{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5GNFAAARZ2252BST5CFE3ATT7U","short_pith_number":"pith:5GNFAAAR","schema_version":"1.0","canonical_sha256":"e99a500011ceb5dd0653e88a4d8273fd2a47d947b592538bfc0a87df552698d1","source":{"kind":"arxiv","id":"2103.14006","version":2},"attestation_state":"computed","paper":{"title":"Designing a Practical Degradation Model for Deep Blind Image Super-Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Jingyun Liang, Kai Zhang, Luc Van Gool, Radu Timofte","submitted_at":"2021-03-25T17:40:53Z","abstract_excerpt":"It is widely acknowledged that single image super-resolution (SISR) methods would not perform well if the assumed degradation model deviates from those in real images. Although several degradation models take additional factors into consideration, such as blur, they are still not effective enough to cover the diverse degradations of real images. To address this issue, this paper proposes to design a more complex but practical degradation model that consists of randomly shuffled blur, downsampling and noise degradations. Specifically, the blur is approximated by two convolutions with isotropic "},"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":"2103.14006","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2021-03-25T17:40:53Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"19136ef1c256a4cf9e70c9c14284a747811569601b936e0926ee9fab4695ce1e","abstract_canon_sha256":"1e4bc6f310a84a1864e9ca43e5c43cd7e2f65bb3aeaf2d538607625a63155bcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:18:40.024836Z","signature_b64":"ROUxFNdvkAnYK7Jn6CnZdrc6HiSkKe4WlrG3S+DDFxNsuJKsl4MVO9w+NjOHz9e1k8+n2Ed6QlfVHakBzpEsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e99a500011ceb5dd0653e88a4d8273fd2a47d947b592538bfc0a87df552698d1","last_reissued_at":"2026-07-05T03:18:40.024283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:18:40.024283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Designing a Practical Degradation Model for Deep Blind Image Super-Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Jingyun Liang, Kai Zhang, Luc Van Gool, Radu Timofte","submitted_at":"2021-03-25T17:40:53Z","abstract_excerpt":"It is widely acknowledged that single image super-resolution (SISR) methods would not perform well if the assumed degradation model deviates from those in real images. Although several degradation models take additional factors into consideration, such as blur, they are still not effective enough to cover the diverse degradations of real images. To address this issue, this paper proposes to design a more complex but practical degradation model that consists of randomly shuffled blur, downsampling and noise degradations. Specifically, the blur is approximated by two convolutions with isotropic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14006","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/2103.14006/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":"2103.14006","created_at":"2026-07-05T03:18:40.024361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.14006v2","created_at":"2026-07-05T03:18:40.024361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14006","created_at":"2026-07-05T03:18:40.024361+00:00"},{"alias_kind":"pith_short_12","alias_value":"5GNFAAARZ225","created_at":"2026-07-05T03:18:40.024361+00:00"},{"alias_kind":"pith_short_16","alias_value":"5GNFAAARZ2252BST","created_at":"2026-07-05T03:18:40.024361+00:00"},{"alias_kind":"pith_short_8","alias_value":"5GNFAAAR","created_at":"2026-07-05T03:18:40.024361+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01157","citing_title":"HiTokSR: A Coarse-to-Fine Tokenizer with Hierarchical Codebooks for High-Fidelity Real-World Image Super-Resolution","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2112.10752","citing_title":"High-Resolution Image Synthesis with Latent Diffusion Models","ref_index":105,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5GNFAAARZ2252BST5CFE3ATT7U","json":"https://pith.science/pith/5GNFAAARZ2252BST5CFE3ATT7U.json","graph_json":"https://pith.science/api/pith-number/5GNFAAARZ2252BST5CFE3ATT7U/graph.json","events_json":"https://pith.science/api/pith-number/5GNFAAARZ2252BST5CFE3ATT7U/events.json","paper":"https://pith.science/paper/5GNFAAAR"},"agent_actions":{"view_html":"https://pith.science/pith/5GNFAAARZ2252BST5CFE3ATT7U","download_json":"https://pith.science/pith/5GNFAAARZ2252BST5CFE3ATT7U.json","view_paper":"https://pith.science/paper/5GNFAAAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.14006&json=true","fetch_graph":"https://pith.science/api/pith-number/5GNFAAARZ2252BST5CFE3ATT7U/graph.json","fetch_events":"https://pith.science/api/pith-number/5GNFAAARZ2252BST5CFE3ATT7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5GNFAAARZ2252BST5CFE3ATT7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5GNFAAARZ2252BST5CFE3ATT7U/action/storage_attestation","attest_author":"https://pith.science/pith/5GNFAAARZ2252BST5CFE3ATT7U/action/author_attestation","sign_citation":"https://pith.science/pith/5GNFAAARZ2252BST5CFE3ATT7U/action/citation_signature","submit_replication":"https://pith.science/pith/5GNFAAARZ2252BST5CFE3ATT7U/action/replication_record"}},"created_at":"2026-07-05T03:18:40.024361+00:00","updated_at":"2026-07-05T03:18:40.024361+00:00"}