{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OL3VFBPBVV6XTXHOE3BAFEYUMJ","short_pith_number":"pith:OL3VFBPB","schema_version":"1.0","canonical_sha256":"72f75285e1ad7d79dcee26c2029314624532bc877ece8fd35585795d5435d170","source":{"kind":"arxiv","id":"2412.01717","version":3},"attestation_state":"computed","paper":{"title":"Driving View Synthesis on Free-form Trajectories with Generative Prior","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Li Zhang, Xiatian Zhu, Yuankun Yang, Zeyu Yang, Zijie Pan","submitted_at":"2024-12-02T17:07:53Z","abstract_excerpt":"Driving view synthesis along free-form trajectories is essential for realistic driving simulations, enabling closed-loop evaluation of end-to-end driving policies. Existing methods excel at view interpolation along recorded paths but struggle to generalize to novel trajectories due to limited viewpoints in driving videos. To tackle this challenge, we propose DriveX, a novel free-form driving view synthesis framework, that progressively distills generative prior into the 3D Gaussian model during its optimization. Within this framework, we utilize a video diffusion model to refine the degraded n"},"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":"2412.01717","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T17:07:53Z","cross_cats_sorted":[],"title_canon_sha256":"1ce5db1b9a786422f499a0faa2aa0d9f0e96cba17a673a236c9fd50e05213a9c","abstract_canon_sha256":"ffa287e973db49598305927d7986edb9bef10daf78a3a3652d8e8b5eb19c31de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:18.022500Z","signature_b64":"7caokGEaYS0esf3YBM057/eqp+R/3PBn1qfgqxdlaHbxj2TxvSZEu3IKcEMF6ATAM1ndhVkFZKkblCzpL5MxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72f75285e1ad7d79dcee26c2029314624532bc877ece8fd35585795d5435d170","last_reissued_at":"2026-07-05T11:33:18.022042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:18.022042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Driving View Synthesis on Free-form Trajectories with Generative Prior","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Li Zhang, Xiatian Zhu, Yuankun Yang, Zeyu Yang, Zijie Pan","submitted_at":"2024-12-02T17:07:53Z","abstract_excerpt":"Driving view synthesis along free-form trajectories is essential for realistic driving simulations, enabling closed-loop evaluation of end-to-end driving policies. Existing methods excel at view interpolation along recorded paths but struggle to generalize to novel trajectories due to limited viewpoints in driving videos. To tackle this challenge, we propose DriveX, a novel free-form driving view synthesis framework, that progressively distills generative prior into the 3D Gaussian model during its optimization. Within this framework, we utilize a video diffusion model to refine the degraded n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01717","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/2412.01717/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":"2412.01717","created_at":"2026-07-05T11:33:18.022100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01717v3","created_at":"2026-07-05T11:33:18.022100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01717","created_at":"2026-07-05T11:33:18.022100+00:00"},{"alias_kind":"pith_short_12","alias_value":"OL3VFBPBVV6X","created_at":"2026-07-05T11:33:18.022100+00:00"},{"alias_kind":"pith_short_16","alias_value":"OL3VFBPBVV6XTXHO","created_at":"2026-07-05T11:33:18.022100+00:00"},{"alias_kind":"pith_short_8","alias_value":"OL3VFBPB","created_at":"2026-07-05T11:33:18.022100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09688","citing_title":"ConFixGS: Learning to Fix Feedforward 3D Gaussian Splatting with Confidence-Aware Diffusion Priors in Driving Scenes","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OL3VFBPBVV6XTXHOE3BAFEYUMJ","json":"https://pith.science/pith/OL3VFBPBVV6XTXHOE3BAFEYUMJ.json","graph_json":"https://pith.science/api/pith-number/OL3VFBPBVV6XTXHOE3BAFEYUMJ/graph.json","events_json":"https://pith.science/api/pith-number/OL3VFBPBVV6XTXHOE3BAFEYUMJ/events.json","paper":"https://pith.science/paper/OL3VFBPB"},"agent_actions":{"view_html":"https://pith.science/pith/OL3VFBPBVV6XTXHOE3BAFEYUMJ","download_json":"https://pith.science/pith/OL3VFBPBVV6XTXHOE3BAFEYUMJ.json","view_paper":"https://pith.science/paper/OL3VFBPB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01717&json=true","fetch_graph":"https://pith.science/api/pith-number/OL3VFBPBVV6XTXHOE3BAFEYUMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/OL3VFBPBVV6XTXHOE3BAFEYUMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OL3VFBPBVV6XTXHOE3BAFEYUMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OL3VFBPBVV6XTXHOE3BAFEYUMJ/action/storage_attestation","attest_author":"https://pith.science/pith/OL3VFBPBVV6XTXHOE3BAFEYUMJ/action/author_attestation","sign_citation":"https://pith.science/pith/OL3VFBPBVV6XTXHOE3BAFEYUMJ/action/citation_signature","submit_replication":"https://pith.science/pith/OL3VFBPBVV6XTXHOE3BAFEYUMJ/action/replication_record"}},"created_at":"2026-07-05T11:33:18.022100+00:00","updated_at":"2026-07-05T11:33:18.022100+00:00"}