{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/primitive-fitting-using-deep-boundary-aware","title":"Primitive Fitting Using Deep Boundary Aware Geometric Segmentation","arxiv_id":"1810.01604","date":"2018-10-03","proceeding":null,"authors":["Duanshun Li","Chen Feng"],"abstract":"To identify and fit geometric primitives (e.g., planes, spheres, cylinders,\ncones) in a noisy point cloud is a challenging yet beneficial task for fields\nsuch as robotics and reverse engineering. As a multi-model multi-instance\nfitting problem, it has been tackled with different approaches including\nRANSAC, which however often fit inferior models in practice with noisy inputs\nof cluttered scenes. Inspired by the corresponding human recognition process,\nand benefiting from the recent advancements in image semantic segmentation\nusing deep neural networks, we propose BAGSFit as a new framework addressing\nthis problem. Firstly, through a fully convolutional neural network, the input\npoint cloud is point-wisely segmented into multiple classes divided by jointly\ndetected instance boundaries without any geometric fitting. Thus, segments can\nserve as primitive hypotheses with a probability estimation of associating\nprimitive classes. Finally, all hypotheses are sent through a geometric\nverification to correct any misclassification by fitting primitives\nrespectively. We performed training using simulated range images and tested it\nwith both simulated and real-world point clouds. Quantitative and qualitative\nexperiments demonstrated the superiority of BAGSFit.","url_abs":"http://arxiv.org/abs/1810.01604v1","url_pdf":"http://arxiv.org/pdf/1810.01604v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"primitive-fitting-using-deep-boundary-aware","repo_url":"https://github.com/ai4ce/BAGSFit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}