{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HY5TVU3MFCV3JWKTFQ7455LGAK","short_pith_number":"pith:HY5TVU3M","schema_version":"1.0","canonical_sha256":"3e3b3ad36c28abb4d9532c3fcef56602892ed3b87d4486143518d3b442906855","source":{"kind":"arxiv","id":"2508.02127","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Event-based Object Detection with Monocular Normal Maps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuang Zhu, Hanqing Liu, Luoping Cui, Mingjie Liu","submitted_at":"2025-08-04T07:19:20Z","abstract_excerpt":"Object detection in autonomous driving is frequently compromised by complex illumination. While event cameras offer a robust solution, they are susceptible to sudden contrast changes such as reflections which often trigger dense, misleading event signals. To overcome this, we leverage RGB-derived surface normal maps as explicit geometric constraints. Crucially, even when RGB degrades, they preserve low-frequency structural priors that effectively assist in event-based detection. Consequently, we present NRE-Net, a trimodal framework that integrates structural priors from surface Normal maps, a"},"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":"2508.02127","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-04T07:19:20Z","cross_cats_sorted":[],"title_canon_sha256":"1e5809cca8956c5c427cedfb8b7b8cc153461716b16ea6ab55800607f1577d04","abstract_canon_sha256":"da31840d176a0ec5faaaafb57edaa396e66516c4e94a62d271a10fc75155acba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:32.051292Z","signature_b64":"VZqANz2s/d0ABxEhis8R9PFULqaZd+F7LpWxUiX7DWFOcqubPUSHBVlvBv7UmBSkHC+e60AjQD2A5sFZX/BQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e3b3ad36c28abb4d9532c3fcef56602892ed3b87d4486143518d3b442906855","last_reissued_at":"2026-05-20T00:05:32.050525Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:32.050525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Event-based Object Detection with Monocular Normal Maps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuang Zhu, Hanqing Liu, Luoping Cui, Mingjie Liu","submitted_at":"2025-08-04T07:19:20Z","abstract_excerpt":"Object detection in autonomous driving is frequently compromised by complex illumination. While event cameras offer a robust solution, they are susceptible to sudden contrast changes such as reflections which often trigger dense, misleading event signals. To overcome this, we leverage RGB-derived surface normal maps as explicit geometric constraints. Crucially, even when RGB degrades, they preserve low-frequency structural priors that effectively assist in event-based detection. Consequently, we present NRE-Net, a trimodal framework that integrates structural priors from surface Normal maps, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02127","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.02127/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":"2508.02127","created_at":"2026-05-20T00:05:32.050644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.02127v2","created_at":"2026-05-20T00:05:32.050644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02127","created_at":"2026-05-20T00:05:32.050644+00:00"},{"alias_kind":"pith_short_12","alias_value":"HY5TVU3MFCV3","created_at":"2026-05-20T00:05:32.050644+00:00"},{"alias_kind":"pith_short_16","alias_value":"HY5TVU3MFCV3JWKT","created_at":"2026-05-20T00:05:32.050644+00:00"},{"alias_kind":"pith_short_8","alias_value":"HY5TVU3M","created_at":"2026-05-20T00:05:32.050644+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.19329","citing_title":"RE-VLM: Event-Augmented Vision-Language Model for Scene Understanding","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19329","citing_title":"RE-VLM: Event-Augmented Vision-Language Model for Scene Understanding","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11140","citing_title":"Sparse Hypergraph-Enhanced Frame-Event Object Detection with Fine-Grained MoE","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HY5TVU3MFCV3JWKTFQ7455LGAK","json":"https://pith.science/pith/HY5TVU3MFCV3JWKTFQ7455LGAK.json","graph_json":"https://pith.science/api/pith-number/HY5TVU3MFCV3JWKTFQ7455LGAK/graph.json","events_json":"https://pith.science/api/pith-number/HY5TVU3MFCV3JWKTFQ7455LGAK/events.json","paper":"https://pith.science/paper/HY5TVU3M"},"agent_actions":{"view_html":"https://pith.science/pith/HY5TVU3MFCV3JWKTFQ7455LGAK","download_json":"https://pith.science/pith/HY5TVU3MFCV3JWKTFQ7455LGAK.json","view_paper":"https://pith.science/paper/HY5TVU3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.02127&json=true","fetch_graph":"https://pith.science/api/pith-number/HY5TVU3MFCV3JWKTFQ7455LGAK/graph.json","fetch_events":"https://pith.science/api/pith-number/HY5TVU3MFCV3JWKTFQ7455LGAK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HY5TVU3MFCV3JWKTFQ7455LGAK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HY5TVU3MFCV3JWKTFQ7455LGAK/action/storage_attestation","attest_author":"https://pith.science/pith/HY5TVU3MFCV3JWKTFQ7455LGAK/action/author_attestation","sign_citation":"https://pith.science/pith/HY5TVU3MFCV3JWKTFQ7455LGAK/action/citation_signature","submit_replication":"https://pith.science/pith/HY5TVU3MFCV3JWKTFQ7455LGAK/action/replication_record"}},"created_at":"2026-05-20T00:05:32.050644+00:00","updated_at":"2026-05-20T00:05:32.050644+00:00"}