{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AR3M4W6XY6G7FETDUFTTYHWR2J","short_pith_number":"pith:AR3M4W6X","schema_version":"1.0","canonical_sha256":"0476ce5bd7c78df29263a1673c1ed1d25f27281a074fa9d77ae8f2d02c4c04a9","source":{"kind":"arxiv","id":"2507.16443","version":2},"attestation_state":"computed","paper":{"title":"VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"By dividing long video sequences into chunks and aligning their overlaps with lightweight loop closure, a foundation 3D model can produce accurate monocular reconstructions and trajectories over kilometer-scale outdoor paths without camera,","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Yang, Jiawei Xu, Jin Xie, Kai Deng, Zexin Ti","submitted_at":"2025-07-22T10:39:04Z","abstract_excerpt":"Foundation models for 3D vision have recently demonstrated remarkable capabilities in 3D perception. However, extending these models to large-scale RGB stream 3D reconstruction remains challenging due to memory limitations. In this work, we propose VGGT-Long, a simple yet effective system that pushes the limits of monocular 3D reconstruction to kilometer-scale, unbounded outdoor environments. Our approach addresses the scalability bottlenecks of existing models through a chunk-based processing strategy combined with overlapping alignment and lightweight loop closure optimization. Without requi"},"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":"2507.16443","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-22T10:39:04Z","cross_cats_sorted":[],"title_canon_sha256":"9108ac9099651f5f1c40ea91e45191e003e1c2b5af5308b7771eddf8c9a52abd","abstract_canon_sha256":"99eefb1edc7b986d451325d37c3696082d8772fa2cbb54fe83b131ac28524973"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:14.547065Z","signature_b64":"bJ+DGsqW237RdwqdC/pLXX6B4c+U4z1fxjyJzYqv8D8PLWte6oX+c1jf5BP2YNiP1G0JyAAIM/nGeJ8jVo6NBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0476ce5bd7c78df29263a1673c1ed1d25f27281a074fa9d77ae8f2d02c4c04a9","last_reissued_at":"2026-05-17T23:38:14.546444Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:14.546444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"By dividing long video sequences into chunks and aligning their overlaps with lightweight loop closure, a foundation 3D model can produce accurate monocular reconstructions and trajectories over kilometer-scale outdoor paths without camera,","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Yang, Jiawei Xu, Jin Xie, Kai Deng, Zexin Ti","submitted_at":"2025-07-22T10:39:04Z","abstract_excerpt":"Foundation models for 3D vision have recently demonstrated remarkable capabilities in 3D perception. However, extending these models to large-scale RGB stream 3D reconstruction remains challenging due to memory limitations. In this work, we propose VGGT-Long, a simple yet effective system that pushes the limits of monocular 3D reconstruction to kilometer-scale, unbounded outdoor environments. Our approach addresses the scalability bottlenecks of existing models through a chunk-based processing strategy combined with overlapping alignment and lightweight loop closure optimization. Without requi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"VGGT-Long achieves trajectory and reconstruction performance comparable to traditional methods on KITTI, Waymo, and Virtual KITTI datasets without requiring camera calibration, depth supervision or model retraining.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That chunk-wise alignment plus lightweight loop closure will maintain global consistency and metric accuracy over kilometer-scale trajectories without drift or scale drift that would require additional constraints or supervision.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VGGT-Long extends VGGT with chunking, overlap alignment, and loop closure to produce consistent kilometer-scale 3D reconstructions from monocular RGB sequences without retraining or extra supervision.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"By dividing long video sequences into chunks and aligning their overlaps with lightweight loop closure, a foundation 3D model can produce accurate monocular reconstructions and trajectories over kilometer-scale outdoor paths without camera,","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0264686dd511248d824ef796d324c7d6ab96ae3858d2ee19806907c42cf3e82d"},"source":{"id":"2507.16443","kind":"arxiv","version":2},"verdict":{"id":"2744134d-a077-4d81-bc40-501d77b106ff","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T08:41:36.975777Z","strongest_claim":"VGGT-Long achieves trajectory and reconstruction performance comparable to traditional methods on KITTI, Waymo, and Virtual KITTI datasets without requiring camera calibration, depth supervision or model retraining.","one_line_summary":"VGGT-Long extends VGGT with chunking, overlap alignment, and loop closure to produce consistent kilometer-scale 3D reconstructions from monocular RGB sequences without retraining or extra supervision.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That chunk-wise alignment plus lightweight loop closure will maintain global consistency and metric accuracy over kilometer-scale trajectories without drift or scale drift that would require additional constraints or supervision.","pith_extraction_headline":"By dividing long video sequences into chunks and aligning their overlaps with lightweight loop closure, a foundation 3D model can produce accurate monocular reconstructions and trajectories over kilometer-scale outdoor paths without camera,"},"references":{"count":47,"sample":[{"doi":"","year":2011,"title":"Building rome in a day.Communications of the ACM, 54 (10):105–112, 2011","work_id":"9cb7cc10-d733-4f1a-947a-632a3dfc22c5","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Learning to match features with seeded graph matching network","work_id":"a15eecc5-1a30-423a-bb06-bf39ded9dc23","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Soft2: