{"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/planenet-piece-wise-planar-reconstruction","title":"PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image","arxiv_id":"1804.06278","date":"2018-04-17","proceeding":"CVPR 2018 6","authors":["Chen Liu","Jimei Yang","Duygu Ceylan","Ersin Yumer","Yasutaka Furukawa"],"abstract":"This paper proposes a deep neural network (DNN) for piece-wise planar\ndepthmap reconstruction from a single RGB image. While DNNs have brought\nremarkable progress to single-image depth prediction, piece-wise planar\ndepthmap reconstruction requires a structured geometry representation, and has\nbeen a difficult task to master even for DNNs. The proposed end-to-end DNN\nlearns to directly infer a set of plane parameters and corresponding plane\nsegmentation masks from a single RGB image. We have generated more than 50,000\npiece-wise planar depthmaps for training and testing from ScanNet, a\nlarge-scale RGBD video database. Our qualitative and quantitative evaluations\ndemonstrate that the proposed approach outperforms baseline methods in terms of\nboth plane segmentation and depth estimation accuracy. To the best of our\nknowledge, this paper presents the first end-to-end neural architecture for\npiece-wise planar reconstruction from a single RGB image. Code and data are\navailable at https://github.com/art-programmer/PlaneNet.","url_abs":"http://arxiv.org/abs/1804.06278v1","url_pdf":"http://arxiv.org/pdf/1804.06278v1.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":"planenet-piece-wise-planar-reconstruction","repo_url":"https://github.com/art-programmer/PlaneNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.06278","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}