{"type":"ScholarlyArticle","title":"TopoSeg: Topology-aware Segmentation for Point Clouds","authors":[{"name":"Weiquan Liu","slug":"weiquan-liu","given":"Weiquan","family":"Liu","affiliation":"Fujian Key Laboratory of Sensing and Computing for Smart Cities , School of Informatics , Xiamen University , Xiamen , China"},{"name":"Hanyun Guo","slug":"hanyun-guo","given":"Hanyun","family":"Guo","affiliation":"Fujian Key Laboratory of Sensing and Computing for Smart Cities , School of Informatics , Xiamen University , Xiamen , China"},{"name":"Weini Zhang","slug":"weini-zhang","given":"Weini","family":"Zhang","affiliation":"Fujian Key Laboratory of Sensing and Computing for Smart Cities , School of Informatics , Xiamen University , Xiamen , China"},{"name":"Yu Zang","slug":"yu-zang","given":"Yu","family":"Zang","affiliation":"Fujian Key Laboratory of Sensing and Computing for Smart Cities , School of Informatics , Xiamen University , Xiamen , China"},{"name":"Cheng Wang","slug":"cheng-wang","given":"Cheng","family":"Wang","affiliation":"Fujian Key Laboratory of Sensing and Computing for Smart Cities , School of Informatics , Xiamen University , Xiamen , China"},{"name":"Jonathan Li","slug":"jonathan-li","given":"Jonathan","family":"Li","affiliation":"Departments of Geography and Environmental Management and Systems Design Engineering , University of Waterloo , Waterloo , Canada"}],"abstract":"Point cloud segmentation plays an important role in AI applications such as autonomous driving, AR, and VR. However, previous point cloud segmentation neural networks rarely pay attention to the topological correctness of the segmentation results. In this paper, focusing on the perspective of topology awareness. First, to optimize the distribution of segmented predictions from the perspective of topology, we introduce the persistent homology theory in topology into a 3D point cloud deep learning framework. Second, we propose a topology-aware 3D point cloud segmentation module, TopoSeg. Specifically, we design a topological loss function embedded in TopoSeg module, which imposes topological constraints on the segmentation of 3D point clouds. Experiments show that our proposed TopoSeg module can be easily embedded into the point cloud segmentation network and improve the segmentation performance. In addition, based on the constructed topology loss function, we propose a topology-aware point cloud edge extraction algorithm, which is demonstrated that has strong robustness.","doi":"10.24963/ijcai.2022/168","url":"https://ijcai.org/proceedings/2022/168","pdf":"https://ijcai.org/proceedings/2022/0168.pdf","markdown":"https://ijcai.org/proceedings/2022/168.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/168","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Computer Vision","track":"Main Track","number":168,"pages":{"first":1201,"last":1208},"keywords":["Machine Learning: Classification","Computer Vision: 3D Computer Vision"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986626","length_sec":82,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984769","length_sec":333,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Adams et al., 2017] Henry Adams, Tegan Emerson, Michael Kirby, Rachel Neville, Chris Peterson, Patrick Shipman, Sofya Chepushtanova, Eric Hanson, Francis Motta, and Lori Ziegelmeier. Persistence images: A stable vector representation of persistent homology. Journal of Machine Learning Research, 18, 2017.","title":"Persistence images: A stable vector representation of persistent homology","authors":"Henry Adams, Tegan Emerson, Michael Kirby, Rachel Neville, Chris Peterson, Patrick Shipman, Sofya Chepushtanova, Eric Hanson, Francis Motta, Lori Ziegelmeier","year":"2017","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Brüel-Gabrielsson et al., 2020] Rickard Brüel-Gabrielsson, Vignesh Ganapathi-Subramanian, Primoz Skraba, and Leonidas J Guibas. Topology-aware surface reconstruc- tion for point clouds. In Computer Graphics Forum, vol- ume 39, pages 197-207, 2020.","title":"Topology-aware surface reconstruc-tion for point clouds","authors":"Rickard Brüel-Gabrielsson, Vignesh Ganapathi-Subramanian, Primoz Skraba, Leonidas J Guibas","year":"2020","venue":"Computer Graphics Forum","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Carlsson and Gabrielsson, 2020] Gunnar Carlsson and Rickard Brüel Gabrielsson. Topological approaches to deep learning. In Topological Data Analysis, pages 119-146. Springer, 2020.","title":"Topological approaches to deep learning","authors":"Gabrielsson Carlsson, Gunnar Carlsson, Rickard Brüel, Gabrielsson","year":"2020","venue":"Topological Data Analysis","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Carrière et al., 2015] Mathieu Carrière, Steve Y Oudot, and Maks Ovsjanikov. Stable topological signatures for points on 3d shapes. In Computer Graphics Forum, volume 34, pages 1-12, 2015.","title":"Stable topological signatures for points on 3d shapes","authors":"Steve Y Mathieu Carrière, Maks Oudot, Ovsjanikov","year":"2015","venue":"Computer Graphics Forum","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Carriere et al., 2019] Mathieu Carriere, Frédéric Chazal, Yuichi Ike, Théo Lacombe, Martin Royer, and Yuhei Umeda. A general neural network architecture for per- sistence diagrams and graph classification. HAL open sci- ence: hal-02105788, 2019.","title":"A general neural network architecture for persistence diagrams and graph classification","authors":"Mathieu Carriere, Frédéric Chazal, Yuichi Ike, Théo Lacombe, Martin Royer, Yuhei Umeda","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chang et al., 2015] Angel X Chang, Thomas Funkhouser, Leonidas Guibas, Pat Hanrahan, Qixing Huang, Zimo Li, Silvio Savarese, Manolis Savva, Shuran Song, Hao Su, et al. