{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5ACKGHHE7IZBH5XJS4HW7YGW3Y","short_pith_number":"pith:5ACKGHHE","schema_version":"1.0","canonical_sha256":"e804a31ce4fa3213f6e9970f6fe0d6de2dee8376b8f08c6e73bae11cc7e7eafd","source":{"kind":"arxiv","id":"2403.06908","version":2},"attestation_state":"computed","paper":{"title":"FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric Xing, Fangneng Zhan, Jiahui Zhang, Muyu Xu, Shijian Lu","submitted_at":"2024-03-11T17:00:27Z","abstract_excerpt":"3D Gaussian splatting has achieved very impressive performance in real-time novel view synthesis. However, it often suffers from over-reconstruction during Gaussian densification where high-variance image regions are covered by a few large Gaussians only, leading to blur and artifacts in the rendered images. We design a progressive frequency regularization (FreGS) technique to tackle the over-reconstruction issue within the frequency space. Specifically, FreGS performs coarse-to-fine Gaussian densification by exploiting low-to-high frequency components that can be easily extracted with low-pas"},"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":"2403.06908","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T17:00:27Z","cross_cats_sorted":[],"title_canon_sha256":"057e2d4a08bd6f542727e75424f7a04350030f6e3063cc324480ce1010a7338f","abstract_canon_sha256":"665ad49b70e32b22550b1ea723fa539832ef32d211959c6feea5141d219f81e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:39.712511Z","signature_b64":"eXN8wCnjjYDI2nBbCwHFzjKRiqTYL8PodcdQp1HQhQB7dxpeg94/9vaY0uT5i6XZr8BxjmWctBRKZj8Cmp0NAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e804a31ce4fa3213f6e9970f6fe0d6de2dee8376b8f08c6e73bae11cc7e7eafd","last_reissued_at":"2026-07-05T08:05:39.711980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:39.711980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric Xing, Fangneng Zhan, Jiahui Zhang, Muyu Xu, Shijian Lu","submitted_at":"2024-03-11T17:00:27Z","abstract_excerpt":"3D Gaussian splatting has achieved very impressive performance in real-time novel view synthesis. However, it often suffers from over-reconstruction during Gaussian densification where high-variance image regions are covered by a few large Gaussians only, leading to blur and artifacts in the rendered images. We design a progressive frequency regularization (FreGS) technique to tackle the over-reconstruction issue within the frequency space. Specifically, FreGS performs coarse-to-fine Gaussian densification by exploiting low-to-high frequency components that can be easily extracted with low-pas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06908","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/2403.06908/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":"2403.06908","created_at":"2026-07-05T08:05:39.712058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06908v2","created_at":"2026-07-05T08:05:39.712058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06908","created_at":"2026-07-05T08:05:39.712058+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ACKGHHE7IZB","created_at":"2026-07-05T08:05:39.712058+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ACKGHHE7IZBH5XJ","created_at":"2026-07-05T08:05:39.712058+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ACKGHHE","created_at":"2026-07-05T08:05:39.712058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24964","citing_title":"ConFi-GS Confidence-Guided High-Frequency Injection for 3D Gaussian Splatting Super-Resolution","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ACKGHHE7IZBH5XJS4HW7YGW3Y","json":"https://pith.science/pith/5ACKGHHE7IZBH5XJS4HW7YGW3Y.json","graph_json":"https://pith.science/api/pith-number/5ACKGHHE7IZBH5XJS4HW7YGW3Y/graph.json","events_json":"https://pith.science/api/pith-number/5ACKGHHE7IZBH5XJS4HW7YGW3Y/events.json","paper":"https://pith.science/paper/5ACKGHHE"},"agent_actions":{"view_html":"https://pith.science/pith/5ACKGHHE7IZBH5XJS4HW7YGW3Y","download_json":"https://pith.science/pith/5ACKGHHE7IZBH5XJS4HW7YGW3Y.json","view_paper":"https://pith.science/paper/5ACKGHHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06908&json=true","fetch_graph":"https://pith.science/api/pith-number/5ACKGHHE7IZBH5XJS4HW7YGW3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/5ACKGHHE7IZBH5XJS4HW7YGW3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ACKGHHE7IZBH5XJS4HW7YGW3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ACKGHHE7IZBH5XJS4HW7YGW3Y/action/storage_attestation","attest_author":"https://pith.science/pith/5ACKGHHE7IZBH5XJS4HW7YGW3Y/action/author_attestation","sign_citation":"https://pith.science/pith/5ACKGHHE7IZBH5XJS4HW7YGW3Y/action/citation_signature","submit_replication":"https://pith.science/pith/5ACKGHHE7IZBH5XJS4HW7YGW3Y/action/replication_record"}},"created_at":"2026-07-05T08:05:39.712058+00:00","updated_at":"2026-07-05T08:05:39.712058+00:00"}