{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GGOUEZLD5VF3OWQB2TCEAQU64K","short_pith_number":"pith:GGOUEZLD","schema_version":"1.0","canonical_sha256":"319d426563ed4bb75a01d4c440429ee28b46149059d2c5bc69dfccb8b72d2e6f","source":{"kind":"arxiv","id":"1905.03561","version":1},"attestation_state":"computed","paper":{"title":"D2-Net: A Trainable CNN for Joint Detection and Description of Local Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akihiko Torii, Ignacio Rocco, Josef Sivic, Marc Pollefeys, Mihai Dusmanu, Tomas Pajdla, Torsten Sattler","submitted_at":"2019-05-09T12:12:14Z","abstract_excerpt":"In this work we address the problem of finding reliable pixel-level correspondences under difficult imaging conditions. We propose an approach where a single convolutional neural network plays a dual role: It is simultaneously a dense feature descriptor and a feature detector. By postponing the detection to a later stage, the obtained keypoints are more stable than their traditional counterparts based on early detection of low-level structures. We show that this model can be trained using pixel correspondences extracted from readily available large-scale SfM reconstructions, without any furthe"},"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":"1905.03561","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-09T12:12:14Z","cross_cats_sorted":[],"title_canon_sha256":"139bd035ff0f9900153411dc18970bd52178f602396aca850d934930bc9796c2","abstract_canon_sha256":"32c8030e324ad8a9af4255a8b573ebe85410b011f52477e5cb1f17d7de2dce31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:37.410926Z","signature_b64":"2GhW3NiasPM4zONS6t54w2Vnc88Bg6NFRnUyVoUdX93hxYPsl1n1g3ecK1Vh/OduSAOpbZ2jhDedx+KsZmYZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"319d426563ed4bb75a01d4c440429ee28b46149059d2c5bc69dfccb8b72d2e6f","last_reissued_at":"2026-05-17T23:46:37.410073Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:37.410073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"D2-Net: A Trainable CNN for Joint Detection and Description of Local Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akihiko Torii, Ignacio Rocco, Josef Sivic, Marc Pollefeys, Mihai Dusmanu, Tomas Pajdla, Torsten Sattler","submitted_at":"2019-05-09T12:12:14Z","abstract_excerpt":"In this work we address the problem of finding reliable pixel-level correspondences under difficult imaging conditions. We propose an approach where a single convolutional neural network plays a dual role: It is simultaneously a dense feature descriptor and a feature detector. By postponing the detection to a later stage, the obtained keypoints are more stable than their traditional counterparts based on early detection of low-level structures. We show that this model can be trained using pixel correspondences extracted from readily available large-scale SfM reconstructions, without any furthe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.03561","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":""},"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":"1905.03561","created_at":"2026-05-17T23:46:37.410215+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.03561v1","created_at":"2026-05-17T23:46:37.410215+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.03561","created_at":"2026-05-17T23:46:37.410215+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGOUEZLD5VF3","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGOUEZLD5VF3OWQB","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGOUEZLD","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.18052","citing_title":"Efficient 3D Content Reconstruction and Generation","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19865","citing_title":"Landscape-Awareness for Geometric View Diffusion Model","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGOUEZLD5VF3OWQB2TCEAQU64K","json":"https://pith.science/pith/GGOUEZLD5VF3OWQB2TCEAQU64K.json","graph_json":"https://pith.science/api/pith-number/GGOUEZLD5VF3OWQB2TCEAQU64K/graph.json","events_json":"https://pith.science/api/pith-number/GGOUEZLD5VF3OWQB2TCEAQU64K/events.json","paper":"https://pith.science/paper/GGOUEZLD"},"agent_actions":{"view_html":"https://pith.science/pith/GGOUEZLD5VF3OWQB2TCEAQU64K","download_json":"https://pith.science/pith/GGOUEZLD5VF3OWQB2TCEAQU64K.json","view_paper":"https://pith.science/paper/GGOUEZLD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.03561&json=true","fetch_graph":"https://pith.science/api/pith-number/GGOUEZLD5VF3OWQB2TCEAQU64K/graph.json","fetch_events":"https://pith.science/api/pith-number/GGOUEZLD5VF3OWQB2TCEAQU64K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGOUEZLD5VF3OWQB2TCEAQU64K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGOUEZLD5VF3OWQB2TCEAQU64K/action/storage_attestation","attest_author":"https://pith.science/pith/GGOUEZLD5VF3OWQB2TCEAQU64K/action/author_attestation","sign_citation":"https://pith.science/pith/GGOUEZLD5VF3OWQB2TCEAQU64K/action/citation_signature","submit_replication":"https://pith.science/pith/GGOUEZLD5VF3OWQB2TCEAQU64K/action/replication_record"}},"created_at":"2026-05-17T23:46:37.410215+00:00","updated_at":"2026-05-17T23:46:37.410215+00:00"}