{"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/csgnet-neural-shape-parser-for-constructive","title":"CSGNet: Neural Shape Parser for Constructive Solid Geometry","arxiv_id":"1712.08290","date":"2017-12-22","proceeding":"CVPR 2018 6","authors":["Gopal Sharma","Rishabh Goyal","Difan Liu","Evangelos Kalogerakis","Subhransu Maji"],"abstract":"We present a neural architecture that takes as input a 2D or 3D shape and\noutputs a program that generates the shape. The instructions in our program are\nbased on constructive solid geometry principles, i.e., a set of boolean\noperations on shape primitives defined recursively. Bottom-up techniques for\nthis shape parsing task rely on primitive detection and are inherently slow\nsince the search space over possible primitive combinations is large. In\ncontrast, our model uses a recurrent neural network that parses the input shape\nin a top-down manner, which is significantly faster and yields a compact and\neasy-to-interpret sequence of modeling instructions. Our model is also more\neffective as a shape detector compared to existing state-of-the-art detection\ntechniques. We finally demonstrate that our network can be trained on novel\ndatasets without ground-truth program annotations through policy gradient\ntechniques.","url_abs":"http://arxiv.org/abs/1712.08290v2","url_pdf":"http://arxiv.org/pdf/1712.08290v2.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":"csgnet-neural-shape-parser-for-constructive","repo_url":"https://github.com/AN313/deformable","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.08290","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}