{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:09:53Z","timestamp":1784268593286,"version":"3.55.0"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2022,2,9]],"date-time":"2022-02-09T00:00:00Z","timestamp":1644364800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key Research & Development Program of China","award":["2018YFE0100900"],"award-info":[{"award-number":["2018YFE0100900"]}]},{"name":"NSF China","award":["61890954, 61772024, and 61732016"],"award-info":[{"award-number":["61890954, 61772024, and 61732016"]}]},{"DOI":"10.13039\/501100003443","name":"The Ministry of Education and Science of Russian Federation","doi-asserted-by":"crossref","award":["14.615.21.0004, RFMEFI61518X0004"],"award-info":[{"award-number":["14.615.21.0004, RFMEFI61518X0004"]}],"id":[{"id":"10.13039\/501100003443","id-type":"DOI","asserted-by":"crossref"}]},{"name":"The Ministry of Science and Higher Education","award":["075-10-2021-068"],"award-info":[{"award-number":["075-10-2021-068"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2022,2,28]]},"abstract":"<jats:p>\n            In this article, we present GCN-Denoiser, a novel feature-preserving mesh denoising method based on\n            <jats:bold>graph convolutional networks<\/jats:bold>\n            (\n            <jats:bold>GCNs<\/jats:bold>\n            ). 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\u00a0achieves 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.\n          <\/jats:p>","DOI":"10.1145\/3480168","type":"journal-article","created":{"date-parts":[[2022,2,10]],"date-time":"2022-02-10T07:36:53Z","timestamp":1644478613000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":53,"title":["GCN-Denoiser: Mesh Denoising with Graph Convolutional Networks"],"prefix":"10.1145","volume":"41","author":[{"given":"Yuefan","family":"Shen","sequence":"first","affiliation":[{"name":"The State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongbo","family":"Fu","sequence":"additional","affiliation":[{"name":"The School of Creative Media, City University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongshuo","family":"Du","sequence":"additional","affiliation":[{"name":"The State Key Lab of CAD&amp;CG, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Chen","sequence":"additional","affiliation":[{"name":"The State Key Lab of CAD&amp;CG, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evgeny","family":"Burnaev","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Denis","family":"Zorin","sequence":"additional","affiliation":[{"name":"New York University, New York, The United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Zhou","sequence":"additional","affiliation":[{"name":"The State Key Lab of CAD&amp;CG, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youyi","family":"Zheng","sequence":"additional","affiliation":[{"name":"The State Key Lab of CAD&amp;CG, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,2,9]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1576246.1531327"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999611.2999778"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/588272.588276"},{"key":"e_1_2_1_4_1","unstructured":"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  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"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354805"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/375213.375276"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157527"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1122501.1122504"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2009.70"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018279"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882368"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322959"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461965"},{"key":"e_1_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Chiyu Max Jiang Avneesh Sud Ameesh Makadia Jingwei Huang Matthias Nie\u00dfner and Thomas Funkhouser. 2020. Local Implicit Grid Representations for 3D Scenes.  Chiyu Max Jiang Avneesh Sud Ameesh Makadia Jingwei Huang Matthias Nie\u00dfner and Thomas Funkhouser. 2020. Local Implicit Grid Representations for 3D Scenes.","DOI":"10.1109\/CVPR42600.2020.00604"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2713099"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882367"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CAD-CG.2005.40"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00936"},{"key":"e_1_2_1_19_1","unstructured":"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.  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."},{"key":"e_1_2_1_20_1","volume-title":"DNF-Net: A deep normal filtering network for mesh denoising","author":"Li Xianzhi","year":"2020","unstructured":"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 ). 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)."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13556"},{"key":"e_1_2_1_22_1","volume-title":"NormalF-Net: Normal filtering neural network for feature-preserving mesh denoising. Computer-Aided Design","author":"Li Zhiqi","year":"2020","unstructured":"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. 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."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.112"},{"key":"e_1_2_1_24_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5115\u20135124","author":"Monti Federico","unstructured":"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\u20135124 . 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\u20135124."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"e_1_2_1_26_1","volume-title":"The IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201917)","author":"Qi Charles R.","unstructured":"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\u201917) . 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\u201917)."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295263"},{"key":"e_1_2_1_28_1","volume-title":"Paul Guerrero, Niloy J. Mitra, and Maks Ovsjanikov.","author":"Rakotosaona Marie-Julie","year":"2019","unstructured":"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. 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."},{"key":"e_1_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Jonas Schult Francis Engelmann Theodora Kontogianni and Bastian Leibe. 2020. DualConvMesh-Net: Joint geodesic and euclidean convolutions on 3D meshes. CoRR abs\/2004.01002.  Jonas Schult Francis Engelmann Theodora Kontogianni and Bastian Leibe. 2020. DualConvMesh-Net: Joint geodesic and euclidean convolutions on 3D meshes. CoRR abs\/2004.01002.","DOI":"10.1109\/CVPR42600.2020.00864"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2004.1272725"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CAD-CG.2005.10"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.11"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00133"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2007.1065"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/602099.602117"},{"key":"e_1_2_1_36_1","volume-title":"International Conference on Learning Representations.","author":"Valsesia Diego","year":"2019","unstructured":"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. 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."},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cad.2012.03.001"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073608"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980232"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2557449"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13863"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2865363"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2014.2326872"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999173"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2828818"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.5555\/795681.797478"},{"key":"e_1_2_1_48_1","volume-title":"Proceedings Computer Graphics International","author":"Yagou Hirokazu","year":"2003","unstructured":"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\u201333. 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\u201333."},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_10"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMI.2006.38"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2662206"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12742"},{"key":"e_1_2_1_53_1","volume-title":"Graph-based feature-preserving mesh normal filtering","author":"Zhao Wenbo","year":"2019","unstructured":"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 ). 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)."},{"key":"e_1_2_1_54_1","unstructured":"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.  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."},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2010.264"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3480168","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3480168","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:16Z","timestamp":1750188676000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3480168"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,9]]},"references-count":55,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,2,28]]}},"alternative-id":["10.1145\/3480168"],"URL":"https:\/\/doi.org\/10.1145\/3480168","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,9]]},"assertion":[{"value":"2020-11-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-08-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-02-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}