{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6WNAGR4PBA76DHLBVANKKOVJ6I","short_pith_number":"pith:6WNAGR4P","schema_version":"1.0","canonical_sha256":"f59a03478f083fe19d61a81aa53aa9f21018851a333e9579b99fdedd37335d68","source":{"kind":"arxiv","id":"2107.10833","version":2},"attestation_state":"computed","paper":{"title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Chao Dong, Liangbin Xie, Xintao Wang, Ying Shan","submitted_at":"2021-07-22T17:43:24Z","abstract_excerpt":"Though many attempts have been made in blind super-resolution to restore low-resolution images with unknown and complex degradations, they are still far from addressing general real-world degraded images. In this work, we extend the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data. Specifically, a high-order degradation modeling process is introduced to better simulate complex real-world degradations. We also consider the common ringing and overshoot artifacts in the synthesis process. In addition, we employ a U-Net discrim"},"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":"2107.10833","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2021-07-22T17:43:24Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"12eb01b22360874c07e327edcc146e9178bd3d2cde3d78eb08d5c4c68fc80dff","abstract_canon_sha256":"63d9ff8e13efed75097b8d601f8632e54e1b1aba9445e655b3aa910cb0be3c7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:32.895291Z","signature_b64":"fpxq0JwQFy+9vUgvR7kBNu1wgNKaXVTkzkdaH3PHnSPOK9uK/M2tlrjTu1YzZcNn03PykILA/7jE0NtpnJRjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f59a03478f083fe19d61a81aa53aa9f21018851a333e9579b99fdedd37335d68","last_reissued_at":"2026-07-05T03:06:32.894818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:32.894818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Chao Dong, Liangbin Xie, Xintao Wang, Ying Shan","submitted_at":"2021-07-22T17:43:24Z","abstract_excerpt":"Though many attempts have been made in blind super-resolution to restore low-resolution images with unknown and complex degradations, they are still far from addressing general real-world degraded images. In this work, we extend the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data. Specifically, a high-order degradation modeling process is introduced to better simulate complex real-world degradations. We also consider the common ringing and overshoot artifacts in the synthesis process. In addition, we employ a U-Net discrim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.10833","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/2107.10833/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":"2107.10833","created_at":"2026-07-05T03:06:32.894867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.10833v2","created_at":"2026-07-05T03:06:32.894867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.10833","created_at":"2026-07-05T03:06:32.894867+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WNAGR4PBA76","created_at":"2026-07-05T03:06:32.894867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WNAGR4PBA76DHLB","created_at":"2026-07-05T03:06:32.894867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WNAGR4P","created_at":"2026-07-05T03:06:32.894867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00367","citing_title":"Flow matching for Sentinel-2 super-resolution: implementation, application, and implications","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6WNAGR4PBA76DHLBVANKKOVJ6I","json":"https://pith.science/pith/6WNAGR4PBA76DHLBVANKKOVJ6I.json","graph_json":"https://pith.science/api/pith-number/6WNAGR4PBA76DHLBVANKKOVJ6I/graph.json","events_json":"https://pith.science/api/pith-number/6WNAGR4PBA76DHLBVANKKOVJ6I/events.json","paper":"https://pith.science/paper/6WNAGR4P"},"agent_actions":{"view_html":"https://pith.science/pith/6WNAGR4PBA76DHLBVANKKOVJ6I","download_json":"https://pith.science/pith/6WNAGR4PBA76DHLBVANKKOVJ6I.json","view_paper":"https://pith.science/paper/6WNAGR4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.10833&json=true","fetch_graph":"https://pith.science/api/pith-number/6WNAGR4PBA76DHLBVANKKOVJ6I/graph.json","fetch_events":"https://pith.science/api/pith-number/6WNAGR4PBA76DHLBVANKKOVJ6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WNAGR4PBA76DHLBVANKKOVJ6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WNAGR4PBA76DHLBVANKKOVJ6I/action/storage_attestation","attest_author":"https://pith.science/pith/6WNAGR4PBA76DHLBVANKKOVJ6I/action/author_attestation","sign_citation":"https://pith.science/pith/6WNAGR4PBA76DHLBVANKKOVJ6I/action/citation_signature","submit_replication":"https://pith.science/pith/6WNAGR4PBA76DHLBVANKKOVJ6I/action/replication_record"}},"created_at":"2026-07-05T03:06:32.894867+00:00","updated_at":"2026-07-05T03:06:32.894867+00:00"}