{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:465QTCOSKJL2J5CVASB7LL2AQV","short_pith_number":"pith:465QTCOS","schema_version":"1.0","canonical_sha256":"e7bb0989d25257a4f4550483f5af408566df40ce3e7926fbdfb3b98fb4e9051f","source":{"kind":"arxiv","id":"2406.03184","version":2},"attestation_state":"computed","paper":{"title":"Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Wen, Lu Sheng, Xinyuan Chen, Yaohui Wang, Zehuan Huang","submitted_at":"2024-06-05T12:15:22Z","abstract_excerpt":"Existing single image-to-3D creation methods typically involve a two-stage process, first generating multi-view images, and then using these images for 3D reconstruction. However, training these two stages separately leads to significant data bias in the inference phase, thus affecting the quality of reconstructed results. We introduce a unified 3D generation framework, named Ouroboros3D, which integrates diffusion-based multi-view image generation and 3D reconstruction into a recursive diffusion process. In our framework, these two modules are jointly trained through a self-conditioning mecha"},"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":"2406.03184","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T12:15:22Z","cross_cats_sorted":[],"title_canon_sha256":"3c06ee7f0069eae9af12a51303a07b5dc2213e5c7af346b3cb4fded41d5c49fe","abstract_canon_sha256":"0694fe0e25cc50a0f0602ecdc0841706981535e2c706fdee91b101c7901caa21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:33.355375Z","signature_b64":"rvzeNKlNQwhkvnmT4r7CUSd9gmiOhnbEz0GSCAN+rHspyyz9N+XkJZaRBKqM4lrEguamYOUWDO/oUncO9BmrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7bb0989d25257a4f4550483f5af408566df40ce3e7926fbdfb3b98fb4e9051f","last_reissued_at":"2026-07-05T10:56:33.354756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:33.354756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Wen, Lu Sheng, Xinyuan Chen, Yaohui Wang, Zehuan Huang","submitted_at":"2024-06-05T12:15:22Z","abstract_excerpt":"Existing single image-to-3D creation methods typically involve a two-stage process, first generating multi-view images, and then using these images for 3D reconstruction. However, training these two stages separately leads to significant data bias in the inference phase, thus affecting the quality of reconstructed results. We introduce a unified 3D generation framework, named Ouroboros3D, which integrates diffusion-based multi-view image generation and 3D reconstruction into a recursive diffusion process. In our framework, these two modules are jointly trained through a self-conditioning mecha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03184","kind":"arxiv","version":2},"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/2406.03184/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":"2406.03184","created_at":"2026-07-05T10:56:33.354838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.03184v2","created_at":"2026-07-05T10:56:33.354838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03184","created_at":"2026-07-05T10:56:33.354838+00:00"},{"alias_kind":"pith_short_12","alias_value":"465QTCOSKJL2","created_at":"2026-07-05T10:56:33.354838+00:00"},{"alias_kind":"pith_short_16","alias_value":"465QTCOSKJL2J5CV","created_at":"2026-07-05T10:56:33.354838+00:00"},{"alias_kind":"pith_short_8","alias_value":"465QTCOS","created_at":"2026-07-05T10:56:33.354838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.16869","citing_title":"SegviGen: Repurposing 3D Generative Model for Part Segmentation","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12309","citing_title":"Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10789","citing_title":"ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/465QTCOSKJL2J5CVASB7LL2AQV","json":"https://pith.science/pith/465QTCOSKJL2J5CVASB7LL2AQV.json","graph_json":"https://pith.science/api/pith-number/465QTCOSKJL2J5CVASB7LL2AQV/graph.json","events_json":"https://pith.science/api/pith-number/465QTCOSKJL2J5CVASB7LL2AQV/events.json","paper":"https://pith.science/paper/465QTCOS"},"agent_actions":{"view_html":"https://pith.science/pith/465QTCOSKJL2J5CVASB7LL2AQV","download_json":"https://pith.science/pith/465QTCOSKJL2J5CVASB7LL2AQV.json","view_paper":"https://pith.science/paper/465QTCOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.03184&json=true","fetch_graph":"https://pith.science/api/pith-number/465QTCOSKJL2J5CVASB7LL2AQV/graph.json","fetch_events":"https://pith.science/api/pith-number/465QTCOSKJL2J5CVASB7LL2AQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/465QTCOSKJL2J5CVASB7LL2AQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/465QTCOSKJL2J5CVASB7LL2AQV/action/storage_attestation","attest_author":"https://pith.science/pith/465QTCOSKJL2J5CVASB7LL2AQV/action/author_attestation","sign_citation":"https://pith.science/pith/465QTCOSKJL2J5CVASB7LL2AQV/action/citation_signature","submit_replication":"https://pith.science/pith/465QTCOSKJL2J5CVASB7LL2AQV/action/replication_record"}},"created_at":"2026-07-05T10:56:33.354838+00:00","updated_at":"2026-07-05T10:56:33.354838+00:00"}