{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YRJPDJPEXWJDAHQSQPVT7WKQEA","short_pith_number":"pith:YRJPDJPE","schema_version":"1.0","canonical_sha256":"c452f1a5e4bd92301e1283eb3fd9502030bfbd80c4d0df75280f7d07c0642fe7","source":{"kind":"arxiv","id":"2411.07462","version":3},"attestation_state":"computed","paper":{"title":"MureObjectStitch: Multi-reference Image Composition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zhang, Jiaxuan Chen, Jinlong Peng, Li Niu, Qingdong He","submitted_at":"2024-11-12T00:53:20Z","abstract_excerpt":"Generative image composition aims to regenerate the given foreground object in the background image to produce a realistic composite image. The existing methods are struggling to preserve the foreground details and adjust the foreground pose/viewpoint at the same time. In this work, we propose an effective finetuning strategy for generative image composition model, in which we finetune a pretrained model using one or more images containing the same foreground object. Moreover, we propose a multi-reference strategy, which allows the model to take in multiple reference images of the foreground o"},"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":"2411.07462","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T00:53:20Z","cross_cats_sorted":[],"title_canon_sha256":"42da13827eff5b11b87c8ec91d30761738ac2d278c3620194145494144cd7d2d","abstract_canon_sha256":"50fa406cab2cef9bcdf6a5e548f2685829e8a9bfbb7a88ca15fec400f2cf77e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:19.721487Z","signature_b64":"jm+X3GNkZ73klQIQfLVVqzUT7oJUTWvZYcCtLlbbA+zsukfC/ZsE04i2tHNlNK5M3liS30hWJ3FT29h4PUPUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c452f1a5e4bd92301e1283eb3fd9502030bfbd80c4d0df75280f7d07c0642fe7","last_reissued_at":"2026-07-05T10:44:19.721061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:19.721061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MureObjectStitch: Multi-reference Image Composition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zhang, Jiaxuan Chen, Jinlong Peng, Li Niu, Qingdong He","submitted_at":"2024-11-12T00:53:20Z","abstract_excerpt":"Generative image composition aims to regenerate the given foreground object in the background image to produce a realistic composite image. The existing methods are struggling to preserve the foreground details and adjust the foreground pose/viewpoint at the same time. In this work, we propose an effective finetuning strategy for generative image composition model, in which we finetune a pretrained model using one or more images containing the same foreground object. Moreover, we propose a multi-reference strategy, which allows the model to take in multiple reference images of the foreground o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07462","kind":"arxiv","version":3},"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/2411.07462/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":"2411.07462","created_at":"2026-07-05T10:44:19.721115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07462v3","created_at":"2026-07-05T10:44:19.721115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07462","created_at":"2026-07-05T10:44:19.721115+00:00"},{"alias_kind":"pith_short_12","alias_value":"YRJPDJPEXWJD","created_at":"2026-07-05T10:44:19.721115+00:00"},{"alias_kind":"pith_short_16","alias_value":"YRJPDJPEXWJDAHQS","created_at":"2026-07-05T10:44:19.721115+00:00"},{"alias_kind":"pith_short_8","alias_value":"YRJPDJPE","created_at":"2026-07-05T10:44:19.721115+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":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YRJPDJPEXWJDAHQSQPVT7WKQEA","json":"https://pith.science/pith/YRJPDJPEXWJDAHQSQPVT7WKQEA.json","graph_json":"https://pith.science/api/pith-number/YRJPDJPEXWJDAHQSQPVT7WKQEA/graph.json","events_json":"https://pith.science/api/pith-number/YRJPDJPEXWJDAHQSQPVT7WKQEA/events.json","paper":"https://pith.science/paper/YRJPDJPE"},"agent_actions":{"view_html":"https://pith.science/pith/YRJPDJPEXWJDAHQSQPVT7WKQEA","download_json":"https://pith.science/pith/YRJPDJPEXWJDAHQSQPVT7WKQEA.json","view_paper":"https://pith.science/paper/YRJPDJPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07462&json=true","fetch_graph":"https://pith.science/api/pith-number/YRJPDJPEXWJDAHQSQPVT7WKQEA/graph.json","fetch_events":"https://pith.science/api/pith-number/YRJPDJPEXWJDAHQSQPVT7WKQEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YRJPDJPEXWJDAHQSQPVT7WKQEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YRJPDJPEXWJDAHQSQPVT7WKQEA/action/storage_attestation","attest_author":"https://pith.science/pith/YRJPDJPEXWJDAHQSQPVT7WKQEA/action/author_attestation","sign_citation":"https://pith.science/pith/YRJPDJPEXWJDAHQSQPVT7WKQEA/action/citation_signature","submit_replication":"https://pith.science/pith/YRJPDJPEXWJDAHQSQPVT7WKQEA/action/replication_record"}},"created_at":"2026-07-05T10:44:19.721115+00:00","updated_at":"2026-07-05T10:44:19.721115+00:00"}