PCT: Point cloud transformer

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 pr...

Full description

Saved in:
Bibliographic Details
Published in:Computational visual media (Beijing) Vol. 7; no. 2; pp. 187 - 199
Main Authors: Guo, Meng-Hao, Cai, Jun-Xiong, Liu, Zheng-Ning, Mu, Tai-Jiang, Martin, Ralph R., Hu, Shi-Min
Format: Journal Article
Language:English
Published: Beijing Tsinghua University Press 01.06.2021
Springer Nature B.V
Subjects:
Artificial Intelligence
Artificial neural networks
Computer Graphics
Computer Science
Image processing
Image Processing and Computer Vision
Image segmentation
Machine learning
Natural language processing
Permutations
Research Article
Transformers
User Interfaces and Human Computer Interaction
deep learning
point cloud processing
3D computer vision
Transformer
ISSN:2096-0433, 2096-0662
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2096-0433
2096-0662
DOI:10.1007/s41095-021-0229-5