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012, 2015.","title":"Shapenet: An information-rich 3d model repository","authors":"Thomas Angel X Chang, Leonidas Funkhouser, Pat Guibas, Qixing Hanrahan, Zimo Huang, Silvio Li, Manolis Savarese, Shuran Savva, Hao Song, Su","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Clough et al., 2020] James Clough, Nicholas Byrne, Ilkay Oksuz, Veronika A Zimmer, Julia A Schnabel, and An- drew King. A topological loss function for deep-learning based image segmentation using persistent homology. IEEE Transactions on Pattern Analysis and Machine In- telligence (Early Access), 2020.","title":"A topological loss function for deep-learning based image segmentation using persistent homology","authors":"James Clough, Nicholas Byrne, Ilkay Oksuz, Veronika A Zimmer, Julia A Schnabel, Andrew King","year":"2020","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gabrielsson and Carlsson, 2019] Rickard Brüel Gabriels- son and Gunnar Carlsson. Exposition and interpretation of the topology of neural networks. In Proceedings of the International Conference on Machine Learning and Appli- cations (ICMLA), pages 1069-1076, 2019. Gabrielsson et al., 2020]","title":"Exposition and interpretation of the topology of neural networks","authors":"Carlsson Gabrielsson, Rickard Brüel, Gabrielsson, Gunnar Carlsson","year":"2019","venue":"Proceedings of the International Conference on Machine Learning and Applications (ICMLA)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"Rickard Brüel Gabrielsson, Bradley J Nelson, Anjan Dwaraknath, and Primoz Skraba. A topology layer for machine learning. In International Conference on Artificial Intelligence and Statistics, pages 1553-1563, 2020.","title":"A topology layer for machine learning","authors":"Rickard Brüel Gabrielsson, Bradley J Nelson, Anjan Dwaraknath, Primoz Skraba","year":"2020","venue":"International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gebhart and Schrater, 2017] Thomas Gebhart and Paul Schrater. Adversary detection in neural networks via per- sistent homology. arXiv preprint arXiv:1711.10056, 2017.","title":"Adversary detection in neural networks via persistent homology","authors":"Schrater Gebhart, Thomas Gebhart, Paul Schrater","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Guss and Salakhutdinov, 2018] William H Guss and Ruslan Salakhutdinov. On characterizing the capacity of neu- ral networks using algebraic topology. arXiv preprint arXiv:1802.04443, 2018.","title":"On characterizing the capacity of neural networks using algebraic topology","authors":"H William, Ruslan Guss, Salakhutdinov","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Hofer et al., 2017] Christoph Hofer, Roland Kwitt, Marc Niethammer, and Andreas Uhl. Deep learning with topo- logical signatures. Advances in Neural Information Pro- cessing Systems (NeurIPS), 30, 2017.","title":"Deep learning with topological signatures","authors":"Christoph Hofer, Roland Kwitt, Marc Niethammer, Andreas Uhl","year":"2017","venue":"Advances in Neural Information Processing Systems (NeurIPS)","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hofer et al., 2019] Christoph Hofer, Roland Kwitt, Marc Niethammer, and Mandar Dixit. Connectivity-optimized representation learning via persistent homology. In Inter- national Conference on Machine Learning (ICML), pages 2751-2760, 2019.","title":"Connectivity-optimized representation learning via persistent homology","authors":"Christoph Hofer, Roland Kwitt, Marc Niethammer, Mandar Dixit","year":"2019","venue":"International Conference on Machine Learning (ICML)","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Hu et al., 2019] Xiaoling Hu, Fuxin Li, Dimitris Samaras, and Chao Chen. Topology-preserving deep image seg- mentation. Advances in Neural Information Processing Systems (NeurIPS), 32, 2019.","title":"Topology-preserving deep image seg-mentation","authors":"Xiaoling Hu, Fuxin Li, Dimitris Samaras, Chao Chen","year":"2019","venue":"Advances in Neural Information Processing Systems (NeurIPS)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lin et al., 2017] Yangbin Lin, Cheng Wang, Bili Chen, Dawei Zai, and Jonathan Li. Facet segmentation- based line segment extraction for large-scale point clouds. IEEE