NormalF-Net: Normal Filtering Neural Network for Feature-preserving Mesh Denoising

• Published in: Computer aided design Vol. 127; p. 102861
• Main Authors: Li, Zhiqi, Zhang, Yingkui, Feng, Yidan, Xie, Xingyu, Wang, Qiong, Wei, Mingqiang, Heng, Pheng-Ann
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Ltd 01.10.2020; Elsevier BV
• Subjects: Algorithms; Artificial neural networks; Filtration; Forecasting; Low-rank matrix recovery; Mapping; Neural network; Neural networks; Noise; Noise reduction; Normal filtering; NormalF-Net; Regularization; NormalF-Net; Normal filtering; Neural network; Low-rank matrix recovery
• ISSN: 0010-4485; 1879-2685
• DOI: 10.1016/j.cad.2020.102861

Normal filtering is a fundamental step of feature-preserving mesh denoising. Methods based on convolutional neural networks (CNNs) have recently made their debut for normal filtering. However, they require complicated voxelization and/or projection operations for regularization, and afford an overall denoising accuracy with few powers of preserving surface features. We devise a novel normal filtering neural network algorithm, which we call as NormalF-Net. NormalF-Net consists of two cascaded subnetworks with a comprehensive loss function. The first subnetwork learns mapping from non-local patch-group normal matrices (NPNMs) to their ground-truth low-rank counterparts for denoising, and the second subnetwork learns mapping from the recovered NPNMs to the ground-truth normals for normal refinement. Different from existing learning-based methods, NormalF-Net, which bridges the connection between CNNs and geometry domain knowledge of non-local similarity, can not only preserve surface features when removing different levels and types of noise, but be free of voxelization/projection. NormalF-Net has been validated on different datasets of meshes with multi-scale features yet corrupted by noise of different distributions. Experimental results consistently demonstrate clear improvements of our method over the state-of-the-arts in both noise-robustness and feature awareness. [Display omitted] •NormalF-Net is an effective normal filtering neural network algorithm.•NormalF-Net is free of complicated voxelization/projection operations.•Many geometric processing tasks can benefit from our well-formatted NPNMs.