{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DEE7LWQQ6OR7E7ZYZFPXKSSBR2","short_pith_number":"pith:DEE7LWQQ","schema_version":"1.0","canonical_sha256":"1909f5da10f3a3f27f38c95f754a418e920f493850c36d5bfb06a9a87588dc6a","source":{"kind":"arxiv","id":"2307.01097","version":7},"attestation_state":"computed","paper":{"title":"MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fuyang Zhang, Jiacheng Chen, Peng Wang, Shitao Tang, Yasutaka Furukawa","submitted_at":"2023-07-03T15:19:17Z","abstract_excerpt":"This paper introduces MVDiffusion, a simple yet effective method for generating consistent multi-view images from text prompts given pixel-to-pixel correspondences (e.g., perspective crops from a panorama or multi-view images given depth maps and poses). Unlike prior methods that rely on iterative image warping and inpainting, MVDiffusion simultaneously generates all images with a global awareness, effectively addressing the prevalent error accumulation issue. At its core, MVDiffusion processes perspective images in parallel with a pre-trained text-to-image diffusion model, while integrating n"},"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":"2307.01097","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-03T15:19:17Z","cross_cats_sorted":[],"title_canon_sha256":"76bc27a31dcedcef0b89ca0d90e388ca015737d226bf699b3c0750017ee6fd9d","abstract_canon_sha256":"4e15abcc88c94a0629174bd3600e40e7ea3b87767ebff1a22c71275b3ba7839b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:47.964858Z","signature_b64":"WrC/ZYeayt1iX5SkU1m0n0Ol14JjzRTqfFWogyQTNhWL6Yu1aiUT8ITB2NqkH162+wt2BLbkA1kxB02w+Ky/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1909f5da10f3a3f27f38c95f754a418e920f493850c36d5bfb06a9a87588dc6a","last_reissued_at":"2026-07-05T07:27:47.964327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:47.964327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fuyang Zhang, Jiacheng Chen, Peng Wang, Shitao Tang, Yasutaka Furukawa","submitted_at":"2023-07-03T15:19:17Z","abstract_excerpt":"This paper introduces MVDiffusion, a simple yet effective method for generating consistent multi-view images from text prompts given pixel-to-pixel correspondences (e.g., perspective crops from a panorama or multi-view images given depth maps and poses). Unlike prior methods that rely on iterative image warping and inpainting, MVDiffusion simultaneously generates all images with a global awareness, effectively addressing the prevalent error accumulation issue. At its core, MVDiffusion processes perspective images in parallel with a pre-trained text-to-image diffusion model, while integrating n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01097","kind":"arxiv","version":7},"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/2307.01097/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":"2307.01097","created_at":"2026-07-05T07:27:47.964386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.01097v7","created_at":"2026-07-05T07:27:47.964386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01097","created_at":"2026-07-05T07:27:47.964386+00:00"},{"alias_kind":"pith_short_12","alias_value":"DEE7LWQQ6OR7","created_at":"2026-07-05T07:27:47.964386+00:00"},{"alias_kind":"pith_short_16","alias_value":"DEE7LWQQ6OR7E7ZY","created_at":"2026-07-05T07:27:47.964386+00:00"},{"alias_kind":"pith_short_8","alias_value":"DEE7LWQQ","created_at":"2026-07-05T07:27:47.964386+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01803","citing_title":"PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11805","citing_title":"TextHOI-3D: Text-to-3D Hand-Object Interaction via Discrete Multi-View Generation and Joint Mesh Optimization","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07117","citing_title":"Native3D: End-to-End 3D Scene Generation via Unified Mesh-Texture Modeling and Semantic Alignment","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00522","citing_title":"Restore3D: Breathing Life into Broken Objects with Shape and Texture Restoration","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2401.16764","citing_title":"BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion","ref_index":33,"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":79,"is_internal_anchor":false},{"citing_arxiv_id":"2309.03453","citing_title":"SyncDreamer: Generating Multiview-consistent Images from a Single-view Image","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2308.16512","citing_title":"MVDream: Multi-view Diffusion for 3D Generation","ref_index":155,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19954","citing_title":"Camera Control for Text-to-Image Generation via Learning Viewpoint Tokens","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DEE7LWQQ6OR7E7ZYZFPXKSSBR2","json":"https://pith.science/pith/DEE7LWQQ6OR7E7ZYZFPXKSSBR2.json","graph_json":"https://pith.science/api/pith-number/DEE7LWQQ6OR7E7ZYZFPXKSSBR2/graph.json","events_json":"https://pith.science/api/pith-number/DEE7LWQQ6OR7E7ZYZFPXKSSBR2/events.json","paper":"https://pith.science/paper/DEE7LWQQ"},"agent_actions":{"view_html":"https://pith.science/pith/DEE7LWQQ6OR7E7ZYZFPXKSSBR2","download_json":"https://pith.science/pith/DEE7LWQQ6OR7E7ZYZFPXKSSBR2.json","view_paper":"https://pith.science/paper/DEE7LWQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.01097&json=true","fetch_graph":"https://pith.science/api/pith-number/DEE7LWQQ6OR7E7ZYZFPXKSSBR2/graph.json","fetch_events":"https://pith.science/api/pith-number/DEE7LWQQ6OR7E7ZYZFPXKSSBR2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DEE7LWQQ6OR7E7ZYZFPXKSSBR2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DEE7LWQQ6OR7E7ZYZFPXKSSBR2/action/storage_attestation","attest_author":"https://pith.science/pith/DEE7LWQQ6OR7E7ZYZFPXKSSBR2/action/author_attestation","sign_citation":"https://pith.science/pith/DEE7LWQQ6OR7E7ZYZFPXKSSBR2/action/citation_signature","submit_replication":"https://pith.science/pith/DEE7LWQQ6OR7E7ZYZFPXKSSBR2/action/replication_record"}},"created_at":"2026-07-05T07:27:47.964386+00:00","updated_at":"2026-07-05T07:27:47.964386+00:00"}