{"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/locate-3d-real-world-object-localization-via","title":"Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D","arxiv_id":"2504.14151","date":"2025-04-19","proceeding":null,"authors":["Sergio Arnaud","Paul McVay","Ada Martin","Arjun Majumdar","Krishna Murthy Jatavallabhula","Phillip Thomas","Ruslan Partsey","Daniel Dugas","Abha Gejji","Alexander Sax","Vincent-Pierre Berges","Mikael Henaff","Ayush Jain","Ang Cao","Ishita Prasad","Mrinal Kalakrishnan","Michael Rabbat","Nicolas Ballas","Mido Assran","Oleksandr Maksymets","Aravind Rajeswaran","Franziska Meier"],"abstract":"We present LOCATE 3D, a model for localizing objects in 3D scenes from referring expressions like \"the small coffee table between the sofa and the lamp.\" LOCATE 3D sets a new state-of-the-art on standard referential grounding benchmarks and showcases robust generalization capabilities. Notably, LOCATE 3D operates directly on sensor observation streams (posed RGB-D frames), enabling real-world deployment on robots and AR devices. Key to our approach is 3D-JEPA, a novel self-supervised learning (SSL) algorithm applicable to sensor point clouds. It takes as input a 3D pointcloud featurized using 2D foundation models (CLIP, DINO). Subsequently, masked prediction in latent space is employed as a pretext task to aid the self-supervised learning of contextualized pointcloud features. Once trained, the 3D-JEPA encoder is finetuned alongside a language-conditioned decoder to jointly predict 3D masks and bounding boxes. Additionally, we introduce LOCATE 3D DATASET, a new dataset for 3D referential grounding, spanning multiple capture setups with over 130K annotations. This enables a systematic study of generalization capabilities as well as a stronger model.","url_abs":"https://arxiv.org/abs/2504.14151v1","url_pdf":"https://arxiv.org/pdf/2504.14151v1.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":"locate-3d-real-world-object-localization-via","repo_url":"https://github.com/facebookresearch/locate-3d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2504.14151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.14151"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/locate-3d","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"43bdff2aef74d168","entry":"downsample","repo":"facebookresearch/locate-3d","repo_kind":"listed","path":"models/locate_3d.py","file_url":"https://github.com/facebookresearch/locate-3d/blob/HEAD/models/locate_3d.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"43bdff2aef74d168"}},{"code_sha256_prefix":"bf69a371a23b5cf6","entry":"load_state_dict","repo":"facebookresearch/locate-3d","repo_kind":"listed","path":"models/locate_3d.py","file_url":"https://github.com/facebookresearch/locate-3d/blob/HEAD/models/locate_3d.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"bf69a371a23b5cf6"}},{"code_sha256_prefix":"eeccfb3e87be9524","entry":"get_text_from_token_indices","repo":"facebookresearch/locate-3d","repo_kind":"listed","path":"models/locate_3d.py","file_url":"https://github.com/facebookresearch/locate-3d/blob/HEAD/models/locate_3d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"eeccfb3e87be9524"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}