{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WRGZTZTFTUTJNHGFHZ64P6LYDI","short_pith_number":"pith:WRGZTZTF","schema_version":"1.0","canonical_sha256":"b44d99e6659d26969cc53e7dc7f9781a1b23065b7bd06bc80e8b8955aa070ccf","source":{"kind":"arxiv","id":"1811.12766","version":3},"attestation_state":"computed","paper":{"title":"Model-blind Video Denoising Via Frame-to-frame Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Axel Davy, Gabriele Facciolo, Jean-Michel Morel, Pablo Arias, Thibaud Ehret","submitted_at":"2018-11-30T12:44:50Z","abstract_excerpt":"Modeling the processing chain that has produced a video is a difficult reverse engineering task, even when the camera is available. This makes model based video processing a still more complex task. In this paper we propose a fully blind video denoising method, with two versions off-line and on-line. This is achieved by fine-tuning a pre-trained AWGN denoising network to the video with a novel frame-to-frame training strategy. Our denoiser can be used without knowledge of the origin of the video or burst and the post processing steps applied from the camera sensor. The on-line process only req"},"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":"1811.12766","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-30T12:44:50Z","cross_cats_sorted":[],"title_canon_sha256":"8d575d3812db6c216cb9ac2f162c057c083c5c182fff713009feaa8fcef1fedc","abstract_canon_sha256":"2c87e8e0e554330d06bdc591f38611329096dabc558bfcef3dd956d8ad420962"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:31.580576Z","signature_b64":"DArrKLeUyB8OI8zixSSSzlOtAG5YLGosSe2xD09p+g4gBkWW3ENMl0Fz25xkYev+i0ofVBTzkZbnptIwBPY3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b44d99e6659d26969cc53e7dc7f9781a1b23065b7bd06bc80e8b8955aa070ccf","last_reissued_at":"2026-07-05T00:43:31.580081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:31.580081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-blind Video Denoising Via Frame-to-frame Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Axel Davy, Gabriele Facciolo, Jean-Michel Morel, Pablo Arias, Thibaud Ehret","submitted_at":"2018-11-30T12:44:50Z","abstract_excerpt":"Modeling the processing chain that has produced a video is a difficult reverse engineering task, even when the camera is available. This makes model based video processing a still more complex task. In this paper we propose a fully blind video denoising method, with two versions off-line and on-line. This is achieved by fine-tuning a pre-trained AWGN denoising network to the video with a novel frame-to-frame training strategy. Our denoiser can be used without knowledge of the origin of the video or burst and the post processing steps applied from the camera sensor. The on-line process only req"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12766","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/1811.12766/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":"1811.12766","created_at":"2026-07-05T00:43:31.580141+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.12766v3","created_at":"2026-07-05T00:43:31.580141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12766","created_at":"2026-07-05T00:43:31.580141+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRGZTZTFTUTJ","created_at":"2026-07-05T00:43:31.580141+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRGZTZTFTUTJNHGF","created_at":"2026-07-05T00:43:31.580141+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRGZTZTF","created_at":"2026-07-05T00:43:31.580141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.02815","citing_title":"Solar image denoising with convolutional neural networks","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WRGZTZTFTUTJNHGFHZ64P6LYDI","json":"https://pith.science/pith/WRGZTZTFTUTJNHGFHZ64P6LYDI.json","graph_json":"https://pith.science/api/pith-number/WRGZTZTFTUTJNHGFHZ64P6LYDI/graph.json","events_json":"https://pith.science/api/pith-number/WRGZTZTFTUTJNHGFHZ64P6LYDI/events.json","paper":"https://pith.science/paper/WRGZTZTF"},"agent_actions":{"view_html":"https://pith.science/pith/WRGZTZTFTUTJNHGFHZ64P6LYDI","download_json":"https://pith.science/pith/WRGZTZTFTUTJNHGFHZ64P6LYDI.json","view_paper":"https://pith.science/paper/WRGZTZTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.12766&json=true","fetch_graph":"https://pith.science/api/pith-number/WRGZTZTFTUTJNHGFHZ64P6LYDI/graph.json","fetch_events":"https://pith.science/api/pith-number/WRGZTZTFTUTJNHGFHZ64P6LYDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRGZTZTFTUTJNHGFHZ64P6LYDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRGZTZTFTUTJNHGFHZ64P6LYDI/action/storage_attestation","attest_author":"https://pith.science/pith/WRGZTZTFTUTJNHGFHZ64P6LYDI/action/author_attestation","sign_citation":"https://pith.science/pith/WRGZTZTFTUTJNHGFHZ64P6LYDI/action/citation_signature","submit_replication":"https://pith.science/pith/WRGZTZTFTUTJNHGFHZ64P6LYDI/action/replication_record"}},"created_at":"2026-07-05T00:43:31.580141+00:00","updated_at":"2026-07-05T00:43:31.580141+00:00"}