{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EULQEUEPSZUEKKE4JHTIXGAMKY","short_pith_number":"pith:EULQEUEP","schema_version":"1.0","canonical_sha256":"251702508f966845289c49e68b980c5609704f45bcf017ddae5d3da6f1aaf364","source":{"kind":"arxiv","id":"1809.00219","version":2},"attestation_state":"computed","paper":{"title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Dong, Chen Change Loy, Jinjin Gu, Ke Yu, Shixiang Wu, Xiaoou Tang, Xintao Wang, Yihao Liu, Yu Qiao","submitted_at":"2018-09-01T16:21:03Z","abstract_excerpt":"The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied with unpleasant artifacts. To further enhance the visual quality, we thoroughly study three key components of SRGAN - network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN). In particular, we introduce the Residual-in-Residual Dense Block (RRDB) without batch normalization as the basic network building unit. Mo"},"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":"1809.00219","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-01T16:21:03Z","cross_cats_sorted":[],"title_canon_sha256":"e19c1bb12c48db9a29c80379f6ce868704b1583dd7029ae708e710cfd71007fd","abstract_canon_sha256":"3934b032d78615995c200854ffc8d0a71644b6ec42d7f368a15ab6fbad744374"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:36.867222Z","signature_b64":"f7Uq3UX5nbaSrqViav31ik1KaVsfT9shKJkS1twdDm6LgC8anqhajPa9W4BXXMDgPuJGRM0Z2kUevSsc8+qRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"251702508f966845289c49e68b980c5609704f45bcf017ddae5d3da6f1aaf364","last_reissued_at":"2026-05-18T00:05:36.866806Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:36.866806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Dong, Chen Change Loy, Jinjin Gu, Ke Yu, Shixiang Wu, Xiaoou Tang, Xintao Wang, Yihao Liu, Yu Qiao","submitted_at":"2018-09-01T16:21:03Z","abstract_excerpt":"The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied with unpleasant artifacts. To further enhance the visual quality, we thoroughly study three key components of SRGAN - network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN). In particular, we introduce the Residual-in-Residual Dense Block (RRDB) without batch normalization as the basic network building unit. Mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.00219","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":""},"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":"1809.00219","created_at":"2026-05-18T00:05:36.866877+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.00219v2","created_at":"2026-05-18T00:05:36.866877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.00219","created_at":"2026-05-18T00:05:36.866877+00:00"},{"alias_kind":"pith_short_12","alias_value":"EULQEUEPSZUE","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EULQEUEPSZUEKKE4","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EULQEUEP","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08373","citing_title":"NeuroGAN-3D: Enhancing Intrinsic Functional Brain Networks via High-Fidelity 3D Generative Super-Resolution","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00652","citing_title":"D-SHIFT: Transferring High Spatial Information from GRACE Monthly TWSA Mascon to Daily Products Using Generative Adversarial Networks","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00367","citing_title":"Flow matching for Sentinel-2 super-resolution: implementation, application, and implications","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EULQEUEPSZUEKKE4JHTIXGAMKY","json":"https://pith.science/pith/EULQEUEPSZUEKKE4JHTIXGAMKY.json","graph_json":"https://pith.science/api/pith-number/EULQEUEPSZUEKKE4JHTIXGAMKY/graph.json","events_json":"https://pith.science/api/pith-number/EULQEUEPSZUEKKE4JHTIXGAMKY/events.json","paper":"https://pith.science/paper/EULQEUEP"},"agent_actions":{"view_html":"https://pith.science/pith/EULQEUEPSZUEKKE4JHTIXGAMKY","download_json":"https://pith.science/pith/EULQEUEPSZUEKKE4JHTIXGAMKY.json","view_paper":"https://pith.science/paper/EULQEUEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.00219&json=true","fetch_graph":"https://pith.science/api/pith-number/EULQEUEPSZUEKKE4JHTIXGAMKY/graph.json","fetch_events":"https://pith.science/api/pith-number/EULQEUEPSZUEKKE4JHTIXGAMKY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EULQEUEPSZUEKKE4JHTIXGAMKY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EULQEUEPSZUEKKE4JHTIXGAMKY/action/storage_attestation","attest_author":"https://pith.science/pith/EULQEUEPSZUEKKE4JHTIXGAMKY/action/author_attestation","sign_citation":"https://pith.science/pith/EULQEUEPSZUEKKE4JHTIXGAMKY/action/citation_signature","submit_replication":"https://pith.science/pith/EULQEUEPSZUEKKE4JHTIXGAMKY/action/replication_record"}},"created_at":"2026-05-18T00:05:36.866877+00:00","updated_at":"2026-05-18T00:05:36.866877+00:00"}