{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QBQ47HHZVB3PWJVLCEAFIWP65F","short_pith_number":"pith:QBQ47HHZ","schema_version":"1.0","canonical_sha256":"8061cf9cf9a876fb26ab11005459fee976fd275bec2d24365bd8f214a9f53fea","source":{"kind":"arxiv","id":"2412.17378","version":4},"attestation_state":"computed","paper":{"title":"Balanced 3DGS: Gaussian-wise Parallelism Rendering with Fine-Grained Tiling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Liu, Hao Gui, Jin Yang, Kun Zhan, Lin Hu, Mingxiao Huang, Rui Chen, Xueyang Zhang, Yong Wu, Yuxin Yin, Zhongxu Sun","submitted_at":"2024-12-23T08:26:30Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) is increasingly attracting attention in both academia and industry owing to its superior visual quality and rendering speed. However, training a 3DGS model remains a time-intensive task, especially in load imbalance scenarios where workload diversity among pixels and Gaussian spheres causes poor renderCUDA kernel performance. We introduce Balanced 3DGS, a Gaussian-wise parallelism rendering with fine-grained tiling approach in 3DGS training process, perfectly solving load-imbalance issues. First, we innovatively introduce the inter-block dynamic workload distributi"},"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":"2412.17378","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-23T08:26:30Z","cross_cats_sorted":[],"title_canon_sha256":"be1690275f27b0460edc9f54bbbeaa5f04d851098ca5406b1f4356c2b24f241a","abstract_canon_sha256":"6f405af5cbb7a01e8a7b1f07b0d614f6d0beb26a3e0082b2002365fb0939cc75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:03.419535Z","signature_b64":"+9bLaV3vtsUoDEfaV/dO7YAs9q4slPAOTloSmLe2Gl10BjZPXsCdeKwcD5EkxC1cAM11OYRNRvksLNdF24vsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8061cf9cf9a876fb26ab11005459fee976fd275bec2d24365bd8f214a9f53fea","last_reissued_at":"2026-07-05T11:00:03.419035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:03.419035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Balanced 3DGS: Gaussian-wise Parallelism Rendering with Fine-Grained Tiling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Liu, Hao Gui, Jin Yang, Kun Zhan, Lin Hu, Mingxiao Huang, Rui Chen, Xueyang Zhang, Yong Wu, Yuxin Yin, Zhongxu Sun","submitted_at":"2024-12-23T08:26:30Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) is increasingly attracting attention in both academia and industry owing to its superior visual quality and rendering speed. However, training a 3DGS model remains a time-intensive task, especially in load imbalance scenarios where workload diversity among pixels and Gaussian spheres causes poor renderCUDA kernel performance. We introduce Balanced 3DGS, a Gaussian-wise parallelism rendering with fine-grained tiling approach in 3DGS training process, perfectly solving load-imbalance issues. First, we innovatively introduce the inter-block dynamic workload distributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17378","kind":"arxiv","version":4},"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/2412.17378/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":"2412.17378","created_at":"2026-07-05T11:00:03.419092+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17378v4","created_at":"2026-07-05T11:00:03.419092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17378","created_at":"2026-07-05T11:00:03.419092+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBQ47HHZVB3P","created_at":"2026-07-05T11:00:03.419092+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBQ47HHZVB3PWJVL","created_at":"2026-07-05T11:00:03.419092+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBQ47HHZ","created_at":"2026-07-05T11:00:03.419092+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20150","citing_title":"TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00352","citing_title":"HiGS: A Hierarchical Rendering Architecture for Real-Time 3D Gaussian Splatting","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20150","citing_title":"TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13855","citing_title":"SparseOIT: Improving Order-Independent Transparency 3DGS via Active Set Method","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QBQ47HHZVB3PWJVLCEAFIWP65F","json":"https://pith.science/pith/QBQ47HHZVB3PWJVLCEAFIWP65F.json","graph_json":"https://pith.science/api/pith-number/QBQ47HHZVB3PWJVLCEAFIWP65F/graph.json","events_json":"https://pith.science/api/pith-number/QBQ47HHZVB3PWJVLCEAFIWP65F/events.json","paper":"https://pith.science/paper/QBQ47HHZ"},"agent_actions":{"view_html":"https://pith.science/pith/QBQ47HHZVB3PWJVLCEAFIWP65F","download_json":"https://pith.science/pith/QBQ47HHZVB3PWJVLCEAFIWP65F.json","view_paper":"https://pith.science/paper/QBQ47HHZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17378&json=true","fetch_graph":"https://pith.science/api/pith-number/QBQ47HHZVB3PWJVLCEAFIWP65F/graph.json","fetch_events":"https://pith.science/api/pith-number/QBQ47HHZVB3PWJVLCEAFIWP65F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBQ47HHZVB3PWJVLCEAFIWP65F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBQ47HHZVB3PWJVLCEAFIWP65F/action/storage_attestation","attest_author":"https://pith.science/pith/QBQ47HHZVB3PWJVLCEAFIWP65F/action/author_attestation","sign_citation":"https://pith.science/pith/QBQ47HHZVB3PWJVLCEAFIWP65F/action/citation_signature","submit_replication":"https://pith.science/pith/QBQ47HHZVB3PWJVLCEAFIWP65F/action/replication_record"}},"created_at":"2026-07-05T11:00:03.419092+00:00","updated_at":"2026-07-05T11:00:03.419092+00:00"}