Stereo visual odometry for road vehicles based on a point- to-epipolar-line metric.IEEE Transactions on Robotics, 39 (1):273–288, 2022","work_id":"e55539dc-2f72-4581-91f7-807cd501547f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"FlashAttention-2: Faster attention with better par- allelism and work partitioning","work_id":"d339dd1a-7759-4a93-ae6c-cea84710cbd6","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Fu, Stefano Ermon, Atri Rudra, and Christopher R´e","work_id":"b96d29be-63c4-4b92-b53f-6d6583896943","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":47,"snapshot_sha256":"95b649b6a2702c2068cb26816984e64621f040a1a8a70d3b02d22f5bbc7b0c2c","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"6c4cdb246c715d5cf3733dc6b854b9448cbcc7a06c2316c916bc11e8809469e8"},"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":"2507.16443","created_at":"2026-05-17T23:38:14.546546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16443v2","created_at":"2026-05-17T23:38:14.546546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16443","created_at":"2026-05-17T23:38:14.546546+00:00"},{"alias_kind":"pith_short_12","alias_value":"AR3M4W6XY6G7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"AR3M4W6XY6G7FETD","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"AR3M4W6X","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":23,"sample":[{"citing_arxiv_id":"2605.05749","citing_title":"Ray-Aware Pointer Memory with Adaptive Updates for Streaming 3D Reconstruction","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21131","citing_title":"UniT: Unified Geometry Learning with Group Autoregressive Transformer","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06270","citing_title":"Spark3R: Asymmetric Token Reduction Makes Fast Feed-Forward 3D Reconstruction","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17303","citing_title":"LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17478","citing_title":"Mamba-VGGT: Persistent Long-Sequence Video Geometry Grounded Transformer via External Sliding Window Mamba Memory","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2509.26645","citing_title":"TTT3R: 3D Reconstruction as Test-Time Training","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2509.02560","citing_title":"FastVGGT: Training-Free Acceleration of Visual Geometry Transformer","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2603.07690","citing_title":"FrameVGGT: Geometry-Aligned Frame-Level Memory for Bounded Streaming VGGT","ref_index":27,"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":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13741","citing_title":"LEXI-SG: Monocular 3D Scene Graph Mapping with Room-Guided Feed-Forward Reconstruction","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05749","citing_title":"Ray-Aware Pointer Memory with Adaptive Updates for Streaming 3D Reconstruction","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11267","citing_title":"Real-Scale Island Area and Coastline Estimation using Only its Place Name or Coordinates","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08371","citing_title":"PaceVGGT: Pre-Alternating-Attention Token Pruning for Visual Geometry Transformers","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09644","citing_title":"Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10789","citing_title":"Rapid Forest Fuel Load Estimation via Virtual Remote Sensing and Metric-Scale Feed-Forward 3D Reconstruction","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08739","citing_title":"ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06270","citing_title":"Spark3R: Asymmetric Token Reduction Makes Fast Feed-Forward 3D Reconstruction","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05749","citing_title":"Ray-Aware Pointer Memory with Adaptive Updates for Streaming 3D Reconstruction","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10593","citing_title":"MonoEM-GS: Monocular Expectation-Maximization Gaussian Splatting SLAM","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11372","citing_title":"MR.ScaleMaster: Scale-Consistent Collaborative Mapping from Crowd-Sourced Monocular Videos","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":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14141","citing_title":"Geometric Context Transformer for Streaming 3D Reconstruction","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14795","citing_title":"Keep It CALM: Toward Calibration-Free Kilometer-Level SLAM with Visual Geometry Foundation Models via an Assistant Eye","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AR3M4W6XY6G7FETDUFTTYHWR2J","json":"https://pith.science/pith/AR3M4W6XY6G7FETDUFTTYHWR2J.json","graph_json":"https://pith.science/api/pith-number/AR3M4W6XY6G7FETDUFTTYHWR2J/graph.json","events_json":"https://pith.science/api/pith-number/AR3M4W6XY6G7FETDUFTTYHWR2J/events.json","paper":"https://pith.science/paper/AR3M4W6X"},"agent_actions":{"view_html":"https://pith.science/pith/AR3M4W6XY6G7FETDUFTTYHWR2J","download_json":"https://pith.science/pith/AR3M4W6XY6G7FETDUFTTYHWR2J.json","view_paper":"https://pith.science/paper/AR3M4W6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16443&json=true","fetch_graph":"https://pith.science/api/pith-number/AR3M4W6XY6G7FETDUFTTYHWR2J/graph.json","fetch_events":"https://pith.science/api/pith-number/AR3M4W6XY6G7FETDUFTTYHWR2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AR3M4W6XY6G7FETDUFTTYHWR2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AR3M4W6XY6G7FETDUFTTYHWR2J/action/storage_attestation","attest_author":"https://pith.science/pith/AR3M4W6XY6G7FETDUFTTYHWR2J/action/author_attestation","sign_citation":"https://pith.science/pith/AR3M4W6XY6G7FETDUFTTYHWR2J/action/citation_signature","submit_replication":"https://pith.science/pith/AR3M4W6XY6G7FETDUFTTYHWR2J/action/replication_record"}},"created_at":"2026-05-17T23:38:14.546546+00:00","updated_at":"2026-05-17T23:38:14.546546+00:00"}