GCN-Denoiser: Mesh Denoising with Graph Convolutional Networks

Yuefan Shen, Hongbo Fu, Zhongshuo Du, Xiang Chen, Evgeny Burnaev, Denis Zorin, Kun Zhou, Youyi Zheng

Research output: Contribution to journalArticlepeer-review

Abstract

In this article, we present GCN-Denoiser, a novel feature-preserving mesh denoising method based on graph convolutional networks (GCNs). Unlike previous learning-based mesh denoising methods that exploit handcrafted or voxel-based representations for feature learning, our method explores the structure of a triangular mesh itself and introduces a graph representation followed by graph convolution operations in the dual space of triangles. We show such a graph representation naturally captures the geometry features while being lightweight for both training and inference. To facilitate effective feature learning, our network exploits both static and dynamic edge convolutions, which allow us to learn information from both the explicit mesh structure and potential implicit relations among unconnected neighbors. To better approximate an unknown noise function, we introduce a cascaded optimization paradigm to progressively regress the noise-free facet normals with multiple GCNs. GCN-Denoiser achieves the new state-of-the-art results in multiple noise datasets, including CAD models often containing sharp features and raw scan models with real noise captured from different devices. We also create a new dataset called PrintData containing 20 real scans with their corresponding ground-truth meshes for the research community. Our code and data are available at https://github.com/Jhonve/GCN-Denoiser.

Original languageEnglish (US)
Article number8
JournalACM Transactions on Graphics
Volume41
Issue number1
DOIs
StatePublished - Feb 2022

Keywords

  • cascaded optimization
  • graph convolutional networks
  • Mesh denoising

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'GCN-Denoiser: Mesh Denoising with Graph Convolutional Networks'. Together they form a unique fingerprint.

Cite this