SAF-Nets: Shape-Adaptive Filter Networks for 3D point cloud processing*
- Authors
- Lee, Seon-Ho; Kim, Chang-Su
- Issue Date
- 8월-2021
- Publisher
- ACADEMIC PRESS INC ELSEVIER SCIENCE
- Keywords
- Deep learning; Point cloud processing; Shape-adaptive filter
- Citation
- JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, v.79
- Indexed
- SCIE
SCOPUS
- Journal Title
- JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
- Volume
- 79
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/136992
- DOI
- 10.1016/j.jvcir.2021.103246
- ISSN
- 1047-3203
- Abstract
- A deep learning framework for 3D point cloud processing is proposed in this work. In a point cloud, local neighborhoods have various shapes, and the semantic meaning of each point is determined within the local shape context. Thus, we propose shape-adaptive filters (SAFs), which are dynamically generated from the distributions of local points. The proposed SAFs can extract robust features against noise or outliers, by employing local shape contexts to suppress them. Also, we develop the SAF-Nets for classification and segmentation using multiple SAF layers. Extensive experimental results demonstrate that the proposed SAF-Nets significantly outperform the state-of-the-art conventional algorithms on several benchmark datasets. Moreover, it is shown that SAFs can improve scene flow estimation performance as well.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > School of Electrical Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.