{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LJREY63N3NIDZMVWDATG64APOY","short_pith_number":"pith:LJREY63N","schema_version":"1.0","canonical_sha256":"5a624c7b6ddb503cb2b618266f700f7610301d3ac6b7e2148d9937e41958a796","source":{"kind":"arxiv","id":"2507.00392","version":2},"attestation_state":"computed","paper":{"title":"Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wenqi Shao, Ying Fu, Yingping Liang, Yutao Hu","submitted_at":"2025-07-01T03:07:21Z","abstract_excerpt":"Feature matching plays a fundamental role in many computer vision tasks, yet existing methods heavily rely on scarce and clean multi-view image collections, which constrains their generalization to diverse and challenging scenarios. Moreover, conventional feature encoders are typically trained on single-view 2D images, limiting their capacity to capture 3D-aware correspondences. In this paper, we propose a novel two-stage framework that lifts 2D images to 3D space, named as \\textbf{Lift to Match (L2M)}, taking full advantage of large-scale and diverse single-view images. To be specific, in the"},"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":"2507.00392","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T03:07:21Z","cross_cats_sorted":[],"title_canon_sha256":"b96d5c9cf91c8a0259ba716045ce68118e43ba38f6e98536afc4bfde56c2a009","abstract_canon_sha256":"2092a9b004bec1cf965b18a6619da4079cd16c28e267154edffaf40c9176043f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:32.892504Z","signature_b64":"8J0vMXmI306vsUk9kM7uYqnLop201zkLMEjSQbtsW7FIS1MgIeYFDZXB3fvG7/31J4rwES9ln0ItK+kt3f4NAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a624c7b6ddb503cb2b618266f700f7610301d3ac6b7e2148d9937e41958a796","last_reissued_at":"2026-07-05T11:32:32.892001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:32.892001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wenqi Shao, Ying Fu, Yingping Liang, Yutao Hu","submitted_at":"2025-07-01T03:07:21Z","abstract_excerpt":"Feature matching plays a fundamental role in many computer vision tasks, yet existing methods heavily rely on scarce and clean multi-view image collections, which constrains their generalization to diverse and challenging scenarios. Moreover, conventional feature encoders are typically trained on single-view 2D images, limiting their capacity to capture 3D-aware correspondences. In this paper, we propose a novel two-stage framework that lifts 2D images to 3D space, named as \\textbf{Lift to Match (L2M)}, taking full advantage of large-scale and diverse single-view images. To be specific, in the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00392","kind":"arxiv","version":2},"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/2507.00392/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":"2507.00392","created_at":"2026-07-05T11:32:32.892063+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00392v2","created_at":"2026-07-05T11:32:32.892063+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00392","created_at":"2026-07-05T11:32:32.892063+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJREY63N3NID","created_at":"2026-07-05T11:32:32.892063+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJREY63N3NIDZMVW","created_at":"2026-07-05T11:32:32.892063+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJREY63N","created_at":"2026-07-05T11:32:32.892063+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/LJREY63N3NIDZMVWDATG64APOY","json":"https://pith.science/pith/LJREY63N3NIDZMVWDATG64APOY.json","graph_json":"https://pith.science/api/pith-number/LJREY63N3NIDZMVWDATG64APOY/graph.json","events_json":"https://pith.science/api/pith-number/LJREY63N3NIDZMVWDATG64APOY/events.json","paper":"https://pith.science/paper/LJREY63N"},"agent_actions":{"view_html":"https://pith.science/pith/LJREY63N3NIDZMVWDATG64APOY","download_json":"https://pith.science/pith/LJREY63N3NIDZMVWDATG64APOY.json","view_paper":"https://pith.science/paper/LJREY63N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00392&json=true","fetch_graph":"https://pith.science/api/pith-number/LJREY63N3NIDZMVWDATG64APOY/graph.json","fetch_events":"https://pith.science/api/pith-number/LJREY63N3NIDZMVWDATG64APOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJREY63N3NIDZMVWDATG64APOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJREY63N3NIDZMVWDATG64APOY/action/storage_attestation","attest_author":"https://pith.science/pith/LJREY63N3NIDZMVWDATG64APOY/action/author_attestation","sign_citation":"https://pith.science/pith/LJREY63N3NIDZMVWDATG64APOY/action/citation_signature","submit_replication":"https://pith.science/pith/LJREY63N3NIDZMVWDATG64APOY/action/replication_record"}},"created_at":"2026-07-05T11:32:32.892063+00:00","updated_at":"2026-07-05T11:32:32.892063+00:00"}