{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LRH4IMVRKXHH5WK7R6JI4JQAAY","short_pith_number":"pith:LRH4IMVR","schema_version":"1.0","canonical_sha256":"5c4fc432b155ce7ed95f8f928e2600060c3c5ae7125af5c2bf693c918c2944c9","source":{"kind":"arxiv","id":"2408.16061","version":1},"attestation_state":"computed","paper":{"title":"3D Reconstruction with Spatial Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Spann3R maintains an external spatial memory to regress per-image pointmaps directly in a global coordinate system from ordered or unordered image collections.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengyi Wang, Lourdes Agapito","submitted_at":"2024-08-28T18:01:00Z","abstract_excerpt":"We present Spann3R, a novel approach for dense 3D reconstruction from ordered or unordered image collections. Built on the DUSt3R paradigm, Spann3R uses a transformer-based architecture to directly regress pointmaps from images without any prior knowledge of the scene or camera parameters. Unlike DUSt3R, which predicts per image-pair pointmaps each expressed in its local coordinate frame, Spann3R can predict per-image pointmaps expressed in a global coordinate system, thus eliminating the need for optimization-based global alignment. The key idea of Spann3R is to manage an external spatial mem"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2408.16061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T18:01:00Z","cross_cats_sorted":[],"title_canon_sha256":"17982137ab62ade0bdda625fa03bdd957a111e965c8102f4d6701d90112f25f8","abstract_canon_sha256":"711a85e5d4b0a857caa58f1b88e7ed5577c5774cdf899299a3dfd5ccd25c0aa4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:14.710873Z","signature_b64":"X7dgkb9pq1/TqvBNoj6h0aDfR3qMcNcWwod1cF3ujiy2o8UFD4Pk+8Y2cOuc0iFnvsemnA5N81UsPh5W9kSyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c4fc432b155ce7ed95f8f928e2600060c3c5ae7125af5c2bf693c918c2944c9","last_reissued_at":"2026-05-17T23:38:14.710171Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:14.710171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D Reconstruction with Spatial Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Spann3R maintains an external spatial memory to regress per-image pointmaps directly in a global coordinate system from ordered or unordered image collections.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengyi Wang, Lourdes Agapito","submitted_at":"2024-08-28T18:01:00Z","abstract_excerpt":"We present Spann3R, a novel approach for dense 3D reconstruction from ordered or unordered image collections. Built on the DUSt3R paradigm, Spann3R uses a transformer-based architecture to directly regress pointmaps from images without any prior knowledge of the scene or camera parameters. Unlike DUSt3R, which predicts per image-pair pointmaps each expressed in its local coordinate frame, Spann3R can predict per-image pointmaps expressed in a global coordinate system, thus eliminating the need for optimization-based global alignment. The key idea of Spann3R is to manage an external spatial mem"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Spann3R can predict per-image pointmaps expressed in a global coordinate system, thus eliminating the need for optimization-based global alignment.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That an external spatial memory can reliably retain and retrieve all relevant prior 3D information across arbitrary ordered or unordered image collections without drift or loss of consistency.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Spann3R uses a learned spatial memory to regress per-image pointmaps directly in a shared global coordinate system, removing the need for optimization-based alignment after per-pair predictions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Spann3R maintains an external spatial memory to regress per-image pointmaps directly in a global coordinate system from ordered or unordered image collections.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"08b1de9de7d50e31b5f29fea6f6e147f7b64c733e38e0b207377e78b468dbc35"},"source":{"id":"2408.16061","kind":"arxiv","version":1},"verdict":{"id":"fe694b86-e570-45e5-b5f6-051412618e53","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T07:25:46.136038Z","strongest_claim":"Spann3R can predict per-image pointmaps expressed in a global coordinate system, thus eliminating the need for optimization-based global alignment.","one_line_summary":"Spann3R uses a learned spatial memory to regress per-image pointmaps directly in a shared global coordinate system, removing the need for optimization-based alignment after per-pair predictions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That an external spatial memory can reliably retain and retrieve all relevant prior 3D information across arbitrary ordered or unordered image collections without drift or loss of consistency.","pith_extraction_headline":"Spann3R maintains an external spatial memory to regress per-image pointmaps directly in a global coordinate system from ordered or unordered image collections."