{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LNNJMTXCA73B7J5MEAW365OHLS","short_pith_number":"pith:LNNJMTXC","schema_version":"1.0","canonical_sha256":"5b5a964ee207f61fa7ac202dbf75c75cb0b073f9a8bd6716fcaa875dcf682037","source":{"kind":"arxiv","id":"2506.00564","version":1},"attestation_state":"computed","paper":{"title":"Image Restoration Learning via Noisy Supervision in the Fourier Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Edmund Y. Lam, Haosen Liu, Jiahao Liu, Shan Tan","submitted_at":"2025-05-31T13:43:56Z","abstract_excerpt":"Noisy supervision refers to supervising image restoration learning with noisy targets. It can alleviate the data collection burden and enhance the practical applicability of deep learning techniques. However, existing methods suffer from two key drawbacks. Firstly, they are ineffective in handling spatially correlated noise commonly observed in practical applications such as low-light imaging and remote sensing. Secondly, they rely on pixel-wise loss functions that only provide limited supervision information. This work addresses these challenges by leveraging the Fourier domain. We highlight "},"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":"2506.00564","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-05-31T13:43:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1a89ccdf1bb98f22c0dcc39ad5bc292d32a4c498f14fcfeaa1445a7edb1e75f9","abstract_canon_sha256":"c394b81edd07f1a866bea038fae19f641d46fb623f0b9619f1e68a996bacfa78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:36.971598Z","signature_b64":"slkXEnownUib5gBmpU02y8ssI+PKeEfa/iGxf3yTDaSkwuz4g1AvpYV9xMqlT9hXyQkg3dzWsuJcmWG0sdEbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b5a964ee207f61fa7ac202dbf75c75cb0b073f9a8bd6716fcaa875dcf682037","last_reissued_at":"2026-07-05T11:13:36.971129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:36.971129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Restoration Learning via Noisy Supervision in the Fourier Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Edmund Y. Lam, Haosen Liu, Jiahao Liu, Shan Tan","submitted_at":"2025-05-31T13:43:56Z","abstract_excerpt":"Noisy supervision refers to supervising image restoration learning with noisy targets. It can alleviate the data collection burden and enhance the practical applicability of deep learning techniques. However, existing methods suffer from two key drawbacks. Firstly, they are ineffective in handling spatially correlated noise commonly observed in practical applications such as low-light imaging and remote sensing. Secondly, they rely on pixel-wise loss functions that only provide limited supervision information. This work addresses these challenges by leveraging the Fourier domain. We highlight "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00564","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/2506.00564/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":"2506.00564","created_at":"2026-07-05T11:13:36.971183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00564v1","created_at":"2026-07-05T11:13:36.971183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00564","created_at":"2026-07-05T11:13:36.971183+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNNJMTXCA73B","created_at":"2026-07-05T11:13:36.971183+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNNJMTXCA73B7J5M","created_at":"2026-07-05T11:13:36.971183+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNNJMTXC","created_at":"2026-07-05T11:13:36.971183+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/LNNJMTXCA73B7J5MEAW365OHLS","json":"https://pith.science/pith/LNNJMTXCA73B7J5MEAW365OHLS.json","graph_json":"https://pith.science/api/pith-number/LNNJMTXCA73B7J5MEAW365OHLS/graph.json","events_json":"https://pith.science/api/pith-number/LNNJMTXCA73B7J5MEAW365OHLS/events.json","paper":"https://pith.science/paper/LNNJMTXC"},"agent_actions":{"view_html":"https://pith.science/pith/LNNJMTXCA73B7J5MEAW365OHLS","download_json":"https://pith.science/pith/LNNJMTXCA73B7J5MEAW365OHLS.json","view_paper":"https://pith.science/paper/LNNJMTXC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00564&json=true","fetch_graph":"https://pith.science/api/pith-number/LNNJMTXCA73B7J5MEAW365OHLS/graph.json","fetch_events":"https://pith.science/api/pith-number/LNNJMTXCA73B7J5MEAW365OHLS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNNJMTXCA73B7J5MEAW365OHLS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNNJMTXCA73B7J5MEAW365OHLS/action/storage_attestation","attest_author":"https://pith.science/pith/LNNJMTXCA73B7J5MEAW365OHLS/action/author_attestation","sign_citation":"https://pith.science/pith/LNNJMTXCA73B7J5MEAW365OHLS/action/citation_signature","submit_replication":"https://pith.science/pith/LNNJMTXCA73B7J5MEAW365OHLS/action/replication_record"}},"created_at":"2026-07-05T11:13:36.971183+00:00","updated_at":"2026-07-05T11:13:36.971183+00:00"}