{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VOIURFCG5XNXOPEQHD32A2Z4EB","short_pith_number":"pith:VOIURFCG","schema_version":"1.0","canonical_sha256":"ab91489446eddb773c9038f7a06b3c204881dd42263fc31ecc346593260b1032","source":{"kind":"arxiv","id":"2402.14650","version":1},"attestation_state":"computed","paper":{"title":"GaussianPro: 3D Gaussian Splatting with Progressive Propagation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kai Cheng, Kaizhi Yang, Wei Yin, Wenping Wang, Xiaoxiao Long, Xuejin Chen, Yao Yao, Yuexin Ma","submitted_at":"2024-02-22T16:00:20Z","abstract_excerpt":"The advent of 3D Gaussian Splatting (3DGS) has recently brought about a revolution in the field of neural rendering, facilitating high-quality renderings at real-time speed. However, 3DGS heavily depends on the initialized point cloud produced by Structure-from-Motion (SfM) techniques. When tackling with large-scale scenes that unavoidably contain texture-less surfaces, the SfM techniques always fail to produce enough points in these surfaces and cannot provide good initialization for 3DGS. As a result, 3DGS suffers from difficult optimization and low-quality renderings. In this paper, inspire"},"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":"2402.14650","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-22T16:00:20Z","cross_cats_sorted":[],"title_canon_sha256":"9e0b60db6dafa75dbfed8373e22dbfe0087db17b0f59e3c1dfbaa012c7532ebb","abstract_canon_sha256":"27da178c303b6f9e6ceb1270aa3146dffeeeb296c571cc8d6fb8ca0e2ab23f7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:13.347720Z","signature_b64":"FXmnU5UM6Lg2PjAg6MvUZZU40dpR1rxn+AIa+yMrEdch86CWCFmm8poAPWHpUMfWKg2cq0G1LehUKzqgbJZ/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab91489446eddb773c9038f7a06b3c204881dd42263fc31ecc346593260b1032","last_reissued_at":"2026-07-05T07:48:13.347249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:13.347249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GaussianPro: 3D Gaussian Splatting with Progressive Propagation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kai Cheng, Kaizhi Yang, Wei Yin, Wenping Wang, Xiaoxiao Long, Xuejin Chen, Yao Yao, Yuexin Ma","submitted_at":"2024-02-22T16:00:20Z","abstract_excerpt":"The advent of 3D Gaussian Splatting (3DGS) has recently brought about a revolution in the field of neural rendering, facilitating high-quality renderings at real-time speed. However, 3DGS heavily depends on the initialized point cloud produced by Structure-from-Motion (SfM) techniques. When tackling with large-scale scenes that unavoidably contain texture-less surfaces, the SfM techniques always fail to produce enough points in these surfaces and cannot provide good initialization for 3DGS. As a result, 3DGS suffers from difficult optimization and low-quality renderings. In this paper, inspire"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14650","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/2402.14650/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":"2402.14650","created_at":"2026-07-05T07:48:13.347302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14650v1","created_at":"2026-07-05T07:48:13.347302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14650","created_at":"2026-07-05T07:48:13.347302+00:00"},{"alias_kind":"pith_short_12","alias_value":"VOIURFCG5XNX","created_at":"2026-07-05T07:48:13.347302+00:00"},{"alias_kind":"pith_short_16","alias_value":"VOIURFCG5XNXOPEQ","created_at":"2026-07-05T07:48:13.347302+00:00"},{"alias_kind":"pith_short_8","alias_value":"VOIURFCG","created_at":"2026-07-05T07:48:13.347302+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24180","citing_title":"Deep Learning Approaches for 3D Medical Scene Completion: From Geometric Modeling to Generative Paradigms","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09473","citing_title":"Realizing Immersive Volumetric Video: A Multimodal Framework for 6-DoF VR Engagement","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VOIURFCG5XNXOPEQHD32A2Z4EB","json":"https://pith.science/pith/VOIURFCG5XNXOPEQHD32A2Z4EB.json","graph_json":"https://pith.science/api/pith-number/VOIURFCG5XNXOPEQHD32A2Z4EB/graph.json","events_json":"https://pith.science/api/pith-number/VOIURFCG5XNXOPEQHD32A2Z4EB/events.json","paper":"https://pith.science/paper/VOIURFCG"},"agent_actions":{"view_html":"https://pith.science/pith/VOIURFCG5XNXOPEQHD32A2Z4EB","download_json":"https://pith.science/pith/VOIURFCG5XNXOPEQHD32A2Z4EB.json","view_paper":"https://pith.science/paper/VOIURFCG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14650&json=true","fetch_graph":"https://pith.science/api/pith-number/VOIURFCG5XNXOPEQHD32A2Z4EB/graph.json","fetch_events":"https://pith.science/api/pith-number/VOIURFCG5XNXOPEQHD32A2Z4EB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VOIURFCG5XNXOPEQHD32A2Z4EB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VOIURFCG5XNXOPEQHD32A2Z4EB/action/storage_attestation","attest_author":"https://pith.science/pith/VOIURFCG5XNXOPEQHD32A2Z4EB/action/author_attestation","sign_citation":"https://pith.science/pith/VOIURFCG5XNXOPEQHD32A2Z4EB/action/citation_signature","submit_replication":"https://pith.science/pith/VOIURFCG5XNXOPEQHD32A2Z4EB/action/replication_record"}},"created_at":"2026-07-05T07:48:13.347302+00:00","updated_at":"2026-07-05T07:48:13.347302+00:00"}