{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FPXBZLRCMFX7JSNYSS6ZEC5SGN","short_pith_number":"pith:FPXBZLRC","schema_version":"1.0","canonical_sha256":"2bee1cae22616ff4c9b894bd920bb23353a873dd1b27171f1838e4f90d986b4c","source":{"kind":"arxiv","id":"2110.03220","version":2},"attestation_state":"computed","paper":{"title":"Gradient Step Denoiser for convergent Plug-and-Play","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV","math.OC"],"primary_cat":"cs.CV","authors_text":"Arthur Leclaire, Nicolas Papadakis, Samuel Hurault","submitted_at":"2021-10-07T07:11:48Z","abstract_excerpt":"Plug-and-Play methods constitute a class of iterative algorithms for imaging problems where regularization is performed by an off-the-shelf denoiser. Although Plug-and-Play methods can lead to tremendous visual performance for various image problems, the few existing convergence guarantees are based on unrealistic (or suboptimal) hypotheses on the denoiser, or limited to strongly convex data terms. In this work, we propose a new type of Plug-and-Play methods, based on half-quadratic splitting, for which the denoiser is realized as a gradient descent step on a functional parameterized by a deep"},"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":"2110.03220","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-07T07:11:48Z","cross_cats_sorted":["eess.IV","math.OC"],"title_canon_sha256":"6fb0eb88b852fcc5d64ccd6bcec5ae3c96290c2f92c65223b83f7b5576a0ff22","abstract_canon_sha256":"b58b06d800a8c0ec2f7312daf9b0f372fd48459043f0c506c21afd22aa0ddc30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:31.394152Z","signature_b64":"Bn5ch0/2sSQvf08kO0Uez3bS+NCp6kevGXH+QrvAn32fiPnJUP3SaKJ1uw8KD0tQmSkY7/ap57DU8xkvNpwjAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bee1cae22616ff4c9b894bd920bb23353a873dd1b27171f1838e4f90d986b4c","last_reissued_at":"2026-07-05T03:56:31.393713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:31.393713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Step Denoiser for convergent Plug-and-Play","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV","math.OC"],"primary_cat":"cs.CV","authors_text":"Arthur Leclaire, Nicolas Papadakis, Samuel Hurault","submitted_at":"2021-10-07T07:11:48Z","abstract_excerpt":"Plug-and-Play methods constitute a class of iterative algorithms for imaging problems where regularization is performed by an off-the-shelf denoiser. Although Plug-and-Play methods can lead to tremendous visual performance for various image problems, the few existing convergence guarantees are based on unrealistic (or suboptimal) hypotheses on the denoiser, or limited to strongly convex data terms. In this work, we propose a new type of Plug-and-Play methods, based on half-quadratic splitting, for which the denoiser is realized as a gradient descent step on a functional parameterized by a deep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03220","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/2110.03220/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":"2110.03220","created_at":"2026-07-05T03:56:31.393774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03220v2","created_at":"2026-07-05T03:56:31.393774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03220","created_at":"2026-07-05T03:56:31.393774+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPXBZLRCMFX7","created_at":"2026-07-05T03:56:31.393774+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPXBZLRCMFX7JSNY","created_at":"2026-07-05T03:56:31.393774+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPXBZLRC","created_at":"2026-07-05T03:56:31.393774+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28124","citing_title":"Gradient Step Plug-and-Play Model for Dental Cone-Beam CT Reconstruction","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2304.11200","citing_title":"A Plug-and-Play Method with Inpainting Network for Bayesian Uncertainty Quantification in Imaging","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08640","citing_title":"FlowADMM: Plug-and-play ADMM with Flow-based Renoise-Denoise Priors","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPXBZLRCMFX7JSNYSS6ZEC5SGN","json":"https://pith.science/pith/FPXBZLRCMFX7JSNYSS6ZEC5SGN.json","graph_json":"https://pith.science/api/pith-number/FPXBZLRCMFX7JSNYSS6ZEC5SGN/graph.json","events_json":"https://pith.science/api/pith-number/FPXBZLRCMFX7JSNYSS6ZEC5SGN/events.json","paper":"https://pith.science/paper/FPXBZLRC"},"agent_actions":{"view_html":"https://pith.science/pith/FPXBZLRCMFX7JSNYSS6ZEC5SGN","download_json":"https://pith.science/pith/FPXBZLRCMFX7JSNYSS6ZEC5SGN.json","view_paper":"https://pith.science/paper/FPXBZLRC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03220&json=true","fetch_graph":"https://pith.science/api/pith-number/FPXBZLRCMFX7JSNYSS6ZEC5SGN/graph.json","fetch_events":"https://pith.science/api/pith-number/FPXBZLRCMFX7JSNYSS6ZEC5SGN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPXBZLRCMFX7JSNYSS6ZEC5SGN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPXBZLRCMFX7JSNYSS6ZEC5SGN/action/storage_attestation","attest_author":"https://pith.science/pith/FPXBZLRCMFX7JSNYSS6ZEC5SGN/action/author_attestation","sign_citation":"https://pith.science/pith/FPXBZLRCMFX7JSNYSS6ZEC5SGN/action/citation_signature","submit_replication":"https://pith.science/pith/FPXBZLRCMFX7JSNYSS6ZEC5SGN/action/replication_record"}},"created_at":"2026-07-05T03:56:31.393774+00:00","updated_at":"2026-07-05T03:56:31.393774+00:00"}