{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:L2P3NBOTEPTMFE5TDWIGOQA33Z","short_pith_number":"pith:L2P3NBOT","schema_version":"1.0","canonical_sha256":"5e9fb685d323e6c293b31d9067401bde70fde23f1292e13d2ca526b7ada9008e","source":{"kind":"arxiv","id":"2203.08444","version":1},"attestation_state":"computed","paper":{"title":"Panini-Net: GAN Prior Based Degradation-Aware Feature Interpolation for Face Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Zhang, Yinhuai Wang, Yujie Hu","submitted_at":"2022-03-16T07:41:07Z","abstract_excerpt":"Emerging high-quality face restoration (FR) methods often utilize pre-trained GAN models (\\textit{i.e.}, StyleGAN2) as GAN Prior. However, these methods usually struggle to balance realness and fidelity when facing various degradation levels. Besides, there is still a noticeable visual quality gap compared with pre-trained GAN models. In this paper, we propose a novel GAN Prior based degradation-aware feature interpolation network, dubbed Panini-Net, for FR tasks by explicitly learning the abstract representations to distinguish various degradations. Specifically, an unsupervised degradation r"},"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":"2203.08444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-16T07:41:07Z","cross_cats_sorted":[],"title_canon_sha256":"5e75572f211a85305165b45ff6e0584bbe3783741cd1597b9ff58b10a38b9700","abstract_canon_sha256":"04ae8f55218682444f218588478e4aa153ec66a1220daa71626318cb9c724068"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:44.719918Z","signature_b64":"Uo3vRIXc2Q8h/laUINJ8OJGi5f1Dw868O6xHShkbx1xcfjA+nng2pkjOkARtoP7A1N4J561/VvRQqq1/AvjMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e9fb685d323e6c293b31d9067401bde70fde23f1292e13d2ca526b7ada9008e","last_reissued_at":"2026-07-05T04:05:44.719439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:44.719439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Panini-Net: GAN Prior Based Degradation-Aware Feature Interpolation for Face Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Zhang, Yinhuai Wang, Yujie Hu","submitted_at":"2022-03-16T07:41:07Z","abstract_excerpt":"Emerging high-quality face restoration (FR) methods often utilize pre-trained GAN models (\\textit{i.e.}, StyleGAN2) as GAN Prior. However, these methods usually struggle to balance realness and fidelity when facing various degradation levels. Besides, there is still a noticeable visual quality gap compared with pre-trained GAN models. In this paper, we propose a novel GAN Prior based degradation-aware feature interpolation network, dubbed Panini-Net, for FR tasks by explicitly learning the abstract representations to distinguish various degradations. Specifically, an unsupervised degradation r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08444","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/2203.08444/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":"2203.08444","created_at":"2026-07-05T04:05:44.719514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.08444v1","created_at":"2026-07-05T04:05:44.719514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08444","created_at":"2026-07-05T04:05:44.719514+00:00"},{"alias_kind":"pith_short_12","alias_value":"L2P3NBOTEPTM","created_at":"2026-07-05T04:05:44.719514+00:00"},{"alias_kind":"pith_short_16","alias_value":"L2P3NBOTEPTMFE5T","created_at":"2026-07-05T04:05:44.719514+00:00"},{"alias_kind":"pith_short_8","alias_value":"L2P3NBOT","created_at":"2026-07-05T04:05:44.719514+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/L2P3NBOTEPTMFE5TDWIGOQA33Z","json":"https://pith.science/pith/L2P3NBOTEPTMFE5TDWIGOQA33Z.json","graph_json":"https://pith.science/api/pith-number/L2P3NBOTEPTMFE5TDWIGOQA33Z/graph.json","events_json":"https://pith.science/api/pith-number/L2P3NBOTEPTMFE5TDWIGOQA33Z/events.json","paper":"https://pith.science/paper/L2P3NBOT"},"agent_actions":{"view_html":"https://pith.science/pith/L2P3NBOTEPTMFE5TDWIGOQA33Z","download_json":"https://pith.science/pith/L2P3NBOTEPTMFE5TDWIGOQA33Z.json","view_paper":"https://pith.science/paper/L2P3NBOT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.08444&json=true","fetch_graph":"https://pith.science/api/pith-number/L2P3NBOTEPTMFE5TDWIGOQA33Z/graph.json","fetch_events":"https://pith.science/api/pith-number/L2P3NBOTEPTMFE5TDWIGOQA33Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L2P3NBOTEPTMFE5TDWIGOQA33Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L2P3NBOTEPTMFE5TDWIGOQA33Z/action/storage_attestation","attest_author":"https://pith.science/pith/L2P3NBOTEPTMFE5TDWIGOQA33Z/action/author_attestation","sign_citation":"https://pith.science/pith/L2P3NBOTEPTMFE5TDWIGOQA33Z/action/citation_signature","submit_replication":"https://pith.science/pith/L2P3NBOTEPTMFE5TDWIGOQA33Z/action/replication_record"}},"created_at":"2026-07-05T04:05:44.719514+00:00","updated_at":"2026-07-05T04:05:44.719514+00:00"}