{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DXSJU44IHICXU54CWMTPZJSHVA","short_pith_number":"pith:DXSJU44I","schema_version":"1.0","canonical_sha256":"1de49a73883a057a7782b326fca647a81fe2a4a9a70e9b5ae37f0a0c07c106b6","source":{"kind":"arxiv","id":"2202.00667","version":3},"attestation_state":"computed","paper":{"title":"DKM: Dense Kernelized Feature Matching for Geometry Estimation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ioannis Athanasiadis, Johan Edstedt, M{\\aa}rten Wadenb\\\"ack, Michael Felsberg","submitted_at":"2022-02-01T18:58:46Z","abstract_excerpt":"Feature matching is a challenging computer vision task that involves finding correspondences between two images of a 3D scene. In this paper we consider the dense approach instead of the more common sparse paradigm, thus striving to find all correspondences. Perhaps counter-intuitively, dense methods have previously shown inferior performance to their sparse and semi-sparse counterparts for estimation of two-view geometry. This changes with our novel dense method, which outperforms both dense and sparse methods on geometry estimation. The novelty is threefold: First, we propose a kernel regres"},"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":"2202.00667","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-01T18:58:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ab74cb97daebf77398d724505e54f7290bdb258a442f6719dae433ba834547bb","abstract_canon_sha256":"a82f42feafd5cefe8b4166e14b1af3a0264029470b73c5bbe1d37bb0806140bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:13.853752Z","signature_b64":"uKW+suqDw9xT7d3k5lsB8BitoEn+4q5LYZYWb3UIIxAf0d/I4ypoChLy8DB7KFLWStvjYraQKyjtytd2haXMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1de49a73883a057a7782b326fca647a81fe2a4a9a70e9b5ae37f0a0c07c106b6","last_reissued_at":"2026-07-05T05:19:13.853200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:13.853200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DKM: Dense Kernelized Feature Matching for Geometry Estimation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ioannis Athanasiadis, Johan Edstedt, M{\\aa}rten Wadenb\\\"ack, Michael Felsberg","submitted_at":"2022-02-01T18:58:46Z","abstract_excerpt":"Feature matching is a challenging computer vision task that involves finding correspondences between two images of a 3D scene. In this paper we consider the dense approach instead of the more common sparse paradigm, thus striving to find all correspondences. Perhaps counter-intuitively, dense methods have previously shown inferior performance to their sparse and semi-sparse counterparts for estimation of two-view geometry. This changes with our novel dense method, which outperforms both dense and sparse methods on geometry estimation. The novelty is threefold: First, we propose a kernel regres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00667","kind":"arxiv","version":3},"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/2202.00667/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":"2202.00667","created_at":"2026-07-05T05:19:13.853262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.00667v3","created_at":"2026-07-05T05:19:13.853262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00667","created_at":"2026-07-05T05:19:13.853262+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXSJU44IHICX","created_at":"2026-07-05T05:19:13.853262+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXSJU44IHICXU54C","created_at":"2026-07-05T05:19:13.853262+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXSJU44I","created_at":"2026-07-05T05:19:13.853262+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXSJU44IHICXU54CWMTPZJSHVA","json":"https://pith.science/pith/DXSJU44IHICXU54CWMTPZJSHVA.json","graph_json":"https://pith.science/api/pith-number/DXSJU44IHICXU54CWMTPZJSHVA/graph.json","events_json":"https://pith.science/api/pith-number/DXSJU44IHICXU54CWMTPZJSHVA/events.json","paper":"https://pith.science/paper/DXSJU44I"},"agent_actions":{"view_html":"https://pith.science/pith/DXSJU44IHICXU54CWMTPZJSHVA","download_json":"https://pith.science/pith/DXSJU44IHICXU54CWMTPZJSHVA.json","view_paper":"https://pith.science/paper/DXSJU44I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.00667&json=true","fetch_graph":"https://pith.science/api/pith-number/DXSJU44IHICXU54CWMTPZJSHVA/graph.json","fetch_events":"https://pith.science/api/pith-number/DXSJU44IHICXU54CWMTPZJSHVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXSJU44IHICXU54CWMTPZJSHVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXSJU44IHICXU54CWMTPZJSHVA/action/storage_attestation","attest_author":"https://pith.science/pith/DXSJU44IHICXU54CWMTPZJSHVA/action/author_attestation","sign_citation":"https://pith.science/pith/DXSJU44IHICXU54CWMTPZJSHVA/action/citation_signature","submit_replication":"https://pith.science/pith/DXSJU44IHICXU54CWMTPZJSHVA/action/replication_record"}},"created_at":"2026-07-05T05:19:13.853262+00:00","updated_at":"2026-07-05T05:19:13.853262+00:00"}