{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NTKP2YVNSK2G2TMHBYAOERKU4I","short_pith_number":"pith:NTKP2YVN","schema_version":"1.0","canonical_sha256":"6cd4fd62ad92b46d4d870e00e24554e2363b464aa8752e27ad21be72fa6f5dce","source":{"kind":"arxiv","id":"2401.03836","version":5},"attestation_state":"computed","paper":{"title":"WidthFormer: Toward Efficient Transformer-based BEV View Transformation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenhongyi Yang, Elliot J. Crowley, Lichao Huang, Tianwei Lin","submitted_at":"2024-01-08T11:50:23Z","abstract_excerpt":"We present WidthFormer, a novel transformer-based module to compute Bird's-Eye-View (BEV) representations from multi-view cameras for real-time autonomous-driving applications. WidthFormer is computationally efficient, robust and does not require any special engineering effort to deploy. We first introduce a novel 3D positional encoding mechanism capable of accurately encapsulating 3D geometric information, which enables our model to compute high-quality BEV representations with only a single transformer decoder layer. This mechanism is also beneficial for existing sparse 3D object detectors. "},"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":"2401.03836","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-08T11:50:23Z","cross_cats_sorted":[],"title_canon_sha256":"82e525a5fcdb2ebaa982e79dd2084d9c2f204d71a42a840a32693b82e7dbc504","abstract_canon_sha256":"38cbdfdd6487a883c071f1519517a97ee765902edb3edbc691cfd34729dd2526"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:09.116776Z","signature_b64":"KDQb1bpbYoG4oKE4axz0EAElHYxs1WIlPnGs5oSK14aoMOGrf7xYGXT9SbR9YW6EI8Un+9YKemc6RjCxE9+IBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cd4fd62ad92b46d4d870e00e24554e2363b464aa8752e27ad21be72fa6f5dce","last_reissued_at":"2026-07-05T08:50:09.116287Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:09.116287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WidthFormer: Toward Efficient Transformer-based BEV View Transformation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenhongyi Yang, Elliot J. Crowley, Lichao Huang, Tianwei Lin","submitted_at":"2024-01-08T11:50:23Z","abstract_excerpt":"We present WidthFormer, a novel transformer-based module to compute Bird's-Eye-View (BEV) representations from multi-view cameras for real-time autonomous-driving applications. WidthFormer is computationally efficient, robust and does not require any special engineering effort to deploy. We first introduce a novel 3D positional encoding mechanism capable of accurately encapsulating 3D geometric information, which enables our model to compute high-quality BEV representations with only a single transformer decoder layer. This mechanism is also beneficial for existing sparse 3D object detectors. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03836","kind":"arxiv","version":5},"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/2401.03836/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":"2401.03836","created_at":"2026-07-05T08:50:09.116358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.03836v5","created_at":"2026-07-05T08:50:09.116358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03836","created_at":"2026-07-05T08:50:09.116358+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTKP2YVNSK2G","created_at":"2026-07-05T08:50:09.116358+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTKP2YVNSK2G2TMH","created_at":"2026-07-05T08:50:09.116358+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTKP2YVN","created_at":"2026-07-05T08:50:09.116358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18884","citing_title":"HV-BEV: Decoupling Horizontal and Vertical Feature Sampling for Multi-View 3D Object Detection","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NTKP2YVNSK2G2TMHBYAOERKU4I","json":"https://pith.science/pith/NTKP2YVNSK2G2TMHBYAOERKU4I.json","graph_json":"https://pith.science/api/pith-number/NTKP2YVNSK2G2TMHBYAOERKU4I/graph.json","events_json":"https://pith.science/api/pith-number/NTKP2YVNSK2G2TMHBYAOERKU4I/events.json","paper":"https://pith.science/paper/NTKP2YVN"},"agent_actions":{"view_html":"https://pith.science/pith/NTKP2YVNSK2G2TMHBYAOERKU4I","download_json":"https://pith.science/pith/NTKP2YVNSK2G2TMHBYAOERKU4I.json","view_paper":"https://pith.science/paper/NTKP2YVN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.03836&json=true","fetch_graph":"https://pith.science/api/pith-number/NTKP2YVNSK2G2TMHBYAOERKU4I/graph.json","fetch_events":"https://pith.science/api/pith-number/NTKP2YVNSK2G2TMHBYAOERKU4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTKP2YVNSK2G2TMHBYAOERKU4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTKP2YVNSK2G2TMHBYAOERKU4I/action/storage_attestation","attest_author":"https://pith.science/pith/NTKP2YVNSK2G2TMHBYAOERKU4I/action/author_attestation","sign_citation":"https://pith.science/pith/NTKP2YVNSK2G2TMHBYAOERKU4I/action/citation_signature","submit_replication":"https://pith.science/pith/NTKP2YVNSK2G2TMHBYAOERKU4I/action/replication_record"}},"created_at":"2026-07-05T08:50:09.116358+00:00","updated_at":"2026-07-05T08:50:09.116358+00:00"}