{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QVHUQTAHADJBDLCPAZL7NFULMC","short_pith_number":"pith:QVHUQTAH","schema_version":"1.0","canonical_sha256":"854f484c0700d211ac4f0657f6968b60a50955ff07a1c718633510b55f62be10","source":{"kind":"arxiv","id":"2207.13751","version":1},"attestation_state":"computed","paper":{"title":"GAUDI: A Neural Architect for Immersive 3D Scene Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Afshin Dehghan, Alexander Toshev, Daniel Ulbricht, Hanlin Goh, Josh Susskind, Laurent Dinh, Miguel Angel Bautista, Pengsheng Guo, Samira Abnar, Shuangfei Zhai, Walter Talbott, Zhuoyuan Chen","submitted_at":"2022-07-27T19:10:32Z","abstract_excerpt":"We introduce GAUDI, a generative model capable of capturing the distribution of complex and realistic 3D scenes that can be rendered immersively from a moving camera. We tackle this challenging problem with a scalable yet powerful approach, where we first optimize a latent representation that disentangles radiance fields and camera poses. This latent representation is then used to learn a generative model that enables both unconditional and conditional generation of 3D scenes. Our model generalizes previous works that focus on single objects by removing the assumption that the camera pose dist"},"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":"2207.13751","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-27T19:10:32Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"4631b6d0575499bb821f612af44e36e1195db5a7844b364f31dd6d67e899eedd","abstract_canon_sha256":"783f108d131bcb0ce89fd767987d3b5bea8746d76fbfec3df3d0e4ba6ed5d21a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:11.877168Z","signature_b64":"RsqKDQ0hz47EANMy/L2WxQAfyKx6PV8l05cQpZZ6T5eBSnHAW1FNwPdhaz/KqTPnD8Hw6TFmtuv+wdiG5Bm/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"854f484c0700d211ac4f0657f6968b60a50955ff07a1c718633510b55f62be10","last_reissued_at":"2026-07-05T04:44:11.876687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:11.876687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GAUDI: A Neural Architect for Immersive 3D Scene Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Afshin Dehghan, Alexander Toshev, Daniel Ulbricht, Hanlin Goh, Josh Susskind, Laurent Dinh, Miguel Angel Bautista, Pengsheng Guo, Samira Abnar, Shuangfei Zhai, Walter Talbott, Zhuoyuan Chen","submitted_at":"2022-07-27T19:10:32Z","abstract_excerpt":"We introduce GAUDI, a generative model capable of capturing the distribution of complex and realistic 3D scenes that can be rendered immersively from a moving camera. We tackle this challenging problem with a scalable yet powerful approach, where we first optimize a latent representation that disentangles radiance fields and camera poses. This latent representation is then used to learn a generative model that enables both unconditional and conditional generation of 3D scenes. Our model generalizes previous works that focus on single objects by removing the assumption that the camera pose dist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.13751","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/2207.13751/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":"2207.13751","created_at":"2026-07-05T04:44:11.876745+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.13751v1","created_at":"2026-07-05T04:44:11.876745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.13751","created_at":"2026-07-05T04:44:11.876745+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVHUQTAHADJB","created_at":"2026-07-05T04:44:11.876745+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVHUQTAHADJBDLCP","created_at":"2026-07-05T04:44:11.876745+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVHUQTAH","created_at":"2026-07-05T04:44:11.876745+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2305.02463","citing_title":"Shap-E: Generating Conditional 3D Implicit Functions","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVHUQTAHADJBDLCPAZL7NFULMC","json":"https://pith.science/pith/QVHUQTAHADJBDLCPAZL7NFULMC.json","graph_json":"https://pith.science/api/pith-number/QVHUQTAHADJBDLCPAZL7NFULMC/graph.json","events_json":"https://pith.science/api/pith-number/QVHUQTAHADJBDLCPAZL7NFULMC/events.json","paper":"https://pith.science/paper/QVHUQTAH"},"agent_actions":{"view_html":"https://pith.science/pith/QVHUQTAHADJBDLCPAZL7NFULMC","download_json":"https://pith.science/pith/QVHUQTAHADJBDLCPAZL7NFULMC.json","view_paper":"https://pith.science/paper/QVHUQTAH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.13751&json=true","fetch_graph":"https://pith.science/api/pith-number/QVHUQTAHADJBDLCPAZL7NFULMC/graph.json","fetch_events":"https://pith.science/api/pith-number/QVHUQTAHADJBDLCPAZL7NFULMC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVHUQTAHADJBDLCPAZL7NFULMC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVHUQTAHADJBDLCPAZL7NFULMC/action/storage_attestation","attest_author":"https://pith.science/pith/QVHUQTAHADJBDLCPAZL7NFULMC/action/author_attestation","sign_citation":"https://pith.science/pith/QVHUQTAHADJBDLCPAZL7NFULMC/action/citation_signature","submit_replication":"https://pith.science/pith/QVHUQTAHADJBDLCPAZL7NFULMC/action/replication_record"}},"created_at":"2026-07-05T04:44:11.876745+00:00","updated_at":"2026-07-05T04:44:11.876745+00:00"}