Region Expansion: Optimization of Patch-Fetching Method for Point Cloud Denoising

Tao Deng, Shengtao Li, Jiadun Wang, Daosong Hu, Kai Huang

Abstract: Point clouds often suffer from noise during capture, which can negatively impact downstream tasks such as analysis and surface reconstruction. Denoising is thus a fundamental task in 3D vision. Large point clouds frequently exceed hardware capabilities, requiring division into smaller patches for efficient processing. Existing denoising methods typically use kNN or ballquery to divide point clouds into patches to learn shape features. However, these methods struggle to recover local features accurately and can be misled by outliers. To address these challenges, we propose the RegionExpansion method, which iteratively selects patches with a relatively small radius on the CUDA platform, enabling localized region expansion. By refining patch extraction, our method balances efficiency and accuracy, successfully removing most outliers during preprocessing and preserving sharp geometric features. Experimental results demonstrate that our method achieves better performance compared to common patch-fetching methods. The source code is available at: https://github.com/only-tao/RegionExpansion.

External IDs:dblp:conf/icann/DengLWHH25