{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5AUDH4FZPWF5ZZ6EJGPCPYRBLA","short_pith_number":"pith:5AUDH4FZ","schema_version":"1.0","canonical_sha256":"e82833f0b97d8bdce7c4499e27e22158067601408b083655445d689df3ca0f25","source":{"kind":"arxiv","id":"2411.16157","version":3},"attestation_state":"computed","paper":{"title":"MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaohui Yu, Chenjie Cao, Fan Wang, Shang Liu, Xiangyang Xue, Yanwei Fu","submitted_at":"2024-11-25T07:34:23Z","abstract_excerpt":"We introduce MVGenMaster, a multi-view diffusion model enhanced with 3D priors to address versatile Novel View Synthesis (NVS) tasks. MVGenMaster leverages 3D priors that are warped using metric depth and camera poses, significantly enhancing both generalization and 3D consistency in NVS. Our model features a simple yet effective pipeline that can generate up to 100 novel views conditioned on variable reference views and camera poses with a single forward process. Additionally, we have developed a comprehensive large-scale multi-view image dataset called MvD-1M, comprising up to 1.6 million sc"},"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":"2411.16157","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T07:34:23Z","cross_cats_sorted":[],"title_canon_sha256":"8f8ee07420cd5aae07fd1717778637e3bc8022d562d64b5809460abc34715dbc","abstract_canon_sha256":"5a3a1f33fb7e6d14b8b202e23316930078ade5804115a75ca39fa283d1e8f0a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:14.419456Z","signature_b64":"4ieH0qFXO+v2bC8mtem/OCAsHN2a8KesOhcxr5SR8VXCW5HbZ67Af56Vg+dSBI4fbhj8GXA5AiLcI6x9QenICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e82833f0b97d8bdce7c4499e27e22158067601408b083655445d689df3ca0f25","last_reissued_at":"2026-07-05T10:25:14.418970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:14.418970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaohui Yu, Chenjie Cao, Fan Wang, Shang Liu, Xiangyang Xue, Yanwei Fu","submitted_at":"2024-11-25T07:34:23Z","abstract_excerpt":"We introduce MVGenMaster, a multi-view diffusion model enhanced with 3D priors to address versatile Novel View Synthesis (NVS) tasks. MVGenMaster leverages 3D priors that are warped using metric depth and camera poses, significantly enhancing both generalization and 3D consistency in NVS. Our model features a simple yet effective pipeline that can generate up to 100 novel views conditioned on variable reference views and camera poses with a single forward process. Additionally, we have developed a comprehensive large-scale multi-view image dataset called MvD-1M, comprising up to 1.6 million sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16157","kind":"arxiv","version":3},"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/2411.16157/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":"2411.16157","created_at":"2026-07-05T10:25:14.419023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16157v3","created_at":"2026-07-05T10:25:14.419023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16157","created_at":"2026-07-05T10:25:14.419023+00:00"},{"alias_kind":"pith_short_12","alias_value":"5AUDH4FZPWF5","created_at":"2026-07-05T10:25:14.419023+00:00"},{"alias_kind":"pith_short_16","alias_value":"5AUDH4FZPWF5ZZ6E","created_at":"2026-07-05T10:25:14.419023+00:00"},{"alias_kind":"pith_short_8","alias_value":"5AUDH4FZ","created_at":"2026-07-05T10:25:14.419023+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31258","citing_title":"WarpHammer: Densifying Scene Warps with 3D Object Priors for Extreme View Synthesis","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5AUDH4FZPWF5ZZ6EJGPCPYRBLA","json":"https://pith.science/pith/5AUDH4FZPWF5ZZ6EJGPCPYRBLA.json","graph_json":"https://pith.science/api/pith-number/5AUDH4FZPWF5ZZ6EJGPCPYRBLA/graph.json","events_json":"https://pith.science/api/pith-number/5AUDH4FZPWF5ZZ6EJGPCPYRBLA/events.json","paper":"https://pith.science/paper/5AUDH4FZ"},"agent_actions":{"view_html":"https://pith.science/pith/5AUDH4FZPWF5ZZ6EJGPCPYRBLA","download_json":"https://pith.science/pith/5AUDH4FZPWF5ZZ6EJGPCPYRBLA.json","view_paper":"https://pith.science/paper/5AUDH4FZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16157&json=true","fetch_graph":"https://pith.science/api/pith-number/5AUDH4FZPWF5ZZ6EJGPCPYRBLA/graph.json","fetch_events":"https://pith.science/api/pith-number/5AUDH4FZPWF5ZZ6EJGPCPYRBLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5AUDH4FZPWF5ZZ6EJGPCPYRBLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5AUDH4FZPWF5ZZ6EJGPCPYRBLA/action/storage_attestation","attest_author":"https://pith.science/pith/5AUDH4FZPWF5ZZ6EJGPCPYRBLA/action/author_attestation","sign_citation":"https://pith.science/pith/5AUDH4FZPWF5ZZ6EJGPCPYRBLA/action/citation_signature","submit_replication":"https://pith.science/pith/5AUDH4FZPWF5ZZ6EJGPCPYRBLA/action/replication_record"}},"created_at":"2026-07-05T10:25:14.419023+00:00","updated_at":"2026-07-05T10:25:14.419023+00:00"}