{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DXKHRFACQEO36TZMFDGJYYW4DY","short_pith_number":"pith:DXKHRFAC","schema_version":"1.0","canonical_sha256":"1dd4789402811dbf4f2c28cc9c62dc1e3ef9d99e5fc43c090ab7133240e50a07","source":{"kind":"arxiv","id":"2205.09743","version":1},"attestation_state":"computed","paper":{"title":"BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guan Huang, Jie Zhou, Jiwen Lu, Junjie Huang, Wenzhao Zheng, Yunpeng Zhang, Zheng Zhu","submitted_at":"2022-05-19T17:55:35Z","abstract_excerpt":"In this paper, we present BEVerse, a unified framework for 3D perception and prediction based on multi-camera systems. Unlike existing studies focusing on the improvement of single-task approaches, BEVerse features in producing spatio-temporal Birds-Eye-View (BEV) representations from multi-camera videos and jointly reasoning about multiple tasks for vision-centric autonomous driving. Specifically, BEVerse first performs shared feature extraction and lifting to generate 4D BEV representations from multi-timestamp and multi-view images. After the ego-motion alignment, the spatio-temporal encode"},"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":"2205.09743","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-19T17:55:35Z","cross_cats_sorted":[],"title_canon_sha256":"6d7da74750efdb5b6a6ea7ff46c42e888763e034ea59d036dff97525be97e070","abstract_canon_sha256":"d39d0d8039a372dcee1145923a30d9771962cb6f10962afe87bb955587e558f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:48.242093Z","signature_b64":"dI6hJOOWUHFNTiJ+Z9fly0CaKdlRkt45rwuui4uLrZguYUk32YkFlH3Cuw8eX3fJ9vu1gHV1DOTaZ0HFMfbgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dd4789402811dbf4f2c28cc9c62dc1e3ef9d99e5fc43c090ab7133240e50a07","last_reissued_at":"2026-07-05T04:24:48.241464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:48.241464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guan Huang, Jie Zhou, Jiwen Lu, Junjie Huang, Wenzhao Zheng, Yunpeng Zhang, Zheng Zhu","submitted_at":"2022-05-19T17:55:35Z","abstract_excerpt":"In this paper, we present BEVerse, a unified framework for 3D perception and prediction based on multi-camera systems. Unlike existing studies focusing on the improvement of single-task approaches, BEVerse features in producing spatio-temporal Birds-Eye-View (BEV) representations from multi-camera videos and jointly reasoning about multiple tasks for vision-centric autonomous driving. Specifically, BEVerse first performs shared feature extraction and lifting to generate 4D BEV representations from multi-timestamp and multi-view images. After the ego-motion alignment, the spatio-temporal encode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09743","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/2205.09743/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":"2205.09743","created_at":"2026-07-05T04:24:48.241524+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.09743v1","created_at":"2026-07-05T04:24:48.241524+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09743","created_at":"2026-07-05T04:24:48.241524+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXKHRFACQEO3","created_at":"2026-07-05T04:24:48.241524+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXKHRFACQEO36TZM","created_at":"2026-07-05T04:24:48.241524+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXKHRFAC","created_at":"2026-07-05T04:24:48.241524+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11507","citing_title":"SceneMiner: Identity-Preserving Multi-Task Fine-Tuning for Unified BEV Scene Mining","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07708","citing_title":"Cross-View Urban Traffic Dataset: Drone-Supervised Ground Truth for Monocular Bird's-Eye View Localization","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2304.10891","citing_title":"Transformer-Based Autonomous Driving Models and Deployment-Oriented Compression: A Survey","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13243","citing_title":"VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15925","citing_title":"VERDI: VLM-Embedded Reasoning for Autonomous Driving","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2512.18954","citing_title":"VOIC: Visible-Occluded Integrated Guidance for 3D Semantic Scene Completion","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02930","citing_title":"BEVPredFormer: Spatio-temporal Attention for BEV Instance Prediction in Autonomous Driving","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01478","citing_title":"LIE: LiDAR-only HD Map Construction with Intensity Enhancement via Online Knowledge Distillation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19411","citing_title":"GOLD-BEV: GrOund and aeriaL Data for Dense Semantic BEV Mapping of Dynamic Scenes","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12918","citing_title":"Radar-Camera BEV Multi-Task Learning with Cross-Task Attention Bridge for Joint 3D Detection and Segmentation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXKHRFACQEO36TZMFDGJYYW4DY","json":"https://pith.science/pith/DXKHRFACQEO36TZMFDGJYYW4DY.json","graph_json":"https://pith.science/api/pith-number/DXKHRFACQEO36TZMFDGJYYW4DY/graph.json","events_json":"https://pith.science/api/pith-number/DXKHRFACQEO36TZMFDGJYYW4DY/events.json","paper":"https://pith.science/paper/DXKHRFAC"},"agent_actions":{"view_html":"https://pith.science/pith/DXKHRFACQEO36TZMFDGJYYW4DY","download_json":"https://pith.science/pith/DXKHRFACQEO36TZMFDGJYYW4DY.json","view_paper":"https://pith.science/paper/DXKHRFAC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.09743&json=true","fetch_graph":"https://pith.science/api/pith-number/DXKHRFACQEO36TZMFDGJYYW4DY/graph.json","fetch_events":"https://pith.science/api/pith-number/DXKHRFACQEO36TZMFDGJYYW4DY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXKHRFACQEO36TZMFDGJYYW4DY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXKHRFACQEO36TZMFDGJYYW4DY/action/storage_attestation","attest_author":"https://pith.science/pith/DXKHRFACQEO36TZMFDGJYYW4DY/action/author_attestation","sign_citation":"https://pith.science/pith/DXKHRFACQEO36TZMFDGJYYW4DY/action/citation_signature","submit_replication":"https://pith.science/pith/DXKHRFACQEO36TZMFDGJYYW4DY/action/replication_record"}},"created_at":"2026-07-05T04:24:48.241524+00:00","updated_at":"2026-07-05T04:24:48.241524+00:00"}