{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DUEWCOMZNFHLBLOD65DZWBA7GM","short_pith_number":"pith:DUEWCOMZ","schema_version":"1.0","canonical_sha256":"1d09613999694eb0adc3f7479b041f331bc92a1f1644c56a8e83ca7ba9f5b08e","source":{"kind":"arxiv","id":"2508.12313","version":1},"attestation_state":"computed","paper":{"title":"Improving Densification in 3D Gaussian Splatting for High-Fidelity Rendering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changyu Diao, Duanqing Xu, Min Li, Ruohan Yu, Xiaobin Deng","submitted_at":"2025-08-17T10:13:21Z","abstract_excerpt":"Although 3D Gaussian Splatting (3DGS) has achieved impressive performance in real-time rendering, its densification strategy often results in suboptimal reconstruction quality. In this work, we present a comprehensive improvement to the densification pipeline of 3DGS from three perspectives: when to densify, how to densify, and how to mitigate overfitting. Specifically, we propose an Edge-Aware Score to effectively select candidate Gaussians for splitting. We further introduce a Long-Axis Split strategy that reduces geometric distortions introduced by clone and split operations. To address ove"},"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":"2508.12313","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-17T10:13:21Z","cross_cats_sorted":[],"title_canon_sha256":"fcd6301b0f44978497401597e6a3fa77cbfc1e3307590ec9858ed74e21e490d3","abstract_canon_sha256":"c954fc923aeec3046053cd1b02598a75147c3ba7125f7822d2802c2f79c3c63b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:03.337539Z","signature_b64":"uaQRtvBZ1pHxuLpO0FmfzFLQA62bmarZgqcQ+hfypY5QEDQSz7W4MySzKuIF5aRrBYYVJD2tpd/cpBdcXr6aBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d09613999694eb0adc3f7479b041f331bc92a1f1644c56a8e83ca7ba9f5b08e","last_reissued_at":"2026-07-05T11:55:03.337074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:03.337074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Densification in 3D Gaussian Splatting for High-Fidelity Rendering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changyu Diao, Duanqing Xu, Min Li, Ruohan Yu, Xiaobin Deng","submitted_at":"2025-08-17T10:13:21Z","abstract_excerpt":"Although 3D Gaussian Splatting (3DGS) has achieved impressive performance in real-time rendering, its densification strategy often results in suboptimal reconstruction quality. In this work, we present a comprehensive improvement to the densification pipeline of 3DGS from three perspectives: when to densify, how to densify, and how to mitigate overfitting. Specifically, we propose an Edge-Aware Score to effectively select candidate Gaussians for splitting. We further introduce a Long-Axis Split strategy that reduces geometric distortions introduced by clone and split operations. To address ove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12313","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/2508.12313/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":"2508.12313","created_at":"2026-07-05T11:55:03.337132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.12313v1","created_at":"2026-07-05T11:55:03.337132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12313","created_at":"2026-07-05T11:55:03.337132+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUEWCOMZNFHL","created_at":"2026-07-05T11:55:03.337132+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUEWCOMZNFHLBLOD","created_at":"2026-07-05T11:55:03.337132+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUEWCOMZ","created_at":"2026-07-05T11:55:03.337132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16158","citing_title":"Smart target point control for Gaussian Splatting methods","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2603.20714","citing_title":"The Role of Initialization in 3D Gaussian Splatting","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DUEWCOMZNFHLBLOD65DZWBA7GM","json":"https://pith.science/pith/DUEWCOMZNFHLBLOD65DZWBA7GM.json","graph_json":"https://pith.science/api/pith-number/DUEWCOMZNFHLBLOD65DZWBA7GM/graph.json","events_json":"https://pith.science/api/pith-number/DUEWCOMZNFHLBLOD65DZWBA7GM/events.json","paper":"https://pith.science/paper/DUEWCOMZ"},"agent_actions":{"view_html":"https://pith.science/pith/DUEWCOMZNFHLBLOD65DZWBA7GM","download_json":"https://pith.science/pith/DUEWCOMZNFHLBLOD65DZWBA7GM.json","view_paper":"https://pith.science/paper/DUEWCOMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.12313&json=true","fetch_graph":"https://pith.science/api/pith-number/DUEWCOMZNFHLBLOD65DZWBA7GM/graph.json","fetch_events":"https://pith.science/api/pith-number/DUEWCOMZNFHLBLOD65DZWBA7GM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUEWCOMZNFHLBLOD65DZWBA7GM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUEWCOMZNFHLBLOD65DZWBA7GM/action/storage_attestation","attest_author":"https://pith.science/pith/DUEWCOMZNFHLBLOD65DZWBA7GM/action/author_attestation","sign_citation":"https://pith.science/pith/DUEWCOMZNFHLBLOD65DZWBA7GM/action/citation_signature","submit_replication":"https://pith.science/pith/DUEWCOMZNFHLBLOD65DZWBA7GM/action/replication_record"}},"created_at":"2026-07-05T11:55:03.337132+00:00","updated_at":"2026-07-05T11:55:03.337132+00:00"}