{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3L3PJJ5H27ZYURKF2H2ETJAJP3","short_pith_number":"pith:3L3PJJ5H","schema_version":"1.0","canonical_sha256":"daf6f4a7a7d7f38a4545d1f449a4097edc0a8d616d0be56c6b72087239021af1","source":{"kind":"arxiv","id":"2208.11247","version":3},"attestation_state":"computed","paper":{"title":"SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dafeng Zhang, Feiyu Huang, Shizhuo Liu, Xiaobing Wang, Zhezhu Jin","submitted_at":"2022-08-24T01:04:47Z","abstract_excerpt":"Transformer-based methods have achieved impressive image restoration performance due to their capacities to model long-range dependency compared to CNN-based methods. However, advances like SwinIR adopts the window-based and local attention strategy to balance the performance and computational overhead, which restricts employing large receptive fields to capture global information and establish long dependencies in the early layers. To further improve the efficiency of capturing global information, in this work, we propose SwinFIR to extend SwinIR by replacing Fast Fourier Convolution (FFC) co"},"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":"2208.11247","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-24T01:04:47Z","cross_cats_sorted":[],"title_canon_sha256":"4309bb3fb1a601320cfc4eabb45a375240ff5b37f876e3d53ce14951a6166b62","abstract_canon_sha256":"e3b087693e7bb06e7b8f9db983c9947e2cefbee28c46f29844bee7e1e7e04c33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:30.996856Z","signature_b64":"6v+coBO6EWZjqBI/sX22isp//8OXvZwCo8ThSQfnRm99ig7uk9UZdbMscPDIssvlJ3onDvjhvIfYQb2kf70CBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"daf6f4a7a7d7f38a4545d1f449a4097edc0a8d616d0be56c6b72087239021af1","last_reissued_at":"2026-07-05T06:53:30.996411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:30.996411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dafeng Zhang, Feiyu Huang, Shizhuo Liu, Xiaobing Wang, Zhezhu Jin","submitted_at":"2022-08-24T01:04:47Z","abstract_excerpt":"Transformer-based methods have achieved impressive image restoration performance due to their capacities to model long-range dependency compared to CNN-based methods. However, advances like SwinIR adopts the window-based and local attention strategy to balance the performance and computational overhead, which restricts employing large receptive fields to capture global information and establish long dependencies in the early layers. To further improve the efficiency of capturing global information, in this work, we propose SwinFIR to extend SwinIR by replacing Fast Fourier Convolution (FFC) co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11247","kind":"arxiv","version":3},"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/2208.11247/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":"2208.11247","created_at":"2026-07-05T06:53:30.996472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.11247v3","created_at":"2026-07-05T06:53:30.996472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11247","created_at":"2026-07-05T06:53:30.996472+00:00"},{"alias_kind":"pith_short_12","alias_value":"3L3PJJ5H27ZY","created_at":"2026-07-05T06:53:30.996472+00:00"},{"alias_kind":"pith_short_16","alias_value":"3L3PJJ5H27ZYURKF","created_at":"2026-07-05T06:53:30.996472+00:00"},{"alias_kind":"pith_short_8","alias_value":"3L3PJJ5H","created_at":"2026-07-05T06:53:30.996472+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31363","citing_title":"Language-Assisted Super-Resolution from Real-World Low-Resolution Patches","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31363","citing_title":"Language-Assisted Super-Resolution from Real-World Low-Resolution Patches","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22208","citing_title":"EvoIR-Agent: Self-Evolving Image Restoration Agentic System via Experience-Driven Learning","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22208","citing_title":"EvoIR-Agent: Self-Evolving Image Restoration Agentic System via Experience-Driven Learning","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22506","citing_title":"ICPR 2026 Competition on Low-Resolution License Plate Recognition","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3L3PJJ5H27ZYURKF2H2ETJAJP3","json":"https://pith.science/pith/3L3PJJ5H27ZYURKF2H2ETJAJP3.json","graph_json":"https://pith.science/api/pith-number/3L3PJJ5H27ZYURKF2H2ETJAJP3/graph.json","events_json":"https://pith.science/api/pith-number/3L3PJJ5H27ZYURKF2H2ETJAJP3/events.json","paper":"https://pith.science/paper/3L3PJJ5H"},"agent_actions":{"view_html":"https://pith.science/pith/3L3PJJ5H27ZYURKF2H2ETJAJP3","download_json":"https://pith.science/pith/3L3PJJ5H27ZYURKF2H2ETJAJP3.json","view_paper":"https://pith.science/paper/3L3PJJ5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.11247&json=true","fetch_graph":"https://pith.science/api/pith-number/3L3PJJ5H27ZYURKF2H2ETJAJP3/graph.json","fetch_events":"https://pith.science/api/pith-number/3L3PJJ5H27ZYURKF2H2ETJAJP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3L3PJJ5H27ZYURKF2H2ETJAJP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3L3PJJ5H27ZYURKF2H2ETJAJP3/action/storage_attestation","attest_author":"https://pith.science/pith/3L3PJJ5H27ZYURKF2H2ETJAJP3/action/author_attestation","sign_citation":"https://pith.science/pith/3L3PJJ5H27ZYURKF2H2ETJAJP3/action/citation_signature","submit_replication":"https://pith.science/pith/3L3PJJ5H27ZYURKF2H2ETJAJP3/action/replication_record"}},"created_at":"2026-07-05T06:53:30.996472+00:00","updated_at":"2026-07-05T06:53:30.996472+00:00"}