{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KANPSP3HUDB3FC4TUX4WM47RCZ","short_pith_number":"pith:KANPSP3H","schema_version":"1.0","canonical_sha256":"501af93f67a0c3b28b93a5f96673f116796654cf68639ca0e38d61c8f7e80c3c","source":{"kind":"arxiv","id":"2405.14475","version":4},"attestation_state":"computed","paper":{"title":"MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kai Chen, Lanqing Hong, Qiang Xu, Ruiyuan Gao, Zhenguo Li, Zhihao Li","submitted_at":"2024-05-23T12:04:51Z","abstract_excerpt":"Controllable generative models for images and videos have seen significant success, yet 3D scene generation, especially in unbounded scenarios like autonomous driving, remains underdeveloped. Existing methods lack flexible controllability and often rely on dense view data collection in controlled environments, limiting their generalizability across common datasets (e.g., nuScenes). In this paper, we introduce MagicDrive3D, a novel framework for controllable 3D street scene generation that combines video-based view synthesis with 3D representation (3DGS) generation. It supports multi-condition "},"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":"2405.14475","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T12:04:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f530d089f8ea1e791595669929db9b00138c0fb86a07b4ca309073c5da00e759","abstract_canon_sha256":"5b3569ecf239cd95f886f0bab3378522b73b9abcc5eae75adc258d4654597160"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:06.192489Z","signature_b64":"DZ62zVDdexa7Fn+WCE1JDauyVpVs7DSpJNwjlOAM/mR/SHiGZWo9kCTKTcalla33R1t+Y67YI00JUlxWYEbbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"501af93f67a0c3b28b93a5f96673f116796654cf68639ca0e38d61c8f7e80c3c","last_reissued_at":"2026-07-05T11:43:06.192041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:06.192041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kai Chen, Lanqing Hong, Qiang Xu, Ruiyuan Gao, Zhenguo Li, Zhihao Li","submitted_at":"2024-05-23T12:04:51Z","abstract_excerpt":"Controllable generative models for images and videos have seen significant success, yet 3D scene generation, especially in unbounded scenarios like autonomous driving, remains underdeveloped. Existing methods lack flexible controllability and often rely on dense view data collection in controlled environments, limiting their generalizability across common datasets (e.g., nuScenes). In this paper, we introduce MagicDrive3D, a novel framework for controllable 3D street scene generation that combines video-based view synthesis with 3D representation (3DGS) generation. It supports multi-condition "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14475","kind":"arxiv","version":4},"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/2405.14475/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":"2405.14475","created_at":"2026-07-05T11:43:06.192098+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14475v4","created_at":"2026-07-05T11:43:06.192098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14475","created_at":"2026-07-05T11:43:06.192098+00:00"},{"alias_kind":"pith_short_12","alias_value":"KANPSP3HUDB3","created_at":"2026-07-05T11:43:06.192098+00:00"},{"alias_kind":"pith_short_16","alias_value":"KANPSP3HUDB3FC4T","created_at":"2026-07-05T11:43:06.192098+00:00"},{"alias_kind":"pith_short_8","alias_value":"KANPSP3H","created_at":"2026-07-05T11:43:06.192098+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20110","citing_title":"FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31109","citing_title":"InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15116","citing_title":"DriveCtrl: Conditioned Sim-to-Real Driving Video Generation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11596","citing_title":"HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02003","citing_title":"ProDiG: Progressive Diffusion-Guided Gaussian Splatting for Aerial to Ground Reconstruction","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11596","citing_title":"HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KANPSP3HUDB3FC4TUX4WM47RCZ","json":"https://pith.science/pith/KANPSP3HUDB3FC4TUX4WM47RCZ.json","graph_json":"https://pith.science/api/pith-number/KANPSP3HUDB3FC4TUX4WM47RCZ/graph.json","events_json":"https://pith.science/api/pith-number/KANPSP3HUDB3FC4TUX4WM47RCZ/events.json","paper":"https://pith.science/paper/KANPSP3H"},"agent_actions":{"view_html":"https://pith.science/pith/KANPSP3HUDB3FC4TUX4WM47RCZ","download_json":"https://pith.science/pith/KANPSP3HUDB3FC4TUX4WM47RCZ.json","view_paper":"https://pith.science/paper/KANPSP3H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14475&json=true","fetch_graph":"https://pith.science/api/pith-number/KANPSP3HUDB3FC4TUX4WM47RCZ/graph.json","fetch_events":"https://pith.science/api/pith-number/KANPSP3HUDB3FC4TUX4WM47RCZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KANPSP3HUDB3FC4TUX4WM47RCZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KANPSP3HUDB3FC4TUX4WM47RCZ/action/storage_attestation","attest_author":"https://pith.science/pith/KANPSP3HUDB3FC4TUX4WM47RCZ/action/author_attestation","sign_citation":"https://pith.science/pith/KANPSP3HUDB3FC4TUX4WM47RCZ/action/citation_signature","submit_replication":"https://pith.science/pith/KANPSP3HUDB3FC4TUX4WM47RCZ/action/replication_record"}},"created_at":"2026-07-05T11:43:06.192098+00:00","updated_at":"2026-07-05T11:43:06.192098+00:00"}