{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EG2JA2PNPQDUXM37K4W2SEQI7C","short_pith_number":"pith:EG2JA2PN","schema_version":"1.0","canonical_sha256":"21b49069ed7c074bb37f572da91208f8bd71b62a48400f985a52be5878b68a71","source":{"kind":"arxiv","id":"2505.09915","version":1},"attestation_state":"computed","paper":{"title":"Large-Scale Gaussian Splatting SLAM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Chenyang Wu, Guoquan Huang, Penghui Huang, Yanyong Zhang, Yinian Mao, Zhe Xin","submitted_at":"2025-05-15T03:00:32Z","abstract_excerpt":"The recently developed Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have shown encouraging and impressive results for visual SLAM. However, most representative methods require RGBD sensors and are only available for indoor environments. The robustness of reconstruction in large-scale outdoor scenarios remains unexplored. This paper introduces a large-scale 3DGS-based visual SLAM with stereo cameras, termed LSG-SLAM. The proposed LSG-SLAM employs a multi-modality strategy to estimate prior poses under large view changes. In tracking, we introduce feature-alignment warping cons"},"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":"2505.09915","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-15T03:00:32Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"fb95b44fde42146eb8ffee5f48834a8c49c7d486cd7b5bc05e629caddf48beef","abstract_canon_sha256":"efefbc120f1f3896427c1f39dd6be67b3c322ffb477d81141c715885dd77430e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:30.395071Z","signature_b64":"++WSpI1ELMRaUKmIIolQvVSnnpG3onLALyeAlj0WeOKl5Ilb2GPoF/CtwOxuxOCHMUjCwisE3R7atEpBwGFcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21b49069ed7c074bb37f572da91208f8bd71b62a48400f985a52be5878b68a71","last_reissued_at":"2026-07-05T11:03:30.394632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:30.394632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-Scale Gaussian Splatting SLAM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Chenyang Wu, Guoquan Huang, Penghui Huang, Yanyong Zhang, Yinian Mao, Zhe Xin","submitted_at":"2025-05-15T03:00:32Z","abstract_excerpt":"The recently developed Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have shown encouraging and impressive results for visual SLAM. However, most representative methods require RGBD sensors and are only available for indoor environments. The robustness of reconstruction in large-scale outdoor scenarios remains unexplored. This paper introduces a large-scale 3DGS-based visual SLAM with stereo cameras, termed LSG-SLAM. The proposed LSG-SLAM employs a multi-modality strategy to estimate prior poses under large view changes. In tracking, we introduce feature-alignment warping cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09915","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/2505.09915/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":"2505.09915","created_at":"2026-07-05T11:03:30.394687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09915v1","created_at":"2026-07-05T11:03:30.394687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09915","created_at":"2026-07-05T11:03:30.394687+00:00"},{"alias_kind":"pith_short_12","alias_value":"EG2JA2PNPQDU","created_at":"2026-07-05T11:03:30.394687+00:00"},{"alias_kind":"pith_short_16","alias_value":"EG2JA2PNPQDUXM37","created_at":"2026-07-05T11:03:30.394687+00:00"},{"alias_kind":"pith_short_8","alias_value":"EG2JA2PN","created_at":"2026-07-05T11:03:30.394687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24796","citing_title":"Pocket-SLAM: Rendering-Area-Aware Pruning for Memory-Efficient 3DGS-SLAM","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02696","citing_title":"VBGS-SLAM: Variational Bayesian Gaussian Splatting Simultaneous Localization and Mapping","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EG2JA2PNPQDUXM37K4W2SEQI7C","json":"https://pith.science/pith/EG2JA2PNPQDUXM37K4W2SEQI7C.json","graph_json":"https://pith.science/api/pith-number/EG2JA2PNPQDUXM37K4W2SEQI7C/graph.json","events_json":"https://pith.science/api/pith-number/EG2JA2PNPQDUXM37K4W2SEQI7C/events.json","paper":"https://pith.science/paper/EG2JA2PN"},"agent_actions":{"view_html":"https://pith.science/pith/EG2JA2PNPQDUXM37K4W2SEQI7C","download_json":"https://pith.science/pith/EG2JA2PNPQDUXM37K4W2SEQI7C.json","view_paper":"https://pith.science/paper/EG2JA2PN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09915&json=true","fetch_graph":"https://pith.science/api/pith-number/EG2JA2PNPQDUXM37K4W2SEQI7C/graph.json","fetch_events":"https://pith.science/api/pith-number/EG2JA2PNPQDUXM37K4W2SEQI7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EG2JA2PNPQDUXM37K4W2SEQI7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EG2JA2PNPQDUXM37K4W2SEQI7C/action/storage_attestation","attest_author":"https://pith.science/pith/EG2JA2PNPQDUXM37K4W2SEQI7C/action/author_attestation","sign_citation":"https://pith.science/pith/EG2JA2PNPQDUXM37K4W2SEQI7C/action/citation_signature","submit_replication":"https://pith.science/pith/EG2JA2PNPQDUXM37K4W2SEQI7C/action/replication_record"}},"created_at":"2026-07-05T11:03:30.394687+00:00","updated_at":"2026-07-05T11:03:30.394687+00:00"}