{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IVXA6EQQHMK5XCULNIBP43AGGT","short_pith_number":"pith:IVXA6EQQ","schema_version":"1.0","canonical_sha256":"456e0f12103b15db8a8b6a02fe6c0634fb6d402d78c1541bf2444a7341016fad","source":{"kind":"arxiv","id":"2501.14265","version":3},"attestation_state":"computed","paper":{"title":"Bayesian Neural Networks for One-to-Many Mapping in Image Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Bull, Guoxi Huang, Nantheera Anantrasirichai, Qirui Yang, Ruirui Lin, Zipeng Qi","submitted_at":"2025-01-24T06:07:11Z","abstract_excerpt":"In image enhancement tasks, such as low-light and underwater image enhancement, a degraded image can correspond to multiple plausible target images due to dynamic photography conditions. This naturally results in a one-to-many mapping problem. To address this, we propose a Bayesian Enhancement Model (BEM) that incorporates Bayesian Neural Networks (BNNs) to capture data uncertainty and produce diverse outputs. To enable fast inference, we introduce a BNN-DNN framework: a BNN is first employed to model the one-to-many mapping in a low-dimensional space, followed by a Deterministic Neural Networ"},"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":"2501.14265","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-24T06:07:11Z","cross_cats_sorted":[],"title_canon_sha256":"15fc58c88512c361b882fd24d27cfa0b0196271c0fb994503348eea81bad678f","abstract_canon_sha256":"74d63347757acf1b8585a5cc57e425961cd2afb106447082f53fd76953e5e28a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"456e0f12103b15db8a8b6a02fe6c0634fb6d402d78c1541bf2444a7341016fad","last_reissued_at":"2026-07-30T01:18:47.264395Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:18:47.264395Z"},"graph_snapshot":{"paper":{"title":"Bayesian Neural Networks for One-to-Many Mapping in Image Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Bull, Guoxi Huang, Nantheera Anantrasirichai, Qirui Yang, Ruirui Lin, Zipeng Qi","submitted_at":"2025-01-24T06:07:11Z","abstract_excerpt":"In image enhancement tasks, such as low-light and underwater image enhancement, a degraded image can correspond to multiple plausible target images due to dynamic photography conditions. This naturally results in a one-to-many mapping problem. To address this, we propose a Bayesian Enhancement Model (BEM) that incorporates Bayesian Neural Networks (BNNs) to capture data uncertainty and produce diverse outputs. To enable fast inference, we introduce a BNN-DNN framework: a BNN is first employed to model the one-to-many mapping in a low-dimensional space, followed by a Deterministic Neural Networ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14265","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/2501.14265/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":"2501.14265","created_at":"2026-07-30T01:18:47.269599+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14265v3","created_at":"2026-07-30T01:18:47.269599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14265","created_at":"2026-07-30T01:18:47.269599+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVXA6EQQHMK5","created_at":"2026-07-30T01:18:47.269599+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVXA6EQQHMK5XCUL","created_at":"2026-07-30T01:18:47.269599+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVXA6EQQ","created_at":"2026-07-30T01:18:47.269599+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.19289","citing_title":"Marine Snow Removal Using Internally Generated Pseudo Ground Truth","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IVXA6EQQHMK5XCULNIBP43AGGT","json":"https://pith.science/pith/IVXA6EQQHMK5XCULNIBP43AGGT.json","graph_json":"https://pith.science/api/pith-number/IVXA6EQQHMK5XCULNIBP43AGGT/graph.json","events_json":"https://pith.science/api/pith-number/IVXA6EQQHMK5XCULNIBP43AGGT/events.json","paper":"https://pith.science/paper/IVXA6EQQ"},"agent_actions":{"view_html":"https://pith.science/pith/IVXA6EQQHMK5XCULNIBP43AGGT","download_json":"https://pith.science/pith/IVXA6EQQHMK5XCULNIBP43AGGT.json","view_paper":"https://pith.science/paper/IVXA6EQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14265&json=true","fetch_graph":"https://pith.science/api/pith-number/IVXA6EQQHMK5XCULNIBP43AGGT/graph.json","fetch_events":"https://pith.science/api/pith-number/IVXA6EQQHMK5XCULNIBP43AGGT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVXA6EQQHMK5XCULNIBP43AGGT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVXA6EQQHMK5XCULNIBP43AGGT/action/storage_attestation","attest_author":"https://pith.science/pith/IVXA6EQQHMK5XCULNIBP43AGGT/action/author_attestation","sign_citation":"https://pith.science/pith/IVXA6EQQHMK5XCULNIBP43AGGT/action/citation_signature","submit_replication":"https://pith.science/pith/IVXA6EQQHMK5XCULNIBP43AGGT/action/replication_record"}},"created_at":"2026-07-30T01:18:47.269599+00:00","updated_at":"2026-07-30T01:18:47.269599+00:00"}