{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7TBQZNNF3RU7ZKOMNFYKQIIUVW","short_pith_number":"pith:7TBQZNNF","schema_version":"1.0","canonical_sha256":"fcc30cb5a5dc69fca9cc6970a82114adbd3da6f81aea321f5660636ea401cd68","source":{"kind":"arxiv","id":"2311.13398","version":3},"attestation_state":"computed","paper":{"title":"Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Jaeyoung Chung, Jeongtaek Oh, Kyoung Mu Lee","submitted_at":"2023-11-22T13:53:04Z","abstract_excerpt":"In this paper, we present a method to optimize Gaussian splatting with a limited number of images while avoiding overfitting. Representing a 3D scene by combining numerous Gaussian splats has yielded outstanding visual quality. However, it tends to overfit the training views when only a small number of images are available. To address this issue, we introduce a dense depth map as a geometry guide to mitigate overfitting. We obtained the depth map using a pre-trained monocular depth estimation model and aligning the scale and offset using sparse COLMAP feature points. The adjusted depth aids in"},"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":"2311.13398","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-22T13:53:04Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"f89e42fc56ac5554bd82859a661a0e79735d4bd51ce9312679d36804f58b7dcc","abstract_canon_sha256":"43d7e2a45da3fed21cf39fe398306e0baf690cfcb26a61f3a4cdebfd254cf7dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:06.017226Z","signature_b64":"xl9lBnnJLXct4K9gqZIyjFQj9gxJQm0d9GkcDCx2K3Fwp5cwZx0zNixMWfnqnOqKJEgxm//DdT/mUN5ks2lcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcc30cb5a5dc69fca9cc6970a82114adbd3da6f81aea321f5660636ea401cd68","last_reissued_at":"2026-07-05T07:30:06.016796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:06.016796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Jaeyoung Chung, Jeongtaek Oh, Kyoung Mu Lee","submitted_at":"2023-11-22T13:53:04Z","abstract_excerpt":"In this paper, we present a method to optimize Gaussian splatting with a limited number of images while avoiding overfitting. Representing a 3D scene by combining numerous Gaussian splats has yielded outstanding visual quality. However, it tends to overfit the training views when only a small number of images are available. To address this issue, we introduce a dense depth map as a geometry guide to mitigate overfitting. We obtained the depth map using a pre-trained monocular depth estimation model and aligning the scale and offset using sparse COLMAP feature points. The adjusted depth aids in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13398","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/2311.13398/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":"2311.13398","created_at":"2026-07-05T07:30:06.016853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13398v3","created_at":"2026-07-05T07:30:06.016853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13398","created_at":"2026-07-05T07:30:06.016853+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TBQZNNF3RU7","created_at":"2026-07-05T07:30:06.016853+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TBQZNNF3RU7ZKOM","created_at":"2026-07-05T07:30:06.016853+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TBQZNNF","created_at":"2026-07-05T07:30:06.016853+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21400","citing_title":"You Only Gaussian Once: Controllable 3D Gaussian Splatting for Ultra-Densely Sampled Scenes","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7TBQZNNF3RU7ZKOMNFYKQIIUVW","json":"https://pith.science/pith/7TBQZNNF3RU7ZKOMNFYKQIIUVW.json","graph_json":"https://pith.science/api/pith-number/7TBQZNNF3RU7ZKOMNFYKQIIUVW/graph.json","events_json":"https://pith.science/api/pith-number/7TBQZNNF3RU7ZKOMNFYKQIIUVW/events.json","paper":"https://pith.science/paper/7TBQZNNF"},"agent_actions":{"view_html":"https://pith.science/pith/7TBQZNNF3RU7ZKOMNFYKQIIUVW","download_json":"https://pith.science/pith/7TBQZNNF3RU7ZKOMNFYKQIIUVW.json","view_paper":"https://pith.science/paper/7TBQZNNF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13398&json=true","fetch_graph":"https://pith.science/api/pith-number/7TBQZNNF3RU7ZKOMNFYKQIIUVW/graph.json","fetch_events":"https://pith.science/api/pith-number/7TBQZNNF3RU7ZKOMNFYKQIIUVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TBQZNNF3RU7ZKOMNFYKQIIUVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TBQZNNF3RU7ZKOMNFYKQIIUVW/action/storage_attestation","attest_author":"https://pith.science/pith/7TBQZNNF3RU7ZKOMNFYKQIIUVW/action/author_attestation","sign_citation":"https://pith.science/pith/7TBQZNNF3RU7ZKOMNFYKQIIUVW/action/citation_signature","submit_replication":"https://pith.science/pith/7TBQZNNF3RU7ZKOMNFYKQIIUVW/action/replication_record"}},"created_at":"2026-07-05T07:30:06.016853+00:00","updated_at":"2026-07-05T07:30:06.016853+00:00"}