{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NW6PVDBCDK5GYYOWJ5XHCT3QD3","short_pith_number":"pith:NW6PVDBC","schema_version":"1.0","canonical_sha256":"6dbcfa8c221aba6c61d64f6e714f701ee5146d8227026e69f75a30d0af5691f2","source":{"kind":"arxiv","id":"2105.06070","version":1},"attestation_state":"computed","paper":{"title":"GAN Prior Embedded Network for Blind Face Restoration in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"2) ((1) DAMO Academy, (2) Department of Computing, Alibaba Group, Lei Zhang (1, Peiran Ren (1), Tao Yang (1), The Hong Kong Polytechnic University), Xuansong Xie (1)","submitted_at":"2021-05-13T04:14:00Z","abstract_excerpt":"Blind face restoration (BFR) from severely degraded face images in the wild is a very challenging problem. Due to the high illness of the problem and the complex unknown degradation, directly training a deep neural network (DNN) usually cannot lead to acceptable results. Existing generative adversarial network (GAN) based methods can produce better results but tend to generate over-smoothed restorations. In this work, we propose a new method by first learning a GAN for high-quality face image generation and embedding it into a U-shaped DNN as a prior decoder, then fine-tuning the GAN prior emb"},"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":"2105.06070","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-13T04:14:00Z","cross_cats_sorted":[],"title_canon_sha256":"098a35671f0ce210087a66381fd8ccad628d6a2e3e2f27840b073e030bd9d533","abstract_canon_sha256":"1362571cd8429dc2a5979d1c62afb176d33a894d062eedbe2f243113ae20933c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:03.959618Z","signature_b64":"zuyGiUIYcGY7FBLkkKF2juhFLkIIrJCd96s0vpUf9CSGz4I5T+6t4INUQ/qU+V6S9AhKKDXv6Vo3bmyvhyk/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dbcfa8c221aba6c61d64f6e714f701ee5146d8227026e69f75a30d0af5691f2","last_reissued_at":"2026-07-05T02:40:03.959254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:03.959254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GAN Prior Embedded Network for Blind Face Restoration in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"2) ((1) DAMO Academy, (2) Department of Computing, Alibaba Group, Lei Zhang (1, Peiran Ren (1), Tao Yang (1), The Hong Kong Polytechnic University), Xuansong Xie (1)","submitted_at":"2021-05-13T04:14:00Z","abstract_excerpt":"Blind face restoration (BFR) from severely degraded face images in the wild is a very challenging problem. Due to the high illness of the problem and the complex unknown degradation, directly training a deep neural network (DNN) usually cannot lead to acceptable results. Existing generative adversarial network (GAN) based methods can produce better results but tend to generate over-smoothed restorations. In this work, we propose a new method by first learning a GAN for high-quality face image generation and embedding it into a U-shaped DNN as a prior decoder, then fine-tuning the GAN prior emb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.06070","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/2105.06070/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":"2105.06070","created_at":"2026-07-05T02:40:03.959320+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.06070v1","created_at":"2026-07-05T02:40:03.959320+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.06070","created_at":"2026-07-05T02:40:03.959320+00:00"},{"alias_kind":"pith_short_12","alias_value":"NW6PVDBCDK5G","created_at":"2026-07-05T02:40:03.959320+00:00"},{"alias_kind":"pith_short_16","alias_value":"NW6PVDBCDK5GYYOW","created_at":"2026-07-05T02:40:03.959320+00:00"},{"alias_kind":"pith_short_8","alias_value":"NW6PVDBC","created_at":"2026-07-05T02:40:03.959320+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NW6PVDBCDK5GYYOWJ5XHCT3QD3","json":"https://pith.science/pith/NW6PVDBCDK5GYYOWJ5XHCT3QD3.json","graph_json":"https://pith.science/api/pith-number/NW6PVDBCDK5GYYOWJ5XHCT3QD3/graph.json","events_json":"https://pith.science/api/pith-number/NW6PVDBCDK5GYYOWJ5XHCT3QD3/events.json","paper":"https://pith.science/paper/NW6PVDBC"},"agent_actions":{"view_html":"https://pith.science/pith/NW6PVDBCDK5GYYOWJ5XHCT3QD3","download_json":"https://pith.science/pith/NW6PVDBCDK5GYYOWJ5XHCT3QD3.json","view_paper":"https://pith.science/paper/NW6PVDBC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.06070&json=true","fetch_graph":"https://pith.science/api/pith-number/NW6PVDBCDK5GYYOWJ5XHCT3QD3/graph.json","fetch_events":"https://pith.science/api/pith-number/NW6PVDBCDK5GYYOWJ5XHCT3QD3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NW6PVDBCDK5GYYOWJ5XHCT3QD3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NW6PVDBCDK5GYYOWJ5XHCT3QD3/action/storage_attestation","attest_author":"https://pith.science/pith/NW6PVDBCDK5GYYOWJ5XHCT3QD3/action/author_attestation","sign_citation":"https://pith.science/pith/NW6PVDBCDK5GYYOWJ5XHCT3QD3/action/citation_signature","submit_replication":"https://pith.science/pith/NW6PVDBCDK5GYYOWJ5XHCT3QD3/action/replication_record"}},"created_at":"2026-07-05T02:40:03.959320+00:00","updated_at":"2026-07-05T02:40:03.959320+00:00"}