{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HU5KZ6XA6C4BQCBDEPGBH2B4XV","short_pith_number":"pith:HU5KZ6XA","schema_version":"1.0","canonical_sha256":"3d3aacfae0f0b818082323cc13e83cbd7ae2467187d1f10ec7bc93d958a127fd","source":{"kind":"arxiv","id":"2312.08885","version":1},"attestation_state":"computed","paper":{"title":"SceneWiz3D: Towards Text-guided 3D Scene Composition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Bolei Zhou, Ceyuan Yang, Chaoyang Wang, Dahua Lin, Hsin-Ying Lee, Peiye Zhuang, Qihang Zhang, Sergey Tulyakov, Yinghao Xu","submitted_at":"2023-12-13T18:59:30Z","abstract_excerpt":"We are witnessing significant breakthroughs in the technology for generating 3D objects from text. Existing approaches either leverage large text-to-image models to optimize a 3D representation or train 3D generators on object-centric datasets. Generating entire scenes, however, remains very challenging as a scene contains multiple 3D objects, diverse and scattered. In this work, we introduce SceneWiz3D, a novel approach to synthesize high-fidelity 3D scenes from text. We marry the locality of objects with globality of scenes by introducing a hybrid 3D representation: explicit for objects and "},"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":"2312.08885","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T18:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"fb6cc9b0a1de1d953a30cd752801f619cbb08b2211519e174b329f42509aa1e5","abstract_canon_sha256":"e27ae2b15e040ff12de9649d5bf0661d0fd6f6ccba6da423dfbe8149cc761a6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:11.083831Z","signature_b64":"hMJIlEfC4qXlSmlNTJsq4VT6Gmf7uYh9N0brpm6YMJhZkitWkzLnyY9qcA0qXhJWylqqMhu8a5gGSKluJ6qeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d3aacfae0f0b818082323cc13e83cbd7ae2467187d1f10ec7bc93d958a127fd","last_reissued_at":"2026-07-05T07:24:11.083345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:11.083345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SceneWiz3D: Towards Text-guided 3D Scene Composition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Bolei Zhou, Ceyuan Yang, Chaoyang Wang, Dahua Lin, Hsin-Ying Lee, Peiye Zhuang, Qihang Zhang, Sergey Tulyakov, Yinghao Xu","submitted_at":"2023-12-13T18:59:30Z","abstract_excerpt":"We are witnessing significant breakthroughs in the technology for generating 3D objects from text. Existing approaches either leverage large text-to-image models to optimize a 3D representation or train 3D generators on object-centric datasets. Generating entire scenes, however, remains very challenging as a scene contains multiple 3D objects, diverse and scattered. In this work, we introduce SceneWiz3D, a novel approach to synthesize high-fidelity 3D scenes from text. We marry the locality of objects with globality of scenes by introducing a hybrid 3D representation: explicit for objects and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08885","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/2312.08885/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":"2312.08885","created_at":"2026-07-05T07:24:11.083407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08885v1","created_at":"2026-07-05T07:24:11.083407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08885","created_at":"2026-07-05T07:24:11.083407+00:00"},{"alias_kind":"pith_short_12","alias_value":"HU5KZ6XA6C4B","created_at":"2026-07-05T07:24:11.083407+00:00"},{"alias_kind":"pith_short_16","alias_value":"HU5KZ6XA6C4BQCBD","created_at":"2026-07-05T07:24:11.083407+00:00"},{"alias_kind":"pith_short_8","alias_value":"HU5KZ6XA","created_at":"2026-07-05T07:24:11.083407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23888","citing_title":"GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16807","citing_title":"DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusion","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2406.02509","citing_title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09423","citing_title":"SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09423","citing_title":"SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning","ref_index":105,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HU5KZ6XA6C4BQCBDEPGBH2B4XV","json":"https://pith.science/pith/HU5KZ6XA6C4BQCBDEPGBH2B4XV.json","graph_json":"https://pith.science/api/pith-number/HU5KZ6XA6C4BQCBDEPGBH2B4XV/graph.json","events_json":"https://pith.science/api/pith-number/HU5KZ6XA6C4BQCBDEPGBH2B4XV/events.json","paper":"https://pith.science/paper/HU5KZ6XA"},"agent_actions":{"view_html":"https://pith.science/pith/HU5KZ6XA6C4BQCBDEPGBH2B4XV","download_json":"https://pith.science/pith/HU5KZ6XA6C4BQCBDEPGBH2B4XV.json","view_paper":"https://pith.science/paper/HU5KZ6XA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08885&json=true","fetch_graph":"https://pith.science/api/pith-number/HU5KZ6XA6C4BQCBDEPGBH2B4XV/graph.json","fetch_events":"https://pith.science/api/pith-number/HU5KZ6XA6C4BQCBDEPGBH2B4XV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HU5KZ6XA6C4BQCBDEPGBH2B4XV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HU5KZ6XA6C4BQCBDEPGBH2B4XV/action/storage_attestation","attest_author":"https://pith.science/pith/HU5KZ6XA6C4BQCBDEPGBH2B4XV/action/author_attestation","sign_citation":"https://pith.science/pith/HU5KZ6XA6C4BQCBDEPGBH2B4XV/action/citation_signature","submit_replication":"https://pith.science/pith/HU5KZ6XA6C4BQCBDEPGBH2B4XV/action/replication_record"}},"created_at":"2026-07-05T07:24:11.083407+00:00","updated_at":"2026-07-05T07:24:11.083407+00:00"}