{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IJXOV4SGLVEOUV4VE36N3FCYNF","short_pith_number":"pith:IJXOV4SG","schema_version":"1.0","canonical_sha256":"426eeaf2465d48ea579526fcdd9458697bce25c23a6f01366cb09e9a874fb136","source":{"kind":"arxiv","id":"2506.05682","version":1},"attestation_state":"computed","paper":{"title":"Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Chen Chen, Jingwen Leng, Minyi Guo, Shixuan Sun, Weikai Lin, Yu Feng, Yuge Cheng, Yuhao Zhu, Zihan Liu","submitted_at":"2025-06-06T02:20:49Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has vastly advanced the pace of neural rendering, but it remains computationally demanding on today's mobile SoCs. To address this challenge, we propose Lumina, a hardware-algorithm co-designed system, which integrates two principal optimizations: a novel algorithm, S^2, and a radiance caching mechanism, RC, to improve the efficiency of neural rendering. S2 algorithm exploits temporal coherence in rendering to reduce the computational overhead, while RC leverages the color integration process of 3DGS to decrease the frequency of intensive rasterization computations"},"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":"2506.05682","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-06-06T02:20:49Z","cross_cats_sorted":[],"title_canon_sha256":"f78fb85cdb82687159864e2da6b8297e3ce86769abd75ba15cc843b83efa3b84","abstract_canon_sha256":"11002a69a0248197effa97ab2fb9e1f46ac00736cde7d4187b44fa8d595bd3ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:07.976933Z","signature_b64":"OCNmHyQZ9Gr6yg4szoj77l3tFQ76GGURAE8xAClT7Jb7UsreIvM1iT/j4xFQ11rC17TbyzxIdD2k7Xc2Q3F2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"426eeaf2465d48ea579526fcdd9458697bce25c23a6f01366cb09e9a874fb136","last_reissued_at":"2026-07-05T11:17:07.976504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:07.976504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Chen Chen, Jingwen Leng, Minyi Guo, Shixuan Sun, Weikai Lin, Yu Feng, Yuge Cheng, Yuhao Zhu, Zihan Liu","submitted_at":"2025-06-06T02:20:49Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has vastly advanced the pace of neural rendering, but it remains computationally demanding on today's mobile SoCs. To address this challenge, we propose Lumina, a hardware-algorithm co-designed system, which integrates two principal optimizations: a novel algorithm, S^2, and a radiance caching mechanism, RC, to improve the efficiency of neural rendering. S2 algorithm exploits temporal coherence in rendering to reduce the computational overhead, while RC leverages the color integration process of 3DGS to decrease the frequency of intensive rasterization computations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05682","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/2506.05682/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":"2506.05682","created_at":"2026-07-05T11:17:07.976565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05682v1","created_at":"2026-07-05T11:17:07.976565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05682","created_at":"2026-07-05T11:17:07.976565+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJXOV4SGLVEO","created_at":"2026-07-05T11:17:07.976565+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJXOV4SGLVEOUV4V","created_at":"2026-07-05T11:17:07.976565+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJXOV4SG","created_at":"2026-07-05T11:17:07.976565+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10716","citing_title":"L-PCN: A Point Cloud Accelerator Exploiting Spatial Locality through Octree-based Islandization","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IJXOV4SGLVEOUV4VE36N3FCYNF","json":"https://pith.science/pith/IJXOV4SGLVEOUV4VE36N3FCYNF.json","graph_json":"https://pith.science/api/pith-number/IJXOV4SGLVEOUV4VE36N3FCYNF/graph.json","events_json":"https://pith.science/api/pith-number/IJXOV4SGLVEOUV4VE36N3FCYNF/events.json","paper":"https://pith.science/paper/IJXOV4SG"},"agent_actions":{"view_html":"https://pith.science/pith/IJXOV4SGLVEOUV4VE36N3FCYNF","download_json":"https://pith.science/pith/IJXOV4SGLVEOUV4VE36N3FCYNF.json","view_paper":"https://pith.science/paper/IJXOV4SG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05682&json=true","fetch_graph":"https://pith.science/api/pith-number/IJXOV4SGLVEOUV4VE36N3FCYNF/graph.json","fetch_events":"https://pith.science/api/pith-number/IJXOV4SGLVEOUV4VE36N3FCYNF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJXOV4SGLVEOUV4VE36N3FCYNF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJXOV4SGLVEOUV4VE36N3FCYNF/action/storage_attestation","attest_author":"https://pith.science/pith/IJXOV4SGLVEOUV4VE36N3FCYNF/action/author_attestation","sign_citation":"https://pith.science/pith/IJXOV4SGLVEOUV4VE36N3FCYNF/action/citation_signature","submit_replication":"https://pith.science/pith/IJXOV4SGLVEOUV4VE36N3FCYNF/action/replication_record"}},"created_at":"2026-07-05T11:17:07.976565+00:00","updated_at":"2026-07-05T11:17:07.976565+00:00"}