research-article

GCN-Denoiser: Mesh Denoising with Graph Convolutional Networks

Authors:

Evgeny Burnaev,

Youyi ZhengAuthors Info & Claims

ACM Transactions on Graphics (TOG), Volume 41, Issue 1

Article No.: 8, Pages 1 - 14

https://doi.org/10.1145/3480168

Published: 09 February 2022 Publication History

Abstract

In this article, 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 handcrafted or voxel-based representations for feature learning, our method explores the structure of a triangular mesh itself and introduces a graph representation followed by graph convolution operations in the dual space of triangles. We show such a graph representation naturally captures the geometry features while being lightweight for both training and inference. To facilitate effective feature learning, our network exploits both static and dynamic edge convolutions, which allow us to learn information from both the explicit mesh structure and potential implicit relations among unconnected neighbors. To better approximate an unknown noise function, we introduce a cascaded optimization paradigm to progressively regress the noise-free facet normals with multiple GCNs. GCN-Denoiser achieves the new state-of-the-art results in multiple noise datasets, including CAD models often containing sharp features and raw scan models with real noise captured from different devices. We also create a new dataset called PrintData containing 20 real scans with their corresponding ground-truth meshes for the research community. Our code and data are available at https://github.com/Jhonve/GCN-Denoiser.

References

[1]

Andrew Adams, Natasha Gelfand, Jennifer Dolson, and Marc Levoy. 2009. Gaussian kd-trees for fast high-dimensional filtering. In ACM SIGGRAPH 2009 papers. 1–12.

Digital Library

[2]

Forest Agostinelli, Michael R. Anderson, and Honglak Lee. 2013. Adaptive multi-column deep neural networks with application to robust image denoising. In Advances in Neural Information Processing Systems. 1493–1501.

Digital Library

[3]

Chandrajit L. Bajaj and Guoliang Xu. 2003. Anisotropic diffusion of surfaces and functions on surfaces. ACM Transactions on Graphics 22, 1 (2003), 4–32.

Digital Library

[4]

Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. 2014. Spectral networks and locally connected networks on graphs. arXiv:1312.6203. https://arxiv.org/abs/1312.6203

[5]

Harold C. Burger, Christian J. Schuler, and Stefan Harmeling. 2012. Image denoising: Can plain neural networks compete with BM3D? In 2012 IEEE Conference on Computer Vision and Pattern Recognition. 2392–2399.

Digital Library

[6]

U. Clarenz, U. Diewald, and M. Rumpf. 2000. Anisotropic geometric diffusion in surface processing. In Proceedings of the Conference on Visualization 2000. 397–405.

Digital Library

[7]

Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In Advances in Neural Information Processing Systems. 3844–3852.

Digital Library

[8]

James R. Diebel, Sebastian Thrun, and Michael Brünig. 2006. A Bayesian method for probable surface reconstruction and decimation. ACM Transactions on Graphics 25, 1 (2006), 39–59.

Digital Library

[9]

Hanqi Fan, Yizhou Yu, and Qunsheng Peng. 2010. Robust feature-preserving mesh denoising based on consistent subneighborhoods. IEEE Transactions on Visualization and Computer Graphics 16, 2 (2010), 312–324.

Digital Library

[10]

Yutong Feng, Yifan Feng, Haoxuan You, Xibin Zhao, and Yue Gao. 2019. MeshNet: Mesh neural network for 3D shape representation. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 8279–8286.

Digital Library

[11]

Shachar Fleishman, Iddo Drori, and Daniel Cohen-Or. 2003. Bilateral mesh denoising. In ACM SIGGRAPH 2003 Papers. 950–953.

Digital Library

[12]

Rana Hanocka, Amir Hertz, Noa Fish, Raja Giryes, Shachar Fleishman, and Daniel Cohen-Or. 2019. MeshCNN: A network with an edge. ACM Transactions on Graphics 38, 4 (2019).

Digital Library

[13]

Lei He and Scott Schaefer. 2013. Mesh denoising via l0 minimization. ACM Transactions on Graphics 32, 4 (2013).

Digital Library

[14]

Chiyu Max Jiang, Avneesh Sud, Ameesh Makadia, Jingwei Huang, Matthias Nießner, and Thomas Funkhouser. 2020. Local Implicit Grid Representations for 3D Scenes.

