{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZU5XEUQMMNCMKOIUGPXUKMIPUK","short_pith_number":"pith:ZU5XEUQM","schema_version":"1.0","canonical_sha256":"cd3b72520c6344c5391433ef45310fa2a28739bc2fa2144609c31ffc55bb00b2","source":{"kind":"arxiv","id":"2307.13510","version":3},"attestation_state":"computed","paper":{"title":"HeightFormer: Explicit Height Modeling without Extra Data for Camera-only 3D Object Detection in Bird's Eye View","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ruixiang Li, Xi Li, Xinhai Zhao, Yiming Wu, Zequn Qin","submitted_at":"2023-07-25T14:02:02Z","abstract_excerpt":"Vision-based Bird's Eye View (BEV) representation is an emerging perception formulation for autonomous driving. The core challenge is to construct BEV space with multi-camera features, which is a one-to-many ill-posed problem. Diving into all previous BEV representation generation methods, we found that most of them fall into two types: modeling depths in image views or modeling heights in the BEV space, mostly in an implicit way. In this work, we propose to explicitly model heights in the BEV space, which needs no extra data like LiDAR and can fit arbitrary camera rigs and types compared to m"},"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":"2307.13510","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-25T14:02:02Z","cross_cats_sorted":[],"title_canon_sha256":"938ad44dce1a9404973a4e7e45af2d245dd298c301850688b6283b2eaa0e4596","abstract_canon_sha256":"32a054f96893297f1159ad8de710ab1668c2582089dc7338f60aa45f2c75b0e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:09.399662Z","signature_b64":"806s1716TcUIzDlDO2Y4dNfCmYMJ4ACRatZnneonsMR/I3UEekkfgkR9FHIO1bY8qLXJrm7CPgXdypaZtFhADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd3b72520c6344c5391433ef45310fa2a28739bc2fa2144609c31ffc55bb00b2","last_reissued_at":"2026-07-05T08:44:09.399221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:09.399221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HeightFormer: Explicit Height Modeling without Extra Data for Camera-only 3D Object Detection in Bird's Eye View","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ruixiang Li, Xi Li, Xinhai Zhao, Yiming Wu, Zequn Qin","submitted_at":"2023-07-25T14:02:02Z","abstract_excerpt":"Vision-based Bird's Eye View (BEV) representation is an emerging perception formulation for autonomous driving. The core challenge is to construct BEV space with multi-camera features, which is a one-to-many ill-posed problem. Diving into all previous BEV representation generation methods, we found that most of them fall into two types: modeling depths in image views or modeling heights in the BEV space, mostly in an implicit way. In this work, we propose to explicitly model heights in the BEV space, which needs no extra data like LiDAR and can fit arbitrary camera rigs and types compared to m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13510","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/2307.13510/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":"2307.13510","created_at":"2026-07-05T08:44:09.399275+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.13510v3","created_at":"2026-07-05T08:44:09.399275+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13510","created_at":"2026-07-05T08:44:09.399275+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZU5XEUQMMNCM","created_at":"2026-07-05T08:44:09.399275+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZU5XEUQMMNCMKOIU","created_at":"2026-07-05T08:44:09.399275+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZU5XEUQM","created_at":"2026-07-05T08:44:09.399275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.16889","citing_title":"Anchor3DLane++: 3D Lane Detection via Sample-Adaptive Sparse 3D Anchor Regression","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZU5XEUQMMNCMKOIUGPXUKMIPUK","json":"https://pith.science/pith/ZU5XEUQMMNCMKOIUGPXUKMIPUK.json","graph_json":"https://pith.science/api/pith-number/ZU5XEUQMMNCMKOIUGPXUKMIPUK/graph.json","events_json":"https://pith.science/api/pith-number/ZU5XEUQMMNCMKOIUGPXUKMIPUK/events.json","paper":"https://pith.science/paper/ZU5XEUQM"},"agent_actions":{"view_html":"https://pith.science/pith/ZU5XEUQMMNCMKOIUGPXUKMIPUK","download_json":"https://pith.science/pith/ZU5XEUQMMNCMKOIUGPXUKMIPUK.json","view_paper":"https://pith.science/paper/ZU5XEUQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.13510&json=true","fetch_graph":"https://pith.science/api/pith-number/ZU5XEUQMMNCMKOIUGPXUKMIPUK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZU5XEUQMMNCMKOIUGPXUKMIPUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZU5XEUQMMNCMKOIUGPXUKMIPUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZU5XEUQMMNCMKOIUGPXUKMIPUK/action/storage_attestation","attest_author":"https://pith.science/pith/ZU5XEUQMMNCMKOIUGPXUKMIPUK/action/author_attestation","sign_citation":"https://pith.science/pith/ZU5XEUQMMNCMKOIUGPXUKMIPUK/action/citation_signature","submit_replication":"https://pith.science/pith/ZU5XEUQMMNCMKOIUGPXUKMIPUK/action/replication_record"}},"created_at":"2026-07-05T08:44:09.399275+00:00","updated_at":"2026-07-05T08:44:09.399275+00:00"}