{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YBCPLBHK33TBHKDMSR7OEK4Y4X","short_pith_number":"pith:YBCPLBHK","schema_version":"1.0","canonical_sha256":"c044f584eadee613a86c947ee22b98e5d0e915c8de627f237d204d8d1b0af5fc","source":{"kind":"arxiv","id":"2410.04224","version":3},"attestation_state":"computed","paper":{"title":"Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianze Li, Jiezhang Cao, Xiaokang Yang, Xin Yuan, Xiongfei Su, Yong Guo, Yulun Zhang, Zichen Zou","submitted_at":"2024-10-05T16:41:36Z","abstract_excerpt":"Diffusion models have demonstrated excellent performance for real-world image super-resolution (Real-ISR), albeit at high computational costs. Most existing methods are trying to derive one-step diffusion models from multi-step counterparts through knowledge distillation (KD) or variational score distillation (VSD). However, these methods are limited by the capabilities of the teacher model, especially if the teacher model itself is not sufficiently strong. To tackle these issues, we propose a new One-Step \\textbf{D}iffusion model with a larger-scale \\textbf{D}iffusion \\textbf{D}iscriminator f"},"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":"2410.04224","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-05T16:41:36Z","cross_cats_sorted":[],"title_canon_sha256":"18d74e5e3460318c4d8d3e9373ced7656e469467aa7022d1ffd1d5bf7782500e","abstract_canon_sha256":"0f2666bf6ef3433c15de77a2a3a698964cc8a17b2704b4ad9e47f5eb4f15f366"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:16.601541Z","signature_b64":"qg2sXAbDEXq1SQbvHiKdzhaDaPP8MXABLjfXKgva66ubVBhl8QpciT3dw/65AIBglY2JYXszhqPhNvEuQRemAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c044f584eadee613a86c947ee22b98e5d0e915c8de627f237d204d8d1b0af5fc","last_reissued_at":"2026-07-05T10:27:16.601034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:16.601034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianze Li, Jiezhang Cao, Xiaokang Yang, Xin Yuan, Xiongfei Su, Yong Guo, Yulun Zhang, Zichen Zou","submitted_at":"2024-10-05T16:41:36Z","abstract_excerpt":"Diffusion models have demonstrated excellent performance for real-world image super-resolution (Real-ISR), albeit at high computational costs. Most existing methods are trying to derive one-step diffusion models from multi-step counterparts through knowledge distillation (KD) or variational score distillation (VSD). However, these methods are limited by the capabilities of the teacher model, especially if the teacher model itself is not sufficiently strong. To tackle these issues, we propose a new One-Step \\textbf{D}iffusion model with a larger-scale \\textbf{D}iffusion \\textbf{D}iscriminator f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04224","kind":"arxiv","version":3},"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/2410.04224/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":"2410.04224","created_at":"2026-07-05T10:27:16.601100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04224v3","created_at":"2026-07-05T10:27:16.601100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04224","created_at":"2026-07-05T10:27:16.601100+00:00"},{"alias_kind":"pith_short_12","alias_value":"YBCPLBHK33TB","created_at":"2026-07-05T10:27:16.601100+00:00"},{"alias_kind":"pith_short_16","alias_value":"YBCPLBHK33TBHKDM","created_at":"2026-07-05T10:27:16.601100+00:00"},{"alias_kind":"pith_short_8","alias_value":"YBCPLBHK","created_at":"2026-07-05T10:27:16.601100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09608","citing_title":"TUDSR: Twice Upsampling-Diffusion for Higher Super-Resolution","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12377","citing_title":"Fast Image Super-Resolution via Consistency Rectified Flow","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12377","citing_title":"Fast Image Super-Resolution via Consistency Rectified Flow","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14560","citing_title":"DVFace: Spatio-Temporal Dual-Prior Diffusion for Video Face Restoration","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21312","citing_title":"The First Challenge on Remote Sensing Infrared Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YBCPLBHK33TBHKDMSR7OEK4Y4X","json":"https://pith.science/pith/YBCPLBHK33TBHKDMSR7OEK4Y4X.json","graph_json":"https://pith.science/api/pith-number/YBCPLBHK33TBHKDMSR7OEK4Y4X/graph.json","events_json":"https://pith.science/api/pith-number/YBCPLBHK33TBHKDMSR7OEK4Y4X/events.json","paper":"https://pith.science/paper/YBCPLBHK"},"agent_actions":{"view_html":"https://pith.science/pith/YBCPLBHK33TBHKDMSR7OEK4Y4X","download_json":"https://pith.science/pith/YBCPLBHK33TBHKDMSR7OEK4Y4X.json","view_paper":"https://pith.science/paper/YBCPLBHK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04224&json=true","fetch_graph":"https://pith.science/api/pith-number/YBCPLBHK33TBHKDMSR7OEK4Y4X/graph.json","fetch_events":"https://pith.science/api/pith-number/YBCPLBHK33TBHKDMSR7OEK4Y4X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YBCPLBHK33TBHKDMSR7OEK4Y4X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YBCPLBHK33TBHKDMSR7OEK4Y4X/action/storage_attestation","attest_author":"https://pith.science/pith/YBCPLBHK33TBHKDMSR7OEK4Y4X/action/author_attestation","sign_citation":"https://pith.science/pith/YBCPLBHK33TBHKDMSR7OEK4Y4X/action/citation_signature","submit_replication":"https://pith.science/pith/YBCPLBHK33TBHKDMSR7OEK4Y4X/action/replication_record"}},"created_at":"2026-07-05T10:27:16.601100+00:00","updated_at":"2026-07-05T10:27:16.601100+00:00"}