{"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/parsing-geometry-using-structure-aware-shape","title":"Parsing Geometry Using Structure-Aware Shape Templates","arxiv_id":"1808.01337","date":"2018-08-03","proceeding":"3D Vision 2018 2018 9","authors":["Vignesh Ganapathi-Subramanian","Olga Diamanti","Soeren Pirk","Chengcheng Tang","Matthias Niessner","Leonidas J. Guibas"],"abstract":"Real-life man-made objects often exhibit strong and easily-identifiable\nstructure, as a direct result of their design or their intended functionality.\nStructure typically appears in the form of individual parts and their\narrangement. Knowing about object structure can be an important cue for object\nrecognition and scene understanding - a key goal for various AR and robotics\napplications. However, commodity RGB-D sensors used in these scenarios only\nproduce raw, unorganized point clouds, without structural information about the\ncaptured scene. Moreover, the generated data is commonly partial and\nsusceptible to artifacts and noise, which makes inferring the structure of\nscanned objects challenging. In this paper, we organize large shape collections\ninto parameterized shape templates to capture the underlying structure of the\nobjects. The templates allow us to transfer the structural information onto new\nobjects and incomplete scans. We employ a deep neural network that matches the\npartial scan with one of the shape templates, then match and fit it to complete\nand detailed models from the collection. This allows us to faithfully label its\nparts and to guide the reconstruction of the scanned object. We showcase the\neffectiveness of our method by comparing it to other state-of-the-art\napproaches.","url_abs":"http://arxiv.org/abs/1808.01337v2","url_pdf":"http://arxiv.org/pdf/1808.01337v2.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":"parsing-geometry-using-structure-aware-shape","repo_url":"https://github.com/vigansub/StructureAwareShapeTemplates","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.01337","atlas_url":"https://app.syntology.ai/?focus=1808.01337","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}