Wang, Tao, Wu, Jing ORCID: https://orcid.org/0000-0001-5123-9861, Ji, Ze ORCID: https://orcid.org/0000-0002-8968-9902 and Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680 2023. RPS-Net: Indoor scene point cloud completion using RBF-point sparse convolution. Presented at: EG UK Computer Graphics & Visual Computing, Aberystwyth, UK, 14-15 September 2023. Proceedings EG UK Computer Graphics & Visual Computing. Eurographics - The European Association for Computer Graphics, 10.2312/cgvc.20231188 |
Preview |
PDF
- Published Version
Available under License Creative Commons Attribution. Download (2MB) | Preview |
Abstract
We introduce a novel approach to the completion of 3D scenes, which is a practically important task as captured point clouds of 3D scenes tend to be incomplete due to limited sensor range and occlusion. We address this problem by utilising sparse convolutions, commonly used for recognition tasks, to this content generation task, which can well capture the spatial relationships while ensuring high efficiency, as only samples near the surface need to be processed. Moreover, traditional sparse convolutions only consider grid occupancies, which cannot accurately locate surface points, with unavoidable quantisation errors. Observing that local surface patches have common patterns, we propose to sample a Radial Basis Function (RBF) field within each grid which is then compactly represented using a Point Encoder-Decoder (PED) network. This further provides a compact and effective representation for 3D completion, and the decoded latent feature includes important information of the local area of the point cloud for more accurate, sub-voxel level completion. Extensive experiments demonstrate that our method outperforms state-of-the-art methods by a large margin
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Status: | Published |
Schools: | Advanced Research Computing @ Cardiff (ARCCA) Computer Science & Informatics Engineering |
Publisher: | Eurographics - The European Association for Computer Graphics |
ISBN: | 978-3-03868-231-8 |
Date of First Compliant Deposit: | 20 September 2023 |
Date of Acceptance: | 25 July 2023 |
Last Modified: | 11 Jun 2024 12:35 |
URI: | https://orca.cardiff.ac.uk/id/eprint/162645 |
Actions (repository staff only)
Edit Item |