{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EMO2FCLVHNJJASFWIPDM7777KS","short_pith_number":"pith:EMO2FCLV","schema_version":"1.0","canonical_sha256":"231da289753b529048b643c6cfffff54b50e6d851df7a078d7ad05abaea13a56","source":{"kind":"arxiv","id":"2508.10893","version":1},"attestation_state":"computed","paper":{"title":"STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Dai, Chen Change Loy, Fangzhou Hong, Honghua Chen, Shangchen Zhou, Shuai Yang, Xingang Pan, Yihang Luo, Yushi Lan, Zhaoyang Lyu","submitted_at":"2025-08-14T17:58:05Z","abstract_excerpt":"We present STream3R, a novel approach to 3D reconstruction that reformulates pointmap prediction as a decoder-only Transformer problem. Existing state-of-the-art methods for multi-view reconstruction either depend on expensive global optimization or rely on simplistic memory mechanisms that scale poorly with sequence length. In contrast, STream3R introduces an streaming framework that processes image sequences efficiently using causal attention, inspired by advances in modern language modeling. By learning geometric priors from large-scale 3D datasets, STream3R generalizes well to diverse and "},"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":"2508.10893","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-14T17:58:05Z","cross_cats_sorted":[],"title_canon_sha256":"1c9414e4699d486e188a1158711797d0851d33b1d87d30a6593746e97068945b","abstract_canon_sha256":"f16dde078e4f12a768ab756389e95f52d58111bd4039acdda39fd1667e4470ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:04.598533Z","signature_b64":"D/aC1wxZo7kx4wUbRNzsMputCd7NlHiMdHk1IVjboaTvfBVvmX5OO7vmexPsB55Y7NKJNA1SkCNvKqLWw6FGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"231da289753b529048b643c6cfffff54b50e6d851df7a078d7ad05abaea13a56","last_reissued_at":"2026-07-05T11:54:04.598067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:04.598067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Dai, Chen Change Loy, Fangzhou Hong, Honghua Chen, Shangchen Zhou, Shuai Yang, Xingang Pan, Yihang Luo, Yushi Lan, Zhaoyang Lyu","submitted_at":"2025-08-14T17:58:05Z","abstract_excerpt":"We present STream3R, a novel approach to 3D reconstruction that reformulates pointmap prediction as a decoder-only Transformer problem. Existing state-of-the-art methods for multi-view reconstruction either depend on expensive global optimization or rely on simplistic memory mechanisms that scale poorly with sequence length. In contrast, STream3R introduces an streaming framework that processes image sequences efficiently using causal attention, inspired by advances in modern language modeling. By learning geometric priors from large-scale 3D datasets, STream3R generalizes well to diverse and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10893","kind":"arxiv","version":1},"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/2508.10893/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":"2508.10893","created_at":"2026-07-05T11:54:04.598129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10893v1","created_at":"2026-07-05T11:54:04.598129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10893","created_at":"2026-07-05T11:54:04.598129+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMO2FCLVHNJJ","created_at":"2026-07-05T11:54:04.598129+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMO2FCLVHNJJASFW","created_at":"2026-07-05T11:54:04.598129+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMO2FCLV","created_at":"2026-07-05T11:54:04.598129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06891","citing_title":"Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05035","citing_title":"Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02552","citing_title":"Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26519","citing_title":"$R^3$: 3D Reconstruction via Relative Regression","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23889","citing_title":"HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23903","citing_title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05749","citing_title":"Ray-Aware Pointer Memory with Adaptive Updates for Streaming 3D Reconstruction","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16258","citing_title":"IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16258","citing_title":"IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2507.11539","citing_title":"Streaming 4D Visual Geometry Transformer","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2603.20284","citing_title":"STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13038","citing_title":"CoGE: Sim-to-Real Online Geometric Estimation for Monocular Colonoscopy","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05749","citing_title":"Ray-Aware Pointer Memory with Adaptive Updates for Streaming 3D Reconstruction","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12027","citing_title":"4DVGGT-D: 4D Visual Geometry Transformer with Improved Dynamic Depth Estimation","ref_index":12,"is_internal_anchor":false},{"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":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05749","citing_title":"Ray-Aware Pointer Memory with Adaptive Updates for Streaming 3D Reconstruction","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08542","citing_title":"Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07279","citing_title":"Mem3R: Streaming 3D Reconstruction with Hybrid Memory via Test-Time Training","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05351","citing_title":"AnyImageNav: Any-View Geometry for Precise Last-Meter Image-Goal Navigation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14025","citing_title":"Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective","ref_index":184,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMO2FCLVHNJJASFWIPDM7777KS","json":"https://pith.science/pith/EMO2FCLVHNJJASFWIPDM7777KS.json","graph_json":"https://pith.science/api/pith-number/EMO2FCLVHNJJASFWIPDM7777KS/graph.json","events_json":"https://pith.science/api/pith-number/EMO2FCLVHNJJASFWIPDM7777KS/events.json","paper":"https://pith.science/paper/EMO2FCLV"},"agent_actions":{"view_html":"https://pith.science/pith/EMO2FCLVHNJJASFWIPDM7777KS","download_json":"https://pith.science/pith/EMO2FCLVHNJJASFWIPDM7777KS.json","view_paper":"https://pith.science/paper/EMO2FCLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10893&json=true","fetch_graph":"https://pith.science/api/pith-number/EMO2FCLVHNJJASFWIPDM7777KS/graph.json","fetch_events":"https://pith.science/api/pith-number/EMO2FCLVHNJJASFWIPDM7777KS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMO2FCLVHNJJASFWIPDM7777KS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMO2FCLVHNJJASFWIPDM7777KS/action/storage_attestation","attest_author":"https://pith.science/pith/EMO2FCLVHNJJASFWIPDM7777KS/action/author_attestation","sign_citation":"https://pith.science/pith/EMO2FCLVHNJJASFWIPDM7777KS/action/citation_signature","submit_replication":"https://pith.science/pith/EMO2FCLVHNJJASFWIPDM7777KS/action/replication_record"}},"created_at":"2026-07-05T11:54:04.598129+00:00","updated_at":"2026-07-05T11:54:04.598129+00:00"}