{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LLP3KQSVIYLLJW4KF5ENTINWOG","short_pith_number":"pith:LLP3KQSV","schema_version":"1.0","canonical_sha256":"5adfb542554616b4db8a2f48d9a1b671a98eda9163ea7860f58fc17186145f42","source":{"kind":"arxiv","id":"2412.06777","version":1},"attestation_state":"computed","paper":{"title":"Driv3R: Learning Dense 4D Reconstruction for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiwen Lu, Kurt Keutzer, Masayoshi Tomizuka, Wei Zhan, Wenzhao Zheng, Xin Fei, Yueqi Duan","submitted_at":"2024-12-09T18:58:03Z","abstract_excerpt":"Realtime 4D reconstruction for dynamic scenes remains a crucial challenge for autonomous driving perception. Most existing methods rely on depth estimation through self-supervision or multi-modality sensor fusion. In this paper, we propose Driv3R, a DUSt3R-based framework that directly regresses per-frame point maps from multi-view image sequences. To achieve streaming dense reconstruction, we maintain a memory pool to reason both spatial relationships across sensors and dynamic temporal contexts to enhance multi-view 3D consistency and temporal integration. Furthermore, we employ a 4D flow pr"},"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":"2412.06777","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T18:58:03Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2e3d4cd54beee5e121a68149dc71fccb004c9b4d421ba8f5c074768193bf9e89","abstract_canon_sha256":"dadb848dfea355040ce9783e627487b6fa10ead1722333100dc5ed8681de1e81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:37.759291Z","signature_b64":"YUxqaV0hHA7AMEn5aVsvsNRJ9LsBxKQ994cGOztMpqqvSVv4msWYPDtZaPKs0yZ2hDSCXjn9/J0RT7vae9SECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5adfb542554616b4db8a2f48d9a1b671a98eda9163ea7860f58fc17186145f42","last_reissued_at":"2026-07-05T09:46:37.758792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:37.758792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Driv3R: Learning Dense 4D Reconstruction for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiwen Lu, Kurt Keutzer, Masayoshi Tomizuka, Wei Zhan, Wenzhao Zheng, Xin Fei, Yueqi Duan","submitted_at":"2024-12-09T18:58:03Z","abstract_excerpt":"Realtime 4D reconstruction for dynamic scenes remains a crucial challenge for autonomous driving perception. Most existing methods rely on depth estimation through self-supervision or multi-modality sensor fusion. In this paper, we propose Driv3R, a DUSt3R-based framework that directly regresses per-frame point maps from multi-view image sequences. To achieve streaming dense reconstruction, we maintain a memory pool to reason both spatial relationships across sensors and dynamic temporal contexts to enhance multi-view 3D consistency and temporal integration. Furthermore, we employ a 4D flow pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06777","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/2412.06777/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":"2412.06777","created_at":"2026-07-05T09:46:37.758852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.06777v1","created_at":"2026-07-05T09:46:37.758852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06777","created_at":"2026-07-05T09:46:37.758852+00:00"},{"alias_kind":"pith_short_12","alias_value":"LLP3KQSVIYLL","created_at":"2026-07-05T09:46:37.758852+00:00"},{"alias_kind":"pith_short_16","alias_value":"LLP3KQSVIYLLJW4K","created_at":"2026-07-05T09:46:37.758852+00:00"},{"alias_kind":"pith_short_8","alias_value":"LLP3KQSV","created_at":"2026-07-05T09:46:37.758852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05801","citing_title":"TRIG: Trajectory-Rig Decoupled Metric Geometry Learning","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2606.30047","citing_title":"Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10656","citing_title":"Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Driving","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22809","citing_title":"Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30047","citing_title":"Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22809","citing_title":"Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2507.07982","citing_title":"Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16428","citing_title":"CylinderDepth: Cylindrical Spatial Attention for Multi-View Consistent Self-Supervised Surround Depth Estimation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2507.11539","citing_title":"Streaming 4D Visual Geometry Transformer","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00813","citing_title":"DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LLP3KQSVIYLLJW4KF5ENTINWOG","json":"https://pith.science/pith/LLP3KQSVIYLLJW4KF5ENTINWOG.json","graph_json":"https://pith.science/api/pith-number/LLP3KQSVIYLLJW4KF5ENTINWOG/graph.json","events_json":"https://pith.science/api/pith-number/LLP3KQSVIYLLJW4KF5ENTINWOG/events.json","paper":"https://pith.science/paper/LLP3KQSV"},"agent_actions":{"view_html":"https://pith.science/pith/LLP3KQSVIYLLJW4KF5ENTINWOG","download_json":"https://pith.science/pith/LLP3KQSVIYLLJW4KF5ENTINWOG.json","view_paper":"https://pith.science/paper/LLP3KQSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.06777&json=true","fetch_graph":"https://pith.science/api/pith-number/LLP3KQSVIYLLJW4KF5ENTINWOG/graph.json","fetch_events":"https://pith.science/api/pith-number/LLP3KQSVIYLLJW4KF5ENTINWOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LLP3KQSVIYLLJW4KF5ENTINWOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LLP3KQSVIYLLJW4KF5ENTINWOG/action/storage_attestation","attest_author":"https://pith.science/pith/LLP3KQSVIYLLJW4KF5ENTINWOG/action/author_attestation","sign_citation":"https://pith.science/pith/LLP3KQSVIYLLJW4KF5ENTINWOG/action/citation_signature","submit_replication":"https://pith.science/pith/LLP3KQSVIYLLJW4KF5ENTINWOG/action/replication_record"}},"created_at":"2026-07-05T09:46:37.758852+00:00","updated_at":"2026-07-05T09:46:37.758852+00:00"}