{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JGYLNDAZ47LYCQUEOQQXOWMMSK","short_pith_number":"pith:JGYLNDAZ","schema_version":"1.0","canonical_sha256":"49b0b68c19e7d7814284742177598c92b3e381550bd62ac7b1c050a523985d24","source":{"kind":"arxiv","id":"2503.20168","version":1},"attestation_state":"computed","paper":{"title":"EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Geiger, Bingbing Liu, Dongfeng Bai, Hongyu Zhou, Jiaxin Huang, Sheng Miao, Xu Yan, Yiyi Liao, Yue Wang","submitted_at":"2025-03-26T02:47:27Z","abstract_excerpt":"Novel view synthesis of urban scenes is essential for autonomous driving-related applications.Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization. We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner. Unlike existing feed-forward, pixel-aligned 3DGS methods, which often suffer from issues like multi-view inconsistencies and duplicated content, our approach predicts 3D Gaussians across multiple frames within a unified volume using a 3D convolut"},"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":"2503.20168","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T02:47:27Z","cross_cats_sorted":[],"title_canon_sha256":"b3d7e398fa6cddadd203e250f64a3c91108ba6bbbb441f34b11ffc9d6f60b792","abstract_canon_sha256":"7067f821d029b9b35d4f5d0639e1743e09120d4103c3a5ebf0821dc4dbe4dfa1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:33.738553Z","signature_b64":"AP8lOiWzWgxFBf3ha9iHTw9lrKboU2mGx0LK/5nIUvapG/SpatIiAB8JEZqq7+l30plQTGUaPblOqW9pdXF+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49b0b68c19e7d7814284742177598c92b3e381550bd62ac7b1c050a523985d24","last_reissued_at":"2026-07-05T10:39:33.738036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:33.738036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Geiger, Bingbing Liu, Dongfeng Bai, Hongyu Zhou, Jiaxin Huang, Sheng Miao, Xu Yan, Yiyi Liao, Yue Wang","submitted_at":"2025-03-26T02:47:27Z","abstract_excerpt":"Novel view synthesis of urban scenes is essential for autonomous driving-related applications.Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization. We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner. Unlike existing feed-forward, pixel-aligned 3DGS methods, which often suffer from issues like multi-view inconsistencies and duplicated content, our approach predicts 3D Gaussians across multiple frames within a unified volume using a 3D convolut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20168","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/2503.20168/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":"2503.20168","created_at":"2026-07-05T10:39:33.738108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.20168v1","created_at":"2026-07-05T10:39:33.738108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20168","created_at":"2026-07-05T10:39:33.738108+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGYLNDAZ47LY","created_at":"2026-07-05T10:39:33.738108+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGYLNDAZ47LYCQUE","created_at":"2026-07-05T10:39:33.738108+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGYLNDAZ","created_at":"2026-07-05T10:39:33.738108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.05236","citing_title":"ArbiViewGen: Controllable Arbitrary Viewpoint Camera Data Generation for Autonomous Driving via Stable Diffusion Models","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JGYLNDAZ47LYCQUEOQQXOWMMSK","json":"https://pith.science/pith/JGYLNDAZ47LYCQUEOQQXOWMMSK.json","graph_json":"https://pith.science/api/pith-number/JGYLNDAZ47LYCQUEOQQXOWMMSK/graph.json","events_json":"https://pith.science/api/pith-number/JGYLNDAZ47LYCQUEOQQXOWMMSK/events.json","paper":"https://pith.science/paper/JGYLNDAZ"},"agent_actions":{"view_html":"https://pith.science/pith/JGYLNDAZ47LYCQUEOQQXOWMMSK","download_json":"https://pith.science/pith/JGYLNDAZ47LYCQUEOQQXOWMMSK.json","view_paper":"https://pith.science/paper/JGYLNDAZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.20168&json=true","fetch_graph":"https://pith.science/api/pith-number/JGYLNDAZ47LYCQUEOQQXOWMMSK/graph.json","fetch_events":"https://pith.science/api/pith-number/JGYLNDAZ47LYCQUEOQQXOWMMSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGYLNDAZ47LYCQUEOQQXOWMMSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGYLNDAZ47LYCQUEOQQXOWMMSK/action/storage_attestation","attest_author":"https://pith.science/pith/JGYLNDAZ47LYCQUEOQQXOWMMSK/action/author_attestation","sign_citation":"https://pith.science/pith/JGYLNDAZ47LYCQUEOQQXOWMMSK/action/citation_signature","submit_replication":"https://pith.science/pith/JGYLNDAZ47LYCQUEOQQXOWMMSK/action/replication_record"}},"created_at":"2026-07-05T10:39:33.738108+00:00","updated_at":"2026-07-05T10:39:33.738108+00:00"}