{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IA2VQ7LTIGRKYBGCEZTIKOU4MK","short_pith_number":"pith:IA2VQ7LT","schema_version":"1.0","canonical_sha256":"4035587d7341a2ac04c22666853a9c62838fd6085f0a7591efc633761e96968b","source":{"kind":"arxiv","id":"1709.03749","version":2},"attestation_state":"computed","paper":{"title":"Deep Mean-Shift Priors for Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Matthias Zwicker, Meiguang Jin, Paolo Favaro, Siavash Arjomand Bigdeli","submitted_at":"2017-09-12T09:11:24Z","abstract_excerpt":"In this paper we introduce a natural image prior that directly represents a Gaussian-smoothed version of the natural image distribution. We include our prior in a formulation of image restoration as a Bayes estimator that also allows us to solve noise-blind image restoration problems. We show that the gradient of our prior corresponds to the mean-shift vector on the natural image distribution. In addition, we learn the mean-shift vector field using denoising autoencoders, and use it in a gradient descent approach to perform Bayes risk minimization. We demonstrate competitive results for noise-"},"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":"1709.03749","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-12T09:11:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3d486692b26acca44175a922ca854182a88a43c441176bb7364151ab471106c4","abstract_canon_sha256":"181dcdd082b94aa6bb866c94359ccc6df4da27c252d9a1c2b082533dadc6d81d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:43.203932Z","signature_b64":"PRv73gsVm5PbXWGpHXGHqp+sO1F3YdSBOrtmAQNTXiBs/JjQv1eiei65dZKEp37Ui2QMMJQhWq4ZBoo/RBkJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4035587d7341a2ac04c22666853a9c62838fd6085f0a7591efc633761e96968b","last_reissued_at":"2026-05-18T00:33:43.203239Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:43.203239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Mean-Shift Priors for Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Matthias Zwicker, Meiguang Jin, Paolo Favaro, Siavash Arjomand Bigdeli","submitted_at":"2017-09-12T09:11:24Z","abstract_excerpt":"In this paper we introduce a natural image prior that directly represents a Gaussian-smoothed version of the natural image distribution. We include our prior in a formulation of image restoration as a Bayes estimator that also allows us to solve noise-blind image restoration problems. We show that the gradient of our prior corresponds to the mean-shift vector on the natural image distribution. In addition, we learn the mean-shift vector field using denoising autoencoders, and use it in a gradient descent approach to perform Bayes risk minimization. We demonstrate competitive results for noise-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.03749","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":""},"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":"1709.03749","created_at":"2026-05-18T00:33:43.203382+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.03749v2","created_at":"2026-05-18T00:33:43.203382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.03749","created_at":"2026-05-18T00:33:43.203382+00:00"},{"alias_kind":"pith_short_12","alias_value":"IA2VQ7LTIGRK","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IA2VQ7LTIGRKYBGC","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IA2VQ7LT","created_at":"2026-05-18T12:31:21.493067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07513","citing_title":"Tessellations of Semi-Discrete Flow Matching","ref_index":177,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IA2VQ7LTIGRKYBGCEZTIKOU4MK","json":"https://pith.science/pith/IA2VQ7LTIGRKYBGCEZTIKOU4MK.json","graph_json":"https://pith.science/api/pith-number/IA2VQ7LTIGRKYBGCEZTIKOU4MK/graph.json","events_json":"https://pith.science/api/pith-number/IA2VQ7LTIGRKYBGCEZTIKOU4MK/events.json","paper":"https://pith.science/paper/IA2VQ7LT"},"agent_actions":{"view_html":"https://pith.science/pith/IA2VQ7LTIGRKYBGCEZTIKOU4MK","download_json":"https://pith.science/pith/IA2VQ7LTIGRKYBGCEZTIKOU4MK.json","view_paper":"https://pith.science/paper/IA2VQ7LT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.03749&json=true","fetch_graph":"https://pith.science/api/pith-number/IA2VQ7LTIGRKYBGCEZTIKOU4MK/graph.json","fetch_events":"https://pith.science/api/pith-number/IA2VQ7LTIGRKYBGCEZTIKOU4MK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IA2VQ7LTIGRKYBGCEZTIKOU4MK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IA2VQ7LTIGRKYBGCEZTIKOU4MK/action/storage_attestation","attest_author":"https://pith.science/pith/IA2VQ7LTIGRKYBGCEZTIKOU4MK/action/author_attestation","sign_citation":"https://pith.science/pith/IA2VQ7LTIGRKYBGCEZTIKOU4MK/action/citation_signature","submit_replication":"https://pith.science/pith/IA2VQ7LTIGRKYBGCEZTIKOU4MK/action/replication_record"}},"created_at":"2026-05-18T00:33:43.203382+00:00","updated_at":"2026-05-18T00:33:43.203382+00:00"}