{"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/matterport3d-learning-from-rgb-d-data-in","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","arxiv_id":"1709.06158","date":"2017-09-18","proceeding":null,"authors":["Angel Chang","Angela Dai","Thomas Funkhouser","Maciej Halber","Matthias Nießner","Manolis Savva","Shuran Song","Andy Zeng","yinda zhang"],"abstract":"Access to large, diverse RGB-D datasets is critical for training RGB-D scene\nunderstanding algorithms. However, existing datasets still cover only a limited\nnumber of views or a restricted scale of spaces. In this paper, we introduce\nMatterport3D, a large-scale RGB-D dataset containing 10,800 panoramic views\nfrom 194,400 RGB-D images of 90 building-scale scenes. Annotations are provided\nwith surface reconstructions, camera poses, and 2D and 3D semantic\nsegmentations. The precise global alignment and comprehensive, diverse\npanoramic set of views over entire buildings enable a variety of supervised and\nself-supervised computer vision tasks, including keypoint matching, view\noverlap prediction, normal prediction from color, semantic segmentation, and\nregion classification.","url_abs":"http://arxiv.org/abs/1709.06158v1","url_pdf":"http://arxiv.org/pdf/1709.06158v1.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":"matterport3d-learning-from-rgb-d-data-in","repo_url":"https://github.com/niessner/Matterport","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"matterport3d","name":"Matterport3D","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.06158","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}