{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MA3736K3H7V2MIXFMABCJJ5NCV","short_pith_number":"pith:MA3736K3","schema_version":"1.0","canonical_sha256":"6037fdf95b3feba622e5600224a7ad155228a4d3756eff0db8f3bfce9ce66ae8","source":{"kind":"arxiv","id":"2412.03632","version":1},"attestation_state":"computed","paper":{"title":"MV-Adapter: Multi-view Consistent Image Generation Made Easy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Wang, Lizhuang Ma, Lu Sheng, Ran Yi, Yan-Pei Cao, Yuan-Chen Guo, Zehuan Huang","submitted_at":"2024-12-04T18:48:20Z","abstract_excerpt":"Existing multi-view image generation methods often make invasive modifications to pre-trained text-to-image (T2I) models and require full fine-tuning, leading to (1) high computational costs, especially with large base models and high-resolution images, and (2) degradation in image quality due to optimization difficulties and scarce high-quality 3D data. In this paper, we propose the first adapter-based solution for multi-view image generation, and introduce MV-Adapter, a versatile plug-and-play adapter that enhances T2I models and their derivatives without altering the original network struct"},"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":"2412.03632","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T18:48:20Z","cross_cats_sorted":[],"title_canon_sha256":"c33638ea82d475fe9cf8007da0a678a57c94d5fd0e58d8cab4dc4f0212f6ac61","abstract_canon_sha256":"06bd5194fad0cd09feb185c261de302f1a9288af668776e65885936ecd4ea361"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:39.298706Z","signature_b64":"VnmkqoF5HMZtDi+TPhai/KqyCCHEYvFDx0mi/mObYEO71G/NaJaTTHCxU6IyRT5qxw0IuvyB9FHhVdLus9ExBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6037fdf95b3feba622e5600224a7ad155228a4d3756eff0db8f3bfce9ce66ae8","last_reissued_at":"2026-07-05T09:44:39.298289Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:39.298289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MV-Adapter: Multi-view Consistent Image Generation Made Easy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Wang, Lizhuang Ma, Lu Sheng, Ran Yi, Yan-Pei Cao, Yuan-Chen Guo, Zehuan Huang","submitted_at":"2024-12-04T18:48:20Z","abstract_excerpt":"Existing multi-view image generation methods often make invasive modifications to pre-trained text-to-image (T2I) models and require full fine-tuning, leading to (1) high computational costs, especially with large base models and high-resolution images, and (2) degradation in image quality due to optimization difficulties and scarce high-quality 3D data. In this paper, we propose the first adapter-based solution for multi-view image generation, and introduce MV-Adapter, a versatile plug-and-play adapter that enhances T2I models and their derivatives without altering the original network struct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03632","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/2412.03632/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":"2412.03632","created_at":"2026-07-05T09:44:39.298352+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03632v1","created_at":"2026-07-05T09:44:39.298352+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03632","created_at":"2026-07-05T09:44:39.298352+00:00"},{"alias_kind":"pith_short_12","alias_value":"MA3736K3H7V2","created_at":"2026-07-05T09:44:39.298352+00:00"},{"alias_kind":"pith_short_16","alias_value":"MA3736K3H7V2MIXF","created_at":"2026-07-05T09:44:39.298352+00:00"},{"alias_kind":"pith_short_8","alias_value":"MA3736K3","created_at":"2026-07-05T09:44:39.298352+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01803","citing_title":"PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13655","citing_title":"Flex4DHuman: Flexible Multi-view Video Diffusion for 4D Human Reconstruction","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00522","citing_title":"Restore3D: Breathing Life into Broken Objects with Shape and Texture Restoration","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2501.12202","citing_title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10239","citing_title":"AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2505.22394","citing_title":"PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2509.07435","citing_title":"DreamLifting: A Plug-in Module Lifting MV Diffusion Models for 3D Asset Generation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2603.16869","citing_title":"SegviGen: Repurposing 3D Generative Model for Part Segmentation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10239","citing_title":"AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12309","citing_title":"Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10789","citing_title":"ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MA3736K3H7V2MIXFMABCJJ5NCV","json":"https://pith.science/pith/MA3736K3H7V2MIXFMABCJJ5NCV.json","graph_json":"https://pith.science/api/pith-number/MA3736K3H7V2MIXFMABCJJ5NCV/graph.json","events_json":"https://pith.science/api/pith-number/MA3736K3H7V2MIXFMABCJJ5NCV/events.json","paper":"https://pith.science/paper/MA3736K3"},"agent_actions":{"view_html":"https://pith.science/pith/MA3736K3H7V2MIXFMABCJJ5NCV","download_json":"https://pith.science/pith/MA3736K3H7V2MIXFMABCJJ5NCV.json","view_paper":"https://pith.science/paper/MA3736K3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03632&json=true","fetch_graph":"https://pith.science/api/pith-number/MA3736K3H7V2MIXFMABCJJ5NCV/graph.json","fetch_events":"https://pith.science/api/pith-number/MA3736K3H7V2MIXFMABCJJ5NCV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MA3736K3H7V2MIXFMABCJJ5NCV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MA3736K3H7V2MIXFMABCJJ5NCV/action/storage_attestation","attest_author":"https://pith.science/pith/MA3736K3H7V2MIXFMABCJJ5NCV/action/author_attestation","sign_citation":"https://pith.science/pith/MA3736K3H7V2MIXFMABCJJ5NCV/action/citation_signature","submit_replication":"https://pith.science/pith/MA3736K3H7V2MIXFMABCJJ5NCV/action/replication_record"}},"created_at":"2026-07-05T09:44:39.298352+00:00","updated_at":"2026-07-05T09:44:39.298352+00:00"}