{"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/predicting-complete-3d-models-of-indoor","title":"Predicting Complete 3D Models of Indoor Scenes","arxiv_id":"1504.02437","date":"2015-04-09","proceeding":null,"authors":["Ruiqi Guo","Chuhang Zou","Derek Hoiem"],"abstract":"One major goal of vision is to infer physical models of objects, surfaces,\nand their layout from sensors. In this paper, we aim to interpret indoor scenes\nfrom one RGBD image. Our representation encodes the layout of walls, which must\nconform to a Manhattan structure but is otherwise flexible, and the layout and\nextent of objects, modeled with CAD-like 3D shapes. We represent both the\nvisible and occluded portions of the scene, producing a complete 3D parse. Such\na scene interpretation is useful for robotics and visual reasoning, but\ndifficult to produce due to the well-known challenge of segmentation, the high\ndegree of occlusion, and the diversity of objects in indoor scene. We take a\ndata-driven approach, generating sets of potential object regions, matching to\nregions in training images, and transferring and aligning associated 3D models\nwhile encouraging fit to observations and overall consistency. We demonstrate\nencouraging results on the NYU v2 dataset and highlight a variety of\ninteresting directions for future work.","url_abs":"http://arxiv.org/abs/1504.02437v3","url_pdf":"http://arxiv.org/pdf/1504.02437v3.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":"predicting-complete-3d-models-of-indoor","repo_url":"https://github.com/arron2003/rgbd2full3d","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1504.02437","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}