GCANet: A Geometric Consistency-driven Aggregation Network for Robust Primitive Segmentation on Point Clouds

Simple item page
dc.contributor.authorHuang, Anyien_US
dc.contributor.authorLi, Zikuanen_US
dc.contributor.authorWang, Zhoutaoen_US
dc.contributor.authorWu, Xiangen_US
dc.contributor.authorWang, Junen_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:03:33Z
dc.date.available2024-10-13T18:03:33Z
dc.date.issued2024
dc.description.abstractPrimitive segmentation aims to decompose a 3D point cloud into parametric surface patches, which is a common task in 3D measurement. Existing methods primarily learn point cloud feature embedding through neural networks and then perform feature clustering to generate segmentation results. Since spatial relationships are not considered, these methods often exhibit poor generalization to noisy real-scan point clouds. To address this problem, this paper proposes a geometric consistency-driven aggregation network (GCANet) that performs spatial aggregation of primitive points driven by a designed geometric consistency feature (GCF). We also design a direction-aware offset prediction module to improve centroid offset prediction accuracy. More specifically, we leverage the GCF to search for geometric consistency points and then construct the direction-aware feature to guide centroid offset prediction. Experimental results on the ABCParts dataset show that our method achieves competitive performance compared to state-of-the-art (SOTA) methods. Moreover, the SOTA results on the noisy ABCParts dataset validate the strong generalization ability of our GCANet. Our code is publicly available at https://github.com/hay-001/GCANet.en_US
dc.description.sectionheadersPoint Cloud Processing and Analysis II
dc.description.seriesinformationPacific Graphics Conference Papers and Posters
dc.identifier.doi10.2312/pg.20241282
dc.identifier.isbn978-3-03868-250-9
dc.identifier.pages8 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20241282
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20241282
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 → Point-based models; Shape analysis
dc.subjectComputing methodologies → Point
dc.subjectbased models
dc.subjectShape analysis
dc.titleGCANet: A Geometric Consistency-driven Aggregation Network for Robust Primitive Segmentation on Point Cloudsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
pg20241282.pdf
Size:
2.39 MB
Format:
Adobe Portable Document Format
Download
Collections
PG2024 Conference Papers and Posters