{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PEDZ54IWHPNKWGFV7RHMZK7CR5","short_pith_number":"pith:PEDZ54IW","schema_version":"1.0","canonical_sha256":"79079ef1163bdaab18b5fc4eccabe28f61604f9a4f6246ea2ee4d45f90bd921b","source":{"kind":"arxiv","id":"2503.09294","version":1},"attestation_state":"computed","paper":{"title":"IQPFR: An Image Quality Prior for Blind Face Restoration and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunming He, Jingduo Tian, Lei Xu, Pei Liu, Peng Hu, Sina Farsiu, Xiu Li, Yulun Zhang","submitted_at":"2025-03-12T11:39:51Z","abstract_excerpt":"Blind Face Restoration (BFR) addresses the challenge of reconstructing degraded low-quality (LQ) facial images into high-quality (HQ) outputs. Conventional approaches predominantly rely on learning feature representations from ground-truth (GT) data; however, inherent imperfections in GT datasets constrain restoration performance to the mean quality level of the training data, rather than attaining maximally attainable visual quality. To overcome this limitation, we propose a novel framework that incorporates an Image Quality Prior (IQP) derived from No-Reference Image Quality Assessment (NR-I"},"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":"2503.09294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T11:39:51Z","cross_cats_sorted":[],"title_canon_sha256":"1bf10ece7e7bbd6b0c325af7396936451cb1df616160e76db7aa54ae31cbd3ca","abstract_canon_sha256":"81df2f967f3d8ed6b8fa12f8a6e3b7ffbdb8101de86d3a38f171c3b3818e2635"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:53.483304Z","signature_b64":"o1DUWXR4AbIGC1F6YnES6ObG9A87r2mOAiSsFM6icoJX5SCRvQSgau9VKLjwFG/vIyX5aHeGcUVbUPGyZoSYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79079ef1163bdaab18b5fc4eccabe28f61604f9a4f6246ea2ee4d45f90bd921b","last_reissued_at":"2026-07-05T10:29:53.482820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:53.482820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IQPFR: An Image Quality Prior for Blind Face Restoration and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunming He, Jingduo Tian, Lei Xu, Pei Liu, Peng Hu, Sina Farsiu, Xiu Li, Yulun Zhang","submitted_at":"2025-03-12T11:39:51Z","abstract_excerpt":"Blind Face Restoration (BFR) addresses the challenge of reconstructing degraded low-quality (LQ) facial images into high-quality (HQ) outputs. Conventional approaches predominantly rely on learning feature representations from ground-truth (GT) data; however, inherent imperfections in GT datasets constrain restoration performance to the mean quality level of the training data, rather than attaining maximally attainable visual quality. To overcome this limitation, we propose a novel framework that incorporates an Image Quality Prior (IQP) derived from No-Reference Image Quality Assessment (NR-I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09294","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/2503.09294/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":"2503.09294","created_at":"2026-07-05T10:29:53.482885+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.09294v1","created_at":"2026-07-05T10:29:53.482885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09294","created_at":"2026-07-05T10:29:53.482885+00:00"},{"alias_kind":"pith_short_12","alias_value":"PEDZ54IWHPNK","created_at":"2026-07-05T10:29:53.482885+00:00"},{"alias_kind":"pith_short_16","alias_value":"PEDZ54IWHPNKWGFV","created_at":"2026-07-05T10:29:53.482885+00:00"},{"alias_kind":"pith_short_8","alias_value":"PEDZ54IW","created_at":"2026-07-05T10:29:53.482885+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.29773","citing_title":"Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PEDZ54IWHPNKWGFV7RHMZK7CR5","json":"https://pith.science/pith/PEDZ54IWHPNKWGFV7RHMZK7CR5.json","graph_json":"https://pith.science/api/pith-number/PEDZ54IWHPNKWGFV7RHMZK7CR5/graph.json","events_json":"https://pith.science/api/pith-number/PEDZ54IWHPNKWGFV7RHMZK7CR5/events.json","paper":"https://pith.science/paper/PEDZ54IW"},"agent_actions":{"view_html":"https://pith.science/pith/PEDZ54IWHPNKWGFV7RHMZK7CR5","download_json":"https://pith.science/pith/PEDZ54IWHPNKWGFV7RHMZK7CR5.json","view_paper":"https://pith.science/paper/PEDZ54IW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.09294&json=true","fetch_graph":"https://pith.science/api/pith-number/PEDZ54IWHPNKWGFV7RHMZK7CR5/graph.json","fetch_events":"https://pith.science/api/pith-number/PEDZ54IWHPNKWGFV7RHMZK7CR5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PEDZ54IWHPNKWGFV7RHMZK7CR5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PEDZ54IWHPNKWGFV7RHMZK7CR5/action/storage_attestation","attest_author":"https://pith.science/pith/PEDZ54IWHPNKWGFV7RHMZK7CR5/action/author_attestation","sign_citation":"https://pith.science/pith/PEDZ54IWHPNKWGFV7RHMZK7CR5/action/citation_signature","submit_replication":"https://pith.science/pith/PEDZ54IWHPNKWGFV7RHMZK7CR5/action/replication_record"}},"created_at":"2026-07-05T10:29:53.482885+00:00","updated_at":"2026-07-05T10:29:53.482885+00:00"}