{"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/scannet-richly-annotated-3d-reconstructions","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","arxiv_id":"1702.04405","date":"2017-02-14","proceeding":"CVPR 2017 7","authors":["Angela Dai","Angel X. Chang","Manolis Savva","Maciej Halber","Thomas Funkhouser","Matthias Nießner"],"abstract":"A key requirement for leveraging supervised deep learning methods is the\navailability of large, labeled datasets. Unfortunately, in the context of RGB-D\nscene understanding, very little data is available -- current datasets cover a\nsmall range of scene views and have limited semantic annotations. To address\nthis issue, we introduce ScanNet, an RGB-D video dataset containing 2.5M views\nin 1513 scenes annotated with 3D camera poses, surface reconstructions, and\nsemantic segmentations. To collect this data, we designed an easy-to-use and\nscalable RGB-D capture system that includes automated surface reconstruction\nand crowdsourced semantic annotation. We show that using this data helps\nachieve state-of-the-art performance on several 3D scene understanding tasks,\nincluding 3D object classification, semantic voxel labeling, and CAD model\nretrieval. The dataset is freely available at http://www.scan-net.org.","url_abs":"http://arxiv.org/abs/1702.04405v2","url_pdf":"http://arxiv.org/pdf/1702.04405v2.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":"scannet-richly-annotated-3d-reconstructions","repo_url":"https://github.com/suryanshkumar/online-joint-depthfusion-and-semantic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-object-classification","task_name":"3D Object Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"surface-reconstruction","task_name":"Surface Reconstruction"}],"methods":[],"datasets_introduced":[{"slug":"scannet","name":"ScanNet","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-scannet","task":"Semantic Segmentation","dataset":"ScanNet","model":"ScanNet","rank_in_archive_order":45,"of":45,"metrics":{"test mIoU":"30.6"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-scannetv2","task":"Semantic Segmentation","dataset":"ScanNetV2","model":"ScanNet (2d proj)","rank_in_archive_order":11,"of":12,"metrics":{"Mean IoU":"33.0%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1702.04405","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}