version Available under License Creative Commons Attribution. Download (1MB)

Abstract

The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing. This paper presents a novel framework named Point Cloud Transformer (PCT) for point cloud learning. PCT is based on Transformer, which achieves huge success in natural language processing and displays great potential in image processing. It is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning. To better capture local context within the point cloud, we enhance input embedding with the support of farthest point sampling and nearest neighbor search. Extensive experiments demonstrate that the PCT achieves the state-of-the-art performance on shape classification, part segmentation, semantic segmentation, and normal estimation tasks.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Additional Information:	This article is licensed under a Creative Commons Attribution 4.0 International License
Publisher:	SpringerOpen
ISSN:	2096-0433
Date of First Compliant Deposit:	27 July 2021
Date of Acceptance:	26 March 2021
Last Modified:	04 May 2023 12:33
URI:	https://orca.cardiff.ac.uk/id/eprint/142935

Citation Data

Cited 157 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item