Curvature‐driven Multi‐stream Network for Feature‐preserving Mesh Denoising

Zhao, Zhibo; Tang, Wenming; Gong, Yuanhao

Curvature‐driven Multi‐stream Network for Feature‐preserving Mesh Denoising

Files

v43i1_06_cgf14993.pdf (4.24 MB)

Date

2024

Authors

Zhao, Zhibo
Tang, Wenming
Gong, Yuanhao

Publisher

Abstract

Mesh denoising is a fundamental yet challenging task. Most of the existing data‐driven methods only consider the zero‐order information (vertex location) and first‐order information (face normal). However, higher‐order geometric information (such as curvature) is more descriptive for the shape of the mesh. Therefore, in order to impose such high‐order information, this paper proposes a novel Curvature‐Driven Multi‐Stream Graph Convolutional Neural Network (CDMS‐Net) architecture. CDMS‐Net has three streams, including curvature stream, face normal stream and vertex stream, where the curvature stream focuses on the high‐order Gaussian curvature information. Moreover, CDMS‐Net proposes a novel block based on residual dense connections, which is used as the core component to extract geometric features from meshes. This innovative design improves the performance of feature‐preserving denoising. The plug‐and‐play modular design makes CDMS‐Net easy to be implemented. Multiple sets of ablation study are carried out to verify the rationality of the CDMS‐Net. Our method establishes new state‐of‐the‐art mesh denoising results on publicly available datasets.

        @article{10.1111:cgf.14993
,
journal = {Computer Graphics Forum},
title = {{Curvature‐driven Multi‐stream Network for Feature‐preserving Mesh Denoising
}},
author = {Zhao, Zhibo and 
Tang, Wenming and 
Gong, Yuanhao
},
year = {2024
},
publisher = {© 2024 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.
},
ISSN = {1467-8659
},
DOI = {10.1111/cgf.14993
}
}