{"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/shape2motion-joint-analysis-of-motion-parts","title":"Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes","arxiv_id":"1903.03911","date":"2019-03-10","proceeding":"CVPR 2019 6","authors":["Xiaogang Wang","Bin Zhou","Yahao Shi","Xiaowu Chen","Qinping Zhao","Kai Xu"],"abstract":"For the task of mobility analysis of 3D shapes, we propose joint analysis for\nsimultaneous motion part segmentation and motion attribute estimation, taking a\nsingle 3D model as input. The problem is significantly different from those\ntackled in the existing works which assume the availability of either a\npre-existing shape segmentation or multiple 3D models in different motion\nstates. To that end, we develop Shape2Motion which takes a single 3D point\ncloud as input, and jointly computes a mobility-oriented segmentation and the\nassociated motion attributes. Shape2Motion is comprised of two deep neural\nnetworks designed for mobility proposal generation and mobility optimization,\nrespectively. The key contribution of these networks is the novel motion-driven\nfeatures and losses used in both motion part segmentation and motion attribute\nestimation. This is based on the observation that the movement of a functional\npart preserves the shape structure. We evaluate Shape2Motion with a newly\nproposed benchmark for mobility analysis of 3D shapes. Results demonstrate that\nour method achieves the state-of-the-art performance both in terms of motion\npart segmentation and motion attribute estimation.","url_abs":"http://arxiv.org/abs/1903.03911v2","url_pdf":"http://arxiv.org/pdf/1903.03911v2.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":"shape2motion-joint-analysis-of-motion-parts","repo_url":"https://github.com/dragonlong/articulated-pose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1903.03911","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}