{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2ORQZHJM2FRB7LH44VTB2DNM67","short_pith_number":"pith:2ORQZHJM","schema_version":"1.0","canonical_sha256":"d3a30c9d2cd1621facfce5661d0dacf7cc5e266d14e35920605021bb6de0a12e","source":{"kind":"arxiv","id":"2512.03621","version":3},"attestation_state":"computed","paper":{"title":"ReCamDriving: LiDAR-Free Camera-Controlled Video Synthesis for Novel Trajectories","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guang Tan, Jiehui Huang, Kaixuan Wang, Mantang Guo, Mu Hu, Shaojie Shen, Shuaixian Wang, Taojun Ding, Yaokun Li","submitted_at":"2025-12-03T09:55:25Z","abstract_excerpt":"Synthesizing multi-pass videos is important for autonomous driving. While current repair-based methods often struggle with out-of-distribution artifacts, camera-controlled methods often produce 3D-inconsistent results due to sparse LiDAR cues. We propose ReCamDriving, a purely vision-based framework that achieves camera-controlled generation by leveraging dense, structurally complete 3DGS renderings as geometric guidance. Specifically, to prevent the model from overfitting to a trivial repair solution when conditioning on 3DGS renderings, we adopt a two-stage progressive training paradigm: the"},"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":"2512.03621","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-03T09:55:25Z","cross_cats_sorted":[],"title_canon_sha256":"920f1d289145b7c7edab62e5f2ac603af7a76f6fcb2c067decfc9d9fcce0a0cc","abstract_canon_sha256":"91643a14af26e3825be100f3f3c25d10ef2b9c7ce7c32c1e7f13e3739406863a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:41:13.537896Z","signature_b64":"lceHuHUF1D+jubh6PFzBC0//RJ+tHiBynCNTOPEjOXujmOAeGPwpHFiw0xgjPQY3YaWJPacTRc2BvJ8AVz0+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3a30c9d2cd1621facfce5661d0dacf7cc5e266d14e35920605021bb6de0a12e","last_reissued_at":"2026-08-05T00:41:13.534909Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:41:13.534909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReCamDriving: LiDAR-Free Camera-Controlled Video Synthesis for Novel Trajectories","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guang Tan, Jiehui Huang, Kaixuan Wang, Mantang Guo, Mu Hu, Shaojie Shen, Shuaixian Wang, Taojun Ding, Yaokun Li","submitted_at":"2025-12-03T09:55:25Z","abstract_excerpt":"Synthesizing multi-pass videos is important for autonomous driving. While current repair-based methods often struggle with out-of-distribution artifacts, camera-controlled methods often produce 3D-inconsistent results due to sparse LiDAR cues. We propose ReCamDriving, a purely vision-based framework that achieves camera-controlled generation by leveraging dense, structurally complete 3DGS renderings as geometric guidance. Specifically, to prevent the model from overfitting to a trivial repair solution when conditioning on 3DGS renderings, we adopt a two-stage progressive training paradigm: the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.03621","kind":"arxiv","version":3},"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/2512.03621/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":"2512.03621","created_at":"2026-08-05T00:41:13.535765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.03621v3","created_at":"2026-08-05T00:41:13.535765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.03621","created_at":"2026-08-05T00:41:13.535765+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ORQZHJM2FRB","created_at":"2026-08-05T00:41:13.535765+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ORQZHJM2FRB7LH4","created_at":"2026-08-05T00:41:13.535765+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ORQZHJM","created_at":"2026-08-05T00:41:13.535765+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06516","citing_title":"Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulation","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ORQZHJM2FRB7LH44VTB2DNM67","json":"https://pith.science/pith/2ORQZHJM2FRB7LH44VTB2DNM67.json","graph_json":"https://pith.science/api/pith-number/2ORQZHJM2FRB7LH44VTB2DNM67/graph.json","events_json":"https://pith.science/api/pith-number/2ORQZHJM2FRB7LH44VTB2DNM67/events.json","paper":"https://pith.science/paper/2ORQZHJM"},"agent_actions":{"view_html":"https://pith.science/pith/2ORQZHJM2FRB7LH44VTB2DNM67","download_json":"https://pith.science/pith/2ORQZHJM2FRB7LH44VTB2DNM67.json","view_paper":"https://pith.science/paper/2ORQZHJM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.03621&json=true","fetch_graph":"https://pith.science/api/pith-number/2ORQZHJM2FRB7LH44VTB2DNM67/graph.json","fetch_events":"https://pith.science/api/pith-number/2ORQZHJM2FRB7LH44VTB2DNM67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ORQZHJM2FRB7LH44VTB2DNM67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ORQZHJM2FRB7LH44VTB2DNM67/action/storage_attestation","attest_author":"https://pith.science/pith/2ORQZHJM2FRB7LH44VTB2DNM67/action/author_attestation","sign_citation":"https://pith.science/pith/2ORQZHJM2FRB7LH44VTB2DNM67/action/citation_signature","submit_replication":"https://pith.science/pith/2ORQZHJM2FRB7LH44VTB2DNM67/action/replication_record"}},"created_at":"2026-08-05T00:41:13.535765+00:00","updated_at":"2026-08-05T00:41:13.535765+00:00"}