[15]

Kyong Hwan Jin, Michael T. McCann, Emmanuel Froustey, and Michael Unser. 2017. Deep convolutional neural network for inverse problems in imaging. IEEE Transactions on Image Processing 26, 9 (2017), 4509–4522.

Digital Library

[16]

Thouis R. Jones, Frédo Durand, and Mathieu Desbrun. 2003. Non-iterative, feature-preserving mesh smoothing. In ACM SIGGRAPH 2003 Papers. 943–949.

Digital Library

[17]

Kai-Wah Lee and Wen-Ping Wang. 2005. Feature-preserving mesh denoising via bilateral normal filtering. In Proceedings of the 9th International Conference on Computer Aided Design and Computer Graphics (CAD-CG’05). 6 pages.

Digital Library

[18]

Guohao Li, Matthias Muller, Ali Thabet, and Bernard Ghanem. 2019. Deepgcns: Can GCNs go as deep as CNNs? In Proceedings of the IEEE International Conference on Computer Vision. 9267–9276.

[19]

Xianzhi Li, Ruihui Li, Guangyong Chen, Chi-Wing Fu, Daniel Cohen-Or, and Pheng-Ann Heng. 2020a. A rotation-invariant framework for deep point cloud analysis. CoRR abs/2003.07238.

[20]

Xianzhi Li, Ruihui Li, Lei Zhu, Chi-Wing Fu, and Pheng-Ann Heng. 2020b. DNF-Net: A deep normal filtering network for mesh denoising. IEEE Transactions on Visualization and Computer Graphics (2020).

[21]

Xianzhi Li, Lei Zhu, Chi-Wing Fu, and Pheng-Ann Heng. 2018. Non-local low-rank normal filtering for mesh denoising. Computer Graphics Forum 37, 7 (2018), 155–166.

[22]

Zhiqi Li, Yingkui Zhang, Yidan Feng, Xingyu Xie, Qiong Wang, Mingqiang Wei, and Pheng-Ann Heng. 2020c. NormalF-Net: Normal filtering neural network for feature-preserving mesh denoising. Computer-Aided Design (2020), 102861.

[23]

Jonathan Masci, Davide Boscaini, Michael Bronstein, and Pierre Vandergheynst. 2015. Geodesic convolutional neural networks on Riemannian manifolds. In Proceedings of the IEEE International Conference on Computer Vision Workshops. 37–45.

Digital Library

[24]

Federico Monti, Davide Boscaini, Jonathan Masci, Emanuele Rodola, Jan Svoboda, and Michael M. Bronstein. 2017. Geometric deep learning on graphs and manifolds using mixture model CNNs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5115–5124.

[25]

Richard A. Newcombe, Shahram Izadi, Otmar Hilliges, David Molyneaux, David Kim, Andrew J. Davison, Pushmeet Kohli, Jamie Shotton, Steve Hodges, and Andrew Fitzgibbon. 2011. KinectFusion: Real-time dense surface mapping and tracking. In Proceedings of the 2011 10th IEEE International Symposium on Mixed and Augmented Reality (ISMAR’11). 127–136.

Digital Library

[26]

Charles R. Qi, Hao Su, Kaichun Mo, and Leonidas J. Guibas. 2017a. PointNet: Deep learning on point sets for 3D classification and segmentation. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17).

[27]

Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J. Guibas. 2017b. PointNet++: Deep hierarchical feature learning on point sets in a metric space. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017. 5099–5108.

Digital Library

[28]

Marie-Julie Rakotosaona, Vittorio La Barbera, Paul Guerrero, Niloy J. Mitra, and Maks Ovsjanikov. 2019. POINTCLEANNET: Learning to denoise and remove outliers from dense point clouds. CoRR abs/1901.01060.

[29]

Jonas Schult, Francis Engelmann, Theodora Kontogianni, and Bastian Leibe. 2020. DualConvMesh-Net: Joint geodesic and euclidean convolutions on 3D meshes. CoRR abs/2004.01002.

[30]

Yuzhong Shen and Kenneth E. Barner. 2004. Fuzzy vector median-based surface smoothing. IEEE Transactions on Visualization and Computer Graphics 10, 3 (2004), 252–265.

