{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6PMVQS4Q2BGPGNVCTNXN2ABTTE","short_pith_number":"pith:6PMVQS4Q","schema_version":"1.0","canonical_sha256":"f3d9584b90d04cf336a29b6edd0033992e156667f4152cf3761253890e4b94fa","source":{"kind":"arxiv","id":"2205.13542","version":3},"attestation_state":"computed","paper":{"title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Amini, Daniela Rus, Haotian Tang, Huizi Mao, Song Han, Xinyu Yang, Zhijian Liu","submitted_at":"2022-05-26T17:59:35Z","abstract_excerpt":"Multi-sensor fusion is essential for an accurate and reliable autonomous driving system. Recent approaches are based on point-level fusion: augmenting the LiDAR point cloud with camera features. However, the camera-to-LiDAR projection throws away the semantic density of camera features, hindering the effectiveness of such methods, especially for semantic-oriented tasks (such as 3D scene segmentation). In this paper, we break this deeply-rooted convention with BEVFusion, an efficient and generic multi-task multi-sensor fusion framework. It unifies multi-modal features in the shared bird's-eye v"},"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":"2205.13542","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-26T17:59:35Z","cross_cats_sorted":[],"title_canon_sha256":"7b09aef40a4ba7cdc94b94f23863c5d7cdd68457edbdfef267aef43680efbf6a","abstract_canon_sha256":"93b810ac1f451f4ed03112883a484e90065c251b04f9a4637361e5b3f4f21877"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:22.026024Z","signature_b64":"1iUlTDpO1zfABI1MoaVO07OA3lksa3Dac85LdFjf85vxfsiZd7jkv8GmeF/d/kUmMGSu2NcSb+5v/hiK6H+zAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3d9584b90d04cf336a29b6edd0033992e156667f4152cf3761253890e4b94fa","last_reissued_at":"2026-07-05T09:01:22.025666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:22.025666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Amini, Daniela Rus, Haotian Tang, Huizi Mao, Song Han, Xinyu Yang, Zhijian Liu","submitted_at":"2022-05-26T17:59:35Z","abstract_excerpt":"Multi-sensor fusion is essential for an accurate and reliable autonomous driving system. Recent approaches are based on point-level fusion: augmenting the LiDAR point cloud with camera features. However, the camera-to-LiDAR projection throws away the semantic density of camera features, hindering the effectiveness of such methods, especially for semantic-oriented tasks (such as 3D scene segmentation). In this paper, we break this deeply-rooted convention with BEVFusion, an efficient and generic multi-task multi-sensor fusion framework. It unifies multi-modal features in the shared bird's-eye v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13542","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/2205.13542/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":"2205.13542","created_at":"2026-07-05T09:01:22.025717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.13542v3","created_at":"2026-07-05T09:01:22.025717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13542","created_at":"2026-07-05T09:01:22.025717+00:00"},{"alias_kind":"pith_short_12","alias_value":"6PMVQS4Q2BGP","created_at":"2026-07-05T09:01:22.025717+00:00"},{"alias_kind":"pith_short_16","alias_value":"6PMVQS4Q2BGPGNVC","created_at":"2026-07-05T09:01:22.025717+00:00"},{"alias_kind":"pith_short_8","alias_value":"6PMVQS4Q","created_at":"2026-07-05T09:01:22.025717+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17598","citing_title":"MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22997","citing_title":"Scene Reconstruction as Mapping Priors for 3D Detection","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2312.06409","citing_title":"LiCamPose: Combining Multi-View LiDAR and RGB Cameras for Robust Single-timestamp 3D Human Pose Estimation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16127","citing_title":"WeatherOcc3D: VLM-Assisted Adverse Weather Aware 3D Semantic Occupancy Prediction","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18074","citing_title":"4DLidarOpen: An Open 4D FMCW Lidar Dataset for Motion-Aware Autonomous Driving","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2510.26641","citing_title":"All You Need for Object Detection: From Pixels, Points, and Prompts to Next-Gen Fusion and Multimodal LLMs/VLMs in Autonomous Vehicles","ref_index":291,"is_internal_anchor":false},{"citing_arxiv_id":"2602.21484","citing_title":"Unified Unsupervised and Sparsely-Supervised 3D Object Detection by Semantic Pseudo-Labeling and Prototype Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17714","citing_title":"From Virtual Environments to Real-World Trials: Emerging Trends in Autonomous Driving","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2301.00493","citing_title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25405","citing_title":"Leveraging Previous-Traversal Point Cloud Map Priors for Camera-Based 3D Object Detection and Tracking","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25574","citing_title":"Control Your Queries: Heterogeneous Query Interaction for Camera-Radar Fusion","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18476","citing_title":"SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detection","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6PMVQS4Q2BGPGNVCTNXN2ABTTE","json":"https://pith.science/pith/6PMVQS4Q2BGPGNVCTNXN2ABTTE.json","graph_json":"https://pith.science/api/pith-number/6PMVQS4Q2BGPGNVCTNXN2ABTTE/graph.json","events_json":"https://pith.science/api/pith-number/6PMVQS4Q2BGPGNVCTNXN2ABTTE/events.json","paper":"https://pith.science/paper/6PMVQS4Q"},"agent_actions":{"view_html":"https://pith.science/pith/6PMVQS4Q2BGPGNVCTNXN2ABTTE","download_json":"https://pith.science/pith/6PMVQS4Q2BGPGNVCTNXN2ABTTE.json","view_paper":"https://pith.science/paper/6PMVQS4Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.13542&json=true","fetch_graph":"https://pith.science/api/pith-number/6PMVQS4Q2BGPGNVCTNXN2ABTTE/graph.json","fetch_events":"https://pith.science/api/pith-number/6PMVQS4Q2BGPGNVCTNXN2ABTTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6PMVQS4Q2BGPGNVCTNXN2ABTTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6PMVQS4Q2BGPGNVCTNXN2ABTTE/action/storage_attestation","attest_author":"https://pith.science/pith/6PMVQS4Q2BGPGNVCTNXN2ABTTE/action/author_attestation","sign_citation":"https://pith.science/pith/6PMVQS4Q2BGPGNVCTNXN2ABTTE/action/citation_signature","submit_replication":"https://pith.science/pith/6PMVQS4Q2BGPGNVCTNXN2ABTTE/action/replication_record"}},"created_at":"2026-07-05T09:01:22.025717+00:00","updated_at":"2026-07-05T09:01:22.025717+00:00"}