{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DQUIYEH7BM5BVSN65KYNTYKMUQ","short_pith_number":"pith:DQUIYEH7","schema_version":"1.0","canonical_sha256":"1c288c10ff0b3a1ac9beeab0d9e14ca41a1f43c1ed570cb55c75f89343b9f225","source":{"kind":"arxiv","id":"2111.11745","version":2},"attestation_state":"computed","paper":{"title":"Intriguing Findings of Frequency Selection for Image Deblurring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengze Liu, Qingli Li, Wei Shen, Xintian Mao, Yan Wang, Yiming Liu","submitted_at":"2021-11-23T09:40:40Z","abstract_excerpt":"Blur was naturally analyzed in the frequency domain, by estimating the latent sharp image and the blur kernel given a blurry image. Recent progress on image deblurring always designs end-to-end architectures and aims at learning the difference between blurry and sharp image pairs from pixel-level, which inevitably overlooks the importance of blur kernels. This paper reveals an intriguing phenomenon that simply applying ReLU operation on the frequency domain of a blur image followed by inverse Fourier transform, i.e., frequency selection, provides faithful information about the blur pattern (e."},"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":"2111.11745","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-23T09:40:40Z","cross_cats_sorted":[],"title_canon_sha256":"c50226d44955cf6acec727a24c7297fc6584cea9d3dccf336d8cc73a0003f5c6","abstract_canon_sha256":"f6fcacd7d39292d84a4a3f280d3b7ea8e6c22aa92396063a5fc330fdc359ecd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:20:09.112070Z","signature_b64":"4P0j7S4pdkraWeXOiEaGO3Q+Xm1SfB+Ve0fmTafyfH3u6pJ3vXL7rUytxxTnzqWcllxoEKHMYDPnM65VSvdqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c288c10ff0b3a1ac9beeab0d9e14ca41a1f43c1ed570cb55c75f89343b9f225","last_reissued_at":"2026-07-05T05:20:09.111518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:20:09.111518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intriguing Findings of Frequency Selection for Image Deblurring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengze Liu, Qingli Li, Wei Shen, Xintian Mao, Yan Wang, Yiming Liu","submitted_at":"2021-11-23T09:40:40Z","abstract_excerpt":"Blur was naturally analyzed in the frequency domain, by estimating the latent sharp image and the blur kernel given a blurry image. Recent progress on image deblurring always designs end-to-end architectures and aims at learning the difference between blurry and sharp image pairs from pixel-level, which inevitably overlooks the importance of blur kernels. This paper reveals an intriguing phenomenon that simply applying ReLU operation on the frequency domain of a blur image followed by inverse Fourier transform, i.e., frequency selection, provides faithful information about the blur pattern (e."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11745","kind":"arxiv","version":2},"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/2111.11745/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":"2111.11745","created_at":"2026-07-05T05:20:09.111577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.11745v2","created_at":"2026-07-05T05:20:09.111577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11745","created_at":"2026-07-05T05:20:09.111577+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQUIYEH7BM5B","created_at":"2026-07-05T05:20:09.111577+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQUIYEH7BM5BVSN6","created_at":"2026-07-05T05:20:09.111577+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQUIYEH7","created_at":"2026-07-05T05:20:09.111577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16157","citing_title":"Fast and Accurate Image Restoration and Generation with Rank Enhanced Linear Attention","ref_index":64,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQUIYEH7BM5BVSN65KYNTYKMUQ","json":"https://pith.science/pith/DQUIYEH7BM5BVSN65KYNTYKMUQ.json","graph_json":"https://pith.science/api/pith-number/DQUIYEH7BM5BVSN65KYNTYKMUQ/graph.json","events_json":"https://pith.science/api/pith-number/DQUIYEH7BM5BVSN65KYNTYKMUQ/events.json","paper":"https://pith.science/paper/DQUIYEH7"},"agent_actions":{"view_html":"https://pith.science/pith/DQUIYEH7BM5BVSN65KYNTYKMUQ","download_json":"https://pith.science/pith/DQUIYEH7BM5BVSN65KYNTYKMUQ.json","view_paper":"https://pith.science/paper/DQUIYEH7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.11745&json=true","fetch_graph":"https://pith.science/api/pith-number/DQUIYEH7BM5BVSN65KYNTYKMUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/DQUIYEH7BM5BVSN65KYNTYKMUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQUIYEH7BM5BVSN65KYNTYKMUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQUIYEH7BM5BVSN65KYNTYKMUQ/action/storage_attestation","attest_author":"https://pith.science/pith/DQUIYEH7BM5BVSN65KYNTYKMUQ/action/author_attestation","sign_citation":"https://pith.science/pith/DQUIYEH7BM5BVSN65KYNTYKMUQ/action/citation_signature","submit_replication":"https://pith.science/pith/DQUIYEH7BM5BVSN65KYNTYKMUQ/action/replication_record"}},"created_at":"2026-07-05T05:20:09.111577+00:00","updated_at":"2026-07-05T05:20:09.111577+00:00"}