{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I6GNSNXSVCG4X7TDVFNJIUM2H5","short_pith_number":"pith:I6GNSNXS","schema_version":"1.0","canonical_sha256":"478cd936f2a88dcbfe63a95a94519a3f556844d60cc6aa2d5b58c5f25f2c5321","source":{"kind":"arxiv","id":"2409.18071","version":1},"attestation_state":"computed","paper":{"title":"FreeEdit: Mask-free Reference-based Image Editing with Multi-modal Instruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jialin Gao, Jiao Dai, Jizhong Han, Kai Ma, LinJiang Huang, Runze He, Shaofei Huang, Si Liu, Xiaoming Wei","submitted_at":"2024-09-26T17:18:39Z","abstract_excerpt":"Introducing user-specified visual concepts in image editing is highly practical as these concepts convey the user's intent more precisely than text-based descriptions. We propose FreeEdit, a novel approach for achieving such reference-based image editing, which can accurately reproduce the visual concept from the reference image based on user-friendly language instructions. Our approach leverages the multi-modal instruction encoder to encode language instructions to guide the editing process. This implicit way of locating the editing area eliminates the need for manual editing masks. To enhanc"},"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":"2409.18071","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T17:18:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dee3552b51e50b3ba428439bf4606327537ba4766e98435c8a6a82c974d17e25","abstract_canon_sha256":"d5f2dc89780561b44edb14caf380a18878136a4387c031d61dd79b82ecff8603"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:20.110078Z","signature_b64":"FplOREebnJ/GRuYMoNFetNPyPAx6iXIjHOnLGrspTJEWFN/n9/EucaAW/UfnY/dCN+bd2oNXmEoawdH9kJiECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"478cd936f2a88dcbfe63a95a94519a3f556844d60cc6aa2d5b58c5f25f2c5321","last_reissued_at":"2026-07-05T09:12:20.109628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:20.109628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FreeEdit: Mask-free Reference-based Image Editing with Multi-modal Instruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jialin Gao, Jiao Dai, Jizhong Han, Kai Ma, LinJiang Huang, Runze He, Shaofei Huang, Si Liu, Xiaoming Wei","submitted_at":"2024-09-26T17:18:39Z","abstract_excerpt":"Introducing user-specified visual concepts in image editing is highly practical as these concepts convey the user's intent more precisely than text-based descriptions. We propose FreeEdit, a novel approach for achieving such reference-based image editing, which can accurately reproduce the visual concept from the reference image based on user-friendly language instructions. Our approach leverages the multi-modal instruction encoder to encode language instructions to guide the editing process. This implicit way of locating the editing area eliminates the need for manual editing masks. To enhanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18071","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/2409.18071/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":"2409.18071","created_at":"2026-07-05T09:12:20.109686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18071v1","created_at":"2026-07-05T09:12:20.109686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18071","created_at":"2026-07-05T09:12:20.109686+00:00"},{"alias_kind":"pith_short_12","alias_value":"I6GNSNXSVCG4","created_at":"2026-07-05T09:12:20.109686+00:00"},{"alias_kind":"pith_short_16","alias_value":"I6GNSNXSVCG4X7TD","created_at":"2026-07-05T09:12:20.109686+00:00"},{"alias_kind":"pith_short_8","alias_value":"I6GNSNXS","created_at":"2026-07-05T09:12:20.109686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07171","citing_title":"When Recovery Matters: The Blind Spot of Surrogate Privacy in MLLM Editing","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08915","citing_title":"Large-Scale Universal Defect Generation: Foundation Models and Datasets","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I6GNSNXSVCG4X7TDVFNJIUM2H5","json":"https://pith.science/pith/I6GNSNXSVCG4X7TDVFNJIUM2H5.json","graph_json":"https://pith.science/api/pith-number/I6GNSNXSVCG4X7TDVFNJIUM2H5/graph.json","events_json":"https://pith.science/api/pith-number/I6GNSNXSVCG4X7TDVFNJIUM2H5/events.json","paper":"https://pith.science/paper/I6GNSNXS"},"agent_actions":{"view_html":"https://pith.science/pith/I6GNSNXSVCG4X7TDVFNJIUM2H5","download_json":"https://pith.science/pith/I6GNSNXSVCG4X7TDVFNJIUM2H5.json","view_paper":"https://pith.science/paper/I6GNSNXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18071&json=true","fetch_graph":"https://pith.science/api/pith-number/I6GNSNXSVCG4X7TDVFNJIUM2H5/graph.json","fetch_events":"https://pith.science/api/pith-number/I6GNSNXSVCG4X7TDVFNJIUM2H5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I6GNSNXSVCG4X7TDVFNJIUM2H5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I6GNSNXSVCG4X7TDVFNJIUM2H5/action/storage_attestation","attest_author":"https://pith.science/pith/I6GNSNXSVCG4X7TDVFNJIUM2H5/action/author_attestation","sign_citation":"https://pith.science/pith/I6GNSNXSVCG4X7TDVFNJIUM2H5/action/citation_signature","submit_replication":"https://pith.science/pith/I6GNSNXSVCG4X7TDVFNJIUM2H5/action/replication_record"}},"created_at":"2026-07-05T09:12:20.109686+00:00","updated_at":"2026-07-05T09:12:20.109686+00:00"}