Journal
COMPUTATIONAL VISUAL MEDIA
Volume 7, Issue 2, Pages 187-199Publisher
TSINGHUA UNIV PRESS
DOI: 10.1007/s41095-021-0229-5
Keywords
3D computer vision; deep learning; point cloud processing; Transformer
Categories
Funding
- National Natural Science Foundation of China [61521002]
- Joint NSFC-DFG Research Program [61761136018]
Ask authors/readers for more resources
This paper introduces a novel framework named Point Cloud Transformer (PCT) for point cloud learning, based on Transformer and enhanced by farthest point sampling and nearest neighbor search for better capturing local context. Extensive experiments demonstrate that the PCT achieves state-of-the-art performance on shape classification, part segmentation, semantic segmentation, and normal estimation tasks.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available