},"references":{"count":95,"sample":[{"doi":"","year":2016,"title":"Large-scale data for multiple-view stereopsis","work_id":"59e8513c-0002-466c-9df6-149362b24863","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2009,"title":"Building rome in a day","work_id":"f5d6ddbf-5d90-485b-bab8-845195de1221","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2010,"title":"Bundle adjustment in the large","work_id":"7999b7bd-140d-481a-8fdd-ed245119639c","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Map-free visual relocalization: Metric pose relative to a single image","work_id":"f07669bc-42a2-4775-95d6-0fc178a4997a","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Human mem- ory: A proposed system and its control processes","work_id":"882e21c1-2606-4802-b75c-f35f0905d0b7","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":95,"snapshot_sha256":"62782dd1bf249ee604bb4810249d5001510c54f98dc5bf6ee4499f89dcff2c27","internal_anchors":1},"formal_canon":{"evidence_count":3,"snapshot_sha256":"bc859328ff2e8efb18e5322841e646239961417c7494790a949d1080b5d7a736"},"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":"2408.16061","created_at":"2026-05-17T23:38:14.710296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.16061v1","created_at":"2026-05-17T23:38:14.710296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16061","created_at":"2026-05-17T23:38:14.710296+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRH4IMVRKXHH","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRH4IMVRKXHH5WK7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRH4IMVR","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":20,"sample":[{"citing_arxiv_id":"2510.17568","citing_title":"PAGE-4D: VGGT-4D Perception via Disentangled Pose and Geometry Estimation","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2511.09818","citing_title":"Lumos3D: A Single-Forward Framework for Low-Light 3D Scene Restoration","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2511.14751","citing_title":"Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2509.26645","citing_title":"TTT3R: 3D Reconstruction as Test-Time Training","ref_index":85,"is_internal_anchor":true},{"citing_arxiv_id":"2508.10934","citing_title":"ViPE: Video Pose Engine for 3D Geometric Perception","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2601.08831","citing_title":"3AM: 3egment Anything with Geometric Consistency in Videos","ref_index":81,"is_internal_anchor":true},{"citing_arxiv_id":"2507.11539","citing_title":"Streaming 4D Visual Geometry Transformer","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2603.04385","citing_title":"ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training","ref_index":67,"is_internal_anchor":true},{"citing_arxiv_id":"2603.20284","citing_title":"STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2603.27222","citing_title":"HD-VGGT: High-Resolution Visual Geometry Transformer","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.00813","citing_title":"DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2507.13347","citing_title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22714","citing_title":"Long-tail Internet photo reconstruction","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22482","citing_title":"Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyond","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11992","citing_title":"ReefMapGS: Enabling Large-Scale Underwater Reconstruction by Closing the Loop Between Multimodal SLAM and Gaussian Splatting","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08542","citing_title":"Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction","ref_index":76,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06830","citing_title":"VGGT-SLAM++","ref_index":81,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09862","citing_title":"FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14025","citing_title":"Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective","ref_index":101,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15284","citing_title":"GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LRH4IMVRKXHH5WK7R6JI4JQAAY","json":"https://pith.science/pith/LRH4IMVRKXHH5WK7R6JI4JQAAY.json","graph_json":"https://pith.science/api/pith-number/LRH4IMVRKXHH5WK7R6JI4JQAAY/graph.json","events_json":"https://pith.science/api/pith-number/LRH4IMVRKXHH5WK7R6JI4JQAAY/events.json","paper":"https://pith.science/paper/LRH4IMVR"},"agent_actions":{"view_html":"https://pith.science/pith/LRH4IMVRKXHH5WK7R6JI4JQAAY","download_json":"https://pith.science/pith/LRH4IMVRKXHH5WK7R6JI4JQAAY.json","view_paper":"https://pith.science/paper/LRH4IMVR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.16061&json=true","fetch_graph":"https://pith.science/api/pith-number/LRH4IMVRKXHH5WK7R6JI4JQAAY/graph.json","fetch_events":"https://pith.science/api/pith-number/LRH4IMVRKXHH5WK7R6JI4JQAAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRH4IMVRKXHH5WK7R6JI4JQAAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRH4IMVRKXHH5WK7R6JI4JQAAY/action/storage_attestation","attest_author":"https://pith.science/pith/LRH4IMVRKXHH5WK7R6JI4JQAAY/action/author_attestation","sign_citation":"https://pith.science/pith/LRH4IMVRKXHH5WK7R6JI4JQAAY/action/citation_signature","submit_replication":"https://pith.science/pith/LRH4IMVRKXHH5WK7R6JI4JQAAY/action/replication_record"}},"created_at":"2026-05-17T23:38:14.710296+00:00","updated_at":"2026-05-17T23:38:14.710296+00:00"}