2 Hits in 2.5 sec

GCN-Denoiser: Mesh Denoising with Graph Convolutional Networks [article]

Yuefan Shen, Hongbo Fu, Zhongshuo Du, Xiang Chen, Evgeny Burnaev, Denis Zorin, Kun Zhou, Youyi Zheng
2021 arXiv   pre-print
In this paper, 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 hand-crafted or voxel-based representations for feature learning, our method explores the structure of a triangular mesh itself and introduces  ...  The work of Evgeny Burnaev in Sections 4-7 related to learning of neural networks was supported by Ministry of Science and Higher Education (No. 075-10-2021-068).  ... 
arXiv:2108.05128v1 fatcat:mq4nzoxrzzgs5ikvtmbl3zb53y

Mesh Total Generalized Variation for Denoising [article]

Zheng Liu, YanLei Li, Weina Wang, Ligang Liu, Renjie Chen
2021 arXiv   pre-print
Further, we propose a TGV-based variational model to restore the face normal field for mesh denoising.  ...  Total Generalized Variation (TGV) has recently been proven certainly successful in image processing for preserving sharp features as well as smooth transition variations.  ...  [47] proposed a normal filtering neural network, called NormalF-Net. It consists of a denoising and refinement subnetwork. Li et al.  ... 
arXiv:2101.02322v2 fatcat:mi5nzytlcnh23pdnahwo2vfdo4