首页|ResGEM: Multi-Scale Graph Embedding Network for Residual Mesh Denoising

ResGEM: Multi-Scale Graph Embedding Network for Residual Mesh Denoising

扫码查看
原文链接
  • NETL
  • NSTL
  • IEEE
Mesh denoising is a crucial technology that aims to recover a high-fidelity 3D mesh from a noise-corrupted one. Deep learning methods, particularly graph convolutional networks (GCNs) based mesh denoisers, have demonstrated their effectiveness in removing various complex real-world noises while preserving authentic geometry. However, it is still a quite challenging work to faithfully regress uncontaminated normals and vertices on meshes with irregular topology. In this article, we propose a novel pipeline that incorporates two parallel normal-aware and vertex-aware branches to achieve a balance between smoothness and geometric details while maintaining the flexibility of surface topology. We introduce ResGEM, a new GCN, with multi-scale embedding modules and residual decoding structures to facilitate normal regression and vertex modification for mesh denoising. To effectively extract multi-scale surface features while avoiding the loss of topological information caused by graph pooling or coarsening operations, we encode the noisy normal and vertex graphs using four edge-conditioned embedding modules (EEMs) at different scales. This allows us to obtain favorable feature representations with multiple receptive field sizes. Formulating the denoising problem into a residual learning problem, the decoder incorporates residual blocks to accurately predict true normals and vertex offsets from the embedded feature space. Moreover, we propose novel regularization terms in the loss function that enhance the smoothing and generalization ability of our network by imposing constraints on normal fidelity and consistency. Comprehensive experiments have been conducted to demonstrate the superiority of our method over the state-of-the-art on both synthetic and real-scanned datasets.

Noise reductionSurface treatmentTopologyFacesPipelinesNetwork topologyTraining

Ziqi Zhou、Mengke Yuan、Mingyang Zhao、Jianwei Guo、Dong-Ming Yan

展开 >

State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China|School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China

State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China|School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China|PIESAT Information Technology Company Ltd, Beijing, China

CAIR, Hong Kong Institute of Science & Innovation, Hong Kong, China

2025

10.1109/TVCG.2024.3378309

IEEE transactions on visualization and computer graphics

IEEE transactions on visualization and computer graphics

SCI
ISSN：
年,卷(期)：2025.31(4)
  • 38