{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:47ZGZ5MPHOMDS2TXCUIPHLSDSM","short_pith_number":"pith:47ZGZ5MP","schema_version":"1.0","canonical_sha256":"e7f26cf58f3b98396a771510f3ae43933601eacfc46384a35defef87e7e9481c","source":{"kind":"arxiv","id":"2502.19694","version":2},"attestation_state":"computed","paper":{"title":"BEVDiffuser: Plug-and-Play Diffusion Model for BEV Denoising with Ground-Truth Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhirup Mallik, Burhaneddin Yaman, Feng Tao, Liu Ren, Sheng Cheng, Xin Ye","submitted_at":"2025-02-27T02:11:29Z","abstract_excerpt":"Bird's-eye-view (BEV) representations play a crucial role in autonomous driving tasks. Despite recent advancements in BEV generation, inherent noise, stemming from sensor limitations and the learning process, remains largely unaddressed, resulting in suboptimal BEV representations that adversely impact the performance of downstream tasks. To address this, we propose BEVDiffuser, a novel diffusion model that effectively denoises BEV feature maps using the ground-truth object layout as guidance. BEVDiffuser can be operated in a plug-and-play manner during training time to enhance existing BEV mo"},"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":"2502.19694","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T02:11:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b124167c18f3293854901f1728026eab440873e9ad8e664b74577aec3e7144c3","abstract_canon_sha256":"f17fd4d3eee865b2224b39e9350283faf890c7f599b57f6e1ca3748b241f5c36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:43.179691Z","signature_b64":"ThhATs263cEBDz59jFNWBWWqwOJA+OulcwCfV+nkGBHSs4FUmH08WkVP2YTouxoSZBEjRFi3IXqIdpQvAw4vBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7f26cf58f3b98396a771510f3ae43933601eacfc46384a35defef87e7e9481c","last_reissued_at":"2026-07-05T10:38:43.179244Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:43.179244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BEVDiffuser: Plug-and-Play Diffusion Model for BEV Denoising with Ground-Truth Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhirup Mallik, Burhaneddin Yaman, Feng Tao, Liu Ren, Sheng Cheng, Xin Ye","submitted_at":"2025-02-27T02:11:29Z","abstract_excerpt":"Bird's-eye-view (BEV) representations play a crucial role in autonomous driving tasks. Despite recent advancements in BEV generation, inherent noise, stemming from sensor limitations and the learning process, remains largely unaddressed, resulting in suboptimal BEV representations that adversely impact the performance of downstream tasks. To address this, we propose BEVDiffuser, a novel diffusion model that effectively denoises BEV feature maps using the ground-truth object layout as guidance. BEVDiffuser can be operated in a plug-and-play manner during training time to enhance existing BEV mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19694","kind":"arxiv","version":2},"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/2502.19694/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":"2502.19694","created_at":"2026-07-05T10:38:43.179294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.19694v2","created_at":"2026-07-05T10:38:43.179294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19694","created_at":"2026-07-05T10:38:43.179294+00:00"},{"alias_kind":"pith_short_12","alias_value":"47ZGZ5MPHOMD","created_at":"2026-07-05T10:38:43.179294+00:00"},{"alias_kind":"pith_short_16","alias_value":"47ZGZ5MPHOMDS2TX","created_at":"2026-07-05T10:38:43.179294+00:00"},{"alias_kind":"pith_short_8","alias_value":"47ZGZ5MP","created_at":"2026-07-05T10:38:43.179294+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22931","citing_title":"BEV-Denoise: Learning Intrinsic Noise for Accurate Bird's-Eye-View Semantic Segmentation","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/47ZGZ5MPHOMDS2TXCUIPHLSDSM","json":"https://pith.science/pith/47ZGZ5MPHOMDS2TXCUIPHLSDSM.json","graph_json":"https://pith.science/api/pith-number/47ZGZ5MPHOMDS2TXCUIPHLSDSM/graph.json","events_json":"https://pith.science/api/pith-number/47ZGZ5MPHOMDS2TXCUIPHLSDSM/events.json","paper":"https://pith.science/paper/47ZGZ5MP"},"agent_actions":{"view_html":"https://pith.science/pith/47ZGZ5MPHOMDS2TXCUIPHLSDSM","download_json":"https://pith.science/pith/47ZGZ5MPHOMDS2TXCUIPHLSDSM.json","view_paper":"https://pith.science/paper/47ZGZ5MP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.19694&json=true","fetch_graph":"https://pith.science/api/pith-number/47ZGZ5MPHOMDS2TXCUIPHLSDSM/graph.json","fetch_events":"https://pith.science/api/pith-number/47ZGZ5MPHOMDS2TXCUIPHLSDSM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47ZGZ5MPHOMDS2TXCUIPHLSDSM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47ZGZ5MPHOMDS2TXCUIPHLSDSM/action/storage_attestation","attest_author":"https://pith.science/pith/47ZGZ5MPHOMDS2TXCUIPHLSDSM/action/author_attestation","sign_citation":"https://pith.science/pith/47ZGZ5MPHOMDS2TXCUIPHLSDSM/action/citation_signature","submit_replication":"https://pith.science/pith/47ZGZ5MPHOMDS2TXCUIPHLSDSM/action/replication_record"}},"created_at":"2026-07-05T10:38:43.179294+00:00","updated_at":"2026-07-05T10:38:43.179294+00:00"}