Digital Library

[31]

Takafumi Shimizu, Hiroaki Date, Satoshi Kanai, and Takeshi Kishinami. 2005. A new bilateral mesh smoothing method by recognizing features. In Proceedings of the 9th International Conference on Computer Aided Design and Computer Graphics (CAD-CG’05). 6 pages.

Digital Library

[32]

Martin Simonovsky and Nikos Komodakis. 2017. Dynamic edge-conditioned filters in convolutional neural networks on graphs. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17). 29–38.

[33]

Vladimiros Sterzentsenko, Leonidas Saroglou, Anargyros Chatzitofis, Spyridon Thermos, Nikolaos Zioulis, Alexandros Doumanoglou, Dimitrios Zarpalas, and Petros Daras. 2019. Self-supervised deep depth denoising. In Proceedings of the IEEE International Conference on Computer Vision. 1242–1251.

[34]

Xianfang Sun, Paul L. Rosin, Ralph Martin, and Frank Langbein. 2007. Fast and effective feature-preserving mesh denoising. IEEE Transactions on Visualization and Computer Graphics 13, 5 (2007), 925–938.

Digital Library

[35]

Tolga Tasdizen, Ross Whitaker, Paul Burchard, and Stanley Osher. 2002. Geometric Surface smoothing via anisotropic diffusion of normals. In Proceedings of the Conference on Visualization’02. 125–132.

Digital Library

[36]

Diego Valsesia, Giulia Fracastoro, and Enrico Magli. 2019. Learning localized generative models for 3D point clouds via graph convolution. In International Conference on Learning Representations.

[37]

Jun Wang, Xi Zhang, and Zeyun Yu. 2012. A cascaded approach for feature-preserving surface mesh denoising. Computer-Aided Design 44, 7 (2012), 597–610.

Digital Library

[38]

Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, and Xin Tong. 2017. O-CNN: Octree-based convolutional neural networks for 3D shape analysis. ACM Transactions on Graphics 36, 4 (2017), Article 72, 11 pages.

Digital Library

[39]

Peng-Shuai Wang, Yang Liu, and Xin Tong. 2016. Mesh denoising via cascaded normal regression. ACM Transactions on Graphics 35, 6 (2016).

Digital Library

[40]

Ruimin Wang, Zhouwang Yang, Ligang Liu, Jiansong Deng, and Falai Chen. 2014. Decoupling noise and features via weighted L1-analysis compressed sensing. ACM Transactions on Graphics 33, 2 (2014).

Digital Library

[41]

Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, and Justin M. Solomon. 2019. Dynamic graph CNN for learning on point clouds. ACM Transactions on Graphics 38, 5 (2019).

Digital Library

[42]

M. Wei, X. Guo, J. Huang, Haoran Xie, H. Zong, R. Kwan, F. L. Wang, and J. Qin. 2019a. Mesh defiltering via cascaded geometry recovery. Computer Graphics Forum 38, 7 (2019), 591–605.

[43]

Mingqiang Wei, Jin Huang, Xingyu Xie, Ligang Liu, Jun Wang, and Jing Qin. 2019b. Mesh denoising guided by patch normal co-filtering via kernel low-rank recovery. IEEE Transactions on Visualization and Computer Graphics 25, 10 (2019), 2910–2926.

[44]

Mingqiang Wei, Jinze Yu, Wai-Man Pang, Jun Wang, Jing Qin, Ligang Liu, and Pheng-Ann Heng. 2015. Bi-normal filtering for mesh denoising. IEEE Transactions on Visualization and Computer Graphics 21, 1 (2015), 43–55.

[45]

Junyuan Xie, Linli Xu, and Enhong Chen. 2012. Image denoising and inpainting with deep neural networks. In Advances in Neural Information Processing Systems. 341–349.

Digital Library

[46]

Sunil Kumar Yadav, Ulrich Reitebuch, and Konrad Polthier. 2019. Robust and high fidelity mesh denoising. IEEE Transactions on Visualization and Computer Graphics 25, 6 (2019), 2304–2310.

[47]

Hirokazu Yagou, Yutaka Ohtake, and Alexander Belyaev. 2002. Mesh smoothing via mean and median filtering applied to face normals. In Proceedings of Geometric Modeling and Processing. Theory and Applications (GMP’02). 124–131.

