{"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/learning-shape-templates-with-structured","title":"Learning Shape Templates with Structured Implicit Functions","arxiv_id":"1904.06447","date":"2019-04-12","proceeding":"ICCV 2019 10","authors":["Kyle Genova","Forrester Cole","Daniel Vlasic","Aaron Sarna","William T. Freeman","Thomas Funkhouser"],"abstract":"Template 3D shapes are useful for many tasks in graphics and vision,\nincluding fitting observation data, analyzing shape collections, and\ntransferring shape attributes. Because of the variety of geometry and topology\nof real-world shapes, previous methods generally use a library of hand-made\ntemplates. In this paper, we investigate learning a general shape template from\ndata. To allow for widely varying geometry and topology, we choose an implicit\nsurface representation based on composition of local shape elements. While long\nknown to computer graphics, this representation has not yet been explored in\nthe context of machine learning for vision. We show that structured implicit\nfunctions are suitable for learning and allow a network to smoothly and\nsimultaneously fit multiple classes of shapes. The learned shape template\nsupports applications such as shape exploration, correspondence, abstraction,\ninterpolation, and semantic segmentation from an RGB image.","url_abs":"http://arxiv.org/abs/1904.06447v1","url_pdf":"http://arxiv.org/pdf/1904.06447v1.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":"learning-shape-templates-with-structured","repo_url":"https://github.com/google/ldif","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.06447","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}