{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RPJOIF7VLKOOP2SWQ4QCM7F345","short_pith_number":"pith:RPJOIF7V","schema_version":"1.0","canonical_sha256":"8bd2e417f55a9ce7ea568720267cbbe75e73e89f49f83fac35ad4c5a77966837","source":{"kind":"arxiv","id":"2303.09472","version":3},"attestation_state":"computed","paper":{"title":"DiffIR: Efficient Diffusion Model for Image Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Xia, Luc Van Gool, Shiyin Wang, Wenming Yang, Xinglong Wu, Yapeng Tian, Yitong Wang, Yulun Zhang","submitted_at":"2023-03-16T16:47:14Z","abstract_excerpt":"Diffusion model (DM) has achieved SOTA performance by modeling the image synthesis process into a sequential application of a denoising network. However, different from image synthesis, image restoration (IR) has a strong constraint to generate results in accordance with ground-truth. Thus, for IR, traditional DMs running massive iterations on a large model to estimate whole images or feature maps is inefficient. To address this issue, we propose an efficient DM for IR (DiffIR), which consists of a compact IR prior extraction network (CPEN), dynamic IR transformer (DIRformer), and denoising ne"},"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":"2303.09472","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T16:47:14Z","cross_cats_sorted":[],"title_canon_sha256":"84023012c74fd8c0cae165e4bc89aeaeddad3f766f771f77bd5aadd2f5bb6697","abstract_canon_sha256":"4853ce842cf0f766625fa5c152b0f44252a6a1aca1ae58a811cb99f9525fdd3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:47.712080Z","signature_b64":"Rhy3FEkKufNZserw5XXj0nIhDYhtXCUHVfG96RxaMhHpDsuHiKGTHvSly9wQpIMXmcS2ahoeRlY9BYu8OnvHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bd2e417f55a9ce7ea568720267cbbe75e73e89f49f83fac35ad4c5a77966837","last_reissued_at":"2026-07-05T06:41:47.711585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:47.711585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffIR: Efficient Diffusion Model for Image Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Xia, Luc Van Gool, Shiyin Wang, Wenming Yang, Xinglong Wu, Yapeng Tian, Yitong Wang, Yulun Zhang","submitted_at":"2023-03-16T16:47:14Z","abstract_excerpt":"Diffusion model (DM) has achieved SOTA performance by modeling the image synthesis process into a sequential application of a denoising network. However, different from image synthesis, image restoration (IR) has a strong constraint to generate results in accordance with ground-truth. Thus, for IR, traditional DMs running massive iterations on a large model to estimate whole images or feature maps is inefficient. To address this issue, we propose an efficient DM for IR (DiffIR), which consists of a compact IR prior extraction network (CPEN), dynamic IR transformer (DIRformer), and denoising ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09472","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/2303.09472/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":"2303.09472","created_at":"2026-07-05T06:41:47.711641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09472v3","created_at":"2026-07-05T06:41:47.711641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09472","created_at":"2026-07-05T06:41:47.711641+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPJOIF7VLKOO","created_at":"2026-07-05T06:41:47.711641+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPJOIF7VLKOOP2SW","created_at":"2026-07-05T06:41:47.711641+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPJOIF7V","created_at":"2026-07-05T06:41:47.711641+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17306","citing_title":"The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview","ref_index":74,"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":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RPJOIF7VLKOOP2SWQ4QCM7F345","json":"https://pith.science/pith/RPJOIF7VLKOOP2SWQ4QCM7F345.json","graph_json":"https://pith.science/api/pith-number/RPJOIF7VLKOOP2SWQ4QCM7F345/graph.json","events_json":"https://pith.science/api/pith-number/RPJOIF7VLKOOP2SWQ4QCM7F345/events.json","paper":"https://pith.science/paper/RPJOIF7V"},"agent_actions":{"view_html":"https://pith.science/pith/RPJOIF7VLKOOP2SWQ4QCM7F345","download_json":"https://pith.science/pith/RPJOIF7VLKOOP2SWQ4QCM7F345.json","view_paper":"https://pith.science/paper/RPJOIF7V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09472&json=true","fetch_graph":"https://pith.science/api/pith-number/RPJOIF7VLKOOP2SWQ4QCM7F345/graph.json","fetch_events":"https://pith.science/api/pith-number/RPJOIF7VLKOOP2SWQ4QCM7F345/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPJOIF7VLKOOP2SWQ4QCM7F345/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPJOIF7VLKOOP2SWQ4QCM7F345/action/storage_attestation","attest_author":"https://pith.science/pith/RPJOIF7VLKOOP2SWQ4QCM7F345/action/author_attestation","sign_citation":"https://pith.science/pith/RPJOIF7VLKOOP2SWQ4QCM7F345/action/citation_signature","submit_replication":"https://pith.science/pith/RPJOIF7VLKOOP2SWQ4QCM7F345/action/replication_record"}},"created_at":"2026-07-05T06:41:47.711641+00:00","updated_at":"2026-07-05T06:41:47.711641+00:00"}