{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RY2G6OVNN3OTKKVPVU6Q7EANHN","short_pith_number":"pith:RY2G6OVN","schema_version":"1.0","canonical_sha256":"8e346f3aad6edd352aafad3d0f900d3b56606c9b1dddfc20aa0c06f3acc1b6db","source":{"kind":"arxiv","id":"2212.06512","version":4},"attestation_state":"computed","paper":{"title":"DifFace: Blind Face Restoration with Diffused Error Contraction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Zongsheng Yue","submitted_at":"2022-12-13T11:52:33Z","abstract_excerpt":"While deep learning-based methods for blind face restoration have achieved unprecedented success, they still suffer from two major limitations. First, most of them deteriorate when facing complex degradations out of their training data. Second, these methods require multiple constraints, e.g., fidelity, perceptual, and adversarial losses, which require laborious hyper-parameter tuning to stabilize and balance their influences. In this work, we propose a novel method named DifFace that is capable of coping with unseen and complex degradations more gracefully without complicated loss designs. Th"},"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":"2212.06512","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-13T11:52:33Z","cross_cats_sorted":[],"title_canon_sha256":"8cf83d77e0dd6b2729bf0fc18fff167393bfad658636d6c29266e5464e5321b4","abstract_canon_sha256":"9a756eff3522a95bd6fc45f87e33c24042413547d614d81c8d4afddcd0beaaf5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:15.710598Z","signature_b64":"ke+CNeeIEqmrHb8r+VDqBnyDGgWPKmVHWnUtqu/XVZn3VCkSajlt5OZ26NV1irPbpXoOJXK+DiGEd2M5bawACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e346f3aad6edd352aafad3d0f900d3b56606c9b1dddfc20aa0c06f3acc1b6db","last_reissued_at":"2026-07-05T08:46:15.710129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:15.710129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DifFace: Blind Face Restoration with Diffused Error Contraction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Zongsheng Yue","submitted_at":"2022-12-13T11:52:33Z","abstract_excerpt":"While deep learning-based methods for blind face restoration have achieved unprecedented success, they still suffer from two major limitations. First, most of them deteriorate when facing complex degradations out of their training data. Second, these methods require multiple constraints, e.g., fidelity, perceptual, and adversarial losses, which require laborious hyper-parameter tuning to stabilize and balance their influences. In this work, we propose a novel method named DifFace that is capable of coping with unseen and complex degradations more gracefully without complicated loss designs. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.06512","kind":"arxiv","version":4},"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/2212.06512/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":"2212.06512","created_at":"2026-07-05T08:46:15.710192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.06512v4","created_at":"2026-07-05T08:46:15.710192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.06512","created_at":"2026-07-05T08:46:15.710192+00:00"},{"alias_kind":"pith_short_12","alias_value":"RY2G6OVNN3OT","created_at":"2026-07-05T08:46:15.710192+00:00"},{"alias_kind":"pith_short_16","alias_value":"RY2G6OVNN3OTKKVP","created_at":"2026-07-05T08:46:15.710192+00:00"},{"alias_kind":"pith_short_8","alias_value":"RY2G6OVN","created_at":"2026-07-05T08:46:15.710192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21450","citing_title":"VARestorer: One-Step VAR Distillation for Real-World Image Super-Resolution","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RY2G6OVNN3OTKKVPVU6Q7EANHN","json":"https://pith.science/pith/RY2G6OVNN3OTKKVPVU6Q7EANHN.json","graph_json":"https://pith.science/api/pith-number/RY2G6OVNN3OTKKVPVU6Q7EANHN/graph.json","events_json":"https://pith.science/api/pith-number/RY2G6OVNN3OTKKVPVU6Q7EANHN/events.json","paper":"https://pith.science/paper/RY2G6OVN"},"agent_actions":{"view_html":"https://pith.science/pith/RY2G6OVNN3OTKKVPVU6Q7EANHN","download_json":"https://pith.science/pith/RY2G6OVNN3OTKKVPVU6Q7EANHN.json","view_paper":"https://pith.science/paper/RY2G6OVN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.06512&json=true","fetch_graph":"https://pith.science/api/pith-number/RY2G6OVNN3OTKKVPVU6Q7EANHN/graph.json","fetch_events":"https://pith.science/api/pith-number/RY2G6OVNN3OTKKVPVU6Q7EANHN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RY2G6OVNN3OTKKVPVU6Q7EANHN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RY2G6OVNN3OTKKVPVU6Q7EANHN/action/storage_attestation","attest_author":"https://pith.science/pith/RY2G6OVNN3OTKKVPVU6Q7EANHN/action/author_attestation","sign_citation":"https://pith.science/pith/RY2G6OVNN3OTKKVPVU6Q7EANHN/action/citation_signature","submit_replication":"https://pith.science/pith/RY2G6OVNN3OTKKVPVU6Q7EANHN/action/replication_record"}},"created_at":"2026-07-05T08:46:15.710192+00:00","updated_at":"2026-07-05T08:46:15.710192+00:00"}