{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FQOTCVTDXP55XMGEHD3JDTSCXG","short_pith_number":"pith:FQOTCVTD","schema_version":"1.0","canonical_sha256":"2c1d315663bbfbdbb0c438f691ce42b9a30ced81ae939bfa9b9bc3ba2d5099a1","source":{"kind":"arxiv","id":"2507.20291","version":1},"attestation_state":"computed","paper":{"title":"Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Lingchen Sun, Qiaosi Yi, Rongyuan Wu, Shuai Li, Yuhui Wu","submitted_at":"2025-07-27T14:11:29Z","abstract_excerpt":"Impressive results on real-world image super-resolution (Real-ISR) have been achieved by employing pre-trained stable diffusion (SD) models. However, one critical issue of such methods lies in their poor reconstruction of image fine structures, such as small characters and textures, due to the aggressive resolution reduction of the VAE (eg., 8$\\times$ downsampling) in the SD model. One solution is to employ a VAE with a lower downsampling rate for diffusion; however, adapting its latent features with the pre-trained UNet while mitigating the increased computational cost poses new challenges. T"},"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":"2507.20291","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-27T14:11:29Z","cross_cats_sorted":[],"title_canon_sha256":"ecb2e4e59b9ba741ac04fe5c7cfa203de4868117b28f11a20e875b73c97483df","abstract_canon_sha256":"e9ace3325267f10a18c9dcf5c36e308efd5d648d78a4f432280db1f51c7b2ac8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:16.582252Z","signature_b64":"uGP62LrLmsLIEw8Is3VlchpEGJXd8o9cbnSkmig0yrpEi91IhnQpQiiYaq6bdGRz9J+ocTsudn1geQ2h3aVxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c1d315663bbfbdbb0c438f691ce42b9a30ced81ae939bfa9b9bc3ba2d5099a1","last_reissued_at":"2026-07-05T11:44:16.581661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:16.581661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Lingchen Sun, Qiaosi Yi, Rongyuan Wu, Shuai Li, Yuhui Wu","submitted_at":"2025-07-27T14:11:29Z","abstract_excerpt":"Impressive results on real-world image super-resolution (Real-ISR) have been achieved by employing pre-trained stable diffusion (SD) models. However, one critical issue of such methods lies in their poor reconstruction of image fine structures, such as small characters and textures, due to the aggressive resolution reduction of the VAE (eg., 8$\\times$ downsampling) in the SD model. One solution is to employ a VAE with a lower downsampling rate for diffusion; however, adapting its latent features with the pre-trained UNet while mitigating the increased computational cost poses new challenges. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20291","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/2507.20291/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":"2507.20291","created_at":"2026-07-05T11:44:16.581738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20291v1","created_at":"2026-07-05T11:44:16.581738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20291","created_at":"2026-07-05T11:44:16.581738+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQOTCVTDXP55","created_at":"2026-07-05T11:44:16.581738+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQOTCVTDXP55XMGE","created_at":"2026-07-05T11:44:16.581738+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQOTCVTD","created_at":"2026-07-05T11:44:16.581738+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.03225","citing_title":"VOSR: A Vision-Only Generative Model for Image Super-Resolution","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQOTCVTDXP55XMGEHD3JDTSCXG","json":"https://pith.science/pith/FQOTCVTDXP55XMGEHD3JDTSCXG.json","graph_json":"https://pith.science/api/pith-number/FQOTCVTDXP55XMGEHD3JDTSCXG/graph.json","events_json":"https://pith.science/api/pith-number/FQOTCVTDXP55XMGEHD3JDTSCXG/events.json","paper":"https://pith.science/paper/FQOTCVTD"},"agent_actions":{"view_html":"https://pith.science/pith/FQOTCVTDXP55XMGEHD3JDTSCXG","download_json":"https://pith.science/pith/FQOTCVTDXP55XMGEHD3JDTSCXG.json","view_paper":"https://pith.science/paper/FQOTCVTD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20291&json=true","fetch_graph":"https://pith.science/api/pith-number/FQOTCVTDXP55XMGEHD3JDTSCXG/graph.json","fetch_events":"https://pith.science/api/pith-number/FQOTCVTDXP55XMGEHD3JDTSCXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQOTCVTDXP55XMGEHD3JDTSCXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQOTCVTDXP55XMGEHD3JDTSCXG/action/storage_attestation","attest_author":"https://pith.science/pith/FQOTCVTDXP55XMGEHD3JDTSCXG/action/author_attestation","sign_citation":"https://pith.science/pith/FQOTCVTDXP55XMGEHD3JDTSCXG/action/citation_signature","submit_replication":"https://pith.science/pith/FQOTCVTDXP55XMGEHD3JDTSCXG/action/replication_record"}},"created_at":"2026-07-05T11:44:16.581738+00:00","updated_at":"2026-07-05T11:44:16.581738+00:00"}