{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZA4NBBRKQKVOF2P4MYEUX7WDRA","short_pith_number":"pith:ZA4NBBRK","schema_version":"1.0","canonical_sha256":"c838d0862a82aae2e9fc66094bfec38833bae4aae045e481361152746cd3e5f8","source":{"kind":"arxiv","id":"2312.01305","version":1},"attestation_state":"computed","paper":{"title":"ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Erqun Dong, Hanseok Ko, Jeong-gi Kwak, Kwang Moo Yi, Shweta Mahajan, Yuhe Jin","submitted_at":"2023-12-03T06:50:15Z","abstract_excerpt":"Generating novel views of an object from a single image is a challenging task. It requires an understanding of the underlying 3D structure of the object from an image and rendering high-quality, spatially consistent new views. While recent methods for view synthesis based on diffusion have shown great progress, achieving consistency among various view estimates and at the same time abiding by the desired camera pose remains a critical problem yet to be solved. In this work, we demonstrate a strikingly simple method, where we utilize a pre-trained video diffusion model to solve this problem. Ou"},"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":"2312.01305","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-03T06:50:15Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"7b2b7d0c29e4513ec1c8af01649aac1c5470802bc225ea9f0c3a6e68f3073126","abstract_canon_sha256":"ef55896e0045e2aa395d0f0da5664fe8523db02f294dd20b4218b1af4795a515"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:33.028382Z","signature_b64":"d5fiqH6YQO9I/N1W0n8KP1ZpVWQT8MPsivmgHUcMh8BQ6YBW8vEmk5kMokCNyB2nyM+GAEt4yQaoNHMAAhARCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c838d0862a82aae2e9fc66094bfec38833bae4aae045e481361152746cd3e5f8","last_reissued_at":"2026-07-05T07:19:33.027901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:33.027901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Erqun Dong, Hanseok Ko, Jeong-gi Kwak, Kwang Moo Yi, Shweta Mahajan, Yuhe Jin","submitted_at":"2023-12-03T06:50:15Z","abstract_excerpt":"Generating novel views of an object from a single image is a challenging task. It requires an understanding of the underlying 3D structure of the object from an image and rendering high-quality, spatially consistent new views. While recent methods for view synthesis based on diffusion have shown great progress, achieving consistency among various view estimates and at the same time abiding by the desired camera pose remains a critical problem yet to be solved. In this work, we demonstrate a strikingly simple method, where we utilize a pre-trained video diffusion model to solve this problem. Ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01305","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/2312.01305/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":"2312.01305","created_at":"2026-07-05T07:19:33.027952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.01305v1","created_at":"2026-07-05T07:19:33.027952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01305","created_at":"2026-07-05T07:19:33.027952+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZA4NBBRKQKVO","created_at":"2026-07-05T07:19:33.027952+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZA4NBBRKQKVOF2P4","created_at":"2026-07-05T07:19:33.027952+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZA4NBBRK","created_at":"2026-07-05T07:19:33.027952+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24799","citing_title":"OrbitForge: Text-to-3D Scene Generation via Reconstruction-Anchored Video Synthesis","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18052","citing_title":"Efficient 3D Content Reconstruction and Generation","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2405.10314","citing_title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZA4NBBRKQKVOF2P4MYEUX7WDRA","json":"https://pith.science/pith/ZA4NBBRKQKVOF2P4MYEUX7WDRA.json","graph_json":"https://pith.science/api/pith-number/ZA4NBBRKQKVOF2P4MYEUX7WDRA/graph.json","events_json":"https://pith.science/api/pith-number/ZA4NBBRKQKVOF2P4MYEUX7WDRA/events.json","paper":"https://pith.science/paper/ZA4NBBRK"},"agent_actions":{"view_html":"https://pith.science/pith/ZA4NBBRKQKVOF2P4MYEUX7WDRA","download_json":"https://pith.science/pith/ZA4NBBRKQKVOF2P4MYEUX7WDRA.json","view_paper":"https://pith.science/paper/ZA4NBBRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.01305&json=true","fetch_graph":"https://pith.science/api/pith-number/ZA4NBBRKQKVOF2P4MYEUX7WDRA/graph.json","fetch_events":"https://pith.science/api/pith-number/ZA4NBBRKQKVOF2P4MYEUX7WDRA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZA4NBBRKQKVOF2P4MYEUX7WDRA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZA4NBBRKQKVOF2P4MYEUX7WDRA/action/storage_attestation","attest_author":"https://pith.science/pith/ZA4NBBRKQKVOF2P4MYEUX7WDRA/action/author_attestation","sign_citation":"https://pith.science/pith/ZA4NBBRKQKVOF2P4MYEUX7WDRA/action/citation_signature","submit_replication":"https://pith.science/pith/ZA4NBBRKQKVOF2P4MYEUX7WDRA/action/replication_record"}},"created_at":"2026-07-05T07:19:33.027952+00:00","updated_at":"2026-07-05T07:19:33.027952+00:00"}