{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RXPAZM2POHD4KTEJPCTXKKWKKK","short_pith_number":"pith:RXPAZM2P","schema_version":"1.0","canonical_sha256":"8dde0cb34f71c7c54c8978a7752aca52bdb1dc9887a258f64a996b85ec7d58f6","source":{"kind":"arxiv","id":"2207.08794","version":4},"attestation_state":"computed","paper":{"title":"D$^3$FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Guofeng Zhang, Hujun Bao, Jinyu Li, Weicai Ye, Xingyuan Yu, Xiyue Guo, Yuhang Ming, Zhaopeng Cui","submitted_at":"2022-07-18T17:47:39Z","abstract_excerpt":"In this paper, we introduce a self-supervised deep SLAM method that robustly operates in dynamic scenes while accurately identifying dynamic components. Our method leverages a dual-flow representation for static flow and dynamic flow, facilitating effective scene decomposition in dynamic environments. We propose a dynamic update module based on this representation and develop a dense SLAM system that excels in dynamic scenarios. In addition, we design a self-supervised training scheme using DINO as a prior, enabling label-free training. Our method achieves superior accuracy compared to other s"},"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":"2207.08794","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-18T17:47:39Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"e6682eeec883d04462923e4302140659a2d3b5c8a1d9b29894d9c727e488dac3","abstract_canon_sha256":"e3ea740cd11131a0f0479e28e9ff6a84ab898667de2fe7d3ede2e81c77fa9cef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:32.463771Z","signature_b64":"ua/u0f+Cp3kgzQnu+gHpNNh2EQUgJui4okb4iwfRWpcR0l5mWUwuFdcpB2+zQuTtgof/2vo1IblSWvuYl1ZTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dde0cb34f71c7c54c8978a7752aca52bdb1dc9887a258f64a996b85ec7d58f6","last_reissued_at":"2026-07-05T08:57:32.463391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:32.463391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"D$^3$FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Guofeng Zhang, Hujun Bao, Jinyu Li, Weicai Ye, Xingyuan Yu, Xiyue Guo, Yuhang Ming, Zhaopeng Cui","submitted_at":"2022-07-18T17:47:39Z","abstract_excerpt":"In this paper, we introduce a self-supervised deep SLAM method that robustly operates in dynamic scenes while accurately identifying dynamic components. Our method leverages a dual-flow representation for static flow and dynamic flow, facilitating effective scene decomposition in dynamic environments. We propose a dynamic update module based on this representation and develop a dense SLAM system that excels in dynamic scenarios. In addition, we design a self-supervised training scheme using DINO as a prior, enabling label-free training. Our method achieves superior accuracy compared to other s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.08794","kind":"arxiv","version":4},"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/2207.08794/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":"2207.08794","created_at":"2026-07-05T08:57:32.463440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.08794v4","created_at":"2026-07-05T08:57:32.463440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.08794","created_at":"2026-07-05T08:57:32.463440+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXPAZM2POHD4","created_at":"2026-07-05T08:57:32.463440+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXPAZM2POHD4KTEJ","created_at":"2026-07-05T08:57:32.463440+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXPAZM2P","created_at":"2026-07-05T08:57:32.463440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05965","citing_title":"Dy3DGS-SLAM: Monocular 3D Gaussian Splatting SLAM for Dynamic Environments","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RXPAZM2POHD4KTEJPCTXKKWKKK","json":"https://pith.science/pith/RXPAZM2POHD4KTEJPCTXKKWKKK.json","graph_json":"https://pith.science/api/pith-number/RXPAZM2POHD4KTEJPCTXKKWKKK/graph.json","events_json":"https://pith.science/api/pith-number/RXPAZM2POHD4KTEJPCTXKKWKKK/events.json","paper":"https://pith.science/paper/RXPAZM2P"},"agent_actions":{"view_html":"https://pith.science/pith/RXPAZM2POHD4KTEJPCTXKKWKKK","download_json":"https://pith.science/pith/RXPAZM2POHD4KTEJPCTXKKWKKK.json","view_paper":"https://pith.science/paper/RXPAZM2P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.08794&json=true","fetch_graph":"https://pith.science/api/pith-number/RXPAZM2POHD4KTEJPCTXKKWKKK/graph.json","fetch_events":"https://pith.science/api/pith-number/RXPAZM2POHD4KTEJPCTXKKWKKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXPAZM2POHD4KTEJPCTXKKWKKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXPAZM2POHD4KTEJPCTXKKWKKK/action/storage_attestation","attest_author":"https://pith.science/pith/RXPAZM2POHD4KTEJPCTXKKWKKK/action/author_attestation","sign_citation":"https://pith.science/pith/RXPAZM2POHD4KTEJPCTXKKWKKK/action/citation_signature","submit_replication":"https://pith.science/pith/RXPAZM2POHD4KTEJPCTXKKWKKK/action/replication_record"}},"created_at":"2026-07-05T08:57:32.463440+00:00","updated_at":"2026-07-05T08:57:32.463440+00:00"}