{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KXLZD3CT32DQIJNNKD3SA6ZTGZ","short_pith_number":"pith:KXLZD3CT","schema_version":"1.0","canonical_sha256":"55d791ec53de870425ad50f7207b33367e1468f20e3e9aebc5a778ef54984612","source":{"kind":"arxiv","id":"2406.00093","version":2},"attestation_state":"computed","paper":{"title":"Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiaqi Wang, Pan Zhang, Tong Wu, Xiaoyi Dong, Yuanjun Xiong, Yuhang Zang, Zeyi Sun","submitted_at":"2024-05-31T17:59:56Z","abstract_excerpt":"Recent years have witnessed remarkable progress in multi-view diffusion models for 3D content creation. However, there remains a significant gap in image quality and prompt-following ability compared to 2D diffusion models. A critical bottleneck is the scarcity of high-quality 3D objects with detailed captions. To address this challenge, we propose Bootstrap3D, a novel framework that automatically generates an arbitrary quantity of multi-view images to assist in training multi-view diffusion models. Specifically, we introduce a data generation pipeline that employs (1) 2D and video diffusion m"},"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":"2406.00093","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T17:59:56Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG","cs.MM"],"title_canon_sha256":"dfbca69c1da9efc4f898e55c4245b9f952d97e7567c2cf2f18aa3b99f2e0c1f6","abstract_canon_sha256":"5be928bc3b2e0c8710643356a0f9d9d1999270078626d51c5c997ec9a124ba18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:10.876812Z","signature_b64":"rq3ZH6eS4xxfLsVbymHwYhoY9SXhtwefe+8H5XpwYmb+HmakAWpCStPHcYH+7dBQvWEXUtUFb8YR6yKp9CqHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55d791ec53de870425ad50f7207b33367e1468f20e3e9aebc5a778ef54984612","last_reissued_at":"2026-07-05T09:15:10.876327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:10.876327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiaqi Wang, Pan Zhang, Tong Wu, Xiaoyi Dong, Yuanjun Xiong, Yuhang Zang, Zeyi Sun","submitted_at":"2024-05-31T17:59:56Z","abstract_excerpt":"Recent years have witnessed remarkable progress in multi-view diffusion models for 3D content creation. However, there remains a significant gap in image quality and prompt-following ability compared to 2D diffusion models. A critical bottleneck is the scarcity of high-quality 3D objects with detailed captions. To address this challenge, we propose Bootstrap3D, a novel framework that automatically generates an arbitrary quantity of multi-view images to assist in training multi-view diffusion models. Specifically, we introduce a data generation pipeline that employs (1) 2D and video diffusion m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00093","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/2406.00093/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":"2406.00093","created_at":"2026-07-05T09:15:10.876388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00093v2","created_at":"2026-07-05T09:15:10.876388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00093","created_at":"2026-07-05T09:15:10.876388+00:00"},{"alias_kind":"pith_short_12","alias_value":"KXLZD3CT32DQ","created_at":"2026-07-05T09:15:10.876388+00:00"},{"alias_kind":"pith_short_16","alias_value":"KXLZD3CT32DQIJNN","created_at":"2026-07-05T09:15:10.876388+00:00"},{"alias_kind":"pith_short_8","alias_value":"KXLZD3CT","created_at":"2026-07-05T09:15:10.876388+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03150","citing_title":"IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KXLZD3CT32DQIJNNKD3SA6ZTGZ","json":"https://pith.science/pith/KXLZD3CT32DQIJNNKD3SA6ZTGZ.json","graph_json":"https://pith.science/api/pith-number/KXLZD3CT32DQIJNNKD3SA6ZTGZ/graph.json","events_json":"https://pith.science/api/pith-number/KXLZD3CT32DQIJNNKD3SA6ZTGZ/events.json","paper":"https://pith.science/paper/KXLZD3CT"},"agent_actions":{"view_html":"https://pith.science/pith/KXLZD3CT32DQIJNNKD3SA6ZTGZ","download_json":"https://pith.science/pith/KXLZD3CT32DQIJNNKD3SA6ZTGZ.json","view_paper":"https://pith.science/paper/KXLZD3CT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00093&json=true","fetch_graph":"https://pith.science/api/pith-number/KXLZD3CT32DQIJNNKD3SA6ZTGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/KXLZD3CT32DQIJNNKD3SA6ZTGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KXLZD3CT32DQIJNNKD3SA6ZTGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KXLZD3CT32DQIJNNKD3SA6ZTGZ/action/storage_attestation","attest_author":"https://pith.science/pith/KXLZD3CT32DQIJNNKD3SA6ZTGZ/action/author_attestation","sign_citation":"https://pith.science/pith/KXLZD3CT32DQIJNNKD3SA6ZTGZ/action/citation_signature","submit_replication":"https://pith.science/pith/KXLZD3CT32DQIJNNKD3SA6ZTGZ/action/replication_record"}},"created_at":"2026-07-05T09:15:10.876388+00:00","updated_at":"2026-07-05T09:15:10.876388+00:00"}