{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2FEFMHF4ANM7U4LXSO5ASRDISX","short_pith_number":"pith:2FEFMHF4","schema_version":"1.0","canonical_sha256":"d148561cbc0359fa717793ba09446895efc34a3c6436920e55ba2312199d9c25","source":{"kind":"arxiv","id":"2203.05625","version":3},"attestation_state":"computed","paper":{"title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Sun, Tiancai Wang, Xiangyu Zhang, Yingfei Liu","submitted_at":"2022-03-10T20:33:28Z","abstract_excerpt":"In this paper, we develop position embedding transformation (PETR) for multi-view 3D object detection. PETR encodes the position information of 3D coordinates into image features, producing the 3D position-aware features. Object query can perceive the 3D position-aware features and perform end-to-end object detection. PETR achieves state-of-the-art performance (50.4% NDS and 44.1% mAP) on standard nuScenes dataset and ranks 1st place on the benchmark. It can serve as a simple yet strong baseline for future research. Code is available at \\url{https://github.com/megvii-research/PETR}."},"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":"2203.05625","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-10T20:33:28Z","cross_cats_sorted":[],"title_canon_sha256":"ff0e6e533049f53cca9b4c9efc35d06f504b3877d667e72d3b1d1c9f66bd72b6","abstract_canon_sha256":"9aa0e60a9716c4dcc190695e0d0a76cc8c7e18a6136fbe4b3e89599626311430"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:41:11.672576Z","signature_b64":"GSRnaBU/QB9Qgn3UCQNeeQyLmNQjSaX406iM9RHCXjN8CGH7gHjUqEAbIOoumb5boIgVzJQXnSzr9PWIi44JCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d148561cbc0359fa717793ba09446895efc34a3c6436920e55ba2312199d9c25","last_reissued_at":"2026-07-05T04:41:11.672072Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:41:11.672072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Sun, Tiancai Wang, Xiangyu Zhang, Yingfei Liu","submitted_at":"2022-03-10T20:33:28Z","abstract_excerpt":"In this paper, we develop position embedding transformation (PETR) for multi-view 3D object detection. PETR encodes the position information of 3D coordinates into image features, producing the 3D position-aware features. Object query can perceive the 3D position-aware features and perform end-to-end object detection. PETR achieves state-of-the-art performance (50.4% NDS and 44.1% mAP) on standard nuScenes dataset and ranks 1st place on the benchmark. It can serve as a simple yet strong baseline for future research. Code is available at \\url{https://github.com/megvii-research/PETR}."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.05625","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/2203.05625/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":"2203.05625","created_at":"2026-07-05T04:41:11.672131+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.05625v3","created_at":"2026-07-05T04:41:11.672131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.05625","created_at":"2026-07-05T04:41:11.672131+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FEFMHF4ANM7","created_at":"2026-07-05T04:41:11.672131+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FEFMHF4ANM7U4LX","created_at":"2026-07-05T04:41:11.672131+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FEFMHF4","created_at":"2026-07-05T04:41:11.672131+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.08237","citing_title":"Fast-BEV++: Fast by Algorithm, Deployable by Design","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2506.07002","citing_title":"BePo: Dual Representation for 3D Occupancy Prediction","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2602.23024","citing_title":"InCoM: Intent-Driven Perception and Structured Coordination for Mobile Manipulation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17915","citing_title":"OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13571","citing_title":"Radar-Informed 3D Multi-Object Tracking under Adverse Conditions","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2FEFMHF4ANM7U4LXSO5ASRDISX","json":"https://pith.science/pith/2FEFMHF4ANM7U4LXSO5ASRDISX.json","graph_json":"https://pith.science/api/pith-number/2FEFMHF4ANM7U4LXSO5ASRDISX/graph.json","events_json":"https://pith.science/api/pith-number/2FEFMHF4ANM7U4LXSO5ASRDISX/events.json","paper":"https://pith.science/paper/2FEFMHF4"},"agent_actions":{"view_html":"https://pith.science/pith/2FEFMHF4ANM7U4LXSO5ASRDISX","download_json":"https://pith.science/pith/2FEFMHF4ANM7U4LXSO5ASRDISX.json","view_paper":"https://pith.science/paper/2FEFMHF4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.05625&json=true","fetch_graph":"https://pith.science/api/pith-number/2FEFMHF4ANM7U4LXSO5ASRDISX/graph.json","fetch_events":"https://pith.science/api/pith-number/2FEFMHF4ANM7U4LXSO5ASRDISX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FEFMHF4ANM7U4LXSO5ASRDISX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FEFMHF4ANM7U4LXSO5ASRDISX/action/storage_attestation","attest_author":"https://pith.science/pith/2FEFMHF4ANM7U4LXSO5ASRDISX/action/author_attestation","sign_citation":"https://pith.science/pith/2FEFMHF4ANM7U4LXSO5ASRDISX/action/citation_signature","submit_replication":"https://pith.science/pith/2FEFMHF4ANM7U4LXSO5ASRDISX/action/replication_record"}},"created_at":"2026-07-05T04:41:11.672131+00:00","updated_at":"2026-07-05T04:41:11.672131+00:00"}