{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6CFBRS54DXTZGQSCUQ6NKPPIR3","short_pith_number":"pith:6CFBRS54","schema_version":"1.0","canonical_sha256":"f08a18cbbc1de7934242a43cd53de88ed9093e8015e297efa097066e29a92a7b","source":{"kind":"arxiv","id":"2406.06526","version":3},"attestation_state":"computed","paper":{"title":"Generative Gaussian Splatting for Unbounded 3D City Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangzhou Hong, Haozhe Xie, Zhaoxi Chen, Ziwei Liu","submitted_at":"2024-06-10T17:59:55Z","abstract_excerpt":"3D city generation with NeRF-based methods shows promising generation results but is computationally inefficient. Recently 3D Gaussian Splatting (3D-GS) has emerged as a highly efficient alternative for object-level 3D generation. However, adapting 3D-GS from finite-scale 3D objects and humans to infinite-scale 3D cities is non-trivial. Unbounded 3D city generation entails significant storage overhead (out-of-memory issues), arising from the need to expand points to billions, often demanding hundreds of Gigabytes of VRAM for a city scene spanning 10km^2. In this paper, we propose GaussianCity,"},"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":"2406.06526","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T17:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"bfcca604738f64346b5df5ae01646737ac80317b57a8453df524ffdc8f52341f","abstract_canon_sha256":"4beca65d55ac08bd926a5f8c0960761ee2d977f031c174afab34767824ea015f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:37.614148Z","signature_b64":"+xEFFgShRcaBgEzHRyDzZO5hqhuEBaLF1Ax0iTVbmdXsApYimI2tYCwK2lpHlx1Q2yRLwuzPifbuAQmOGMgEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f08a18cbbc1de7934242a43cd53de88ed9093e8015e297efa097066e29a92a7b","last_reissued_at":"2026-07-05T10:20:37.613615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:37.613615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Gaussian Splatting for Unbounded 3D City Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangzhou Hong, Haozhe Xie, Zhaoxi Chen, Ziwei Liu","submitted_at":"2024-06-10T17:59:55Z","abstract_excerpt":"3D city generation with NeRF-based methods shows promising generation results but is computationally inefficient. Recently 3D Gaussian Splatting (3D-GS) has emerged as a highly efficient alternative for object-level 3D generation. However, adapting 3D-GS from finite-scale 3D objects and humans to infinite-scale 3D cities is non-trivial. Unbounded 3D city generation entails significant storage overhead (out-of-memory issues), arising from the need to expand points to billions, often demanding hundreds of Gigabytes of VRAM for a city scene spanning 10km^2. In this paper, we propose GaussianCity,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06526","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/2406.06526/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":"2406.06526","created_at":"2026-07-05T10:20:37.613686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06526v3","created_at":"2026-07-05T10:20:37.613686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06526","created_at":"2026-07-05T10:20:37.613686+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CFBRS54DXTZ","created_at":"2026-07-05T10:20:37.613686+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CFBRS54DXTZGQSC","created_at":"2026-07-05T10:20:37.613686+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CFBRS54","created_at":"2026-07-05T10:20:37.613686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24138","citing_title":"Sat2City v2: Native 3D City Asset Generation from a Single Satellite Image","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CFBRS54DXTZGQSCUQ6NKPPIR3","json":"https://pith.science/pith/6CFBRS54DXTZGQSCUQ6NKPPIR3.json","graph_json":"https://pith.science/api/pith-number/6CFBRS54DXTZGQSCUQ6NKPPIR3/graph.json","events_json":"https://pith.science/api/pith-number/6CFBRS54DXTZGQSCUQ6NKPPIR3/events.json","paper":"https://pith.science/paper/6CFBRS54"},"agent_actions":{"view_html":"https://pith.science/pith/6CFBRS54DXTZGQSCUQ6NKPPIR3","download_json":"https://pith.science/pith/6CFBRS54DXTZGQSCUQ6NKPPIR3.json","view_paper":"https://pith.science/paper/6CFBRS54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06526&json=true","fetch_graph":"https://pith.science/api/pith-number/6CFBRS54DXTZGQSCUQ6NKPPIR3/graph.json","fetch_events":"https://pith.science/api/pith-number/6CFBRS54DXTZGQSCUQ6NKPPIR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CFBRS54DXTZGQSCUQ6NKPPIR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CFBRS54DXTZGQSCUQ6NKPPIR3/action/storage_attestation","attest_author":"https://pith.science/pith/6CFBRS54DXTZGQSCUQ6NKPPIR3/action/author_attestation","sign_citation":"https://pith.science/pith/6CFBRS54DXTZGQSCUQ6NKPPIR3/action/citation_signature","submit_replication":"https://pith.science/pith/6CFBRS54DXTZGQSCUQ6NKPPIR3/action/replication_record"}},"created_at":"2026-07-05T10:20:37.613686+00:00","updated_at":"2026-07-05T10:20:37.613686+00:00"}