{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EZ73VFLNB6IIDMZM6KIA4AT22Z","short_pith_number":"pith:EZ73VFLN","schema_version":"1.0","canonical_sha256":"267fba956d0f9081b32cf2900e027ad67e59318859ea4cac463133197f8e568a","source":{"kind":"arxiv","id":"2405.03894","version":2},"attestation_state":"computed","paper":{"title":"MVDiff: Scalable and Flexible Multi-View Diffusion for 3D Object Reconstruction from Single-View","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Emmanuelle Bourigault, Pauline Bourigault","submitted_at":"2024-05-06T22:55:53Z","abstract_excerpt":"Generating consistent multiple views for 3D reconstruction tasks is still a challenge to existing image-to-3D diffusion models. Generally, incorporating 3D representations into diffusion model decrease the model's speed as well as generalizability and quality. This paper proposes a general framework to generate consistent multi-view images from single image or leveraging scene representation transformer and view-conditioned diffusion model. In the model, we introduce epipolar geometry constraints and multi-view attention to enforce 3D consistency. From as few as one image input, our model is a"},"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":"2405.03894","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-06T22:55:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9f541cca9b6d3b857a76e6f91eacbb5c95675db75855745170b0d2227190273d","abstract_canon_sha256":"6c918eaeb3717392dce31691102b42d78a5b4d546372ec56f05da9b58265c9c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:15.058088Z","signature_b64":"2YlVwnU+eQY6y94lh8WyxVRjfcqNaRREoDneT4cg/IPUQpez3V80pEi9uZ8nqEdpeuVqoS6NJIzcSABJT/I9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"267fba956d0f9081b32cf2900e027ad67e59318859ea4cac463133197f8e568a","last_reissued_at":"2026-07-05T08:31:15.057619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:15.057619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVDiff: Scalable and Flexible Multi-View Diffusion for 3D Object Reconstruction from Single-View","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Emmanuelle Bourigault, Pauline Bourigault","submitted_at":"2024-05-06T22:55:53Z","abstract_excerpt":"Generating consistent multiple views for 3D reconstruction tasks is still a challenge to existing image-to-3D diffusion models. Generally, incorporating 3D representations into diffusion model decrease the model's speed as well as generalizability and quality. This paper proposes a general framework to generate consistent multi-view images from single image or leveraging scene representation transformer and view-conditioned diffusion model. In the model, we introduce epipolar geometry constraints and multi-view attention to enforce 3D consistency. From as few as one image input, our model is a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03894","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/2405.03894/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":"2405.03894","created_at":"2026-07-05T08:31:15.057676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.03894v2","created_at":"2026-07-05T08:31:15.057676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03894","created_at":"2026-07-05T08:31:15.057676+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZ73VFLNB6II","created_at":"2026-07-05T08:31:15.057676+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZ73VFLNB6IIDMZM","created_at":"2026-07-05T08:31:15.057676+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZ73VFLN","created_at":"2026-07-05T08:31:15.057676+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.18509","citing_title":"Eval3D: Interpretable and Fine-grained Evaluation for 3D Generation","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EZ73VFLNB6IIDMZM6KIA4AT22Z","json":"https://pith.science/pith/EZ73VFLNB6IIDMZM6KIA4AT22Z.json","graph_json":"https://pith.science/api/pith-number/EZ73VFLNB6IIDMZM6KIA4AT22Z/graph.json","events_json":"https://pith.science/api/pith-number/EZ73VFLNB6IIDMZM6KIA4AT22Z/events.json","paper":"https://pith.science/paper/EZ73VFLN"},"agent_actions":{"view_html":"https://pith.science/pith/EZ73VFLNB6IIDMZM6KIA4AT22Z","download_json":"https://pith.science/pith/EZ73VFLNB6IIDMZM6KIA4AT22Z.json","view_paper":"https://pith.science/paper/EZ73VFLN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.03894&json=true","fetch_graph":"https://pith.science/api/pith-number/EZ73VFLNB6IIDMZM6KIA4AT22Z/graph.json","fetch_events":"https://pith.science/api/pith-number/EZ73VFLNB6IIDMZM6KIA4AT22Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZ73VFLNB6IIDMZM6KIA4AT22Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZ73VFLNB6IIDMZM6KIA4AT22Z/action/storage_attestation","attest_author":"https://pith.science/pith/EZ73VFLNB6IIDMZM6KIA4AT22Z/action/author_attestation","sign_citation":"https://pith.science/pith/EZ73VFLNB6IIDMZM6KIA4AT22Z/action/citation_signature","submit_replication":"https://pith.science/pith/EZ73VFLNB6IIDMZM6KIA4AT22Z/action/replication_record"}},"created_at":"2026-07-05T08:31:15.057676+00:00","updated_at":"2026-07-05T08:31:15.057676+00:00"}