{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KV4CQNZX5SD2MPY7XIC3QEX6UH","short_pith_number":"pith:KV4CQNZX","schema_version":"1.0","canonical_sha256":"5578283737ec87a63f1fba05b812fea1ef380efba378e081bd8ad7d29e3be74b","source":{"kind":"arxiv","id":"2208.11803","version":3},"attestation_state":"computed","paper":{"title":"Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Jiezhang Cao, Jingyun Liang, Kai Zhang, Luc Van Gool, Qin Wang, Radu Timofte, Yulun Zhang","submitted_at":"2022-08-25T00:09:18Z","abstract_excerpt":"Video denoising aims at removing noise from videos to recover clean ones. Some existing works show that optical flow can help the denoising by exploiting the additional spatial-temporal clues from nearby frames. However, the flow estimation itself is also sensitive to noise, and can be unusable under large noise levels. To this end, we propose a new multi-scale refined optical flow-guided video denoising method, which is more robust to different noise levels. Our method mainly consists of a denoising-oriented flow refinement (DFR) module and a flow-guided mutual denoising propagation (FMDP) mo"},"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":"2208.11803","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-25T00:09:18Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"2f4c0ed10c2acddb73f8654c215bb48099a06dcfe280c54554fec6387e209733","abstract_canon_sha256":"dafaa94d6bc5e8b8e0fd788c40f7d98fedd11a43c8c66689e7362d12873627f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:30.536882Z","signature_b64":"4rwQGWef58rbfTV6L7g7vYmTZI4qd83Xx8gnJuqb3MJA9kFfofSFGG/AzHNMf8Or6QyeO/zDjJzMzq88YgQKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5578283737ec87a63f1fba05b812fea1ef380efba378e081bd8ad7d29e3be74b","last_reissued_at":"2026-07-05T05:54:30.536419Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:30.536419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Jiezhang Cao, Jingyun Liang, Kai Zhang, Luc Van Gool, Qin Wang, Radu Timofte, Yulun Zhang","submitted_at":"2022-08-25T00:09:18Z","abstract_excerpt":"Video denoising aims at removing noise from videos to recover clean ones. Some existing works show that optical flow can help the denoising by exploiting the additional spatial-temporal clues from nearby frames. However, the flow estimation itself is also sensitive to noise, and can be unusable under large noise levels. To this end, we propose a new multi-scale refined optical flow-guided video denoising method, which is more robust to different noise levels. Our method mainly consists of a denoising-oriented flow refinement (DFR) module and a flow-guided mutual denoising propagation (FMDP) mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11803","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/2208.11803/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":"2208.11803","created_at":"2026-07-05T05:54:30.536483+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.11803v3","created_at":"2026-07-05T05:54:30.536483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11803","created_at":"2026-07-05T05:54:30.536483+00:00"},{"alias_kind":"pith_short_12","alias_value":"KV4CQNZX5SD2","created_at":"2026-07-05T05:54:30.536483+00:00"},{"alias_kind":"pith_short_16","alias_value":"KV4CQNZX5SD2MPY7","created_at":"2026-07-05T05:54:30.536483+00:00"},{"alias_kind":"pith_short_8","alias_value":"KV4CQNZX","created_at":"2026-07-05T05:54:30.536483+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.02269","citing_title":"TDM: Temporally-Consistent Diffusion Model for All-in-One Real-World Video Restoration","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KV4CQNZX5SD2MPY7XIC3QEX6UH","json":"https://pith.science/pith/KV4CQNZX5SD2MPY7XIC3QEX6UH.json","graph_json":"https://pith.science/api/pith-number/KV4CQNZX5SD2MPY7XIC3QEX6UH/graph.json","events_json":"https://pith.science/api/pith-number/KV4CQNZX5SD2MPY7XIC3QEX6UH/events.json","paper":"https://pith.science/paper/KV4CQNZX"},"agent_actions":{"view_html":"https://pith.science/pith/KV4CQNZX5SD2MPY7XIC3QEX6UH","download_json":"https://pith.science/pith/KV4CQNZX5SD2MPY7XIC3QEX6UH.json","view_paper":"https://pith.science/paper/KV4CQNZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.11803&json=true","fetch_graph":"https://pith.science/api/pith-number/KV4CQNZX5SD2MPY7XIC3QEX6UH/graph.json","fetch_events":"https://pith.science/api/pith-number/KV4CQNZX5SD2MPY7XIC3QEX6UH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KV4CQNZX5SD2MPY7XIC3QEX6UH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KV4CQNZX5SD2MPY7XIC3QEX6UH/action/storage_attestation","attest_author":"https://pith.science/pith/KV4CQNZX5SD2MPY7XIC3QEX6UH/action/author_attestation","sign_citation":"https://pith.science/pith/KV4CQNZX5SD2MPY7XIC3QEX6UH/action/citation_signature","submit_replication":"https://pith.science/pith/KV4CQNZX5SD2MPY7XIC3QEX6UH/action/replication_record"}},"created_at":"2026-07-05T05:54:30.536483+00:00","updated_at":"2026-07-05T05:54:30.536483+00:00"}