NormalF-Net: Normal Filtering Neural Network for Feature-preserving Mesh Denoising. (October 2020)

• Record Type: Journal Article
• Authors: Li, Zhiqi; Zhang, Yingkui; Feng, Yidan; Xie, Xingyu; Wang, Qiong; Wei, Mingqiang; Heng, Pheng-Ann
• Is Part Of: Computer aided design. Volume 127(2020)
• Publication Date: 2020-10
• Subjects: NormalF-Net -- Normal filtering -- Neural network -- Low-rank matrix recovery; 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.2020.102861
• Languages: English
• ISSNs: 0010-4485

Abstract

Abstract: 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. Graphical abstract: Highlights: 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.