{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P7ISE7VWEP5G3EPD3KBEZCXT26","short_pith_number":"pith:P7ISE7VW","schema_version":"1.0","canonical_sha256":"7fd1227eb623fa6d91e3da824c8af3d78dbaca2540fc2136fdcc7c5fbf7826c2","source":{"kind":"arxiv","id":"2410.04618","version":3},"attestation_state":"computed","paper":{"title":"Towards Unsupervised Blind Face Restoration using Diffusion Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Levinshtein, Igor Gilitschenski, Sina Honari, Tianshu Kuai","submitted_at":"2024-10-06T20:38:14Z","abstract_excerpt":"Blind face restoration methods have shown remarkable performance, particularly when trained on large-scale synthetic datasets with supervised learning. These datasets are often generated by simulating low-quality face images with a handcrafted image degradation pipeline. The models trained on such synthetic degradations, however, cannot deal with inputs of unseen degradations. In this paper, we address this issue by using only a set of input images, with unknown degradations and without ground truth targets, to fine-tune a restoration model that learns to map them to clean and contextually con"},"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":"2410.04618","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-06T20:38:14Z","cross_cats_sorted":[],"title_canon_sha256":"0dfe3202807286b867226131a3434bf7cd1638398ef23f65cf02a7745331b36d","abstract_canon_sha256":"cf10bb3179526fa9eddfacb284b675e1fc92907f6d55453458be567c4a2ae724"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:58.989377Z","signature_b64":"Zh0c9/Hn0/6bEPWWpnuqF8987/cJdG1WjoxHH6QKYVe53qHauuMIT28HiR4FeAa8sed41skx6AjsutGkdYE6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fd1227eb623fa6d91e3da824c8af3d78dbaca2540fc2136fdcc7c5fbf7826c2","last_reissued_at":"2026-07-05T09:39:58.988945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:58.988945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Unsupervised Blind Face Restoration using Diffusion Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Levinshtein, Igor Gilitschenski, Sina Honari, Tianshu Kuai","submitted_at":"2024-10-06T20:38:14Z","abstract_excerpt":"Blind face restoration methods have shown remarkable performance, particularly when trained on large-scale synthetic datasets with supervised learning. These datasets are often generated by simulating low-quality face images with a handcrafted image degradation pipeline. The models trained on such synthetic degradations, however, cannot deal with inputs of unseen degradations. In this paper, we address this issue by using only a set of input images, with unknown degradations and without ground truth targets, to fine-tune a restoration model that learns to map them to clean and contextually con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04618","kind":"arxiv","version":3},"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/2410.04618/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":"2410.04618","created_at":"2026-07-05T09:39:58.988996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04618v3","created_at":"2026-07-05T09:39:58.988996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04618","created_at":"2026-07-05T09:39:58.988996+00:00"},{"alias_kind":"pith_short_12","alias_value":"P7ISE7VWEP5G","created_at":"2026-07-05T09:39:58.988996+00:00"},{"alias_kind":"pith_short_16","alias_value":"P7ISE7VWEP5G3EPD","created_at":"2026-07-05T09:39:58.988996+00:00"},{"alias_kind":"pith_short_8","alias_value":"P7ISE7VW","created_at":"2026-07-05T09:39:58.988996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10293","citing_title":"Show and Polish: Reference-Guided Identity Preservation in Face Video Restoration","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P7ISE7VWEP5G3EPD3KBEZCXT26","json":"https://pith.science/pith/P7ISE7VWEP5G3EPD3KBEZCXT26.json","graph_json":"https://pith.science/api/pith-number/P7ISE7VWEP5G3EPD3KBEZCXT26/graph.json","events_json":"https://pith.science/api/pith-number/P7ISE7VWEP5G3EPD3KBEZCXT26/events.json","paper":"https://pith.science/paper/P7ISE7VW"},"agent_actions":{"view_html":"https://pith.science/pith/P7ISE7VWEP5G3EPD3KBEZCXT26","download_json":"https://pith.science/pith/P7ISE7VWEP5G3EPD3KBEZCXT26.json","view_paper":"https://pith.science/paper/P7ISE7VW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04618&json=true","fetch_graph":"https://pith.science/api/pith-number/P7ISE7VWEP5G3EPD3KBEZCXT26/graph.json","fetch_events":"https://pith.science/api/pith-number/P7ISE7VWEP5G3EPD3KBEZCXT26/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P7ISE7VWEP5G3EPD3KBEZCXT26/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P7ISE7VWEP5G3EPD3KBEZCXT26/action/storage_attestation","attest_author":"https://pith.science/pith/P7ISE7VWEP5G3EPD3KBEZCXT26/action/author_attestation","sign_citation":"https://pith.science/pith/P7ISE7VWEP5G3EPD3KBEZCXT26/action/citation_signature","submit_replication":"https://pith.science/pith/P7ISE7VWEP5G3EPD3KBEZCXT26/action/replication_record"}},"created_at":"2026-07-05T09:39:58.988996+00:00","updated_at":"2026-07-05T09:39:58.988996+00:00"}