{"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/unsupervised-learning-of-3d-structure-from","title":"Unsupervised Learning of 3D Structure from Images","arxiv_id":"1607.00662","date":"2016-07-03","proceeding":"NeurIPS 2016 12","authors":["Danilo Jimenez Rezende","S. M. Ali Eslami","Shakir Mohamed","Peter Battaglia","Max Jaderberg","Nicolas Heess"],"abstract":"A key goal of computer vision is to recover the underlying 3D structure from\n2D observations of the world. In this paper we learn strong deep generative\nmodels of 3D structures, and recover these structures from 3D and 2D images via\nprobabilistic inference. We demonstrate high-quality samples and report\nlog-likelihoods on several datasets, including ShapeNet [2], and establish the\nfirst benchmarks in the literature. We also show how these models and their\ninference networks can be trained end-to-end from 2D images. This demonstrates\nfor the first time the feasibility of learning to infer 3D representations of\nthe world in a purely unsupervised manner.","url_abs":"http://arxiv.org/abs/1607.00662v2","url_pdf":"http://arxiv.org/pdf/1607.00662v2.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":"unsupervised-learning-of-3d-structure-from","repo_url":"https://github.com/fgolemo/threedee-tools","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1607.00662","atlas_url":"https://app.syntology.ai/?focus=1607.00662","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}