{"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/deep-functional-dictionaries-learning","title":"Deep Functional Dictionaries: Learning Consistent Semantic Structures on 3D Models from Functions","arxiv_id":"1805.09957","date":"2018-05-25","proceeding":"NeurIPS 2018 12","authors":["Minhyuk Sung","Hao Su","Ronald Yu","Leonidas Guibas"],"abstract":"Various 3D semantic attributes such as segmentation masks, geometric\nfeatures, keypoints, and materials can be encoded as per-point probe functions\non 3D geometries. Given a collection of related 3D shapes, we consider how to\njointly analyze such probe functions over different shapes, and how to discover\ncommon latent structures using a neural network --- even in the absence of any\ncorrespondence information. Our network is trained on point cloud\nrepresentations of shape geometry and associated semantic functions on that\npoint cloud. These functions express a shared semantic understanding of the\nshapes but are not coordinated in any way. For example, in a segmentation task,\nthe functions can be indicator functions of arbitrary sets of shape parts, with\nthe particular combination involved not known to the network. Our network is\nable to produce a small dictionary of basis functions for each shape, a\ndictionary whose span includes the semantic functions provided for that shape.\nEven though our shapes have independent discretizations and no functional\ncorrespondences are provided, the network is able to generate latent bases, in\na consistent order, that reflect the shared semantic structure among the\nshapes. We demonstrate the effectiveness of our technique in various\nsegmentation and keypoint selection applications.","url_abs":"http://arxiv.org/abs/1805.09957v3","url_pdf":"http://arxiv.org/pdf/1805.09957v3.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":"deep-functional-dictionaries-learning","repo_url":"https://github.com/mhsung/deep-functional-dictionaries","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"segmentation","task_name":"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}