Digital Library

[48]

Hirokazu Yagou, Yutaka Ohtake, and Alexander G. Belyaev. 2003. Mesh denoising via iterative alpha-trimming and nonlinear diffusion of normals with automatic thresholding. In Proceedings Computer Graphics International 2003. 28–33.

[49]

Shi Yan, Chenglei Wu, Lizhen Wang, Feng Xu, Liang An, Kaiwen Guo, and Yebin Liu. 2018. DDRNet: Depth map denoising and refinement for consumer depth cameras using cascaded CNNs. In Proceedings of the European Conference on Computer Vision (ECCV’18). 151–167.

[50]

Shin Yoshizawa, A. Belyaev, and H.-P. Seidel. 2006. Smoothing by example: Mesh denoising by averaging with similarity-based weights. In IEEE International Conference on Shape Modeling and Applications 2006 (SMI’06). 9–9. https://doi.org/10.1109/SMI.2006.38

Digital Library

[51]

Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, and Lei Zhang. 2017. Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising. IEEE Transactions on Image Processing 26, 7 (2017), 3142–3155.

Digital Library

[52]

Wangyu Zhang, Bailin Deng, Juyong Zhang, Sofien Bouaziz, and Ligang Liu. 2015. Guided mesh normal filtering. Computer Graphics Forum 34, 7 (2015), 23–34.

Digital Library

[53]

Wenbo Zhao, Xianming Liu, Shiqi Wang, Xiaopeng Fan, and Debin Zhao. 2019a. Graph-based feature-preserving mesh normal filtering. IEEE Transactions on Visualization and Computer Graphics (2019).

[54]

Wenbo Zhao, Xianming Liu, Yongsen Zhao, Xiaopeng Fan, and Debin Zhao. 2019b. NormalNet: Learning based guided normal filtering for mesh denoising. arXiv:1903.04015 http://arxiv.org/abs/1903.04015.

[55]

Youyi Zheng, Hongbo Fu, Oscar Kin-Chung Au, and Chiew-Lan Tai. 2011. Bilateral normal filtering for mesh denoising. IEEE Transactions on Visualization and Computer Graphics 17, 10 (2011), 1521–1530.

Digital Library

Cited By

Godó ÁWu SOkura FMakihara YIkeda MSato SSuzuki MSatake YTaomoto DYagi Y(2024)PPGCN: Phase-Aligned Periodic Graph Convolutional Network for Dual-Task-Based Cognitive Impairment DetectionIEEE Access10.1109/ACCESS.2024.337151712(37679-37691)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3371517
Lazzaro DMorigi SZuzolo P(2024)Learning intrinsic shape representations via spectral mesh convolutionsNeurocomputing10.1016/j.neucom.2024.128152598(128152)Online publication date: Oct-2024
https://doi.org/10.1016/j.neucom.2024.128152
Ho TTran MCui XLin CBaek SKim WLee CJin GChae KChoi S(2024)Human-airway surface mesh smoothing based on graph convolutional neural networksComputer Methods and Programs in Biomedicine10.1016/j.cmpb.2024.108061246:COnline publication date: 25-Jun-2024
https://dl.acm.org/doi/10.1016/j.cmpb.2024.108061
Show More Cited By

Index Terms

GCN-Denoiser: Mesh Denoising with Graph Convolutional Networks
1. Computing methodologies
  1. Computer graphics
    1. Shape modeling
      1. Mesh models
      2. Shape analysis

Recommendations

Learning Self-prior for Mesh Denoising Using Dual Graph Convolutional Networks
Computer Vision – ECCV 2022
Abstract
This study proposes a deep-learning framework for mesh denoising from a single noisy input, where two graph convolutional networks are trained jointly to filter vertex positions and facet normals apart. The prior obtained only from a single input ...
Towards multiscale mesh denoising
SCCG '04: Proceedings of the 20th Spring Conference on Computer Graphics

Recently developed methods address the problem of denoising polygonal meshes derived from automatic scanning procedures. Nonlinear filtering is applied iteratively based on the estimated statistical properties of errors associated with the measured ...
Bilateral mesh denoising
SIGGRAPH '03: ACM SIGGRAPH 2003 Papers

We present an anisotropic mesh denoising algorithm that is effective, simple and fast. This is accomplished by filtering vertices of the mesh in the normal direction using local neighborhoods. Motivated by the impressive results of bilateral filtering ...

