{"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/scanrefer-3d-object-localization-in-rgb-d","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","arxiv_id":"1912.08830","date":"2019-12-18","proceeding":"ECCV 2020 8","authors":["Dave Zhenyu Chen","Angel X. Chang","Matthias Nießner"],"abstract":"We introduce the task of 3D object localization in RGB-D scans using natural language descriptions. As input, we assume a point cloud of a scanned 3D scene along with a free-form description of a specified target object. To address this task, we propose ScanRefer, learning a fused descriptor from 3D object proposals and encoded sentence embeddings. This fused descriptor correlates language expressions with geometric features, enabling regression of the 3D bounding box of a target object. We also introduce the ScanRefer dataset, containing 51,583 descriptions of 11,046 objects from 800 ScanNet scenes. ScanRefer is the first large-scale effort to perform object localization via natural language expression directly in 3D.","url_abs":"https://arxiv.org/abs/1912.08830v3","url_pdf":"https://arxiv.org/pdf/1912.08830v3.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":"scanrefer-3d-object-localization-in-rgb-d","repo_url":"https://github.com/chodi150/scanrefer-pointgroup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"scanrefer-3d-object-localization-in-rgb-d","repo_url":"https://github.com/daveredrum/ScanRefer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"scanrefer-3d-object-localization-in-rgb-d","repo_url":"https://github.com/yuhaonankaka/adl_maskrcnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embeddings","task_name":"Sentence Embeddings"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[{"slug":"scanrefer-dataset","name":"ScanRefer Dataset","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.08830","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}