{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KIZGDRMFV2CUTUZEO3KLGDZMZQ","short_pith_number":"pith:KIZGDRMF","schema_version":"1.0","canonical_sha256":"523261c585ae8549d32476d4b30f2ccc100a41c294d422a264cfe71dcc1695d7","source":{"kind":"arxiv","id":"2403.06406","version":2},"attestation_state":"computed","paper":{"title":"When No-Reference Image Quality Models Meet MAP Estimation in Diffusion Latents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingquan Li, Guangtao Zhai, Kede Ma, Weixia Zhang, Xiaokang Yang","submitted_at":"2024-03-11T03:35:41Z","abstract_excerpt":"Contemporary no-reference image quality assessment (NR-IQA) models can effectively quantify perceived image quality, often achieving strong correlations with human perceptual scores on standard IQA benchmarks. Yet, limited efforts have been devoted to treating NR-IQA models as natural image priors for real-world image enhancement, and consequently comparing them from a perceptual optimization standpoint. In this work, we show -- for the first time -- that NR-IQA models can be plugged into the maximum a posteriori (MAP) estimation framework for image enhancement. This is achieved by performing "},"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":"2403.06406","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T03:35:41Z","cross_cats_sorted":[],"title_canon_sha256":"f63227ff81e92d4b21209b74b0682d8dc93cd4a8728143f0bb902a13be32ad96","abstract_canon_sha256":"eb386c7f0bf6343ba2027a5c03b7c21d5499e32bd6f233de0cf01575f78489dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:12.015644Z","signature_b64":"ZMPFPZsVcp31h5rWMR+qHjAEj6BEXSH5y2cMxbTdzDquBlO4mfXTtJAML9VVglq/9/AHkoZKLSUFYYLn3Xg+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"523261c585ae8549d32476d4b30f2ccc100a41c294d422a264cfe71dcc1695d7","last_reissued_at":"2026-07-05T10:01:12.015200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:12.015200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When No-Reference Image Quality Models Meet MAP Estimation in Diffusion Latents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingquan Li, Guangtao Zhai, Kede Ma, Weixia Zhang, Xiaokang Yang","submitted_at":"2024-03-11T03:35:41Z","abstract_excerpt":"Contemporary no-reference image quality assessment (NR-IQA) models can effectively quantify perceived image quality, often achieving strong correlations with human perceptual scores on standard IQA benchmarks. Yet, limited efforts have been devoted to treating NR-IQA models as natural image priors for real-world image enhancement, and consequently comparing them from a perceptual optimization standpoint. In this work, we show -- for the first time -- that NR-IQA models can be plugged into the maximum a posteriori (MAP) estimation framework for image enhancement. This is achieved by performing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06406","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/2403.06406/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":"2403.06406","created_at":"2026-07-05T10:01:12.015256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06406v2","created_at":"2026-07-05T10:01:12.015256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06406","created_at":"2026-07-05T10:01:12.015256+00:00"},{"alias_kind":"pith_short_12","alias_value":"KIZGDRMFV2CU","created_at":"2026-07-05T10:01:12.015256+00:00"},{"alias_kind":"pith_short_16","alias_value":"KIZGDRMFV2CUTUZE","created_at":"2026-07-05T10:01:12.015256+00:00"},{"alias_kind":"pith_short_8","alias_value":"KIZGDRMF","created_at":"2026-07-05T10:01:12.015256+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.14600","citing_title":"NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results","ref_index":83,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KIZGDRMFV2CUTUZEO3KLGDZMZQ","json":"https://pith.science/pith/KIZGDRMFV2CUTUZEO3KLGDZMZQ.json","graph_json":"https://pith.science/api/pith-number/KIZGDRMFV2CUTUZEO3KLGDZMZQ/graph.json","events_json":"https://pith.science/api/pith-number/KIZGDRMFV2CUTUZEO3KLGDZMZQ/events.json","paper":"https://pith.science/paper/KIZGDRMF"},"agent_actions":{"view_html":"https://pith.science/pith/KIZGDRMFV2CUTUZEO3KLGDZMZQ","download_json":"https://pith.science/pith/KIZGDRMFV2CUTUZEO3KLGDZMZQ.json","view_paper":"https://pith.science/paper/KIZGDRMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06406&json=true","fetch_graph":"https://pith.science/api/pith-number/KIZGDRMFV2CUTUZEO3KLGDZMZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KIZGDRMFV2CUTUZEO3KLGDZMZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KIZGDRMFV2CUTUZEO3KLGDZMZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KIZGDRMFV2CUTUZEO3KLGDZMZQ/action/storage_attestation","attest_author":"https://pith.science/pith/KIZGDRMFV2CUTUZEO3KLGDZMZQ/action/author_attestation","sign_citation":"https://pith.science/pith/KIZGDRMFV2CUTUZEO3KLGDZMZQ/action/citation_signature","submit_replication":"https://pith.science/pith/KIZGDRMFV2CUTUZEO3KLGDZMZQ/action/replication_record"}},"created_at":"2026-07-05T10:01:12.015256+00:00","updated_at":"2026-07-05T10:01:12.015256+00:00"}