Abstract | ||
---|---|---|
We examine the problem of mesh denoising, which consists of removing noise from corrupted 3D meshes while preserving existing geometric features. Most mesh denoising methods require a lot of mesh-specific parameter fine-tuning, to account for specific features and noise types. In recent years, data-driven methods have demonstrated their robustness and effectiveness with respect to noise and feature properties on a wide variety of geometry and image problems. Most existing mesh denoising methods still use hand-crafted features, and locally denoise facets rather than examine the mesh globally. In this work, we propose the use of a fully end-to-end learning strategy based on graph convolutions, where meaningful features are learned directly by our network. It operates on a graph of facets, directly on the existing topology of the mesh, without resampling, and follows a multi-scale design to extract geometric features at different resolution levels. Similar to most recent pipelines, given a noisy mesh, we first denoise face normals with our novel approach, then update vertex positions accordingly. Our method performs significantly better than the current state-of-the-art learning-based methods. Additionally, we show that it can be trained on noisy data, without explicit correspondence between noisy and ground-truth facets. We also propose a multi-scale denoising strategy, better suited to correct noise with a low spatial frequency. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TVCG.2020.3045490 | IEEE Transactions on Visualization and Computer Graphics |
Keywords | DocType | Volume |
Mesh denoising,normal filtering,graph convolution,feature preserving,geometric deep learning | Journal | 28 |
Issue | ISSN | Citations |
8 | 1077-2626 | 1 |
PageRank | References | Authors |
0.36 | 25 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Matthieu Armando | 1 | 1 | 0.36 |
Jean-Sebastien Franco | 2 | 342 | 18.05 |
Edmond Boyer | 3 | 2758 | 130.84 |