{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XYJLOAVNSN3IQ7W46XQ2EBDWE4","short_pith_number":"pith:XYJLOAVN","schema_version":"1.0","canonical_sha256":"be12b702ad9376887edcf5e1a20476272f962702450ef365e81fbe71c657cc6c","source":{"kind":"arxiv","id":"2408.10154","version":2},"attestation_state":"computed","paper":{"title":"LoopSplat: Loop Closure by Registering 3D Gaussian Splats","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Erik Sandstr\\\"om, Iro Armeni, Konrad Schindler, Liyuan Zhu, Shengyu Huang, Yue Li","submitted_at":"2024-08-19T17:04:18Z","abstract_excerpt":"Simultaneous Localization and Mapping (SLAM) based on 3D Gaussian Splats (3DGS) has recently shown promise towards more accurate, dense 3D scene maps. However, existing 3DGS-based methods fail to address the global consistency of the scene via loop closure and/or global bundle adjustment. To this end, we propose LoopSplat, which takes RGB-D images as input and performs dense mapping with 3DGS submaps and frame-to-model tracking. LoopSplat triggers loop closure online and computes relative loop edge constraints between submaps directly via 3DGS registration, leading to improvements in efficienc"},"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":"2408.10154","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-19T17:04:18Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"47c9462217f175e9b75ff1d570b888d9e9caf1ad79a409e962421d2c84f72c33","abstract_canon_sha256":"d34f2a514f495ac2432d23bb3fbe7184279f9b3dff38942d8601d68777f4cc79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:07.444231Z","signature_b64":"GQS5irt2WcNtFTfsfsIKGWKkBl1xvhEoySSHPJ+149bZMzhv2OM9r4cGkuWgCCMBdD/OWeD9pVW/pCjJ4hF/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be12b702ad9376887edcf5e1a20476272f962702450ef365e81fbe71c657cc6c","last_reissued_at":"2026-07-05T08:57:07.443702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:07.443702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LoopSplat: Loop Closure by Registering 3D Gaussian Splats","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Erik Sandstr\\\"om, Iro Armeni, Konrad Schindler, Liyuan Zhu, Shengyu Huang, Yue Li","submitted_at":"2024-08-19T17:04:18Z","abstract_excerpt":"Simultaneous Localization and Mapping (SLAM) based on 3D Gaussian Splats (3DGS) has recently shown promise towards more accurate, dense 3D scene maps. However, existing 3DGS-based methods fail to address the global consistency of the scene via loop closure and/or global bundle adjustment. To this end, we propose LoopSplat, which takes RGB-D images as input and performs dense mapping with 3DGS submaps and frame-to-model tracking. LoopSplat triggers loop closure online and computes relative loop edge constraints between submaps directly via 3DGS registration, leading to improvements in efficienc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10154","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/2408.10154/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":"2408.10154","created_at":"2026-07-05T08:57:07.443773+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10154v2","created_at":"2026-07-05T08:57:07.443773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10154","created_at":"2026-07-05T08:57:07.443773+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYJLOAVNSN3I","created_at":"2026-07-05T08:57:07.443773+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYJLOAVNSN3IQ7W4","created_at":"2026-07-05T08:57:07.443773+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYJLOAVN","created_at":"2026-07-05T08:57:07.443773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"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":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYJLOAVNSN3IQ7W46XQ2EBDWE4","json":"https://pith.science/pith/XYJLOAVNSN3IQ7W46XQ2EBDWE4.json","graph_json":"https://pith.science/api/pith-number/XYJLOAVNSN3IQ7W46XQ2EBDWE4/graph.json","events_json":"https://pith.science/api/pith-number/XYJLOAVNSN3IQ7W46XQ2EBDWE4/events.json","paper":"https://pith.science/paper/XYJLOAVN"},"agent_actions":{"view_html":"https://pith.science/pith/XYJLOAVNSN3IQ7W46XQ2EBDWE4","download_json":"https://pith.science/pith/XYJLOAVNSN3IQ7W46XQ2EBDWE4.json","view_paper":"https://pith.science/paper/XYJLOAVN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10154&json=true","fetch_graph":"https://pith.science/api/pith-number/XYJLOAVNSN3IQ7W46XQ2EBDWE4/graph.json","fetch_events":"https://pith.science/api/pith-number/XYJLOAVNSN3IQ7W46XQ2EBDWE4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYJLOAVNSN3IQ7W46XQ2EBDWE4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYJLOAVNSN3IQ7W46XQ2EBDWE4/action/storage_attestation","attest_author":"https://pith.science/pith/XYJLOAVNSN3IQ7W46XQ2EBDWE4/action/author_attestation","sign_citation":"https://pith.science/pith/XYJLOAVNSN3IQ7W46XQ2EBDWE4/action/citation_signature","submit_replication":"https://pith.science/pith/XYJLOAVNSN3IQ7W46XQ2EBDWE4/action/replication_record"}},"created_at":"2026-07-05T08:57:07.443773+00:00","updated_at":"2026-07-05T08:57:07.443773+00:00"}