RPS-Net: Indoor Scene Point Cloud Completion using RBF-Point Sparse Convolution

Simple item page
dc.contributor.authorWang, Taoen_US
dc.contributor.authorWu, Jingen_US
dc.contributor.authorJi, Zeen_US
dc.contributor.authorLai, Yu-Kunen_US
dc.contributor.editorVangorp, Peteren_US
dc.contributor.editorHunter, Daviden_US
dc.date.accessioned2023-09-12T05:44:46Z
dc.date.available2023-09-12T05:44:46Z
dc.date.issued2023
dc.description.abstractWe 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.en_US
dc.description.sectionheadersShape Reconstruction
dc.description.seriesinformationComputer Graphics and Visual Computing (CGVC)
dc.identifier.doi10.2312/cgvc.20231188
dc.identifier.isbn978-3-03868-231-8
dc.identifier.pages29-37
dc.identifier.pages9 pages
dc.identifier.urihttps://doi.org/10.2312/cgvc.20231188
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/cgvc20231188
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies -> Shape representations; Point-based models
dc.subjectComputing methodologies
dc.subjectShape representations
dc.subjectPoint
dc.subjectbased models
dc.titleRPS-Net: Indoor Scene Point Cloud Completion using RBF-Point Sparse Convolutionen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
029-037.pdf
Size:
2.89 MB
Format:
Adobe Portable Document Format
Download
Collections
Computer Graphics & Visual Computing (CGVC) 2023