{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NXLZSAJT2TXGXHCGJG7DIDG7W7","short_pith_number":"pith:NXLZSAJT","schema_version":"1.0","canonical_sha256":"6dd7990133d4ee6b9c4649be340cdfb7c989d452f20b6b1acbbe48bd9f70bef4","source":{"kind":"arxiv","id":"2402.16936","version":1},"attestation_state":"computed","paper":{"title":"Disentangled 3D Scene Generation with Layout Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aleksander Holynski, Alexei A. Efros, Ben Mildenhall, Ben Poole, Dave Epstein","submitted_at":"2024-02-26T18:54:15Z","abstract_excerpt":"We introduce a method to generate 3D scenes that are disentangled into their component objects. This disentanglement is unsupervised, relying only on the knowledge of a large pretrained text-to-image model. Our key insight is that objects can be discovered by finding parts of a 3D scene that, when rearranged spatially, still produce valid configurations of the same scene. Concretely, our method jointly optimizes multiple NeRFs from scratch - each representing its own object - along with a set of layouts that composite these objects into scenes. We then encourage these composited scenes to be i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.16936","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-26T18:54:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"894b35ae56c6681d0a304c52f43cb412113c3d4f51ae1fa2c1cffcea4027f9fe","abstract_canon_sha256":"44953e049a31c942103e99ccbceac4fc14383d93f1904e68eb9bfc26b281a061"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:39.355800Z","signature_b64":"zjmRSQ6bMU2qS9t8O7FXEzZTFFLbl43GLVHoqjBQuansDtuI1m84zLpG4z7Tz68cdokaJetTpO49ywKL1uBrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dd7990133d4ee6b9c4649be340cdfb7c989d452f20b6b1acbbe48bd9f70bef4","last_reissued_at":"2026-07-05T07:49:39.355336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:39.355336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangled 3D Scene Generation with Layout Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aleksander Holynski, Alexei A. Efros, Ben Mildenhall, Ben Poole, Dave Epstein","submitted_at":"2024-02-26T18:54:15Z","abstract_excerpt":"We introduce a method to generate 3D scenes that are disentangled into their component objects. This disentanglement is unsupervised, relying only on the knowledge of a large pretrained text-to-image model. Our key insight is that objects can be discovered by finding parts of a 3D scene that, when rearranged spatially, still produce valid configurations of the same scene. Concretely, our method jointly optimizes multiple NeRFs from scratch - each representing its own object - along with a set of layouts that composite these objects into scenes. We then encourage these composited scenes to be i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16936","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.16936/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.16936","created_at":"2026-07-05T07:49:39.355403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16936v1","created_at":"2026-07-05T07:49:39.355403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16936","created_at":"2026-07-05T07:49:39.355403+00:00"},{"alias_kind":"pith_short_12","alias_value":"NXLZSAJT2TXG","created_at":"2026-07-05T07:49:39.355403+00:00"},{"alias_kind":"pith_short_16","alias_value":"NXLZSAJT2TXGXHCG","created_at":"2026-07-05T07:49:39.355403+00:00"},{"alias_kind":"pith_short_8","alias_value":"NXLZSAJT","created_at":"2026-07-05T07:49:39.355403+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24138","citing_title":"Sat2City v2: Native 3D City Asset Generation from a Single Satellite Image","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2405.10314","citing_title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10772","citing_title":"HOG-Layout: Hierarchical 3D Scene Generation, Optimization and Editing via Vision-Language Models","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NXLZSAJT2TXGXHCGJG7DIDG7W7","json":"https://pith.science/pith/NXLZSAJT2TXGXHCGJG7DIDG7W7.json","graph_json":"https://pith.science/api/pith-number/NXLZSAJT2TXGXHCGJG7DIDG7W7/graph.json","events_json":"https://pith.science/api/pith-number/NXLZSAJT2TXGXHCGJG7DIDG7W7/events.json","paper":"https://pith.science/paper/NXLZSAJT"},"agent_actions":{"view_html":"https://pith.science/pith/NXLZSAJT2TXGXHCGJG7DIDG7W7","download_json":"https://pith.science/pith/NXLZSAJT2TXGXHCGJG7DIDG7W7.json","view_paper":"https://pith.science/paper/NXLZSAJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16936&json=true","fetch_graph":"https://pith.science/api/pith-number/NXLZSAJT2TXGXHCGJG7DIDG7W7/graph.json","fetch_events":"https://pith.science/api/pith-number/NXLZSAJT2TXGXHCGJG7DIDG7W7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NXLZSAJT2TXGXHCGJG7DIDG7W7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NXLZSAJT2TXGXHCGJG7DIDG7W7/action/storage_attestation","attest_author":"https://pith.science/pith/NXLZSAJT2TXGXHCGJG7DIDG7W7/action/author_attestation","sign_citation":"https://pith.science/pith/NXLZSAJT2TXGXHCGJG7DIDG7W7/action/citation_signature","submit_replication":"https://pith.science/pith/NXLZSAJT2TXGXHCGJG7DIDG7W7/action/replication_record"}},"created_at":"2026-07-05T07:49:39.355403+00:00","updated_at":"2026-07-05T07:49:39.355403+00:00"}