Geometry-Guided Latent Diffusion Model for Static Point Cloud Color Attribute Denoising
IEEE Signal Processing Letters · 2025 · 32 · 2947-2951
DOI: 10.1109/lsp.2025.3590672 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2025. Verfasst von Linwei Zhu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 26 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Basic and Applied Basic Research Foundation of Guangdong Province, Shenzhen Science and Technology Program.
Abstract (Originalsprache)
Point cloud denoising is a challenging task due to the high-dimensional nature of data. To remove the compression artifact in the point cloud, this letter presents a static point cloud color attribute denoising method based on the geometry-guided Latent Diffusion Model (LDM). In specific, to better mimic realistic noise in LDM, we propose a color noise simulation strategy that interpolates distortion levels from Geometry-Based Point Cloud Compression (G-PCC) into the continuous noise distribution. Additionally, a dynamic sampling step control mechanism adaptively allocates diffusion steps based on local texture complexity, ensuring detailed denoising in complex regions while efficiently processing smoother areas. In the reverse denoising process, the geometry information is enabled as condition to guide color attribute recovery. Experimental results indicate that our method outperforms the state-of-the-art work, effectively balancing denoising quality and computational efficiency.
Förderung
- National Natural Science Foundation of China
- Basic and Applied Basic Research Foundation of Guangdong Province
- Shenzhen Science and Technology Program
- Chinese Academy of Sciences
- International Fellowship Initiative
Zitieren
APA
Zhu, L., Liang, R., Zhang, Y., Jiang, G., & Ho, Y. (2025). Geometry-Guided Latent Diffusion Model for Static Point Cloud Color Attribute Denoising. IEEE Signal Processing Letters, 32, 2947-2951. https://doi.org/10.1109/lsp.2025.3590672
Vancouver
Zhu L, Liang R, Zhang Y, Jiang G, Ho Y. Geometry-Guided Latent Diffusion Model for Static Point Cloud Color Attribute Denoising. IEEE Signal Processing Letters. 2025;32:2947-2951. doi:10.1109/lsp.2025.3590672
BibTeX
@article{Zhu2025,
author = {Zhu, Linwei and Liang, Ruxu and Zhang, Yun and Jiang, Gangyi and Ho, Yo-Sung},
title = {Geometry-Guided Latent Diffusion Model for Static Point Cloud Color Attribute Denoising},
journal = {IEEE Signal Processing Letters},
year = {2025},
volume = {32},
pages = {2947--2951},
doi = {10.1109/lsp.2025.3590672}
}
EUVIMED