{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VJMGOASSHEX54W6F7KSEK6XMLY","short_pith_number":"pith:VJMGOASS","schema_version":"1.0","canonical_sha256":"aa58670252392fde5bc5faa4457aec5e112b8c7fba6208d49196e59ba9eead39","source":{"kind":"arxiv","id":"2108.10257","version":1},"attestation_state":"computed","paper":{"title":"SwinIR: Image Restoration Using Swin Transformer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Guolei Sun, Jiezhang Cao, Jingyun Liang, Kai Zhang, Luc Van Gool, Radu Timofte","submitted_at":"2021-08-23T15:55:32Z","abstract_excerpt":"Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from low-quality images (e.g., downscaled, noisy and compressed images). While state-of-the-art image restoration methods are based on convolutional neural networks, few attempts have been made with Transformers which show impressive performance on high-level vision tasks. In this paper, we propose a strong baseline model SwinIR for image restoration based on the Swin Transformer. SwinIR consists of three parts: shallow feature extraction, deep feature extraction and high-quality image recons"},"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":"2108.10257","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2021-08-23T15:55:32Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"89479c191e9943f82405a3d92b4dfa93016018419858e479cbbc61920e75b970","abstract_canon_sha256":"246feb00af64ec23b15d6f80c6185214d66a572e89da0a8a28dd669ed95e2006"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:08:03.831248Z","signature_b64":"1cdWSNGyMnI451CkqKsKr3lfbzg8mGQa1ax4J5Sgt1CFfC3GnFzXx7rsMQNnh3zY53iZqv7vjSjL7dNAymURBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa58670252392fde5bc5faa4457aec5e112b8c7fba6208d49196e59ba9eead39","last_reissued_at":"2026-07-05T03:08:03.830755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:08:03.830755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SwinIR: Image Restoration Using Swin Transformer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Guolei Sun, Jiezhang Cao, Jingyun Liang, Kai Zhang, Luc Van Gool, Radu Timofte","submitted_at":"2021-08-23T15:55:32Z","abstract_excerpt":"Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from low-quality images (e.g., downscaled, noisy and compressed images). While state-of-the-art image restoration methods are based on convolutional neural networks, few attempts have been made with Transformers which show impressive performance on high-level vision tasks. In this paper, we propose a strong baseline model SwinIR for image restoration based on the Swin Transformer. SwinIR consists of three parts: shallow feature extraction, deep feature extraction and high-quality image recons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.10257","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/2108.10257/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":"2108.10257","created_at":"2026-07-05T03:08:03.830814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.10257v1","created_at":"2026-07-05T03:08:03.830814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.10257","created_at":"2026-07-05T03:08:03.830814+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJMGOASSHEX5","created_at":"2026-07-05T03:08:03.830814+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJMGOASSHEX54W6F","created_at":"2026-07-05T03:08:03.830814+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJMGOASS","created_at":"2026-07-05T03:08:03.830814+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22353","citing_title":"Interest Entanglement: The Hidden Barrier to Blind Super-Resolution Optimization","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14891","citing_title":"Hierarchical Image Tokenization for Multi-Scale Image Super Resolution","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19512","citing_title":"Defining Robust Ultrasound Quality Metrics via an Ultrasound Foundation Model","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21244","citing_title":"SR-Ground: Image Quality Grounding for Super-Resolved Content","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22414","citing_title":"LucidFlux: Caption-Free Photo-Realistic Image Restoration via a Large-Scale Diffusion Transformer","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19512","citing_title":"Defining Robust Ultrasound Quality Metrics via an Ultrasound Foundation Model","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10081","citing_title":"MatRes: Zero-Shot Test-Time Model Adaptation for Simultaneous Matching and Restoration","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJMGOASSHEX54W6F7KSEK6XMLY","json":"https://pith.science/pith/VJMGOASSHEX54W6F7KSEK6XMLY.json","graph_json":"https://pith.science/api/pith-number/VJMGOASSHEX54W6F7KSEK6XMLY/graph.json","events_json":"https://pith.science/api/pith-number/VJMGOASSHEX54W6F7KSEK6XMLY/events.json","paper":"https://pith.science/paper/VJMGOASS"},"agent_actions":{"view_html":"https://pith.science/pith/VJMGOASSHEX54W6F7KSEK6XMLY","download_json":"https://pith.science/pith/VJMGOASSHEX54W6F7KSEK6XMLY.json","view_paper":"https://pith.science/paper/VJMGOASS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.10257&json=true","fetch_graph":"https://pith.science/api/pith-number/VJMGOASSHEX54W6F7KSEK6XMLY/graph.json","fetch_events":"https://pith.science/api/pith-number/VJMGOASSHEX54W6F7KSEK6XMLY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJMGOASSHEX54W6F7KSEK6XMLY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJMGOASSHEX54W6F7KSEK6XMLY/action/storage_attestation","attest_author":"https://pith.science/pith/VJMGOASSHEX54W6F7KSEK6XMLY/action/author_attestation","sign_citation":"https://pith.science/pith/VJMGOASSHEX54W6F7KSEK6XMLY/action/citation_signature","submit_replication":"https://pith.science/pith/VJMGOASSHEX54W6F7KSEK6XMLY/action/replication_record"}},"created_at":"2026-07-05T03:08:03.830814+00:00","updated_at":"2026-07-05T03:08:03.830814+00:00"}