GeoBi-GNN: Geometry-aware Bi-domain Mesh Denoising via Graph Neural Networks. (March 2022)

• Record Type: Journal Article
• Authors: Zhang, Yingkui; Shen, Guibao; Wang, Qiong; Qian, Yinling; Wei, Mingqiang; Qin, Jing
• Is Part Of: Computer aided design. Volume 144(2022)
• Publication Date: 2022-03
• Subjects: GeoBi-GNN -- Mesh denoising -- Bi-domain -- Graph neural network -- Geometric deep learning; Computer-aided design -- Periodicals; Engineering design -- Data processing -- Periodicals; Computer graphics -- Periodicals; Conception technique -- Informatique -- Périodiques; Infographie -- Périodiques; Computer graphics; Engineering design -- Data processing; Periodicals; Electronic journals; 620.00420285
• DOI: 10.1016/j.cad.2021.103154
• Languages: English
• ISSNs: 0010-4485

Abstract

Abstract: Mesh denoising is an essential geometric processing step for raw meshes generated by 3D scanners and depth cameras. It is intended to remove noise while preserving surface intrinsic features of the underlying model. Existing mesh denoising wisdoms of (1) updating mesh vertices directly (referred to as one-step mesh denoising in the spatial domain) or (2) normal filtering followed by vertex updating (referred to as two-step mesh denoising in the normal domain) seldom consider the correlation between vertex updating and normal filtering. This paper proposes a novel end-to-end geometry-aware dual-graph neural network, called GeoBi-GNN, to perform denoising in spatial and normal domains simultaneously. For the first time, we optimize both positions and normals (i.e., dual domains) in a unified framework of GNN, and show the powerful inter-coordination between the dual domains. GeoBi-GNN fully excavates the native dual-graph structure in the mesh, and creates two graph structures for the spatial noise and the normal noise respectively through the adjacency relationship between vertices and surfaces. We design each GNN as a three-layer U-Net architecture to gradually extract multi-scale features from the input graphs. In addition, a specific graph pooling layer with a cascaded weight estimation strategy is designed to improve the robustness and denoising effect. Due to the intuitive relation between the mesh connectivity and the dual graphs, the proposed method is simple to implement. Comprehensive experiments exhibit that the proposed method is significantly superior to the state-of-the-arts of mesh denoising, especially for the large-scale noise and the complex real scans. Our code is available at https://github.com/zhangyk18/GeoBi-GNN . Highlights: We formulate mesh denoising in a novel insight and propose a geometry-aware dual-graph neural network, called GeoBi-GNN, to perform denoising in the spatial and normal domains simultaneously. By constructing a dual-graph structure in a mesh, GeoBi-GNN excavates the inter-benefits between normal filtering and vertex denoising under the GNN framework, and achieves better geometric feature preservation while effectively removing noise. A novel graph pooling layer with a cascaded weight estimation strategy is designed for mesh denoising, which further improves the robustness to noise.