Mesh Denoising with Facet Graph Convolutions - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Transactions on Visualization and Computer Graphics Year : 2022

Mesh Denoising with Facet Graph Convolutions

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.
Fichier principal
Vignette du fichier
tvcg2019_final_file.pdf (20.72 Mo) Télécharger le fichier
Vignette du fichier
mesh_denoising_child_cropped (1).png (1.77 Mo) Télécharger le fichier
supplementary_final_file.pdf (43.36 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image

Dates and versions

hal-03066322 , version 1 (15-12-2020)

Identifiers

Cite

Matthieu Armando, Jean-Sébastien Franco, Edmond Boyer. Mesh Denoising with Facet Graph Convolutions. IEEE Transactions on Visualization and Computer Graphics, 2022, 28 (8), pp.2999-3012. ⟨10.1109/TVCG.2020.3045490⟩. ⟨hal-03066322⟩
383 View
441 Download

Altmetric

Share

Gmail Facebook X LinkedIn More