{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EY5O6FBB4MQF6DCIYJ34OROSJO","short_pith_number":"pith:EY5O6FBB","schema_version":"1.0","canonical_sha256":"263aef1421e3205f0c48c277c745d24b87209c0ca9e9785b429ca46dc1062176","source":{"kind":"arxiv","id":"2412.06234","version":3},"attestation_state":"computed","paper":{"title":"Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Eunbyung Park, Gyeongjin Kang, Seungjun Oh, Seungtae Nam, Xiangyu Sun, Younggeun Lee","submitted_at":"2024-12-09T06:20:51Z","abstract_excerpt":"Generalized feed-forward Gaussian models have achieved significant progress in sparse-view 3D reconstruction by leveraging prior knowledge from large multi-view datasets. However, these models often struggle to represent high-frequency details due to the limited number of Gaussians. While the densification strategy used in per-scene 3D Gaussian splatting (3D-GS) optimization can be adapted to the feed-forward models, it may not be ideally suited for generalized scenarios. In this paper, we propose Generative Densification, an efficient and generalizable method to densify Gaussians generated by"},"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":"2412.06234","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T06:20:51Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"fc516f0114f9dcbf59a164280ac5c8972b93734b7a995ad5d1fe1eb1e6ed9734","abstract_canon_sha256":"1f58f28b4485dc4f4377d5ea490fc6dacd8d987903851878f0bd10fe4a1cb9b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:11.509381Z","signature_b64":"M4A2CUYCbSNmf7zMIjz8RnM662P8ZQR4KwdAcfKqES9sos3i5lZBXTd1OSzQ+ObrCI+ifIdZYJLEGsjl4uWfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"263aef1421e3205f0c48c277c745d24b87209c0ca9e9785b429ca46dc1062176","last_reissued_at":"2026-07-05T10:26:11.508473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:11.508473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Eunbyung Park, Gyeongjin Kang, Seungjun Oh, Seungtae Nam, Xiangyu Sun, Younggeun Lee","submitted_at":"2024-12-09T06:20:51Z","abstract_excerpt":"Generalized feed-forward Gaussian models have achieved significant progress in sparse-view 3D reconstruction by leveraging prior knowledge from large multi-view datasets. However, these models often struggle to represent high-frequency details due to the limited number of Gaussians. While the densification strategy used in per-scene 3D Gaussian splatting (3D-GS) optimization can be adapted to the feed-forward models, it may not be ideally suited for generalized scenarios. In this paper, we propose Generative Densification, an efficient and generalizable method to densify Gaussians generated by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06234","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/2412.06234/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":"2412.06234","created_at":"2026-07-05T10:26:11.508583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.06234v3","created_at":"2026-07-05T10:26:11.508583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06234","created_at":"2026-07-05T10:26:11.508583+00:00"},{"alias_kind":"pith_short_12","alias_value":"EY5O6FBB4MQF","created_at":"2026-07-05T10:26:11.508583+00:00"},{"alias_kind":"pith_short_16","alias_value":"EY5O6FBB4MQF6DCI","created_at":"2026-07-05T10:26:11.508583+00:00"},{"alias_kind":"pith_short_8","alias_value":"EY5O6FBB","created_at":"2026-07-05T10:26:11.508583+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EY5O6FBB4MQF6DCIYJ34OROSJO","json":"https://pith.science/pith/EY5O6FBB4MQF6DCIYJ34OROSJO.json","graph_json":"https://pith.science/api/pith-number/EY5O6FBB4MQF6DCIYJ34OROSJO/graph.json","events_json":"https://pith.science/api/pith-number/EY5O6FBB4MQF6DCIYJ34OROSJO/events.json","paper":"https://pith.science/paper/EY5O6FBB"},"agent_actions":{"view_html":"https://pith.science/pith/EY5O6FBB4MQF6DCIYJ34OROSJO","download_json":"https://pith.science/pith/EY5O6FBB4MQF6DCIYJ34OROSJO.json","view_paper":"https://pith.science/paper/EY5O6FBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.06234&json=true","fetch_graph":"https://pith.science/api/pith-number/EY5O6FBB4MQF6DCIYJ34OROSJO/graph.json","fetch_events":"https://pith.science/api/pith-number/EY5O6FBB4MQF6DCIYJ34OROSJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EY5O6FBB4MQF6DCIYJ34OROSJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EY5O6FBB4MQF6DCIYJ34OROSJO/action/storage_attestation","attest_author":"https://pith.science/pith/EY5O6FBB4MQF6DCIYJ34OROSJO/action/author_attestation","sign_citation":"https://pith.science/pith/EY5O6FBB4MQF6DCIYJ34OROSJO/action/citation_signature","submit_replication":"https://pith.science/pith/EY5O6FBB4MQF6DCIYJ34OROSJO/action/replication_record"}},"created_at":"2026-07-05T10:26:11.508583+00:00","updated_at":"2026-07-05T10:26:11.508583+00:00"}