{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UFH2BRMXBWL6VSE2OVDPZCPHXH","short_pith_number":"pith:UFH2BRMX","schema_version":"1.0","canonical_sha256":"a14fa0c5970d97eac89a7546fc89e7b9f47a688e6f8b51a256cce23285068277","source":{"kind":"arxiv","id":"2501.13928","version":2},"attestation_state":"computed","paper":{"title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexander Sax, Ang Cao, Franziska Meier, Hao Tang, Jianing Yang, Joyce Chai, Kevin J. Liang, Matt Feiszli, Mikael Henaff","submitted_at":"2025-01-23T18:59:55Z","abstract_excerpt":"Multi-view 3D reconstruction remains a core challenge in computer vision, particularly in applications requiring accurate and scalable representations across diverse perspectives. Current leading methods such as DUSt3R employ a fundamentally pairwise approach, processing images in pairs and necessitating costly global alignment procedures to reconstruct from multiple views. In this work, we propose Fast 3D Reconstruction (Fast3R), a novel multi-view generalization to DUSt3R that achieves efficient and scalable 3D reconstruction by processing many views in parallel. Fast3R's Transformer-based a"},"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":"2501.13928","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T18:59:55Z","cross_cats_sorted":["cs.AI","cs.GR","cs.RO"],"title_canon_sha256":"a0b95c021fe1663c27b2891cbc1207159d188552081e40f46d5d05eda43d3099","abstract_canon_sha256":"e8a368414d54949bdc3756084130a1f7b9f6e92b3561fb0d8987de4c7e6058c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:44.811381Z","signature_b64":"doYI1DHH3Qnbrlhh4SiX00B0QzrY0SPKHFqHZmn4t7uXCWWjeK4i6SLh7GcGxClzaJgXgT0PO9kZ8bg6sWAaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a14fa0c5970d97eac89a7546fc89e7b9f47a688e6f8b51a256cce23285068277","last_reissued_at":"2026-07-05T10:35:44.810501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:44.810501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexander Sax, Ang Cao, Franziska Meier, Hao Tang, Jianing Yang, Joyce Chai, Kevin J. Liang, Matt Feiszli, Mikael Henaff","submitted_at":"2025-01-23T18:59:55Z","abstract_excerpt":"Multi-view 3D reconstruction remains a core challenge in computer vision, particularly in applications requiring accurate and scalable representations across diverse perspectives. Current leading methods such as DUSt3R employ a fundamentally pairwise approach, processing images in pairs and necessitating costly global alignment procedures to reconstruct from multiple views. In this work, we propose Fast 3D Reconstruction (Fast3R), a novel multi-view generalization to DUSt3R that achieves efficient and scalable 3D reconstruction by processing many views in parallel. Fast3R's Transformer-based a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13928","kind":"arxiv","version":2},"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/2501.13928/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":"2501.13928","created_at":"2026-07-05T10:35:44.810627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13928v2","created_at":"2026-07-05T10:35:44.810627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13928","created_at":"2026-07-05T10:35:44.810627+00:00"},{"alias_kind":"pith_short_12","alias_value":"UFH2BRMXBWL6","created_at":"2026-07-05T10:35:44.810627+00:00"},{"alias_kind":"pith_short_16","alias_value":"UFH2BRMXBWL6VSE2","created_at":"2026-07-05T10:35:44.810627+00:00"},{"alias_kind":"pith_short_8","alias_value":"UFH2BRMX","created_at":"2026-07-05T10:35:44.810627+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22882","citing_title":"GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26115","citing_title":"TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22882","citing_title":"GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23903","citing_title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2409.12190","citing_title":"Bundle Adjustment in the Eager Mode","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16258","citing_title":"IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22190","citing_title":"No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16258","citing_title":"IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18052","citing_title":"Efficient 3D Content Reconstruction and Generation","ref_index":293,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20279","citing_title":"VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2507.07982","citing_title":"Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2510.00978","citing_title":"A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00503","citing_title":"Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16443","citing_title":"VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10934","citing_title":"ViPE: Video Pose Engine for 3D Geometric Perception","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2507.11539","citing_title":"Streaming 4D Visual Geometry Transformer","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2507.13347","citing_title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08371","citing_title":"PaceVGGT: Pre-Alternating-Attention Token Pruning for Visual Geometry Transformers","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10204","citing_title":"3DReflecNet: A Large-Scale Dataset for 3D Reconstruction of Reflective, Transparent, and Low-Texture Objects","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UFH2BRMXBWL6VSE2OVDPZCPHXH","json":"https://pith.science/pith/UFH2BRMXBWL6VSE2OVDPZCPHXH.json","graph_json":"https://pith.science/api/pith-number/UFH2BRMXBWL6VSE2OVDPZCPHXH/graph.json","events_json":"https://pith.science/api/pith-number/UFH2BRMXBWL6VSE2OVDPZCPHXH/events.json","paper":"https://pith.science/paper/UFH2BRMX"},"agent_actions":{"view_html":"https://pith.science/pith/UFH2BRMXBWL6VSE2OVDPZCPHXH","download_json":"https://pith.science/pith/UFH2BRMXBWL6VSE2OVDPZCPHXH.json","view_paper":"https://pith.science/paper/UFH2BRMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13928&json=true","fetch_graph":"https://pith.science/api/pith-number/UFH2BRMXBWL6VSE2OVDPZCPHXH/graph.json","fetch_events":"https://pith.science/api/pith-number/UFH2BRMXBWL6VSE2OVDPZCPHXH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UFH2BRMXBWL6VSE2OVDPZCPHXH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UFH2BRMXBWL6VSE2OVDPZCPHXH/action/storage_attestation","attest_author":"https://pith.science/pith/UFH2BRMXBWL6VSE2OVDPZCPHXH/action/author_attestation","sign_citation":"https://pith.science/pith/UFH2BRMXBWL6VSE2OVDPZCPHXH/action/citation_signature","submit_replication":"https://pith.science/pith/UFH2BRMXBWL6VSE2OVDPZCPHXH/action/replication_record"}},"created_at":"2026-07-05T10:35:44.810627+00:00","updated_at":"2026-07-05T10:35:44.810627+00:00"}