GCANet: A Geometric Consistency-driven Aggregation Network for Robust Primitive Segmentation on Point Clouds
Loading...
Date
2024
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Primitive 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.
Description
CCS Concepts: Computing methodologies → Point-based models; Shape analysis
@inproceedings{10.2312:pg.20241282,
booktitle = {Pacific Graphics Conference Papers and Posters},
editor = {Chen, Renjie and Ritschel, Tobias and Whiting, Emily},
title = {{GCANet: A Geometric Consistency-driven Aggregation Network for Robust Primitive Segmentation on Point Clouds}},
author = {Huang, Anyi and Li, Zikuan and Wang, Zhoutao and Wu, Xiang and Wang, Jun},
year = {2024},
publisher = {The Eurographics Association},
ISBN = {978-3-03868-250-9},
DOI = {10.2312/pg.20241282}
}