Graph Smoothing for Enhanced Local Geometry Learning in Point Cloud Analysis
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (15) · 12250-12258
DOI: 10.1609/aaai.v40i15.38216 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Shangbo Yuan und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
Graph-based methods have proven to be effective in capturing relationships among points for 3D point cloud analysis. However, these methods often suffer from suboptimal graph structures, particularly due to sparse connections at boundary points and noisy connections in junction areas. To address these challenges, we propose a novel method that integrates a graph smoothing module with an enhanced local geometry learning module. Specifically, we identify the limitations of conventional graph structures, particularly in handling boundary points and junction areas. In response, we introduce a graph smoothing module designed to optimize the graph structure and minimize the negative impact of unreliable sparse and noisy connections. Based on the optimized graph structure, we improve the feature extract function with local geometry information. These include shape features derived from adaptive geometric descriptors based on eigenvectors and distribution features obtained through cylindrical coordinate transformation. Experimental results on real-world datasets validate the effectiveness of our method in various point cloud learning tasks, i.e., classification, part segmentation, and semantic segmentation.
Zitieren
APA
Yuan, S., Xu, J., Hu, P., Zhu, X., & Zhao, N. (2026). Graph Smoothing for Enhanced Local Geometry Learning in Point Cloud Analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 40(15), 12250-12258. https://doi.org/10.1609/aaai.v40i15.38216
Vancouver
Yuan S, Xu J, Hu P, Zhu X, Zhao N. Graph Smoothing for Enhanced Local Geometry Learning in Point Cloud Analysis. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(15):12250-12258. doi:10.1609/aaai.v40i15.38216
BibTeX
@article{Yuan2026,
author = {Yuan, Shangbo and Xu, Jie and Hu, Ping and Zhu, Xiaofeng and Zhao, Na},
title = {Graph Smoothing for Enhanced Local Geometry Learning in Point Cloud Analysis},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {15},
pages = {12250--12258},
doi = {10.1609/aaai.v40i15.38216}
}
EUVIMED