{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HG4F6JGUYPX3AQWXGGW7COV63Y","short_pith_number":"pith:HG4F6JGU","schema_version":"1.0","canonical_sha256":"39b85f24d4c3efb042d731adf13abede3004684d9ce1710d86d1d0e5fe00ad8b","source":{"kind":"arxiv","id":"2404.19174","version":1},"attestation_state":"computed","paper":{"title":"XFeat: Accelerated Features for Lightweight Image Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andre Araujo, Erickson R. Nascimento, Felipe Cadar, Guilherme Potje, Renato Martins","submitted_at":"2024-04-30T00:37:55Z","abstract_excerpt":"We introduce a lightweight and accurate architecture for resource-efficient visual correspondence. Our method, dubbed XFeat (Accelerated Features), revisits fundamental design choices in convolutional neural networks for detecting, extracting, and matching local features. Our new model satisfies a critical need for fast and robust algorithms suitable to resource-limited devices. In particular, accurate image matching requires sufficiently large image resolutions - for this reason, we keep the resolution as large as possible while limiting the number of channels in the network. Besides, our mod"},"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":"2404.19174","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-30T00:37:55Z","cross_cats_sorted":[],"title_canon_sha256":"bbb2e994c31c19f6d2c2d693063f516688914abb939b399744bc808fb69b7062","abstract_canon_sha256":"0214a8d5ba63ace36de962a02a1dcb73f03c6a15edc090b258af373ed4de1651"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:39.318521Z","signature_b64":"FOquo8wWEbnQj7s6qlfjWDROJnufbrGleA/liDsyDrk2aPvvY6autZknFViACGNezlknn7/4ydfrPmBs0fU4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39b85f24d4c3efb042d731adf13abede3004684d9ce1710d86d1d0e5fe00ad8b","last_reissued_at":"2026-07-05T08:13:39.317961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:39.317961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XFeat: Accelerated Features for Lightweight Image Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andre Araujo, Erickson R. Nascimento, Felipe Cadar, Guilherme Potje, Renato Martins","submitted_at":"2024-04-30T00:37:55Z","abstract_excerpt":"We introduce a lightweight and accurate architecture for resource-efficient visual correspondence. Our method, dubbed XFeat (Accelerated Features), revisits fundamental design choices in convolutional neural networks for detecting, extracting, and matching local features. Our new model satisfies a critical need for fast and robust algorithms suitable to resource-limited devices. In particular, accurate image matching requires sufficiently large image resolutions - for this reason, we keep the resolution as large as possible while limiting the number of channels in the network. Besides, our mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19174","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/2404.19174/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":"2404.19174","created_at":"2026-07-05T08:13:39.318032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.19174v1","created_at":"2026-07-05T08:13:39.318032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19174","created_at":"2026-07-05T08:13:39.318032+00:00"},{"alias_kind":"pith_short_12","alias_value":"HG4F6JGUYPX3","created_at":"2026-07-05T08:13:39.318032+00:00"},{"alias_kind":"pith_short_16","alias_value":"HG4F6JGUYPX3AQWX","created_at":"2026-07-05T08:13:39.318032+00:00"},{"alias_kind":"pith_short_8","alias_value":"HG4F6JGU","created_at":"2026-07-05T08:13:39.318032+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.01383","citing_title":"CaRLi-V: Camera-RADAR-LiDAR Point-Wise 3D Velocity Estimation","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HG4F6JGUYPX3AQWXGGW7COV63Y","json":"https://pith.science/pith/HG4F6JGUYPX3AQWXGGW7COV63Y.json","graph_json":"https://pith.science/api/pith-number/HG4F6JGUYPX3AQWXGGW7COV63Y/graph.json","events_json":"https://pith.science/api/pith-number/HG4F6JGUYPX3AQWXGGW7COV63Y/events.json","paper":"https://pith.science/paper/HG4F6JGU"},"agent_actions":{"view_html":"https://pith.science/pith/HG4F6JGUYPX3AQWXGGW7COV63Y","download_json":"https://pith.science/pith/HG4F6JGUYPX3AQWXGGW7COV63Y.json","view_paper":"https://pith.science/paper/HG4F6JGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.19174&json=true","fetch_graph":"https://pith.science/api/pith-number/HG4F6JGUYPX3AQWXGGW7COV63Y/graph.json","fetch_events":"https://pith.science/api/pith-number/HG4F6JGUYPX3AQWXGGW7COV63Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HG4F6JGUYPX3AQWXGGW7COV63Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HG4F6JGUYPX3AQWXGGW7COV63Y/action/storage_attestation","attest_author":"https://pith.science/pith/HG4F6JGUYPX3AQWXGGW7COV63Y/action/author_attestation","sign_citation":"https://pith.science/pith/HG4F6JGUYPX3AQWXGGW7COV63Y/action/citation_signature","submit_replication":"https://pith.science/pith/HG4F6JGUYPX3AQWXGGW7COV63Y/action/replication_record"}},"created_at":"2026-07-05T08:13:39.318032+00:00","updated_at":"2026-07-05T08:13:39.318032+00:00"}