{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JULNET4BKR2CMIOYAMTYKDJKSR","short_pith_number":"pith:JULNET4B","schema_version":"1.0","canonical_sha256":"4d16d24f8154742621d80327850d2a9445da6c13d8c16542979e51a885de64b8","source":{"kind":"arxiv","id":"2605.13600","version":1},"attestation_state":"computed","paper":{"title":"Sparse Code Uplifting for Efficient 3D Language Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Sparse code uplifting from 2D images to 3D Gaussians delivers up to 400 times faster training for open-vocabulary scene understanding.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lovre Antonio Budimir, Nandita Vijaykumar, Steve Ryhner, Sven Lon\\v{c}ari\\'c, Yushi Guan","submitted_at":"2026-05-13T14:35:31Z","abstract_excerpt":"3D Language Gaussian Splatting (3DLGS) augments 3D Gaussian Splatting with language-aligned visual features for open-vocabulary 3D scene understanding. A core challenge is efficiently associating high-dimensional vision-language embeddings with millions of 3D Gaussians while preserving efficient feature rendering for text-based querying. Existing methods either store dense features directly on Gaussians, causing high storage costs and slow rendering, or learn compact representations through expensive per-scene optimization with repeated feature rasterization. No existing method simultaneously "},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13600","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:35:31Z","cross_cats_sorted":[],"title_canon_sha256":"56ec71ba0809b46f7455cae7774de84fa51c0fa451e7e1cb1ca712a53841b1ed","abstract_canon_sha256":"53369c60f99a84e2d7edfb95564554667a3fbe94f3656a8dcd1a53b0888d7f2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:22.942783Z","signature_b64":"jBQWUn1J7hbxY8RcTDVKG9yaWqcIvP2A9YUn6atqtdYF5li1E+070Nx8Ib0lIthwSpgvhlClGNSN4CvcmMnLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d16d24f8154742621d80327850d2a9445da6c13d8c16542979e51a885de64b8","last_reissued_at":"2026-05-18T02:44:22.942376Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:22.942376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse Code Uplifting for Efficient 3D Language Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Sparse code uplifting from 2D images to 3D Gaussians delivers up to 400 times faster training for open-vocabulary scene understanding.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lovre Antonio Budimir, Nandita Vijaykumar, Steve Ryhner, Sven Lon\\v{c}ari\\'c, Yushi Guan","submitted_at":"2026-05-13T14:35:31Z","abstract_excerpt":"3D Language Gaussian Splatting (3DLGS) augments 3D Gaussian Splatting with language-aligned visual features for open-vocabulary 3D scene understanding. A core challenge is efficiently associating high-dimensional vision-language embeddings with millions of 3D Gaussians while preserving efficient feature rendering for text-based querying. Existing methods either store dense features directly on Gaussians, causing high storage costs and slow rendering, or learn compact representations through expensive per-scene optimization with repeated feature rasterization. No existing method simultaneously "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our method achieves up to 400× training speedup while being 3× more memory efficient during training compared to the state-of-the-art in rendering speed. Across multiple benchmarks, SCOUP matches or outperforms existing methods in open-vocabulary querying accuracy.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That sparse codebook coefficients learned entirely from 2D image regions can be uplifted to 3D Gaussians via weighted multi-view aggregation and Top-K filtering without substantial loss of semantic accuracy or the need for per-scene language optimization.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SCOUP decouples 2D sparse code learning from 3D Gaussian optimization to deliver up to 400x training speedup and 3x better memory efficiency while matching accuracy on open-vocabulary 3D queries.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Sparse code uplifting from 2D images to 3D Gaussians delivers up to 400 times faster training for open-vocabulary scene understanding.