{"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/3d-prnn-generating-shape-primitives-with","title":"3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks","arxiv_id":"1708.01648","date":"2017-08-04","proceeding":"ICCV 2017 10","authors":["Chuhang Zou","Ersin Yumer","Jimei Yang","Duygu Ceylan","Derek Hoiem"],"abstract":"The success of various applications including robotics, digital content\ncreation, and visualization demand a structured and abstract representation of\nthe 3D world from limited sensor data. Inspired by the nature of human\nperception of 3D shapes as a collection of simple parts, we explore such an\nabstract shape representation based on primitives. Given a single depth image\nof an object, we present 3D-PRNN, a generative recurrent neural network that\nsynthesizes multiple plausible shapes composed of a set of primitives. Our\ngenerative model encodes symmetry characteristics of common man-made objects,\npreserves long-range structural coherence, and describes objects of varying\ncomplexity with a compact representation. We also propose a method based on\nGaussian Fields to generate a large scale dataset of primitive-based shape\nrepresentations to train our network. We evaluate our approach on a wide range\nof examples and show that it outperforms nearest-neighbor based shape retrieval\nmethods and is on-par with voxel-based generative models while using a\nsignificantly reduced parameter space.","url_abs":"http://arxiv.org/abs/1708.01648v1","url_pdf":"http://arxiv.org/pdf/1708.01648v1.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":"3d-prnn-generating-shape-primitives-with","repo_url":"https://github.com/zouchuhang/3D-PRNN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"torch","reach":{"status":"unanswered"}},{"paper_slug":"3d-prnn-generating-shape-primitives-with","repo_url":"https://github.com/paschalidoud/superquadric_parsing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.01648","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}