{"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/a-coarse-to-fine-indoor-layout-estimation","title":"A Coarse-to-Fine Indoor Layout Estimation (CFILE) Method","arxiv_id":"1607.00598","date":"2016-07-03","proceeding":null,"authors":["Yuzhuo Ren","Chen Chen","Shang-Wen Li","C. -C. Jay Kuo"],"abstract":"The task of estimating the spatial layout of cluttered indoor scenes from a\nsingle RGB image is addressed in this work. Existing solutions to this problems\nlargely rely on hand-craft features and vanishing lines, and they often fail in\nhighly cluttered indoor rooms. The proposed coarse-to-fine indoor layout\nestimation (CFILE) method consists of two stages: 1) coarse layout estimation;\nand 2) fine layout localization. In the first stage, we adopt a fully\nconvolutional neural network (FCN) to obtain a coarse-scale room layout\nestimate that is close to the ground truth globally. The proposed FCN considers\ncombines the layout contour property and the surface property so as to provide\na robust estimate in the presence of cluttered objects. In the second stage, we\nformulate an optimization framework that enforces several constraints such as\nlayout contour straightness, surface smoothness and geometric constraints for\nlayout detail refinement. Our proposed system offers the state-of-the-art\nperformance on two commonly used benchmark datasets.","url_abs":"http://arxiv.org/abs/1607.00598v1","url_pdf":"http://arxiv.org/pdf/1607.00598v1.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":"a-coarse-to-fine-indoor-layout-estimation","repo_url":"https://github.com/yuzhuoren/IndoorLayout","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fcn","method_name":"FCN"},{"method_slug":"max-pooling","method_name":"Max Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1607.00598","atlas_url":"https://app.syntology.ai/?focus=1607.00598","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}