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"454fefc7b7b2f4d3960379d71122ce926740c8aff21402d0c9655603f5a68839"},"source":{"id":"2605.13600","kind":"arxiv","version":1},"verdict":{"id":"9b550f01-b106-4a13-bbe0-6dbff00084df","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:22:41.364916Z","strongest_claim":"Our method achieves up to 400× training speedup while being 3× more memory efficient during training compared to the state-of-the-art in rendering speed. Across multiple benchmarks, SCOUP matches or outperforms existing methods in open-vocabulary querying accuracy.","one_line_summary":"SCOUP decouples 2D sparse code learning from 3D Gaussian optimization to deliver up to 400x training speedup and 3x better memory efficiency while matching accuracy on open-vocabulary 3D queries.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That sparse codebook coefficients learned entirely from 2D image regions can be uplifted to 3D Gaussians via weighted multi-view aggregation and Top-K filtering without substantial loss of semantic accuracy or the need for per-scene language optimization.","pith_extraction_headline":"Sparse code uplifting from 2D images to 3D Gaussians delivers up to 400 times faster training for open-vocabulary scene understanding."},"references":{"count":43,"sample":[{"doi":"","year":2026,"title":"GALA: Guided attention with language alignment for open vocabulary gaussian splatting","work_id":"e8b07e34-4e73-4283-8b36-e419ae34b2b2","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Barron, Ben Mildenhall, Dor Verbin, Pratul P","work_id":"0aedd240-1463-4d03-bd4e-c8aff93e2414","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Gaussianeditor: Swift and controllable 3d editing with gaussian splatting.2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 21476–21485, 2023","work_id":"05058a69-c172-4cf0-bec7-c096214c88c7","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/cvpr52733.2024.02022","year":2024,"title":"URL https://doi.org/10.1109/CVPR52733","work_id":"7efbc2dd-b0f2-4f71-bb1c-d2fcf110d805","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Occam’s lgs: An efficient approach for language gaussian splatting","work_id":"9baf9d6e-f4e6-46a2-abfe-cd7588f4a792","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":43,"snapshot_sha256":"a1f80dc2a830356b712bebeaed8e5861d118bcec65f35261555cbad8f6049d82","internal_anchors":2},"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":"2605.13600","created_at":"2026-05-18T02:44:22.942446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13600v1","created_at":"2026-05-18T02:44:22.942446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13600","created_at":"2026-05-18T02:44:22.942446+00:00"},{"alias_kind":"pith_short_12","alias_value":"JULNET4BKR2C","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"JULNET4BKR2CMIOY","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"JULNET4B","created_at":"2026-05-18T12:33:37.589309+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/JULNET4BKR2CMIOYAMTYKDJKSR","json":"https://pith.science/pith/JULNET4BKR2CMIOYAMTYKDJKSR.json","graph_json":"https://pith.science/api/pith-number/JULNET4BKR2CMIOYAMTYKDJKSR/graph.json","events_json":"https://pith.science/api/pith-number/JULNET4BKR2CMIOYAMTYKDJKSR/events.json","paper":"https://pith.science/paper/JULNET4B"},"agent_actions":{"view_html":"https://pith.science/pith/JULNET4BKR2CMIOYAMTYKDJKSR","download_json":"https://pith.science/pith/JULNET4BKR2CMIOYAMTYKDJKSR.json","view_paper":"https://pith.science/paper/JULNET4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13600&json=true","fetch_graph":"https://pith.science/api/pith-number/JULNET4BKR2CMIOYAMTYKDJKSR/graph.json","fetch_events":"https://pith.science/api/pith-number/JULNET4BKR2CMIOYAMTYKDJKSR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JULNET4BKR2CMIOYAMTYKDJKSR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JULNET4BKR2CMIOYAMTYKDJKSR/action/storage_attestation","attest_author":"https://pith.science/pith/JULNET4BKR2CMIOYAMTYKDJKSR/action/author_attestation","sign_citation":"https://pith.science/pith/JULNET4BKR2CMIOYAMTYKDJKSR/action/citation_signature","submit_replication":"https://pith.science/pith/JULNET4BKR2CMIOYAMTYKDJKSR/action/replication_record"}},"created_at":"2026-05-18T02:44:22.942446+00:00","updated_at":"2026-05-18T02:44:22.942446+00:00"}