{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LFZJZPNSNFJ5E4O4TIRYTDTBL7","short_pith_number":"pith:LFZJZPNS","schema_version":"1.0","canonical_sha256":"59729cbdb26953d271dc9a23898e615fd559f34d4933eca69823127abf19c9c7","source":{"kind":"arxiv","id":"2403.12010","version":1},"attestation_state":"computed","paper":{"title":"VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Liefeng Bo, Lingteng Qiu, Qixing Huang, Qi Zuo, Rui Peng, Siyu Zhu, Weihao Yuan, Xiaodong Gu, Yuan Dong, Zhengyi Zhao, Zilong Dong","submitted_at":"2024-03-18T17:48:15Z","abstract_excerpt":"Generating multi-view images based on text or single-image prompts is a critical capability for the creation of 3D content. Two fundamental questions on this topic are what data we use for training and how to ensure multi-view consistency. This paper introduces a novel framework that makes fundamental contributions to both questions. Unlike leveraging images from 2D diffusion models for training, we propose a dense consistent multi-view generation model that is fine-tuned from off-the-shelf video generative models. Images from video generative models are more suitable for multi-view generation"},"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":"2403.12010","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:48:15Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"98ccad2af5ecb1c4112b4d18ba23b74abe5718b81f8cea913e6254d977902e98","abstract_canon_sha256":"0c38dffe1988f3d713b9cf1c9078a9f977226e96f8283250d0e069e1c0c8fe8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:35.009179Z","signature_b64":"vQ48yu0UVhIT39lKrndzpEDf4YQFtG4Dii2A/Wom8GJVIP+dd7w2VRJEUX/8vsLEi1aXTpNDDKDG32YsYaIeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59729cbdb26953d271dc9a23898e615fd559f34d4933eca69823127abf19c9c7","last_reissued_at":"2026-07-05T07:57:35.008625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:35.008625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Liefeng Bo, Lingteng Qiu, Qixing Huang, Qi Zuo, Rui Peng, Siyu Zhu, Weihao Yuan, Xiaodong Gu, Yuan Dong, Zhengyi Zhao, Zilong Dong","submitted_at":"2024-03-18T17:48:15Z","abstract_excerpt":"Generating multi-view images based on text or single-image prompts is a critical capability for the creation of 3D content. Two fundamental questions on this topic are what data we use for training and how to ensure multi-view consistency. This paper introduces a novel framework that makes fundamental contributions to both questions. Unlike leveraging images from 2D diffusion models for training, we propose a dense consistent multi-view generation model that is fine-tuned from off-the-shelf video generative models. Images from video generative models are more suitable for multi-view generation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12010","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/2403.12010/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":"2403.12010","created_at":"2026-07-05T07:57:35.008686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12010v1","created_at":"2026-07-05T07:57:35.008686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12010","created_at":"2026-07-05T07:57:35.008686+00:00"},{"alias_kind":"pith_short_12","alias_value":"LFZJZPNSNFJ5","created_at":"2026-07-05T07:57:35.008686+00:00"},{"alias_kind":"pith_short_16","alias_value":"LFZJZPNSNFJ5E4O4","created_at":"2026-07-05T07:57:35.008686+00:00"},{"alias_kind":"pith_short_8","alias_value":"LFZJZPNS","created_at":"2026-07-05T07:57:35.008686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"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":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21121","citing_title":"ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2406.02509","citing_title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2404.07191","citing_title":"InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LFZJZPNSNFJ5E4O4TIRYTDTBL7","json":"https://pith.science/pith/LFZJZPNSNFJ5E4O4TIRYTDTBL7.json","graph_json":"https://pith.science/api/pith-number/LFZJZPNSNFJ5E4O4TIRYTDTBL7/graph.json","events_json":"https://pith.science/api/pith-number/LFZJZPNSNFJ5E4O4TIRYTDTBL7/events.json","paper":"https://pith.science/paper/LFZJZPNS"},"agent_actions":{"view_html":"https://pith.science/pith/LFZJZPNSNFJ5E4O4TIRYTDTBL7","download_json":"https://pith.science/pith/LFZJZPNSNFJ5E4O4TIRYTDTBL7.json","view_paper":"https://pith.science/paper/LFZJZPNS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12010&json=true","fetch_graph":"https://pith.science/api/pith-number/LFZJZPNSNFJ5E4O4TIRYTDTBL7/graph.json","fetch_events":"https://pith.science/api/pith-number/LFZJZPNSNFJ5E4O4TIRYTDTBL7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LFZJZPNSNFJ5E4O4TIRYTDTBL7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LFZJZPNSNFJ5E4O4TIRYTDTBL7/action/storage_attestation","attest_author":"https://pith.science/pith/LFZJZPNSNFJ5E4O4TIRYTDTBL7/action/author_attestation","sign_citation":"https://pith.science/pith/LFZJZPNSNFJ5E4O4TIRYTDTBL7/action/citation_signature","submit_replication":"https://pith.science/pith/LFZJZPNSNFJ5E4O4TIRYTDTBL7/action/replication_record"}},"created_at":"2026-07-05T07:57:35.008686+00:00","updated_at":"2026-07-05T07:57:35.008686+00:00"}