Comments

Information & Contributors

Information

Published In

cover image ACM Transactions on Graphics

ACM Transactions on Graphics Volume 41, Issue 1

February 2022

178 pages

ISSN:0730-0301

EISSN:1557-7368

DOI:10.1145/3484929

Editor:
Carol O'Sullivan
Trinity College Dublin, Ireland

Issue’s Table of Contents

Copyright © 2022 Copyright held by the owner/author(s). Publication rights licensed to ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 09 February 2022

Accepted: 01 August 2021

Revised: 01 June 2021

Received: 01 November 2020

Published in TOG Volume 41, Issue 1

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Refereed

Funding Sources

National Key Research & Development Program of China
NSF China
The Ministry of Education and Science of Russian Federation
The Ministry of Science and Higher Education

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

20
Total Citations
View Citations
826
Total Downloads

Downloads (Last 12 months)214
Downloads (Last 6 weeks)12

Reflects downloads up to 26 Jul 2024

Other Metrics

View Author Metrics

Citations

Cited By

Godó ÁWu SOkura FMakihara YIkeda MSato SSuzuki MSatake YTaomoto DYagi Y(2024)PPGCN: Phase-Aligned Periodic Graph Convolutional Network for Dual-Task-Based Cognitive Impairment DetectionIEEE Access10.1109/ACCESS.2024.337151712(37679-37691)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3371517
Lazzaro DMorigi SZuzolo P(2024)Learning intrinsic shape representations via spectral mesh convolutionsNeurocomputing10.1016/j.neucom.2024.128152598(128152)Online publication date: Oct-2024
https://doi.org/10.1016/j.neucom.2024.128152
Ho TTran MCui XLin CBaek SKim WLee CJin GChae KChoi S(2024)Human-airway surface mesh smoothing based on graph convolutional neural networksComputer Methods and Programs in Biomedicine10.1016/j.cmpb.2024.108061246:COnline publication date: 25-Jun-2024
https://dl.acm.org/doi/10.1016/j.cmpb.2024.108061
Wang MFeng YLyu BShen LYuan C(2024)An attention enhanced dual graph neural network for mesh denoisingComputer Aided Geometric Design10.1016/j.cagd.2024.102307111(102307)Online publication date: Jul-2024
https://doi.org/10.1016/j.cagd.2024.102307
Pan JBo PLi YWang Z(2024)Mesh Denoising of Developable Surfaces with Curved FoldingsComputer-Aided Design10.1016/j.cad.2024.103776(103776)Online publication date: Jul-2024
https://doi.org/10.1016/j.cad.2024.103776
Hurtado JGattass MRaposo ALopez C(2024)Sharp feature-preserving mesh denoisingMultimedia Tools and Applications10.1007/s11042-024-18390-x83:27(69555-69580)Online publication date: 1-Feb-2024
https://doi.org/10.1007/s11042-024-18390-x
Sarmah MNeelima A(2024)Enhanced 3D reconstruction with all-neighbor-first philosophy and Ricci flow-based mesh smoothing approachMultimedia Systems10.1007/s00530-023-01210-x30:1Online publication date: 19-Jan-2024
https://dl.acm.org/doi/10.1007/s00530-023-01210-x
Zhao YLi KWang TZhang S(2024)Joint entity and relation extraction model based on directed-relation GAT oriented to Chinese patent textsSoft Computing - A Fusion of Foundations, Methodologies and Applications10.1007/s00500-024-09629-828:11-12(7557-7574)Online publication date: 1-Jun-2024
https://dl.acm.org/doi/10.1007/s00500-024-09629-8
Lan XWang LWang CSun GFeng JZhang M(2023)Prediction of Transonic Flow over Cascades via Graph Embedding Methods on Large-Scale Point CloudsAerospace10.3390/aerospace1012102910:12(1029)Online publication date: 14-Dec-2023
https://doi.org/10.3390/aerospace10121029
Bhatti UTang HWu GMarjan SHussain A(2023)Deep Learning with Graph Convolutional NetworksInternational Journal of Intelligent Systems10.1155/2023/83421042023Online publication date: 1-Jan-2023
https://dl.acm.org/doi/10.1155/2023/8342104
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Media

Figures

Other

Tables

View Issue’s Table of Contents