Gradient-based Point Cloud Denoising with Uniformity
This work solves the problem of noisy point clouds for applications like surface reconstruction, but it is incremental as it builds on prior gradient-based denoisers.
The paper tackles point cloud denoising by addressing the lack of uniformity in existing gradient-based methods, proposing GPCD++ with a lightweight UniNet to improve uniformity while achieving competitive or better denoising results.
Point clouds captured by depth sensors are often contaminated by noises, obstructing further analysis and applications. In this paper, we emphasize the importance of point distribution uniformity to downstream tasks. We demonstrate that point clouds produced by existing gradient-based denoisers lack uniformity despite having achieved promising quantitative results. To this end, we propose GPCD++, a gradient-based denoiser with an ultra-lightweight network named UniNet to address uniformity. Compared with previous state-of-the-art methods, our approach not only generates competitive or even better denoising results, but also significantly improves uniformity which largely benefits applications such as surface reconstruction.