{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SIGBPRACKG4GL3G6PFEVA4ZYJ7","short_pith_number":"pith:SIGBPRAC","schema_version":"1.0","canonical_sha256":"920c17c40251b865ecde79495073384fef659ef38945529f5dd1bc2ee1312bb9","source":{"kind":"arxiv","id":"2311.14926","version":1},"attestation_state":"computed","paper":{"title":"FreePIH: Training-Free Painterly Image Harmonization with Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jie Zhang, Jingcai Guo, Qihua Zhou, Ruibin Li, Song Guo","submitted_at":"2023-11-25T04:23:49Z","abstract_excerpt":"This paper provides an efficient training-free painterly image harmonization (PIH) method, dubbed FreePIH, that leverages only a pre-trained diffusion model to achieve state-of-the-art harmonization results. Unlike existing methods that require either training auxiliary networks or fine-tuning a large pre-trained backbone, or both, to harmonize a foreground object with a painterly-style background image, our FreePIH tames the denoising process as a plug-in module for foreground image style transfer. Specifically, we find that the very last few steps of the denoising (i.e., generation) process "},"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":"2311.14926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-25T04:23:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c9c52286849a12d539878fd4c3af40da0ea5b1b75db377f73e4c2c9d8ba72c4","abstract_canon_sha256":"3d14e26d7f3e0e4713316a409b1456495c7a2d4013bc16d4ce3c7a8c7e4f54ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:55.746144Z","signature_b64":"cPIt5FxrGJHt4OZHj4EKq/Lmdn0no1YyVFOJHMzCiVkByhLw2gkOkA9nMO/G3x1oT0Nw6fP1JMefznQ01qfJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"920c17c40251b865ecde79495073384fef659ef38945529f5dd1bc2ee1312bb9","last_reissued_at":"2026-07-05T07:16:55.745689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:55.745689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FreePIH: Training-Free Painterly Image Harmonization with Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jie Zhang, Jingcai Guo, Qihua Zhou, Ruibin Li, Song Guo","submitted_at":"2023-11-25T04:23:49Z","abstract_excerpt":"This paper provides an efficient training-free painterly image harmonization (PIH) method, dubbed FreePIH, that leverages only a pre-trained diffusion model to achieve state-of-the-art harmonization results. Unlike existing methods that require either training auxiliary networks or fine-tuning a large pre-trained backbone, or both, to harmonize a foreground object with a painterly-style background image, our FreePIH tames the denoising process as a plug-in module for foreground image style transfer. Specifically, we find that the very last few steps of the denoising (i.e., generation) process "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14926","kind":"arxiv","version":1},"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/2311.14926/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":"2311.14926","created_at":"2026-07-05T07:16:55.745745+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.14926v1","created_at":"2026-07-05T07:16:55.745745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14926","created_at":"2026-07-05T07:16:55.745745+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIGBPRACKG4G","created_at":"2026-07-05T07:16:55.745745+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIGBPRACKG4GL3G6","created_at":"2026-07-05T07:16:55.745745+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIGBPRAC","created_at":"2026-07-05T07:16:55.745745+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00740","citing_title":"RORem: Training a Robust Object Remover with Human-in-the-Loop","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SIGBPRACKG4GL3G6PFEVA4ZYJ7","json":"https://pith.science/pith/SIGBPRACKG4GL3G6PFEVA4ZYJ7.json","graph_json":"https://pith.science/api/pith-number/SIGBPRACKG4GL3G6PFEVA4ZYJ7/graph.json","events_json":"https://pith.science/api/pith-number/SIGBPRACKG4GL3G6PFEVA4ZYJ7/events.json","paper":"https://pith.science/paper/SIGBPRAC"},"agent_actions":{"view_html":"https://pith.science/pith/SIGBPRACKG4GL3G6PFEVA4ZYJ7","download_json":"https://pith.science/pith/SIGBPRACKG4GL3G6PFEVA4ZYJ7.json","view_paper":"https://pith.science/paper/SIGBPRAC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.14926&json=true","fetch_graph":"https://pith.science/api/pith-number/SIGBPRACKG4GL3G6PFEVA4ZYJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/SIGBPRACKG4GL3G6PFEVA4ZYJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIGBPRACKG4GL3G6PFEVA4ZYJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIGBPRACKG4GL3G6PFEVA4ZYJ7/action/storage_attestation","attest_author":"https://pith.science/pith/SIGBPRACKG4GL3G6PFEVA4ZYJ7/action/author_attestation","sign_citation":"https://pith.science/pith/SIGBPRACKG4GL3G6PFEVA4ZYJ7/action/citation_signature","submit_replication":"https://pith.science/pith/SIGBPRACKG4GL3G6PFEVA4ZYJ7/action/replication_record"}},"created_at":"2026-07-05T07:16:55.745745+00:00","updated_at":"2026-07-05T07:16:55.745745+00:00"}