{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XTNRKIZQZI563CZIRBEWGBD5PB","short_pith_number":"pith:XTNRKIZQ","schema_version":"1.0","canonical_sha256":"bcdb152330ca3bed8b28884963047d78635f73783e033829a221658c51c3d6e7","source":{"kind":"arxiv","id":"2507.17083","version":1},"attestation_state":"computed","paper":{"title":"SDGOCC: Semantic and Depth-Guided Bird's-Eye View Transformation for 3D Multimodal Occupancy Prediction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenxu Dang, Jie Ma, Jie Zhan, Junfeng Ding, Pei An, Xuzhong Hu, Yunbiao Xu, Zaipeng Duan","submitted_at":"2025-07-22T23:49:40Z","abstract_excerpt":"Multimodal 3D occupancy prediction has garnered significant attention for its potential in autonomous driving. However, most existing approaches are single-modality: camera-based methods lack depth information, while LiDAR-based methods struggle with occlusions. Current lightweight methods primarily rely on the Lift-Splat-Shoot (LSS) pipeline, which suffers from inaccurate depth estimation and fails to fully exploit the geometric and semantic information of 3D LiDAR points. Therefore, we propose a novel multimodal occupancy prediction network called SDG-OCC, which incorporates a joint semantic"},"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":"2507.17083","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-22T23:49:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"45c05c1871fcbc7dad720f30708fa698e0dcd355780a6211d5e1d48034c9c46d","abstract_canon_sha256":"2e0eef9ee318e60c57218021c36d666dad2edea7465cb8840015bd078dbcbe97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:01.316988Z","signature_b64":"Z2D7UpgMSIRyBXcFHPSLjvhs5WRAQdqa9ELki5+LDwSkHQ9OniohSb8i0pnP9xToY8R8naAATeT0atIKXRl+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcdb152330ca3bed8b28884963047d78635f73783e033829a221658c51c3d6e7","last_reissued_at":"2026-07-05T11:42:01.316486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:01.316486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SDGOCC: Semantic and Depth-Guided Bird's-Eye View Transformation for 3D Multimodal Occupancy Prediction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenxu Dang, Jie Ma, Jie Zhan, Junfeng Ding, Pei An, Xuzhong Hu, Yunbiao Xu, Zaipeng Duan","submitted_at":"2025-07-22T23:49:40Z","abstract_excerpt":"Multimodal 3D occupancy prediction has garnered significant attention for its potential in autonomous driving. However, most existing approaches are single-modality: camera-based methods lack depth information, while LiDAR-based methods struggle with occlusions. Current lightweight methods primarily rely on the Lift-Splat-Shoot (LSS) pipeline, which suffers from inaccurate depth estimation and fails to fully exploit the geometric and semantic information of 3D LiDAR points. Therefore, we propose a novel multimodal occupancy prediction network called SDG-OCC, which incorporates a joint semantic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17083","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/2507.17083/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":"2507.17083","created_at":"2026-07-05T11:42:01.316544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.17083v1","created_at":"2026-07-05T11:42:01.316544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17083","created_at":"2026-07-05T11:42:01.316544+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTNRKIZQZI56","created_at":"2026-07-05T11:42:01.316544+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTNRKIZQZI563CZI","created_at":"2026-07-05T11:42:01.316544+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTNRKIZQ","created_at":"2026-07-05T11:42:01.316544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XTNRKIZQZI563CZIRBEWGBD5PB","json":"https://pith.science/pith/XTNRKIZQZI563CZIRBEWGBD5PB.json","graph_json":"https://pith.science/api/pith-number/XTNRKIZQZI563CZIRBEWGBD5PB/graph.json","events_json":"https://pith.science/api/pith-number/XTNRKIZQZI563CZIRBEWGBD5PB/events.json","paper":"https://pith.science/paper/XTNRKIZQ"},"agent_actions":{"view_html":"https://pith.science/pith/XTNRKIZQZI563CZIRBEWGBD5PB","download_json":"https://pith.science/pith/XTNRKIZQZI563CZIRBEWGBD5PB.json","view_paper":"https://pith.science/paper/XTNRKIZQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.17083&json=true","fetch_graph":"https://pith.science/api/pith-number/XTNRKIZQZI563CZIRBEWGBD5PB/graph.json","fetch_events":"https://pith.science/api/pith-number/XTNRKIZQZI563CZIRBEWGBD5PB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTNRKIZQZI563CZIRBEWGBD5PB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTNRKIZQZI563CZIRBEWGBD5PB/action/storage_attestation","attest_author":"https://pith.science/pith/XTNRKIZQZI563CZIRBEWGBD5PB/action/author_attestation","sign_citation":"https://pith.science/pith/XTNRKIZQZI563CZIRBEWGBD5PB/action/citation_signature","submit_replication":"https://pith.science/pith/XTNRKIZQZI563CZIRBEWGBD5PB/action/replication_record"}},"created_at":"2026-07-05T11:42:01.316544+00:00","updated_at":"2026-07-05T11:42:01.316544+00:00"}