{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N2D4QICJIW5WUESU6SV3NQDVTC","short_pith_number":"pith:N2D4QICJ","schema_version":"1.0","canonical_sha256":"6e87c8204945bb6a1254f4abb6c0759893eb6e16adbd35c2e18721a75911690e","source":{"kind":"arxiv","id":"2508.11185","version":1},"attestation_state":"computed","paper":{"title":"CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhinav Kumar, Liu Ren, Xiaoming Liu, Xinyu Huang, Yuliang Guo, Zhihao Zhang","submitted_at":"2025-08-15T03:27:17Z","abstract_excerpt":"Monocular 3D object detectors, while effective on data from one ego camera height, struggle with unseen or out-of-distribution camera heights. Existing methods often rely on Plucker embeddings, image transformations or data augmentation. This paper takes a step towards this understudied problem by first investigating the impact of camera height variations on state-of-the-art (SoTA) Mono3D models. With a systematic analysis on the extended CARLA dataset with multiple camera heights, we observe that depth estimation is a primary factor influencing performance under height variations. We mathemat"},"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":"2508.11185","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-15T03:27:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"08fcf95a35f43bb381c9e286781877b5bfacd8a46ccd291f207b837bb073e9b0","abstract_canon_sha256":"203cb8052bf6203dd7de4ab4a9304e0c018d5cbd6b67a60ce01c1a7e8f1dfb3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:20.207204Z","signature_b64":"ACmEH3VWgfSjzDIzJkqlEUmS9MoF2TCAi5UT1bBxiTN9Hi0HoJbQcRX9xagz3NQalR6kycfA130qfc6zykMhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e87c8204945bb6a1254f4abb6c0759893eb6e16adbd35c2e18721a75911690e","last_reissued_at":"2026-07-05T11:54:20.206743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:20.206743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhinav Kumar, Liu Ren, Xiaoming Liu, Xinyu Huang, Yuliang Guo, Zhihao Zhang","submitted_at":"2025-08-15T03:27:17Z","abstract_excerpt":"Monocular 3D object detectors, while effective on data from one ego camera height, struggle with unseen or out-of-distribution camera heights. Existing methods often rely on Plucker embeddings, image transformations or data augmentation. This paper takes a step towards this understudied problem by first investigating the impact of camera height variations on state-of-the-art (SoTA) Mono3D models. With a systematic analysis on the extended CARLA dataset with multiple camera heights, we observe that depth estimation is a primary factor influencing performance under height variations. We mathemat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11185","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/2508.11185/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":"2508.11185","created_at":"2026-07-05T11:54:20.206798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11185v1","created_at":"2026-07-05T11:54:20.206798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11185","created_at":"2026-07-05T11:54:20.206798+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2D4QICJIW5W","created_at":"2026-07-05T11:54:20.206798+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2D4QICJIW5WUESU","created_at":"2026-07-05T11:54:20.206798+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2D4QICJ","created_at":"2026-07-05T11:54:20.206798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.11181","citing_title":"HistoViT: Vision Transformer for Accurate and Scalable Histopathological Cancer Diagnosis","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2D4QICJIW5WUESU6SV3NQDVTC","json":"https://pith.science/pith/N2D4QICJIW5WUESU6SV3NQDVTC.json","graph_json":"https://pith.science/api/pith-number/N2D4QICJIW5WUESU6SV3NQDVTC/graph.json","events_json":"https://pith.science/api/pith-number/N2D4QICJIW5WUESU6SV3NQDVTC/events.json","paper":"https://pith.science/paper/N2D4QICJ"},"agent_actions":{"view_html":"https://pith.science/pith/N2D4QICJIW5WUESU6SV3NQDVTC","download_json":"https://pith.science/pith/N2D4QICJIW5WUESU6SV3NQDVTC.json","view_paper":"https://pith.science/paper/N2D4QICJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11185&json=true","fetch_graph":"https://pith.science/api/pith-number/N2D4QICJIW5WUESU6SV3NQDVTC/graph.json","fetch_events":"https://pith.science/api/pith-number/N2D4QICJIW5WUESU6SV3NQDVTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2D4QICJIW5WUESU6SV3NQDVTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2D4QICJIW5WUESU6SV3NQDVTC/action/storage_attestation","attest_author":"https://pith.science/pith/N2D4QICJIW5WUESU6SV3NQDVTC/action/author_attestation","sign_citation":"https://pith.science/pith/N2D4QICJIW5WUESU6SV3NQDVTC/action/citation_signature","submit_replication":"https://pith.science/pith/N2D4QICJIW5WUESU6SV3NQDVTC/action/replication_record"}},"created_at":"2026-07-05T11:54:20.206798+00:00","updated_at":"2026-07-05T11:54:20.206798+00:00"}