CMG-Net: Robust Normal Estimation for Point Clouds via Chamfer Normal Distance and Multi-Scale Geometry
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (6) · 6171-6179
DOI: 10.1609/aaai.v38i6.28434 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Yingrui Wu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref).
Abstract (Originalsprache)
This work presents an accurate and robust method for estimating normals from point clouds. In contrast to predecessor approaches that minimize the deviations between the annotated and the predicted normals directly, leading to direction inconsistency, we first propose a new metric termed Chamfer Normal Distance to address this issue. This not only mitigates the challenge but also facilitates network training and substantially enhances the network robustness against noise. Subsequently, we devise an innovative architecture that encompasses Multi-scale Local Feature Aggregation and Hierarchical Geometric Information Fusion. This design empowers the network to capture intricate geometric details more effectively and alleviate the ambiguity in scale selection. Extensive experiments demonstrate that our method achieves the state-of-the-art performance on both synthetic and real-world datasets, particularly in scenarios contaminated by noise. Our implementation is available at https://github.com/YingruiWoo/CMG-Net_Pytorch.
Zitieren
APA
Wu, Y., Zhao, M., Li, K., Quan, W., Yu, T., Yang, J., Jia, X., & Yan, D. (2024). CMG-Net: Robust Normal Estimation for Point Clouds via Chamfer Normal Distance and Multi-Scale Geometry. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 6171-6179. https://doi.org/10.1609/aaai.v38i6.28434
Vancouver
Wu Y, Zhao M, Li K, Quan W, Yu T, Yang J, et al. CMG-Net: Robust Normal Estimation for Point Clouds via Chamfer Normal Distance and Multi-Scale Geometry. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(6):6171-6179. doi:10.1609/aaai.v38i6.28434
BibTeX
@article{Wu2024,
author = {Wu, Yingrui and Zhao, Mingyang and Li, Keqiang and Quan, Weize and Yu, Tianqi and Yang, Jianfeng and Jia, Xiaohong and Yan, Dong-Ming},
title = {CMG-Net: Robust Normal Estimation for Point Clouds via Chamfer Normal Distance and Multi-Scale Geometry},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {6},
pages = {6171--6179},
doi = {10.1609/aaai.v38i6.28434}
}
EUVIMED