{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XWCSG7TRPDTRZIBEHUWVT5OV5U","short_pith_number":"pith:XWCSG7TR","schema_version":"1.0","canonical_sha256":"bd85237e7178e71ca0243d2d59f5d5ed12f91b6e37ae95f587113d9dc82c1ada","source":{"kind":"arxiv","id":"2403.10983","version":2},"attestation_state":"computed","paper":{"title":"OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bizhu Wu, Guanying Chen, Kaihao Zhang, Tao Wang, Tianyu Yang, Wei Liu, Wenhan Luo, Yong Zhang, Zhe Kong","submitted_at":"2024-03-16T17:30:15Z","abstract_excerpt":"Personalization is an important topic in text-to-image generation, especially the challenging multi-concept personalization. Current multi-concept methods are struggling with identity preservation, occlusion, and the harmony between foreground and background. In this work, we propose OMG, an occlusion-friendly personalized generation framework designed to seamlessly integrate multiple concepts within a single image. We propose a novel two-stage sampling solution. The first stage takes charge of layout generation and visual comprehension information collection for handling occlusions. The secon"},"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":"2403.10983","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-16T17:30:15Z","cross_cats_sorted":[],"title_canon_sha256":"9ec1a8a1c94ffdb316c860fc449b77a562cce88a2e8778ac6d1e6bd1ed9b780c","abstract_canon_sha256":"58809269bbe961047aaa71b08ccbdcb630abe825a3b3f0e38fdc59949ee3ca55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:22.993775Z","signature_b64":"pq7TAdp84KU51Dm8bgGwu9Qmi2YB1+6MfRQtufVgejXRyP+Yfd4KjK4mMkmjoVxZ1O+fjWoByInpRsb/rQdWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd85237e7178e71ca0243d2d59f5d5ed12f91b6e37ae95f587113d9dc82c1ada","last_reissued_at":"2026-07-05T08:46:22.993276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:22.993276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bizhu Wu, Guanying Chen, Kaihao Zhang, Tao Wang, Tianyu Yang, Wei Liu, Wenhan Luo, Yong Zhang, Zhe Kong","submitted_at":"2024-03-16T17:30:15Z","abstract_excerpt":"Personalization is an important topic in text-to-image generation, especially the challenging multi-concept personalization. Current multi-concept methods are struggling with identity preservation, occlusion, and the harmony between foreground and background. In this work, we propose OMG, an occlusion-friendly personalized generation framework designed to seamlessly integrate multiple concepts within a single image. We propose a novel two-stage sampling solution. The first stage takes charge of layout generation and visual comprehension information collection for handling occlusions. The secon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10983","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/2403.10983/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":"2403.10983","created_at":"2026-07-05T08:46:22.993344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10983v2","created_at":"2026-07-05T08:46:22.993344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10983","created_at":"2026-07-05T08:46:22.993344+00:00"},{"alias_kind":"pith_short_12","alias_value":"XWCSG7TRPDTR","created_at":"2026-07-05T08:46:22.993344+00:00"},{"alias_kind":"pith_short_16","alias_value":"XWCSG7TRPDTRZIBE","created_at":"2026-07-05T08:46:22.993344+00:00"},{"alias_kind":"pith_short_8","alias_value":"XWCSG7TR","created_at":"2026-07-05T08:46:22.993344+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13863","citing_title":"PostureObjectstitch: Anomaly Image Generation Considering Assembly Relationships in Industrial Scenarios","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XWCSG7TRPDTRZIBEHUWVT5OV5U","json":"https://pith.science/pith/XWCSG7TRPDTRZIBEHUWVT5OV5U.json","graph_json":"https://pith.science/api/pith-number/XWCSG7TRPDTRZIBEHUWVT5OV5U/graph.json","events_json":"https://pith.science/api/pith-number/XWCSG7TRPDTRZIBEHUWVT5OV5U/events.json","paper":"https://pith.science/paper/XWCSG7TR"},"agent_actions":{"view_html":"https://pith.science/pith/XWCSG7TRPDTRZIBEHUWVT5OV5U","download_json":"https://pith.science/pith/XWCSG7TRPDTRZIBEHUWVT5OV5U.json","view_paper":"https://pith.science/paper/XWCSG7TR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10983&json=true","fetch_graph":"https://pith.science/api/pith-number/XWCSG7TRPDTRZIBEHUWVT5OV5U/graph.json","fetch_events":"https://pith.science/api/pith-number/XWCSG7TRPDTRZIBEHUWVT5OV5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XWCSG7TRPDTRZIBEHUWVT5OV5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XWCSG7TRPDTRZIBEHUWVT5OV5U/action/storage_attestation","attest_author":"https://pith.science/pith/XWCSG7TRPDTRZIBEHUWVT5OV5U/action/author_attestation","sign_citation":"https://pith.science/pith/XWCSG7TRPDTRZIBEHUWVT5OV5U/action/citation_signature","submit_replication":"https://pith.science/pith/XWCSG7TRPDTRZIBEHUWVT5OV5U/action/replication_record"}},"created_at":"2026-07-05T08:46:22.993344+00:00","updated_at":"2026-07-05T08:46:22.993344+00:00"}