{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L72HCJPGD3ZOJEAO72RMZXZH3C","short_pith_number":"pith:L72HCJPG","schema_version":"1.0","canonical_sha256":"5ff47125e61ef2e4900efea2ccdf27d89622cbf893a5adac147c28914e95fbd4","source":{"kind":"arxiv","id":"2403.10520","version":1},"attestation_state":"computed","paper":{"title":"Strong and Controllable Blind Image Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Chenhui Gou, Hongdong Li, Junlin Han, Liang Zheng, Zeyu Zhang","submitted_at":"2024-03-15T17:59:44Z","abstract_excerpt":"Blind image decomposition aims to decompose all components present in an image, typically used to restore a multi-degraded input image. While fully recovering the clean image is appealing, in some scenarios, users might want to retain certain degradations, such as watermarks, for copyright protection. To address this need, we add controllability to the blind image decomposition process, allowing users to enter which types of degradation to remove or retain. We design an architecture named controllable blind image decomposition network. Inserted in the middle of U-Net structure, our method firs"},"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":"2403.10520","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T17:59:44Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"3225f660ef1654c7f2fffd0d84f6a8517c37e467d32d4c00c265f5f54f5a4f5b","abstract_canon_sha256":"29cdce73154bcf87da820e3280ae64742991e405bb4eede66ed8e61e6b1a411d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:42.627398Z","signature_b64":"MQsIWyx4qazq1BABnSzf6DZu++Z+vE4Qw6c/q56aXoWbGIaXexD0aV9Z2Wn8wxgq4wMmqIWPm9mAfRh4M5jZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ff47125e61ef2e4900efea2ccdf27d89622cbf893a5adac147c28914e95fbd4","last_reissued_at":"2026-07-05T07:56:42.626875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:42.626875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Strong and Controllable Blind Image Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Chenhui Gou, Hongdong Li, Junlin Han, Liang Zheng, Zeyu Zhang","submitted_at":"2024-03-15T17:59:44Z","abstract_excerpt":"Blind image decomposition aims to decompose all components present in an image, typically used to restore a multi-degraded input image. While fully recovering the clean image is appealing, in some scenarios, users might want to retain certain degradations, such as watermarks, for copyright protection. To address this need, we add controllability to the blind image decomposition process, allowing users to enter which types of degradation to remove or retain. We design an architecture named controllable blind image decomposition network. Inserted in the middle of U-Net structure, our method firs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10520","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/2403.10520/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":"2403.10520","created_at":"2026-07-05T07:56:42.626939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10520v1","created_at":"2026-07-05T07:56:42.626939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10520","created_at":"2026-07-05T07:56:42.626939+00:00"},{"alias_kind":"pith_short_12","alias_value":"L72HCJPGD3ZO","created_at":"2026-07-05T07:56:42.626939+00:00"},{"alias_kind":"pith_short_16","alias_value":"L72HCJPGD3ZOJEAO","created_at":"2026-07-05T07:56:42.626939+00:00"},{"alias_kind":"pith_short_8","alias_value":"L72HCJPG","created_at":"2026-07-05T07:56:42.626939+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22291","citing_title":"Neural Restoration of Greening Defects in Historical Autochrome Photographs Based on Purely Synthetic Data","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L72HCJPGD3ZOJEAO72RMZXZH3C","json":"https://pith.science/pith/L72HCJPGD3ZOJEAO72RMZXZH3C.json","graph_json":"https://pith.science/api/pith-number/L72HCJPGD3ZOJEAO72RMZXZH3C/graph.json","events_json":"https://pith.science/api/pith-number/L72HCJPGD3ZOJEAO72RMZXZH3C/events.json","paper":"https://pith.science/paper/L72HCJPG"},"agent_actions":{"view_html":"https://pith.science/pith/L72HCJPGD3ZOJEAO72RMZXZH3C","download_json":"https://pith.science/pith/L72HCJPGD3ZOJEAO72RMZXZH3C.json","view_paper":"https://pith.science/paper/L72HCJPG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10520&json=true","fetch_graph":"https://pith.science/api/pith-number/L72HCJPGD3ZOJEAO72RMZXZH3C/graph.json","fetch_events":"https://pith.science/api/pith-number/L72HCJPGD3ZOJEAO72RMZXZH3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L72HCJPGD3ZOJEAO72RMZXZH3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L72HCJPGD3ZOJEAO72RMZXZH3C/action/storage_attestation","attest_author":"https://pith.science/pith/L72HCJPGD3ZOJEAO72RMZXZH3C/action/author_attestation","sign_citation":"https://pith.science/pith/L72HCJPGD3ZOJEAO72RMZXZH3C/action/citation_signature","submit_replication":"https://pith.science/pith/L72HCJPGD3ZOJEAO72RMZXZH3C/action/replication_record"}},"created_at":"2026-07-05T07:56:42.626939+00:00","updated_at":"2026-07-05T07:56:42.626939+00:00"}