{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AY7GH6MXWJCK4PNHGNRSXNL7IX","short_pith_number":"pith:AY7GH6MX","schema_version":"1.0","canonical_sha256":"063e63f997b244ae3da733632bb57f45e1d4f4bfe8907e45de164c25586dfa74","source":{"kind":"arxiv","id":"2306.13643","version":1},"attestation_state":"computed","paper":{"title":"LightGlue: Local Feature Matching at Light Speed","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Marc Pollefeys, Paul-Edouard Sarlin, Philipp Lindenberger","submitted_at":"2023-06-23T17:52:54Z","abstract_excerpt":"We introduce LightGlue, a deep neural network that learns to match local features across images. We revisit multiple design decisions of SuperGlue, the state of the art in sparse matching, and derive simple but effective improvements. Cumulatively, they make LightGlue more efficient - in terms of both memory and computation, more accurate, and much easier to train. One key property is that LightGlue is adaptive to the difficulty of the problem: the inference is much faster on image pairs that are intuitively easy to match, for example because of a larger visual overlap or limited appearance ch"},"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":"2306.13643","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-23T17:52:54Z","cross_cats_sorted":[],"title_canon_sha256":"5d1133732ea595d5a134b9cfc5b9523f6d7d1fc26896dc69c6aee16c47a3cc79","abstract_canon_sha256":"ce05a3e8d020065e38613d4d834d6f902ec5c09cf849d5a3bf79b908ba167df7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:07.506769Z","signature_b64":"nMBp+jG3Ys9nZVnmj5AttEEETkOOOWdPgf8Y0+7Vsu2lxVzVTrrcC1phnEolFNzXntukygQZDwSgSQMiedp7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"063e63f997b244ae3da733632bb57f45e1d4f4bfe8907e45de164c25586dfa74","last_reissued_at":"2026-07-05T06:24:07.506393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:07.506393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LightGlue: Local Feature Matching at Light Speed","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Marc Pollefeys, Paul-Edouard Sarlin, Philipp Lindenberger","submitted_at":"2023-06-23T17:52:54Z","abstract_excerpt":"We introduce LightGlue, a deep neural network that learns to match local features across images. We revisit multiple design decisions of SuperGlue, the state of the art in sparse matching, and derive simple but effective improvements. Cumulatively, they make LightGlue more efficient - in terms of both memory and computation, more accurate, and much easier to train. One key property is that LightGlue is adaptive to the difficulty of the problem: the inference is much faster on image pairs that are intuitively easy to match, for example because of a larger visual overlap or limited appearance ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13643","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/2306.13643/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":"2306.13643","created_at":"2026-07-05T06:24:07.506451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.13643v1","created_at":"2026-07-05T06:24:07.506451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13643","created_at":"2026-07-05T06:24:07.506451+00:00"},{"alias_kind":"pith_short_12","alias_value":"AY7GH6MXWJCK","created_at":"2026-07-05T06:24:07.506451+00:00"},{"alias_kind":"pith_short_16","alias_value":"AY7GH6MXWJCK4PNH","created_at":"2026-07-05T06:24:07.506451+00:00"},{"alias_kind":"pith_short_8","alias_value":"AY7GH6MX","created_at":"2026-07-05T06:24:07.506451+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09162","citing_title":"Zero-Parameter Geometric Gating for Temporally Stable Low-Altitude UAV Video Semantic Segmentation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08795","citing_title":"PairWise Image Finder: An Open-source Tool for Finding Visually Aligned Street-Level Image Pairs for Urban Perception Studies","ref_index":8,"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":12,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17434","citing_title":"Leveraging AV1 motion vectors for Fast and Dense Feature Matching","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22714","citing_title":"Long-tail Internet photo reconstruction","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AY7GH6MXWJCK4PNHGNRSXNL7IX","json":"https://pith.science/pith/AY7GH6MXWJCK4PNHGNRSXNL7IX.json","graph_json":"https://pith.science/api/pith-number/AY7GH6MXWJCK4PNHGNRSXNL7IX/graph.json","events_json":"https://pith.science/api/pith-number/AY7GH6MXWJCK4PNHGNRSXNL7IX/events.json","paper":"https://pith.science/paper/AY7GH6MX"},"agent_actions":{"view_html":"https://pith.science/pith/AY7GH6MXWJCK4PNHGNRSXNL7IX","download_json":"https://pith.science/pith/AY7GH6MXWJCK4PNHGNRSXNL7IX.json","view_paper":"https://pith.science/paper/AY7GH6MX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.13643&json=true","fetch_graph":"https://pith.science/api/pith-number/AY7GH6MXWJCK4PNHGNRSXNL7IX/graph.json","fetch_events":"https://pith.science/api/pith-number/AY7GH6MXWJCK4PNHGNRSXNL7IX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AY7GH6MXWJCK4PNHGNRSXNL7IX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AY7GH6MXWJCK4PNHGNRSXNL7IX/action/storage_attestation","attest_author":"https://pith.science/pith/AY7GH6MXWJCK4PNHGNRSXNL7IX/action/author_attestation","sign_citation":"https://pith.science/pith/AY7GH6MXWJCK4PNHGNRSXNL7IX/action/citation_signature","submit_replication":"https://pith.science/pith/AY7GH6MXWJCK4PNHGNRSXNL7IX/action/replication_record"}},"created_at":"2026-07-05T06:24:07.506451+00:00","updated_at":"2026-07-05T06:24:07.506451+00:00"}