Transactions on Geoscience and Remote Sensing, 55(9):4839-4854, 2017.","title":"Facet segmentationbased line segment extraction for large-scale point clouds","authors":"Yangbin Lin, Cheng Wang, Bili Chen, Dawei Zai, Jonathan Li","year":"2017","venue":"IEEE Transactions on Geoscience and Remote Sensing","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Offroy and Duponchel, 2016] Marc Offroy and Ludovic Duponchel. Topological data analysis: A promising big data exploration tool in biology, analytical chemistry and physical chemistry. Analytica chimica acta, 910:1-11, 2016.","title":"Marc Offroy and Ludovic Duponchel. Topological data analysis: A promising big data exploration tool in biology, analytical chemistry and physical chemistry","authors":"Duponchel Offroy","year":"2016","venue":"Analytica chimica acta","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Qi et al., 2017a] Charles R Qi, Hao Su, Kaichun Mo, and Leonidas J Guibas. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 652-660, 2017.","title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","authors":"Qi","year":"2017","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Qi et al., 2017b] Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J Guibas. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in Neural Information Processing Systems (NeurIPS), 30, 2017.","title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","authors":"Qi","year":"2017","venue":"Advances in Neural Information Processing Systems (NeurIPS)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Rieck et al., 2018] Bastian Rieck, Matteo Togninalli, Chris- tian Bock, Michael Moor, Max Horn, Thomas Gumbsch, and Karsten Borgwardt. Neural persistence: A complexity measure for deep neural networks using algebraic topol- ogy. arXiv preprint arXiv:1812.09764, 2018.","title":"Neural persistence: A complexity measure for deep neural networks using algebraic topology","authors":"Bastian Rieck, Matteo Togninalli, Christian Bock, Michael Moor, Max Horn, Thomas Gumbsch, Karsten Borgwardt","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Taylor et al., 2015] Dane Taylor, Florian Klimm, Heather A Harrington, Miroslav Kramár, Konstantin Mischaikow, Mason A Porter, and Peter J Mucha. Topological data anal- ysis of contagion maps for examining spreading processes on networks. Nature Communications, 6(1):1-11, 2015.","title":"Topological data analysis of contagion maps for examining spreading processes on networks","authors":"Dane Taylor, Florian Klimm, Heather A Harrington, Miroslav Kramár, Konstantin Mischaikow, Mason A Porter, Peter J Mucha","year":"2015","venue":"Nature Communications","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wang et al., 2019] Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E Sarma, Michael M Bronstein, and Justin M Solomon. Dynamic graph cnn for learning on point clouds. ACM Transactions on Graphics, 38(5):1-12, 2019.","title":"Dynamic graph cnn for learning on point clouds","authors":"Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E Sarma, Michael M Bronstein, Justin M Solomon","year":"2019","venue":"ACM Transactions on Graphics","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Xiang et al., 2021] Tiange Xiang, Chaoyi Zhang, Yang Song, Jianhui Yu, and Weidong Cai. Walk in the cloud: Learning curves for point clouds shape analysis. In Pro- ceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 915-924, 2021.","title":"Walk in the cloud: Learning curves for point clouds shape analysis","authors":"Tiange Xiang, Chaoyi Zhang, Yang Song, Jianhui Yu, Weidong Cai","year":"2021","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Xie et al., 2014] Zhige Xie, Kai Xu, Ligang Liu, and Yue- shan Xiong. 3d shape segmentation and labeling via ex- treme learning machine. In Computer graphics forum, vol- ume 33, pages 85-95, 2014.","title":"3d shape segmentation and labeling via extreme learning machine","authors":"Zhige Xie, Kai Xu, Ligang Liu, Yueshan Xiong","year":"2014","venue":"Computer graphics forum","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yu et al., 2018] Lequan Yu, Xianzhi Li, Chi-Wing Fu, Daniel Cohen-Or, and Pheng-Ann Heng. Ec-net: an edge- aware point set consolidation network. In Proceedings of the European conference on computer vision (ECCV), pages 386-402, 2018.","title":"Ec-net: an edgeaware point set consolidation network","authors":"Lequan Yu, Xianzhi Li, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng","year":"2018","venue":"Proceedings of the European conference on computer vision (ECCV)","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhang et al., 2020] Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, and Kai Xu. Fusion-aware point convolution for online semantic 3d scene segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition (CVPR), pages 4534-4543, 2020.","title":"Fusion-aware point convolution for online semantic 3d scene segmentation","authors":"Zhang","year":"2020","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}