{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D3VTHCBYECPYKZAICLXLL3WZHF","short_pith_number":"pith:D3VTHCBY","schema_version":"1.0","canonical_sha256":"1eeb338838209f85640812eeb5eed93951741b69d79ac94ec2dc535cedea9ff0","source":{"kind":"arxiv","id":"2406.09756","version":1},"attestation_state":"computed","paper":{"title":"Grounding Image Matching in 3D with MASt3R","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"J\\'er\\^ome Revaud, Vincent Leroy, Yohann Cabon","submitted_at":"2024-06-14T06:46:30Z","abstract_excerpt":"Image Matching is a core component of all best-performing algorithms and pipelines in 3D vision. Yet despite matching being fundamentally a 3D problem, intrinsically linked to camera pose and scene geometry, it is typically treated as a 2D problem. This makes sense as the goal of matching is to establish correspondences between 2D pixel fields, but also seems like a potentially hazardous choice. In this work, we take a different stance and propose to cast matching as a 3D task with DUSt3R, a recent and powerful 3D reconstruction framework based on Transformers. Based on pointmaps regression, t"},"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":"2406.09756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-14T06:46:30Z","cross_cats_sorted":[],"title_canon_sha256":"e2409e6aef66f273d489320c9b2e7c62b3e8d146f4d5e46f7f317d60bcae5416","abstract_canon_sha256":"98bc37e3941e51d81125b24db2fe628c9477a2a6f6f6c30731f9bf93399ec353"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:59.378681Z","signature_b64":"nfpUU1YqQX8e7uHc0gqQ/tEiMlzf0Z9lpvgoYxloaWvfhA/T7ct37fwRfu2IgWWBUdFh8+5g4Qg0WpvhLvG0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1eeb338838209f85640812eeb5eed93951741b69d79ac94ec2dc535cedea9ff0","last_reissued_at":"2026-07-05T08:31:59.378191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:59.378191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounding Image Matching in 3D with MASt3R","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"J\\'er\\^ome Revaud, Vincent Leroy, Yohann Cabon","submitted_at":"2024-06-14T06:46:30Z","abstract_excerpt":"Image Matching is a core component of all best-performing algorithms and pipelines in 3D vision. Yet despite matching being fundamentally a 3D problem, intrinsically linked to camera pose and scene geometry, it is typically treated as a 2D problem. This makes sense as the goal of matching is to establish correspondences between 2D pixel fields, but also seems like a potentially hazardous choice. In this work, we take a different stance and propose to cast matching as a 3D task with DUSt3R, a recent and powerful 3D reconstruction framework based on Transformers. Based on pointmaps regression, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09756","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/2406.09756/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":"2406.09756","created_at":"2026-07-05T08:31:59.378259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09756v1","created_at":"2026-07-05T08:31:59.378259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09756","created_at":"2026-07-05T08:31:59.378259+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3VTHCBYECPY","created_at":"2026-07-05T08:31:59.378259+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3VTHCBYECPYKZAI","created_at":"2026-07-05T08:31:59.378259+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3VTHCBY","created_at":"2026-07-05T08:31:59.378259+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13676","citing_title":"Modality Forcing for Scalable Spatial Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09268","citing_title":"VGP-Nav: Metric-Aware Visual Geometric Perception for Robot Navigation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01939","citing_title":"SAVMap: Structure-Aided Visual Mapping of Large-Scale 2.5D Manhattan Wireframes from Panoramic Video","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30855","citing_title":"Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31534","citing_title":"Feature-Optimized Vision for Adaptive 3D Scene Reconstruction","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23888","citing_title":"GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23903","citing_title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2409.12190","citing_title":"Bundle Adjustment in the Eager Mode","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2412.03077","citing_title":"RoDyGS: Robust Dynamic Gaussian Splatting for Casual Videos","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22467","citing_title":"SADGE: Structure and Appearance Domain Gap Estimation of Synthetic and Real Data","ref_index":22,"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":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21862","citing_title":"EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control","ref_index":16,"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":10,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00503","citing_title":"Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2502.20110","citing_title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2408.13912","citing_title":"Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2601.09211","citing_title":"Affostruction: 3D Affordance Grounding with Generative Reconstruction","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2507.11539","citing_title":"Streaming 4D Visual Geometry Transformer","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12938","citing_title":"CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2409.02048","citing_title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09449","citing_title":"SpaceMind++: Toward Allocentric Cognitive Maps for Spatially Grounded Video MLLMs","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21182","citing_title":"WildSplatter: Feed-forward 3D Gaussian Splatting with Appearance Control from Unconstrained Images","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20038","citing_title":"FluSplat: Sparse-View 3D Editing without Test-Time Optimization","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13153","citing_title":"PatchPoison: Poisoning Multi-View Datasets to Degrade 3D Reconstruction","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10106","citing_title":"VGGT-HPE: Reframing Head Pose Estimation as Relative Pose Prediction","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D3VTHCBYECPYKZAICLXLL3WZHF","json":"https://pith.science/pith/D3VTHCBYECPYKZAICLXLL3WZHF.json","graph_json":"https://pith.science/api/pith-number/D3VTHCBYECPYKZAICLXLL3WZHF/graph.json","events_json":"https://pith.science/api/pith-number/D3VTHCBYECPYKZAICLXLL3WZHF/events.json","paper":"https://pith.science/paper/D3VTHCBY"},"agent_actions":{"view_html":"https://pith.science/pith/D3VTHCBYECPYKZAICLXLL3WZHF","download_json":"https://pith.science/pith/D3VTHCBYECPYKZAICLXLL3WZHF.json","view_paper":"https://pith.science/paper/D3VTHCBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09756&json=true","fetch_graph":"https://pith.science/api/pith-number/D3VTHCBYECPYKZAICLXLL3WZHF/graph.json","fetch_events":"https://pith.science/api/pith-number/D3VTHCBYECPYKZAICLXLL3WZHF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3VTHCBYECPYKZAICLXLL3WZHF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3VTHCBYECPYKZAICLXLL3WZHF/action/storage_attestation","attest_author":"https://pith.science/pith/D3VTHCBYECPYKZAICLXLL3WZHF/action/author_attestation","sign_citation":"https://pith.science/pith/D3VTHCBYECPYKZAICLXLL3WZHF/action/citation_signature","submit_replication":"https://pith.science/pith/D3VTHCBYECPYKZAICLXLL3WZHF/action/replication_record"}},"created_at":"2026-07-05T08:31:59.378259+00:00","updated_at":"2026-07-05T08:31:59.378259+00:00"}