{"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/layouts-from-panoramic-images-with-geometry","title":"Layouts from Panoramic Images with Geometry and Deep Learning","arxiv_id":"1806.08294","date":"2018-06-21","proceeding":null,"authors":["Clara Fernandez-Labrador","Alejandro Perez-Yus","Gonzalo Lopez-Nicolas","Jose J. Guerrero"],"abstract":"In this paper, we propose a novel procedure for 3D layout recovery of indoor\nscenes from single 360 degrees panoramic images. With such images, all scene is\nseen at once, allowing to recover closed geometries. Our method combines\nstrategically the accuracy provided by geometric reasoning (lines and vanishing\npoints) with the higher level of data abstraction and pattern recognition\nachieved by deep learning techniques (edge and normal maps). Thus, we extract\nstructural corners from which we generate layout hypotheses of the room\nassuming Manhattan world. The best layout model is selected, achieving good\nperformance on both simple rooms (box-type) and complex shaped rooms (with more\nthan four walls). Experiments of the proposed approach are conducted within two\npublic datasets, SUN360 and Stanford (2D-3D-S) demonstrating the advantages of\nestimating layouts by combining geometry and deep learning and the\neffectiveness of our proposal with respect to the state of the art.","url_abs":"http://arxiv.org/abs/1806.08294v1","url_pdf":"http://arxiv.org/pdf/1806.08294v1.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":"layouts-from-panoramic-images-with-geometry","repo_url":"https://github.com/cfernandezlab/Lines-and-Vanishing-Points-directly-on-Panoramas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.08294","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}