{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZR3CY5NB3OU2CL7CIHGKIB4NUJ","short_pith_number":"pith:ZR3CY5NB","schema_version":"1.0","canonical_sha256":"cc762c75a1dba9a12fe241cca4078da263d4d603a0c514a7ff928faaf0be0a48","source":{"kind":"arxiv","id":"2207.09302","version":1},"attestation_state":"computed","paper":{"title":"Deep Semantic Statistics Matching (D2SM) Denoising Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kangfu Mei, Rui Huang, Vishal M. Patel","submitted_at":"2022-07-19T14:35:42Z","abstract_excerpt":"The ultimate aim of image restoration like denoising is to find an exact correlation between the noisy and clear image domains. But the optimization of end-to-end denoising learning like pixel-wise losses is performed in a sample-to-sample manner, which ignores the intrinsic correlation of images, especially semantics. In this paper, we introduce the Deep Semantic Statistics Matching (D2SM) Denoising Network. It exploits semantic features of pretrained classification networks, then it implicitly matches the probabilistic distribution of clear images at the semantic feature space. By learning t"},"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":"2207.09302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-19T14:35:42Z","cross_cats_sorted":[],"title_canon_sha256":"756cb02e2b64a3f8327e1a6861fb07c568f456be73dde1abc4aa5f65548e18a3","abstract_canon_sha256":"5dbe4db510480d9191b874a94abb9e979bfbad006a4fd5c5bb90be7619c013f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:41:48.513007Z","signature_b64":"p/PXWEFXMlyuo5lqOZUzP5Dkb2ffy/lCyfYYjo8dl+W7Iw/KqFgxbM5jfmHL/44LxX9n0vhOIfbq/L8Wpyz2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc762c75a1dba9a12fe241cca4078da263d4d603a0c514a7ff928faaf0be0a48","last_reissued_at":"2026-07-05T04:41:48.512617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:41:48.512617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Semantic Statistics Matching (D2SM) Denoising Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kangfu Mei, Rui Huang, Vishal M. Patel","submitted_at":"2022-07-19T14:35:42Z","abstract_excerpt":"The ultimate aim of image restoration like denoising is to find an exact correlation between the noisy and clear image domains. But the optimization of end-to-end denoising learning like pixel-wise losses is performed in a sample-to-sample manner, which ignores the intrinsic correlation of images, especially semantics. In this paper, we introduce the Deep Semantic Statistics Matching (D2SM) Denoising Network. It exploits semantic features of pretrained classification networks, then it implicitly matches the probabilistic distribution of clear images at the semantic feature space. By learning t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.09302","kind":"arxiv","version":1},"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/2207.09302/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":"2207.09302","created_at":"2026-07-05T04:41:48.512678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.09302v1","created_at":"2026-07-05T04:41:48.512678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.09302","created_at":"2026-07-05T04:41:48.512678+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZR3CY5NB3OU2","created_at":"2026-07-05T04:41:48.512678+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZR3CY5NB3OU2CL7C","created_at":"2026-07-05T04:41:48.512678+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZR3CY5NB","created_at":"2026-07-05T04:41:48.512678+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.02067","citing_title":"YOLOv1 to YOLOv11: A Comprehensive Survey of Real-Time Object Detection Innovations and Challenges","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZR3CY5NB3OU2CL7CIHGKIB4NUJ","json":"https://pith.science/pith/ZR3CY5NB3OU2CL7CIHGKIB4NUJ.json","graph_json":"https://pith.science/api/pith-number/ZR3CY5NB3OU2CL7CIHGKIB4NUJ/graph.json","events_json":"https://pith.science/api/pith-number/ZR3CY5NB3OU2CL7CIHGKIB4NUJ/events.json","paper":"https://pith.science/paper/ZR3CY5NB"},"agent_actions":{"view_html":"https://pith.science/pith/ZR3CY5NB3OU2CL7CIHGKIB4NUJ","download_json":"https://pith.science/pith/ZR3CY5NB3OU2CL7CIHGKIB4NUJ.json","view_paper":"https://pith.science/paper/ZR3CY5NB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.09302&json=true","fetch_graph":"https://pith.science/api/pith-number/ZR3CY5NB3OU2CL7CIHGKIB4NUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZR3CY5NB3OU2CL7CIHGKIB4NUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZR3CY5NB3OU2CL7CIHGKIB4NUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZR3CY5NB3OU2CL7CIHGKIB4NUJ/action/storage_attestation","attest_author":"https://pith.science/pith/ZR3CY5NB3OU2CL7CIHGKIB4NUJ/action/author_attestation","sign_citation":"https://pith.science/pith/ZR3CY5NB3OU2CL7CIHGKIB4NUJ/action/citation_signature","submit_replication":"https://pith.science/pith/ZR3CY5NB3OU2CL7CIHGKIB4NUJ/action/replication_record"}},"created_at":"2026-07-05T04:41:48.512678+00:00","updated_at":"2026-07-05T04:41:48.512678+00:00"}