{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3QEDOQZ3SOYQDUQAR7MBYVMGD3","short_pith_number":"pith:3QEDOQZ3","schema_version":"1.0","canonical_sha256":"dc0837433b93b101d2008fd81c55861ec46258bccc512f2124a73f22dcba9a2a","source":{"kind":"arxiv","id":"2412.09401","version":3},"attestation_state":"computed","paper":{"title":"SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoquan Chen, Qingnan Fan, Shuzhe Wang, Siyan Dong, Yanchao Yang, Yingda Yin, Yuzheng Liu","submitted_at":"2024-12-12T16:08:03Z","abstract_excerpt":"In this paper, we introduce SLAM3R, a novel and effective system for real-time, high-quality, dense 3D reconstruction using RGB videos. SLAM3R provides an end-to-end solution by seamlessly integrating local 3D reconstruction and global coordinate registration through feed-forward neural networks. Given an input video, the system first converts it into overlapping clips using a sliding window mechanism. Unlike traditional pose optimization-based methods, SLAM3R directly regresses 3D pointmaps from RGB images in each window and progressively aligns and deforms these local pointmaps to create a g"},"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":"2412.09401","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T16:08:03Z","cross_cats_sorted":[],"title_canon_sha256":"11ec6a5da9dbf8cd40475526b54b8e3cf11956d77173785916ecbb8aa7cba19a","abstract_canon_sha256":"4cec2cd5f1e80de2bea83651998e918d26ca1a6fbd1ea7a0c1c1458d95d6a40a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:40.101041Z","signature_b64":"i1RAj50LGtEMXKuyr+wnBdUQ3euy+7eyhoUpdiLUJtVyl2KbXoJe7WS6RZLq/1zmKR3aCGcZaqgdEhpGunn0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc0837433b93b101d2008fd81c55861ec46258bccc512f2124a73f22dcba9a2a","last_reissued_at":"2026-07-05T10:37:40.100048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:40.100048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoquan Chen, Qingnan Fan, Shuzhe Wang, Siyan Dong, Yanchao Yang, Yingda Yin, Yuzheng Liu","submitted_at":"2024-12-12T16:08:03Z","abstract_excerpt":"In this paper, we introduce SLAM3R, a novel and effective system for real-time, high-quality, dense 3D reconstruction using RGB videos. SLAM3R provides an end-to-end solution by seamlessly integrating local 3D reconstruction and global coordinate registration through feed-forward neural networks. Given an input video, the system first converts it into overlapping clips using a sliding window mechanism. Unlike traditional pose optimization-based methods, SLAM3R directly regresses 3D pointmaps from RGB images in each window and progressively aligns and deforms these local pointmaps to create a g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09401","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/2412.09401/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":"2412.09401","created_at":"2026-07-05T10:37:40.100164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09401v3","created_at":"2026-07-05T10:37:40.100164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09401","created_at":"2026-07-05T10:37:40.100164+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QEDOQZ3SOYQ","created_at":"2026-07-05T10:37:40.100164+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QEDOQZ3SOYQDUQA","created_at":"2026-07-05T10:37:40.100164+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QEDOQZ3","created_at":"2026-07-05T10:37:40.100164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26519","citing_title":"$R^3$: 3D Reconstruction via Relative Regression","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23903","citing_title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3QEDOQZ3SOYQDUQAR7MBYVMGD3","json":"https://pith.science/pith/3QEDOQZ3SOYQDUQAR7MBYVMGD3.json","graph_json":"https://pith.science/api/pith-number/3QEDOQZ3SOYQDUQAR7MBYVMGD3/graph.json","events_json":"https://pith.science/api/pith-number/3QEDOQZ3SOYQDUQAR7MBYVMGD3/events.json","paper":"https://pith.science/paper/3QEDOQZ3"},"agent_actions":{"view_html":"https://pith.science/pith/3QEDOQZ3SOYQDUQAR7MBYVMGD3","download_json":"https://pith.science/pith/3QEDOQZ3SOYQDUQAR7MBYVMGD3.json","view_paper":"https://pith.science/paper/3QEDOQZ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09401&json=true","fetch_graph":"https://pith.science/api/pith-number/3QEDOQZ3SOYQDUQAR7MBYVMGD3/graph.json","fetch_events":"https://pith.science/api/pith-number/3QEDOQZ3SOYQDUQAR7MBYVMGD3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QEDOQZ3SOYQDUQAR7MBYVMGD3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QEDOQZ3SOYQDUQAR7MBYVMGD3/action/storage_attestation","attest_author":"https://pith.science/pith/3QEDOQZ3SOYQDUQAR7MBYVMGD3/action/author_attestation","sign_citation":"https://pith.science/pith/3QEDOQZ3SOYQDUQAR7MBYVMGD3/action/citation_signature","submit_replication":"https://pith.science/pith/3QEDOQZ3SOYQDUQAR7MBYVMGD3/action/replication_record"}},"created_at":"2026-07-05T10:37:40.100164+00:00","updated_at":"2026-07-05T10:37:40.100164+00:00"}