{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U3ZZAWIL4G6ZXLVIVHFW2J3MRC","short_pith_number":"pith:U3ZZAWIL","schema_version":"1.0","canonical_sha256":"a6f390590be1bd9baea8a9cb6d276c889e21381da0a6013b5005765ca341e67e","source":{"kind":"arxiv","id":"2403.09413","version":2},"attestation_state":"computed","paper":{"title":"Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Honggyu An, Jaewoo Jung, Jisang Han, Jiwon Kang, Seonghoon Park, Seungryong Kim","submitted_at":"2024-03-14T14:04:21Z","abstract_excerpt":"3D Gaussian splatting (3DGS) has recently demonstrated impressive capabilities in real-time novel view synthesis and 3D reconstruction. However, 3DGS heavily depends on the accurate initialization derived from Structure-from-Motion (SfM) methods. When the quality of the initial point cloud deteriorates, such as in the presence of noise or when using randomly initialized point cloud, 3DGS often undergoes large performance drops. To address this limitation, we propose a novel optimization strategy dubbed RAIN-GS (Relaing Accurate Initialization Constraint for 3D Gaussian Splatting). Our approach"},"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":"2403.09413","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T14:04:21Z","cross_cats_sorted":[],"title_canon_sha256":"b14cd3c072477e014f27e8bad3ebb14d315779ae824c433d827274ad6a7ffdd7","abstract_canon_sha256":"517099bde093ae65a57e2f04c2cf722256505554fee6b6e02397d5e3561877a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:03.687039Z","signature_b64":"szm56CkSBaoyOPPpmQXCdJJPuNEPIhEw86ccYzJNHrZKV0BaAGJFIfApnqJKp82bSMnfgi08ojVyo5uKQ2aDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6f390590be1bd9baea8a9cb6d276c889e21381da0a6013b5005765ca341e67e","last_reissued_at":"2026-07-05T08:24:03.686586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:03.686586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Honggyu An, Jaewoo Jung, Jisang Han, Jiwon Kang, Seonghoon Park, Seungryong Kim","submitted_at":"2024-03-14T14:04:21Z","abstract_excerpt":"3D Gaussian splatting (3DGS) has recently demonstrated impressive capabilities in real-time novel view synthesis and 3D reconstruction. However, 3DGS heavily depends on the accurate initialization derived from Structure-from-Motion (SfM) methods. When the quality of the initial point cloud deteriorates, such as in the presence of noise or when using randomly initialized point cloud, 3DGS often undergoes large performance drops. To address this limitation, we propose a novel optimization strategy dubbed RAIN-GS (Relaing Accurate Initialization Constraint for 3D Gaussian Splatting). Our approach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09413","kind":"arxiv","version":2},"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/2403.09413/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":"2403.09413","created_at":"2026-07-05T08:24:03.686652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09413v2","created_at":"2026-07-05T08:24:03.686652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09413","created_at":"2026-07-05T08:24:03.686652+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3ZZAWIL4G6Z","created_at":"2026-07-05T08:24:03.686652+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3ZZAWIL4G6ZXLVI","created_at":"2026-07-05T08:24:03.686652+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3ZZAWIL","created_at":"2026-07-05T08:24:03.686652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.03890","citing_title":"A Survey on 3D Gaussian Splatting","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2412.13547","citing_title":"Turbo-GS: Accelerating 3D Gaussian Fitting for High-Quality Radiance Fields","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2603.20714","citing_title":"The Role of Initialization in 3D Gaussian Splatting","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U3ZZAWIL4G6ZXLVIVHFW2J3MRC","json":"https://pith.science/pith/U3ZZAWIL4G6ZXLVIVHFW2J3MRC.json","graph_json":"https://pith.science/api/pith-number/U3ZZAWIL4G6ZXLVIVHFW2J3MRC/graph.json","events_json":"https://pith.science/api/pith-number/U3ZZAWIL4G6ZXLVIVHFW2J3MRC/events.json","paper":"https://pith.science/paper/U3ZZAWIL"},"agent_actions":{"view_html":"https://pith.science/pith/U3ZZAWIL4G6ZXLVIVHFW2J3MRC","download_json":"https://pith.science/pith/U3ZZAWIL4G6ZXLVIVHFW2J3MRC.json","view_paper":"https://pith.science/paper/U3ZZAWIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09413&json=true","fetch_graph":"https://pith.science/api/pith-number/U3ZZAWIL4G6ZXLVIVHFW2J3MRC/graph.json","fetch_events":"https://pith.science/api/pith-number/U3ZZAWIL4G6ZXLVIVHFW2J3MRC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3ZZAWIL4G6ZXLVIVHFW2J3MRC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3ZZAWIL4G6ZXLVIVHFW2J3MRC/action/storage_attestation","attest_author":"https://pith.science/pith/U3ZZAWIL4G6ZXLVIVHFW2J3MRC/action/author_attestation","sign_citation":"https://pith.science/pith/U3ZZAWIL4G6ZXLVIVHFW2J3MRC/action/citation_signature","submit_replication":"https://pith.science/pith/U3ZZAWIL4G6ZXLVIVHFW2J3MRC/action/replication_record"}},"created_at":"2026-07-05T08:24:03.686652+00:00","updated_at":"2026-07-05T08:24:03.686652+00:00"}