{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YY3Z6V464OBGLNUPC7DYSDL25L","short_pith_number":"pith:YY3Z6V46","schema_version":"1.0","canonical_sha256":"c6379f579ee38265b68f17c7890d7aead66a2ded8d442dddeffc0f704cd8dbfd","source":{"kind":"arxiv","id":"2405.00676","version":1},"attestation_state":"computed","paper":{"title":"Spectrally Pruned Gaussian Fields with Neural Compensation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baijun Ye, Hao Zhao, Jian Zhao, Runyi Yang, Xiaoxue Chen, Yifei Zhang, Yuantao Chen, Zhenxin Zhu, Zhou Jiang","submitted_at":"2024-05-01T17:59:45Z","abstract_excerpt":"Recently, 3D Gaussian Splatting, as a novel 3D representation, has garnered attention for its fast rendering speed and high rendering quality. However, this comes with high memory consumption, e.g., a well-trained Gaussian field may utilize three million Gaussian primitives and over 700 MB of memory. We credit this high memory footprint to the lack of consideration for the relationship between primitives. In this paper, we propose a memory-efficient Gaussian field named SUNDAE with spectral pruning and neural compensation. On one hand, we construct a graph on the set of Gaussian primitives to "},"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":"2405.00676","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-01T17:59:45Z","cross_cats_sorted":[],"title_canon_sha256":"bf9dc0453600f89f7f13733e0b105d6a30fc8cbeb34be3360eebd60c23696713","abstract_canon_sha256":"3118df598ae63486d4d73bd02fbc8f9a5879b50c5b7500dea028e08201c82c2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:16.261223Z","signature_b64":"b4Da/sjHypItE6kted7LuIs0J4li+I3uGkwNnD+ddVJ2aSp5ncPG9gfujjp7Zgwnc3L5//Cte9+Yif5rN/BSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6379f579ee38265b68f17c7890d7aead66a2ded8d442dddeffc0f704cd8dbfd","last_reissued_at":"2026-07-05T08:14:16.260787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:16.260787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectrally Pruned Gaussian Fields with Neural Compensation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baijun Ye, Hao Zhao, Jian Zhao, Runyi Yang, Xiaoxue Chen, Yifei Zhang, Yuantao Chen, Zhenxin Zhu, Zhou Jiang","submitted_at":"2024-05-01T17:59:45Z","abstract_excerpt":"Recently, 3D Gaussian Splatting, as a novel 3D representation, has garnered attention for its fast rendering speed and high rendering quality. However, this comes with high memory consumption, e.g., a well-trained Gaussian field may utilize three million Gaussian primitives and over 700 MB of memory. We credit this high memory footprint to the lack of consideration for the relationship between primitives. In this paper, we propose a memory-efficient Gaussian field named SUNDAE with spectral pruning and neural compensation. On one hand, we construct a graph on the set of Gaussian primitives to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00676","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/2405.00676/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":"2405.00676","created_at":"2026-07-05T08:14:16.260840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.00676v1","created_at":"2026-07-05T08:14:16.260840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00676","created_at":"2026-07-05T08:14:16.260840+00:00"},{"alias_kind":"pith_short_12","alias_value":"YY3Z6V464OBG","created_at":"2026-07-05T08:14:16.260840+00:00"},{"alias_kind":"pith_short_16","alias_value":"YY3Z6V464OBGLNUP","created_at":"2026-07-05T08:14:16.260840+00:00"},{"alias_kind":"pith_short_8","alias_value":"YY3Z6V46","created_at":"2026-07-05T08:14:16.260840+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18588","citing_title":"Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03309","citing_title":"TreeGaussian: Tree-Guided Cascaded Contrastive Learning for Hierarchical Consistent 3D Gaussian Scene Segmentation and Understanding","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YY3Z6V464OBGLNUPC7DYSDL25L","json":"https://pith.science/pith/YY3Z6V464OBGLNUPC7DYSDL25L.json","graph_json":"https://pith.science/api/pith-number/YY3Z6V464OBGLNUPC7DYSDL25L/graph.json","events_json":"https://pith.science/api/pith-number/YY3Z6V464OBGLNUPC7DYSDL25L/events.json","paper":"https://pith.science/paper/YY3Z6V46"},"agent_actions":{"view_html":"https://pith.science/pith/YY3Z6V464OBGLNUPC7DYSDL25L","download_json":"https://pith.science/pith/YY3Z6V464OBGLNUPC7DYSDL25L.json","view_paper":"https://pith.science/paper/YY3Z6V46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.00676&json=true","fetch_graph":"https://pith.science/api/pith-number/YY3Z6V464OBGLNUPC7DYSDL25L/graph.json","fetch_events":"https://pith.science/api/pith-number/YY3Z6V464OBGLNUPC7DYSDL25L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YY3Z6V464OBGLNUPC7DYSDL25L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YY3Z6V464OBGLNUPC7DYSDL25L/action/storage_attestation","attest_author":"https://pith.science/pith/YY3Z6V464OBGLNUPC7DYSDL25L/action/author_attestation","sign_citation":"https://pith.science/pith/YY3Z6V464OBGLNUPC7DYSDL25L/action/citation_signature","submit_replication":"https://pith.science/pith/YY3Z6V464OBGLNUPC7DYSDL25L/action/replication_record"}},"created_at":"2026-07-05T08:14:16.260840+00:00","updated_at":"2026-07-05T08:14:16.260840+00:00"}