{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5M7BSCJXYII7QPBCA2FMZTEE3D","short_pith_number":"pith:5M7BSCJX","schema_version":"1.0","canonical_sha256":"eb3e190937c211f83c22068acccc84d8f3e8150e2e85356dba42f263129f01ba","source":{"kind":"arxiv","id":"2304.14560","version":2},"attestation_state":"computed","paper":{"title":"Neural Implicit Dense Semantic SLAM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jean-Philippe Thiran, Luc Van Gool, Suryansh Kumar, Yasaman Haghighi","submitted_at":"2023-04-27T23:03:52Z","abstract_excerpt":"Visual Simultaneous Localization and Mapping (vSLAM) is a widely used technique in robotics and computer vision that enables a robot to create a map of an unfamiliar environment using a camera sensor while simultaneously tracking its position over time. In this paper, we propose a novel RGBD vSLAM algorithm that can learn a memory-efficient, dense 3D geometry, and semantic segmentation of an indoor scene in an online manner. Our pipeline combines classical 3D vision-based tracking and loop closing with neural fields-based mapping. The mapping network learns the SDF of the scene as well as RGB,"},"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":"2304.14560","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T23:03:52Z","cross_cats_sorted":[],"title_canon_sha256":"b4283786a5aa3ce158f1d36859eab4a8ed438564e0bcfa6ed6f90069d9add5d9","abstract_canon_sha256":"adff4b27a52b37e9c2e508476aa9d9c038c366e49ec2b366eb943dead1bf0e90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:27.534224Z","signature_b64":"1J2b0ZfWLjsr9mNEosdky6S/3ZZ9wzDf1O8wZBctyteKm56l/4+t0sTXjHIoPcrjb5qgaOKoz9wnKj7QpDmeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb3e190937c211f83c22068acccc84d8f3e8150e2e85356dba42f263129f01ba","last_reissued_at":"2026-07-05T06:08:27.533762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:27.533762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Implicit Dense Semantic SLAM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jean-Philippe Thiran, Luc Van Gool, Suryansh Kumar, Yasaman Haghighi","submitted_at":"2023-04-27T23:03:52Z","abstract_excerpt":"Visual Simultaneous Localization and Mapping (vSLAM) is a widely used technique in robotics and computer vision that enables a robot to create a map of an unfamiliar environment using a camera sensor while simultaneously tracking its position over time. In this paper, we propose a novel RGBD vSLAM algorithm that can learn a memory-efficient, dense 3D geometry, and semantic segmentation of an indoor scene in an online manner. Our pipeline combines classical 3D vision-based tracking and loop closing with neural fields-based mapping. The mapping network learns the SDF of the scene as well as RGB,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14560","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/2304.14560/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":"2304.14560","created_at":"2026-07-05T06:08:27.533816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.14560v2","created_at":"2026-07-05T06:08:27.533816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14560","created_at":"2026-07-05T06:08:27.533816+00:00"},{"alias_kind":"pith_short_12","alias_value":"5M7BSCJXYII7","created_at":"2026-07-05T06:08:27.533816+00:00"},{"alias_kind":"pith_short_16","alias_value":"5M7BSCJXYII7QPBC","created_at":"2026-07-05T06:08:27.533816+00:00"},{"alias_kind":"pith_short_8","alias_value":"5M7BSCJX","created_at":"2026-07-05T06:08:27.533816+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29494","citing_title":"VCS-SLAM: Geometry-Validated Semantic Evidence Fusion for 3D Gaussian SLAM","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12437","citing_title":"3D Gaussian Splatting for Efficient Retrospective Dynamic Scene Novel View Synthesis with a Standardized Benchmark","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5M7BSCJXYII7QPBCA2FMZTEE3D","json":"https://pith.science/pith/5M7BSCJXYII7QPBCA2FMZTEE3D.json","graph_json":"https://pith.science/api/pith-number/5M7BSCJXYII7QPBCA2FMZTEE3D/graph.json","events_json":"https://pith.science/api/pith-number/5M7BSCJXYII7QPBCA2FMZTEE3D/events.json","paper":"https://pith.science/paper/5M7BSCJX"},"agent_actions":{"view_html":"https://pith.science/pith/5M7BSCJXYII7QPBCA2FMZTEE3D","download_json":"https://pith.science/pith/5M7BSCJXYII7QPBCA2FMZTEE3D.json","view_paper":"https://pith.science/paper/5M7BSCJX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.14560&json=true","fetch_graph":"https://pith.science/api/pith-number/5M7BSCJXYII7QPBCA2FMZTEE3D/graph.json","fetch_events":"https://pith.science/api/pith-number/5M7BSCJXYII7QPBCA2FMZTEE3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5M7BSCJXYII7QPBCA2FMZTEE3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5M7BSCJXYII7QPBCA2FMZTEE3D/action/storage_attestation","attest_author":"https://pith.science/pith/5M7BSCJXYII7QPBCA2FMZTEE3D/action/author_attestation","sign_citation":"https://pith.science/pith/5M7BSCJXYII7QPBCA2FMZTEE3D/action/citation_signature","submit_replication":"https://pith.science/pith/5M7BSCJXYII7QPBCA2FMZTEE3D/action/replication_record"}},"created_at":"2026-07-05T06:08:27.533816+00:00","updated_at":"2026-07-05T06:08:27.533816+00:00"}