{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GJE3R5SESPGGJEBJ22URSLCGXR","short_pith_number":"pith:GJE3R5SE","schema_version":"1.0","canonical_sha256":"3249b8f64493cc649029d6a9192c46bc5e58d6b9192048bdb2d398789afa7268","source":{"kind":"arxiv","id":"2409.05463","version":4},"attestation_state":"computed","paper":{"title":"DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenjing Ding, Chiyu Wang, Dongyue Chen, Tingxuan Huang, Wei Wu, Weixuan Tang, Xi Guo","submitted_at":"2024-09-09T09:43:17Z","abstract_excerpt":"Recent advancements in generative models have provided promising solutions for synthesizing realistic driving videos, which are crucial for training autonomous driving perception models. However, existing approaches often struggle with multi-view video generation due to the challenges of integrating 3D information while maintaining spatial-temporal consistency and effectively learning from a unified model. We propose DriveScape, an end-to-end framework for multi-view, 3D condition-guided video generation, capable of producing 1024 x 576 high-resolution videos at 10Hz. Unlike other methods limi"},"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":"2409.05463","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-09T09:43:17Z","cross_cats_sorted":[],"title_canon_sha256":"0aa619043c14e4698960592091e101f5c3a11c8ff2d4e42d2a2a69cdfe97aaa4","abstract_canon_sha256":"26338fa2da5b26ade1f38880bd986e63965b4cf7390c074c26f6b260eabc84f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:09.489228Z","signature_b64":"479GI3OfOvgM0/cvZmqgINaj70PBKPEAj63ygoG7FYThDSTU15W3Dqtx5TRb2ouqsT3vilUlzolWbnbAez4ZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3249b8f64493cc649029d6a9192c46bc5e58d6b9192048bdb2d398789afa7268","last_reissued_at":"2026-07-05T09:06:09.488769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:09.488769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenjing Ding, Chiyu Wang, Dongyue Chen, Tingxuan Huang, Wei Wu, Weixuan Tang, Xi Guo","submitted_at":"2024-09-09T09:43:17Z","abstract_excerpt":"Recent advancements in generative models have provided promising solutions for synthesizing realistic driving videos, which are crucial for training autonomous driving perception models. However, existing approaches often struggle with multi-view video generation due to the challenges of integrating 3D information while maintaining spatial-temporal consistency and effectively learning from a unified model. We propose DriveScape, an end-to-end framework for multi-view, 3D condition-guided video generation, capable of producing 1024 x 576 high-resolution videos at 10Hz. Unlike other methods limi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05463","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/2409.05463/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":"2409.05463","created_at":"2026-07-05T09:06:09.488826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.05463v4","created_at":"2026-07-05T09:06:09.488826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05463","created_at":"2026-07-05T09:06:09.488826+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJE3R5SESPGG","created_at":"2026-07-05T09:06:09.488826+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJE3R5SESPGGJEBJ","created_at":"2026-07-05T09:06:09.488826+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJE3R5SE","created_at":"2026-07-05T09:06:09.488826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19805","citing_title":"ParaScale: Scale-Calibrated Camera-Motion Transfer via a Gauge-Invariant Parallax Number","ref_index":26,"is_internal_anchor":false},{"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":95,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17536","citing_title":"OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generation","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJE3R5SESPGGJEBJ22URSLCGXR","json":"https://pith.science/pith/GJE3R5SESPGGJEBJ22URSLCGXR.json","graph_json":"https://pith.science/api/pith-number/GJE3R5SESPGGJEBJ22URSLCGXR/graph.json","events_json":"https://pith.science/api/pith-number/GJE3R5SESPGGJEBJ22URSLCGXR/events.json","paper":"https://pith.science/paper/GJE3R5SE"},"agent_actions":{"view_html":"https://pith.science/pith/GJE3R5SESPGGJEBJ22URSLCGXR","download_json":"https://pith.science/pith/GJE3R5SESPGGJEBJ22URSLCGXR.json","view_paper":"https://pith.science/paper/GJE3R5SE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.05463&json=true","fetch_graph":"https://pith.science/api/pith-number/GJE3R5SESPGGJEBJ22URSLCGXR/graph.json","fetch_events":"https://pith.science/api/pith-number/GJE3R5SESPGGJEBJ22URSLCGXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJE3R5SESPGGJEBJ22URSLCGXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJE3R5SESPGGJEBJ22URSLCGXR/action/storage_attestation","attest_author":"https://pith.science/pith/GJE3R5SESPGGJEBJ22URSLCGXR/action/author_attestation","sign_citation":"https://pith.science/pith/GJE3R5SESPGGJEBJ22URSLCGXR/action/citation_signature","submit_replication":"https://pith.science/pith/GJE3R5SESPGGJEBJ22URSLCGXR/action/replication_record"}},"created_at":"2026-07-05T09:06:09.488826+00:00","updated_at":"2026-07-05T09:06:09.488826+00:00"}