{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LZJ66MXMUQZO7QQ4MO7NRCDCA3","short_pith_number":"pith:LZJ66MXM","schema_version":"1.0","canonical_sha256":"5e53ef32eca432efc21c63bed8886206cb00ce087918d69258f097c4bc8b4f95","source":{"kind":"arxiv","id":"2408.10605","version":5},"attestation_state":"computed","paper":{"title":"MUSES: 3D-Controllable Image Generation via Multi-Modal Agent Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kunchang Li, Shaobin Zhuang, Yali Wang, Yanbo Ding, Yu Qiao, Zhengrong Yue","submitted_at":"2024-08-20T07:37:23Z","abstract_excerpt":"Despite recent advancements in text-to-image generation, most existing methods struggle to create images with multiple objects and complex spatial relationships in the 3D world. To tackle this limitation, we introduce a generic AI system, namely MUSES, for 3D-controllable image generation from user queries. Specifically, our MUSES addresses this challenging task by developing a progressive workflow with three key components, including (1) Layout Manager for 2D-to-3D layout lifting, (2) Model Engineer for 3D object acquisition and calibration, (3) Image Artist for 3D-to-2D image rendering. By 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":"2408.10605","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-20T07:37:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7dcf529253a54e51a3bae1b19b9c8c7869a799160eb42e39c3c5e62dcb24ef22","abstract_canon_sha256":"163fa66505115fd953bea048e2ed1bda789bc4ad180644f37fc8fb00b01fb1bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:09.105964Z","signature_b64":"HxjbA6hhyUS+oNUil2PlLnzsYi9lBol1NhE/S3D8YHX2UBIz3PJFgMPCxugS6+elzmut/4rXfGAbi9UZt1P5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e53ef32eca432efc21c63bed8886206cb00ce087918d69258f097c4bc8b4f95","last_reissued_at":"2026-07-05T09:49:09.105504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:09.105504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MUSES: 3D-Controllable Image Generation via Multi-Modal Agent Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kunchang Li, Shaobin Zhuang, Yali Wang, Yanbo Ding, Yu Qiao, Zhengrong Yue","submitted_at":"2024-08-20T07:37:23Z","abstract_excerpt":"Despite recent advancements in text-to-image generation, most existing methods struggle to create images with multiple objects and complex spatial relationships in the 3D world. To tackle this limitation, we introduce a generic AI system, namely MUSES, for 3D-controllable image generation from user queries. Specifically, our MUSES addresses this challenging task by developing a progressive workflow with three key components, including (1) Layout Manager for 2D-to-3D layout lifting, (2) Model Engineer for 3D object acquisition and calibration, (3) Image Artist for 3D-to-2D image rendering. By m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10605","kind":"arxiv","version":5},"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/2408.10605/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":"2408.10605","created_at":"2026-07-05T09:49:09.105560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10605v5","created_at":"2026-07-05T09:49:09.105560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10605","created_at":"2026-07-05T09:49:09.105560+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZJ66MXMUQZO","created_at":"2026-07-05T09:49:09.105560+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZJ66MXMUQZO7QQ4","created_at":"2026-07-05T09:49:09.105560+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZJ66MXM","created_at":"2026-07-05T09:49:09.105560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18900","citing_title":"Audit & Repair: An Agentic Framework for Consistent Story Visualization in Text-to-Image Diffusion Models","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZJ66MXMUQZO7QQ4MO7NRCDCA3","json":"https://pith.science/pith/LZJ66MXMUQZO7QQ4MO7NRCDCA3.json","graph_json":"https://pith.science/api/pith-number/LZJ66MXMUQZO7QQ4MO7NRCDCA3/graph.json","events_json":"https://pith.science/api/pith-number/LZJ66MXMUQZO7QQ4MO7NRCDCA3/events.json","paper":"https://pith.science/paper/LZJ66MXM"},"agent_actions":{"view_html":"https://pith.science/pith/LZJ66MXMUQZO7QQ4MO7NRCDCA3","download_json":"https://pith.science/pith/LZJ66MXMUQZO7QQ4MO7NRCDCA3.json","view_paper":"https://pith.science/paper/LZJ66MXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10605&json=true","fetch_graph":"https://pith.science/api/pith-number/LZJ66MXMUQZO7QQ4MO7NRCDCA3/graph.json","fetch_events":"https://pith.science/api/pith-number/LZJ66MXMUQZO7QQ4MO7NRCDCA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZJ66MXMUQZO7QQ4MO7NRCDCA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZJ66MXMUQZO7QQ4MO7NRCDCA3/action/storage_attestation","attest_author":"https://pith.science/pith/LZJ66MXMUQZO7QQ4MO7NRCDCA3/action/author_attestation","sign_citation":"https://pith.science/pith/LZJ66MXMUQZO7QQ4MO7NRCDCA3/action/citation_signature","submit_replication":"https://pith.science/pith/LZJ66MXMUQZO7QQ4MO7NRCDCA3/action/replication_record"}},"created_at":"2026-07-05T09:49:09.105560+00:00","updated_at":"2026-07-05T09:49:09.105560+00:00"}