{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EPJBCFVIUFTS5S6UTXAP6UK3CP","short_pith_number":"pith:EPJBCFVI","schema_version":"1.0","canonical_sha256":"23d21116a8a1672ecbd49dc0ff515b13e5cd488a60c069ec28b2baf52ec546aa","source":{"kind":"arxiv","id":"2507.23685","version":2},"attestation_state":"computed","paper":{"title":"UniLDiff: Unlocking the Power of Diffusion Priors for All-in-One Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dian Chen, Liangtai Zhou, Ni Tang, Xiaotong Luo, Yanyun Qu, Zihan Cheng","submitted_at":"2025-07-31T16:02:00Z","abstract_excerpt":"All-in-One Image Restoration (AiOIR) has emerged as a promising yet challenging research direction. To address the core challenges of diverse degradation modeling and detail preservation, we propose UniLDiff, a unified framework enhanced with degradation- and detail-aware mechanisms, unlocking the power of diffusion priors for robust image restoration. Specifically, we introduce a Degradation-Aware Feature Fusion (DAFF) to dynamically inject low-quality features into each denoising step via decoupled fusion and adaptive modulation, enabling implicit modeling of diverse and compound degradation"},"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":"2507.23685","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-31T16:02:00Z","cross_cats_sorted":[],"title_canon_sha256":"32977b027b4423886b7e4aea40f89176f9c39ef102f181a2489b9d7e09b451eb","abstract_canon_sha256":"f421ace3b66f58e83991f6d05a3f85728da16e5d1e27e2d36ae70c95e899351e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:06.560719Z","signature_b64":"3TUfYvk+zi8ITJqqNGeZQXxTsxh1mu5wX0Kw4Z8PW1x+hQExPuv0XJLM4xHBHIHEKDnGbMVsgvyldxeHJiVSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23d21116a8a1672ecbd49dc0ff515b13e5cd488a60c069ec28b2baf52ec546aa","last_reissued_at":"2026-07-05T11:48:06.559953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:06.559953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniLDiff: Unlocking the Power of Diffusion Priors for All-in-One Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dian Chen, Liangtai Zhou, Ni Tang, Xiaotong Luo, Yanyun Qu, Zihan Cheng","submitted_at":"2025-07-31T16:02:00Z","abstract_excerpt":"All-in-One Image Restoration (AiOIR) has emerged as a promising yet challenging research direction. To address the core challenges of diverse degradation modeling and detail preservation, we propose UniLDiff, a unified framework enhanced with degradation- and detail-aware mechanisms, unlocking the power of diffusion priors for robust image restoration. Specifically, we introduce a Degradation-Aware Feature Fusion (DAFF) to dynamically inject low-quality features into each denoising step via decoupled fusion and adaptive modulation, enabling implicit modeling of diverse and compound degradation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23685","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/2507.23685/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":"2507.23685","created_at":"2026-07-05T11:48:06.560031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.23685v2","created_at":"2026-07-05T11:48:06.560031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23685","created_at":"2026-07-05T11:48:06.560031+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPJBCFVIUFTS","created_at":"2026-07-05T11:48:06.560031+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPJBCFVIUFTS5S6U","created_at":"2026-07-05T11:48:06.560031+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPJBCFVI","created_at":"2026-07-05T11:48:06.560031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04924","citing_title":"Your Pre-trained Diffusion Model Secretly Knows Restoration","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EPJBCFVIUFTS5S6UTXAP6UK3CP","json":"https://pith.science/pith/EPJBCFVIUFTS5S6UTXAP6UK3CP.json","graph_json":"https://pith.science/api/pith-number/EPJBCFVIUFTS5S6UTXAP6UK3CP/graph.json","events_json":"https://pith.science/api/pith-number/EPJBCFVIUFTS5S6UTXAP6UK3CP/events.json","paper":"https://pith.science/paper/EPJBCFVI"},"agent_actions":{"view_html":"https://pith.science/pith/EPJBCFVIUFTS5S6UTXAP6UK3CP","download_json":"https://pith.science/pith/EPJBCFVIUFTS5S6UTXAP6UK3CP.json","view_paper":"https://pith.science/paper/EPJBCFVI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.23685&json=true","fetch_graph":"https://pith.science/api/pith-number/EPJBCFVIUFTS5S6UTXAP6UK3CP/graph.json","fetch_events":"https://pith.science/api/pith-number/EPJBCFVIUFTS5S6UTXAP6UK3CP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPJBCFVIUFTS5S6UTXAP6UK3CP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPJBCFVIUFTS5S6UTXAP6UK3CP/action/storage_attestation","attest_author":"https://pith.science/pith/EPJBCFVIUFTS5S6UTXAP6UK3CP/action/author_attestation","sign_citation":"https://pith.science/pith/EPJBCFVIUFTS5S6UTXAP6UK3CP/action/citation_signature","submit_replication":"https://pith.science/pith/EPJBCFVIUFTS5S6UTXAP6UK3CP/action/replication_record"}},"created_at":"2026-07-05T11:48:06.560031+00:00","updated_at":"2026-07-05T11:48:06.560031+00:00"}