{"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/contrastive-lift-3d-object-instance","title":"Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion","arxiv_id":"2306.04633","date":"2023-06-07","proceeding":"NeurIPS 2023 11","authors":["Yash Bhalgat","Iro Laina","João F. Henriques","Andrew Zisserman","Andrea Vedaldi"],"abstract":"Instance segmentation in 3D is a challenging task due to the lack of large-scale annotated datasets. In this paper, we show that this task can be addressed effectively by leveraging instead 2D pre-trained models for instance segmentation. We propose a novel approach to lift 2D segments to 3D and fuse them by means of a neural field representation, which encourages multi-view consistency across frames. The core of our approach is a slow-fast clustering objective function, which is scalable and well-suited for scenes with a large number of objects. Unlike previous approaches, our method does not require an upper bound on the number of objects or object tracking across frames. To demonstrate the scalability of the slow-fast clustering, we create a new semi-realistic dataset called the Messy Rooms dataset, which features scenes with up to 500 objects per scene. Our approach outperforms the state-of-the-art on challenging scenes from the ScanNet, Hypersim, and Replica datasets, as well as on our newly created Messy Rooms dataset, demonstrating the effectiveness and scalability of our slow-fast clustering method.","url_abs":"https://arxiv.org/abs/2306.04633v2","url_pdf":"https://arxiv.org/pdf/2306.04633v2.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":"contrastive-lift-3d-object-instance","repo_url":"https://github.com/yashbhalgat/contrastive-lift","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.04633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.04633"}},"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":"deterministic:regex_extraction","url":"https://github.com/yashbhalgat/Contrastive-Lift","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yashbhalgat/contrastive-lift","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"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":"d68f29ddbc748c2e","entry":"MLPRenderInstanceFeature","repo":"yashbhalgat/contrastive-lift","repo_kind":"official","path":"model/radiance_field/tensoRF.py","file_url":"https://github.com/yashbhalgat/contrastive-lift/blob/HEAD/model/radiance_field/tensoRF.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d68f29ddbc748c2e"}},{"code_sha256_prefix":"c9258250b51c0801","entry":"output_dirname","repo":"yashbhalgat/Contrastive-Lift","repo_kind":"official","path":"inference/render_panopli.py","file_url":"https://github.com/yashbhalgat/Contrastive-Lift/blob/HEAD/inference/render_panopli.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c9258250b51c0801"}},{"code_sha256_prefix":"53f2bf6ca030d384","entry":"MLPRenderFeature","repo":"yashbhalgat/contrastive-lift","repo_kind":"official","path":"model/radiance_field/tensoRF.py","file_url":"https://github.com/yashbhalgat/contrastive-lift/blob/HEAD/model/radiance_field/tensoRF.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"53f2bf6ca030d384"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}