{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J7YP6FRKS4L6YKPI4QFZUZVP7J","short_pith_number":"pith:J7YP6FRK","schema_version":"1.0","canonical_sha256":"4ff0ff162a9717ec29e8e40b9a66affa731287bee9ba5e80950bd23109779fad","source":{"kind":"arxiv","id":"2405.07392","version":3},"attestation_state":"computed","paper":{"title":"NGD-SLAM: Towards Real-Time Dynamic SLAM without GPU","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Mihai Bujanca, Mikel Luj\\'an, Yuhao Zhang","submitted_at":"2024-05-12T23:00:53Z","abstract_excerpt":"Many existing visual SLAM methods can achieve high localization accuracy in dynamic environments by leveraging deep learning to mask moving objects. However, these methods incur significant computational overhead as the camera tracking needs to wait for the deep neural network to generate mask at each frame, and they typically require GPUs for real-time operation, which restricts their practicality in real-world robotic applications. Therefore, this paper proposes a real-time dynamic SLAM system that runs exclusively on a CPU. Our approach incorporates a mask propagation mechanism that decoupl"},"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":"2405.07392","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-05-12T23:00:53Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"8eb158e0f5af025f77bec5cd479519cf8e69f4b62f8b7f4419af37d1c518be63","abstract_canon_sha256":"010f465285daf09c7fcfb39b9db0601607179d1627e338bea03885e27ed828ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:30.502300Z","signature_b64":"EOcVV7zbHKsrC1anKwnEE7t4PQFrDnHgYlXZuSIK7uzTy2YnZtmKMw5nRkypDauwxfp9cUfN5Vz5BowqHcjzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ff0ff162a9717ec29e8e40b9a66affa731287bee9ba5e80950bd23109779fad","last_reissued_at":"2026-07-05T11:22:30.501785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:30.501785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NGD-SLAM: Towards Real-Time Dynamic SLAM without GPU","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Mihai Bujanca, Mikel Luj\\'an, Yuhao Zhang","submitted_at":"2024-05-12T23:00:53Z","abstract_excerpt":"Many existing visual SLAM methods can achieve high localization accuracy in dynamic environments by leveraging deep learning to mask moving objects. However, these methods incur significant computational overhead as the camera tracking needs to wait for the deep neural network to generate mask at each frame, and they typically require GPUs for real-time operation, which restricts their practicality in real-world robotic applications. Therefore, this paper proposes a real-time dynamic SLAM system that runs exclusively on a CPU. Our approach incorporates a mask propagation mechanism that decoupl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07392","kind":"arxiv","version":3},"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/2405.07392/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":"2405.07392","created_at":"2026-07-05T11:22:30.501846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.07392v3","created_at":"2026-07-05T11:22:30.501846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07392","created_at":"2026-07-05T11:22:30.501846+00:00"},{"alias_kind":"pith_short_12","alias_value":"J7YP6FRKS4L6","created_at":"2026-07-05T11:22:30.501846+00:00"},{"alias_kind":"pith_short_16","alias_value":"J7YP6FRKS4L6YKPI","created_at":"2026-07-05T11:22:30.501846+00:00"},{"alias_kind":"pith_short_8","alias_value":"J7YP6FRK","created_at":"2026-07-05T11:22:30.501846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00741","citing_title":"DyPho-SLAM : Real-time Photorealistic SLAM in Dynamic Environments","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J7YP6FRKS4L6YKPI4QFZUZVP7J","json":"https://pith.science/pith/J7YP6FRKS4L6YKPI4QFZUZVP7J.json","graph_json":"https://pith.science/api/pith-number/J7YP6FRKS4L6YKPI4QFZUZVP7J/graph.json","events_json":"https://pith.science/api/pith-number/J7YP6FRKS4L6YKPI4QFZUZVP7J/events.json","paper":"https://pith.science/paper/J7YP6FRK"},"agent_actions":{"view_html":"https://pith.science/pith/J7YP6FRKS4L6YKPI4QFZUZVP7J","download_json":"https://pith.science/pith/J7YP6FRKS4L6YKPI4QFZUZVP7J.json","view_paper":"https://pith.science/paper/J7YP6FRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.07392&json=true","fetch_graph":"https://pith.science/api/pith-number/J7YP6FRKS4L6YKPI4QFZUZVP7J/graph.json","fetch_events":"https://pith.science/api/pith-number/J7YP6FRKS4L6YKPI4QFZUZVP7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J7YP6FRKS4L6YKPI4QFZUZVP7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J7YP6FRKS4L6YKPI4QFZUZVP7J/action/storage_attestation","attest_author":"https://pith.science/pith/J7YP6FRKS4L6YKPI4QFZUZVP7J/action/author_attestation","sign_citation":"https://pith.science/pith/J7YP6FRKS4L6YKPI4QFZUZVP7J/action/citation_signature","submit_replication":"https://pith.science/pith/J7YP6FRKS4L6YKPI4QFZUZVP7J/action/replication_record"}},"created_at":"2026-07-05T11:22:30.501846+00:00","updated_at":"2026-07-05T11:22:30.501846+00:00"}