{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PWZIW5N35HQE6ABMUXZOBIMCF3","short_pith_number":"pith:PWZIW5N3","schema_version":"1.0","canonical_sha256":"7db28b75bbe9e04f002ca5f2e0a1822ec1ab9c26bd5d0c89274f61d83c8f597b","source":{"kind":"arxiv","id":"2309.15508","version":2},"attestation_state":"computed","paper":{"title":"DreamCom: Finetuning Text-guided Inpainting Model for Image Composition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zhang, Jiangtong Li, Lingxiao Lu, Li Niu","submitted_at":"2023-09-27T09:23:50Z","abstract_excerpt":"The goal of image composition is merging a foreground object into a background image to obtain a realistic composite image. Recently, generative composition methods are built on large pretrained diffusion models, due to their unprecedented image generation ability. However, they are weak in preserving the foreground object details. Inspired by recent text-to-image generation customized for certain object, we propose DreamCom by treating image composition as text-guided image inpainting customized for certain object. Specifically , we finetune pretrained text-guided image inpainting model based"},"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":"2309.15508","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-27T09:23:50Z","cross_cats_sorted":[],"title_canon_sha256":"68a4b7a178843dbb518436ca1eb034a385f1449224dd90ce98f5f58917677c55","abstract_canon_sha256":"cb9c9079cb346f70abeafbdb73bf08d5ec82a675c0cc51afc18509694ce0def5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:54.543734Z","signature_b64":"sUmlZb389DYt5aON8R3FGPn4kTzO12RkQAcKeca3uLQvJQywamB25udneC6av3RA06LcJlcwo3AtL/e/ytyXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7db28b75bbe9e04f002ca5f2e0a1822ec1ab9c26bd5d0c89274f61d83c8f597b","last_reissued_at":"2026-07-05T07:36:54.543221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:54.543221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DreamCom: Finetuning Text-guided Inpainting Model for Image Composition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zhang, Jiangtong Li, Lingxiao Lu, Li Niu","submitted_at":"2023-09-27T09:23:50Z","abstract_excerpt":"The goal of image composition is merging a foreground object into a background image to obtain a realistic composite image. Recently, generative composition methods are built on large pretrained diffusion models, due to their unprecedented image generation ability. However, they are weak in preserving the foreground object details. Inspired by recent text-to-image generation customized for certain object, we propose DreamCom by treating image composition as text-guided image inpainting customized for certain object. Specifically , we finetune pretrained text-guided image inpainting model based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15508","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/2309.15508/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":"2309.15508","created_at":"2026-07-05T07:36:54.543287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.15508v2","created_at":"2026-07-05T07:36:54.543287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15508","created_at":"2026-07-05T07:36:54.543287+00:00"},{"alias_kind":"pith_short_12","alias_value":"PWZIW5N35HQE","created_at":"2026-07-05T07:36:54.543287+00:00"},{"alias_kind":"pith_short_16","alias_value":"PWZIW5N35HQE6ABM","created_at":"2026-07-05T07:36:54.543287+00:00"},{"alias_kind":"pith_short_8","alias_value":"PWZIW5N3","created_at":"2026-07-05T07:36:54.543287+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10675","citing_title":"HiddenObjects: Scalable Diffusion-Distilled Spatial Priors for Object Placement","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13863","citing_title":"PostureObjectstitch: Anomaly Image Generation Considering Assembly Relationships in Industrial Scenarios","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PWZIW5N35HQE6ABMUXZOBIMCF3","json":"https://pith.science/pith/PWZIW5N35HQE6ABMUXZOBIMCF3.json","graph_json":"https://pith.science/api/pith-number/PWZIW5N35HQE6ABMUXZOBIMCF3/graph.json","events_json":"https://pith.science/api/pith-number/PWZIW5N35HQE6ABMUXZOBIMCF3/events.json","paper":"https://pith.science/paper/PWZIW5N3"},"agent_actions":{"view_html":"https://pith.science/pith/PWZIW5N35HQE6ABMUXZOBIMCF3","download_json":"https://pith.science/pith/PWZIW5N35HQE6ABMUXZOBIMCF3.json","view_paper":"https://pith.science/paper/PWZIW5N3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.15508&json=true","fetch_graph":"https://pith.science/api/pith-number/PWZIW5N35HQE6ABMUXZOBIMCF3/graph.json","fetch_events":"https://pith.science/api/pith-number/PWZIW5N35HQE6ABMUXZOBIMCF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PWZIW5N35HQE6ABMUXZOBIMCF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PWZIW5N35HQE6ABMUXZOBIMCF3/action/storage_attestation","attest_author":"https://pith.science/pith/PWZIW5N35HQE6ABMUXZOBIMCF3/action/author_attestation","sign_citation":"https://pith.science/pith/PWZIW5N35HQE6ABMUXZOBIMCF3/action/citation_signature","submit_replication":"https://pith.science/pith/PWZIW5N35HQE6ABMUXZOBIMCF3/action/replication_record"}},"created_at":"2026-07-05T07:36:54.543287+00:00","updated_at":"2026-07-05T07:36:54.543287+00:00"}