{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZGUYYBFQQEY2PSBV3ZPYUMULCD","short_pith_number":"pith:ZGUYYBFQ","schema_version":"1.0","canonical_sha256":"c9a98c04b08131a7c835de5f8a328b10d49a6c5ceffda7854fdbe4ea5039fef6","source":{"kind":"arxiv","id":"2401.00877","version":2},"attestation_state":"computed","paper":{"title":"Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Hongwei Yong, Jie Liang, Lei Zhang, Lingchen Sun, Rongyuan Wu, Zhengqiang Zhang","submitted_at":"2023-12-30T10:22:59Z","abstract_excerpt":"The generative priors of pre-trained latent diffusion models (DMs) have demonstrated great potential to enhance the visual quality of image super-resolution (SR) results. However, the noise sampling process in DMs introduces randomness in the SR outputs, and the generated contents can differ a lot with different noise samples. The multi-step diffusion process can be accelerated by distilling methods, but the generative capacity is difficult to control. To address these issues, we analyze the respective advantages of DMs and generative adversarial networks (GANs) and propose to partition the ge"},"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":"2401.00877","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2023-12-30T10:22:59Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"91d290245ad9dc2776dfa8b2e9629f514a7184bfb5bfd8c58b422bcb417fbf2e","abstract_canon_sha256":"d736f84f29168ed463ed03971a67c86d177a321defaadcd90031e272ac32a6fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:23.480800Z","signature_b64":"xFZQ2YV+2j3jRdQ5nqBfBx0uBWW2DNvYHUOmiLMe2lsGhd2BZ0l4U5iG6P1KMUml+3ZlZCOUMF9RvIBsLILYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9a98c04b08131a7c835de5f8a328b10d49a6c5ceffda7854fdbe4ea5039fef6","last_reissued_at":"2026-07-05T09:11:23.480384Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:23.480384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Hongwei Yong, Jie Liang, Lei Zhang, Lingchen Sun, Rongyuan Wu, Zhengqiang Zhang","submitted_at":"2023-12-30T10:22:59Z","abstract_excerpt":"The generative priors of pre-trained latent diffusion models (DMs) have demonstrated great potential to enhance the visual quality of image super-resolution (SR) results. However, the noise sampling process in DMs introduces randomness in the SR outputs, and the generated contents can differ a lot with different noise samples. The multi-step diffusion process can be accelerated by distilling methods, but the generative capacity is difficult to control. To address these issues, we analyze the respective advantages of DMs and generative adversarial networks (GANs) and propose to partition the ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00877","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/2401.00877/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":"2401.00877","created_at":"2026-07-05T09:11:23.480444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.00877v2","created_at":"2026-07-05T09:11:23.480444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00877","created_at":"2026-07-05T09:11:23.480444+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZGUYYBFQQEY2","created_at":"2026-07-05T09:11:23.480444+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZGUYYBFQQEY2PSBV","created_at":"2026-07-05T09:11:23.480444+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZGUYYBFQ","created_at":"2026-07-05T09:11:23.480444+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10275","citing_title":"FoA-SR: Faithful or Aesthetic? Profile-Aware Preference Optimization for Real-World Image Super-Resolution","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2602.07069","citing_title":"Bird-SR: Bidirectional Reward-Guided Diffusion for Real-World Image Super-Resolution","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03225","citing_title":"VOSR: A Vision-Only Generative Model for Image Super-Resolution","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25457","citing_title":"GramSR: Visual Feature Conditioning for Diffusion-Based Super-Resolution","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZGUYYBFQQEY2PSBV3ZPYUMULCD","json":"https://pith.science/pith/ZGUYYBFQQEY2PSBV3ZPYUMULCD.json","graph_json":"https://pith.science/api/pith-number/ZGUYYBFQQEY2PSBV3ZPYUMULCD/graph.json","events_json":"https://pith.science/api/pith-number/ZGUYYBFQQEY2PSBV3ZPYUMULCD/events.json","paper":"https://pith.science/paper/ZGUYYBFQ"},"agent_actions":{"view_html":"https://pith.science/pith/ZGUYYBFQQEY2PSBV3ZPYUMULCD","download_json":"https://pith.science/pith/ZGUYYBFQQEY2PSBV3ZPYUMULCD.json","view_paper":"https://pith.science/paper/ZGUYYBFQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.00877&json=true","fetch_graph":"https://pith.science/api/pith-number/ZGUYYBFQQEY2PSBV3ZPYUMULCD/graph.json","fetch_events":"https://pith.science/api/pith-number/ZGUYYBFQQEY2PSBV3ZPYUMULCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZGUYYBFQQEY2PSBV3ZPYUMULCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZGUYYBFQQEY2PSBV3ZPYUMULCD/action/storage_attestation","attest_author":"https://pith.science/pith/ZGUYYBFQQEY2PSBV3ZPYUMULCD/action/author_attestation","sign_citation":"https://pith.science/pith/ZGUYYBFQQEY2PSBV3ZPYUMULCD/action/citation_signature","submit_replication":"https://pith.science/pith/ZGUYYBFQQEY2PSBV3ZPYUMULCD/action/replication_record"}},"created_at":"2026-07-05T09:11:23.480444+00:00","updated_at":"2026-07-05T09:11:23.480444+00:00"}