{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5NVYXOOQRPU2XMNNRWNU3IAR5Y","short_pith_number":"pith:5NVYXOOQ","schema_version":"1.0","canonical_sha256":"eb6b8bb9d08be9abb1ad8d9b4da011ee160876c85e2ba1c7557b86ede75a0a71","source":{"kind":"arxiv","id":"2412.02245","version":2},"attestation_state":"computed","paper":{"title":"SparseLGS: Sparse View Language Embedded Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Hu, Juyong Zhang, Yi Xu, Zhang Chen, Zhong Li","submitted_at":"2024-12-03T08:18:56Z","abstract_excerpt":"Recently, several studies have combined Gaussian Splatting to obtain scene representations with language embeddings for open-vocabulary 3D scene understanding. While these methods perform well, they essentially require very dense multi-view inputs, limiting their applicability in real-world scenarios. In this work, we propose SparseLGS to address the challenge of 3D scene understanding with pose-free and sparse view input images. Our method leverages a learning-based dense stereo model to handle pose-free and sparse inputs, and a three-step region matching approach to address the multi-view se"},"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":"2412.02245","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T08:18:56Z","cross_cats_sorted":[],"title_canon_sha256":"c61f4898f1865cc1f5b2bda5882049b103a81b2b47ff883744f3c55378262936","abstract_canon_sha256":"2dd5b50674809aa31df8ff6c3710f55336a2fff9dc607f07645e2b0ba075f05e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:17.990687Z","signature_b64":"f4H8zqhiUiESl4DLOUtVPMg/FoHAEUtNoyAOF1a8JMofnGZVmZxCVMa17C4+z78/I6q7gCuamVBOiePweojRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb6b8bb9d08be9abb1ad8d9b4da011ee160876c85e2ba1c7557b86ede75a0a71","last_reissued_at":"2026-07-05T09:44:17.990230Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:17.990230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SparseLGS: Sparse View Language Embedded Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Hu, Juyong Zhang, Yi Xu, Zhang Chen, Zhong Li","submitted_at":"2024-12-03T08:18:56Z","abstract_excerpt":"Recently, several studies have combined Gaussian Splatting to obtain scene representations with language embeddings for open-vocabulary 3D scene understanding. While these methods perform well, they essentially require very dense multi-view inputs, limiting their applicability in real-world scenarios. In this work, we propose SparseLGS to address the challenge of 3D scene understanding with pose-free and sparse view input images. Our method leverages a learning-based dense stereo model to handle pose-free and sparse inputs, and a three-step region matching approach to address the multi-view se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02245","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/2412.02245/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":"2412.02245","created_at":"2026-07-05T09:44:17.990289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02245v2","created_at":"2026-07-05T09:44:17.990289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02245","created_at":"2026-07-05T09:44:17.990289+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NVYXOOQRPU2","created_at":"2026-07-05T09:44:17.990289+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NVYXOOQRPU2XMNN","created_at":"2026-07-05T09:44:17.990289+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NVYXOOQ","created_at":"2026-07-05T09:44:17.990289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02813","citing_title":"LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5NVYXOOQRPU2XMNNRWNU3IAR5Y","json":"https://pith.science/pith/5NVYXOOQRPU2XMNNRWNU3IAR5Y.json","graph_json":"https://pith.science/api/pith-number/5NVYXOOQRPU2XMNNRWNU3IAR5Y/graph.json","events_json":"https://pith.science/api/pith-number/5NVYXOOQRPU2XMNNRWNU3IAR5Y/events.json","paper":"https://pith.science/paper/5NVYXOOQ"},"agent_actions":{"view_html":"https://pith.science/pith/5NVYXOOQRPU2XMNNRWNU3IAR5Y","download_json":"https://pith.science/pith/5NVYXOOQRPU2XMNNRWNU3IAR5Y.json","view_paper":"https://pith.science/paper/5NVYXOOQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02245&json=true","fetch_graph":"https://pith.science/api/pith-number/5NVYXOOQRPU2XMNNRWNU3IAR5Y/graph.json","fetch_events":"https://pith.science/api/pith-number/5NVYXOOQRPU2XMNNRWNU3IAR5Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NVYXOOQRPU2XMNNRWNU3IAR5Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NVYXOOQRPU2XMNNRWNU3IAR5Y/action/storage_attestation","attest_author":"https://pith.science/pith/5NVYXOOQRPU2XMNNRWNU3IAR5Y/action/author_attestation","sign_citation":"https://pith.science/pith/5NVYXOOQRPU2XMNNRWNU3IAR5Y/action/citation_signature","submit_replication":"https://pith.science/pith/5NVYXOOQRPU2XMNNRWNU3IAR5Y/action/replication_record"}},"created_at":"2026-07-05T09:44:17.990289+00:00","updated_at":"2026-07-05T09:44:17.990289+00:00"}