{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BLISAKK7DGXSIYOEDYFD7VDSMP","short_pith_number":"pith:BLISAKK7","schema_version":"1.0","canonical_sha256":"0ad120295f19af2461c41e0a3fd47263c265e847652935d55d96c323eac39355","source":{"kind":"arxiv","id":"2305.19094","version":2},"attestation_state":"computed","paper":{"title":"Diffusion Model for Dense Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gyuseong Lee, Hyeonsu Kim, Hyoungwon Cho, Jisu Nam, Seungryong Kim, Seyeon Kim, Sunwoo Kim","submitted_at":"2023-05-30T14:58:24Z","abstract_excerpt":"The objective for establishing dense correspondence between paired images consists of two terms: a data term and a prior term. While conventional techniques focused on defining hand-designed prior terms, which are difficult to formulate, recent approaches have focused on learning the data term with deep neural networks without explicitly modeling the prior, assuming that the model itself has the capacity to learn an optimal prior from a large-scale dataset. The performance improvement was obvious, however, they often fail to address inherent ambiguities of matching, such as textureless regions"},"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":"2305.19094","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-30T14:58:24Z","cross_cats_sorted":[],"title_canon_sha256":"779f62684ea6e4682ab6458e8f3ecad90ff4adad68fbd220e415cbd35f3fedae","abstract_canon_sha256":"01028e57b21fc8ac88af185a751f0f558aa9737a97d646466a8650608f549dc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:11.403209Z","signature_b64":"3xD3tJQMBtVfsqlBjE1uOeFUyhQgeaQs0F2fnrPwQ5AcPT2Gaj4OGfPhqSzYjxtOqBHELe9mxunDiHnkUvEuBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ad120295f19af2461c41e0a3fd47263c265e847652935d55d96c323eac39355","last_reissued_at":"2026-07-05T07:37:11.402770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:11.402770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Model for Dense Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gyuseong Lee, Hyeonsu Kim, Hyoungwon Cho, Jisu Nam, Seungryong Kim, Seyeon Kim, Sunwoo Kim","submitted_at":"2023-05-30T14:58:24Z","abstract_excerpt":"The objective for establishing dense correspondence between paired images consists of two terms: a data term and a prior term. While conventional techniques focused on defining hand-designed prior terms, which are difficult to formulate, recent approaches have focused on learning the data term with deep neural networks without explicitly modeling the prior, assuming that the model itself has the capacity to learn an optimal prior from a large-scale dataset. The performance improvement was obvious, however, they often fail to address inherent ambiguities of matching, such as textureless regions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19094","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/2305.19094/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":"2305.19094","created_at":"2026-07-05T07:37:11.402824+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.19094v2","created_at":"2026-07-05T07:37:11.402824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19094","created_at":"2026-07-05T07:37:11.402824+00:00"},{"alias_kind":"pith_short_12","alias_value":"BLISAKK7DGXS","created_at":"2026-07-05T07:37:11.402824+00:00"},{"alias_kind":"pith_short_16","alias_value":"BLISAKK7DGXSIYOE","created_at":"2026-07-05T07:37:11.402824+00:00"},{"alias_kind":"pith_short_8","alias_value":"BLISAKK7","created_at":"2026-07-05T07:37:11.402824+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12587","citing_title":"TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BLISAKK7DGXSIYOEDYFD7VDSMP","json":"https://pith.science/pith/BLISAKK7DGXSIYOEDYFD7VDSMP.json","graph_json":"https://pith.science/api/pith-number/BLISAKK7DGXSIYOEDYFD7VDSMP/graph.json","events_json":"https://pith.science/api/pith-number/BLISAKK7DGXSIYOEDYFD7VDSMP/events.json","paper":"https://pith.science/paper/BLISAKK7"},"agent_actions":{"view_html":"https://pith.science/pith/BLISAKK7DGXSIYOEDYFD7VDSMP","download_json":"https://pith.science/pith/BLISAKK7DGXSIYOEDYFD7VDSMP.json","view_paper":"https://pith.science/paper/BLISAKK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.19094&json=true","fetch_graph":"https://pith.science/api/pith-number/BLISAKK7DGXSIYOEDYFD7VDSMP/graph.json","fetch_events":"https://pith.science/api/pith-number/BLISAKK7DGXSIYOEDYFD7VDSMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BLISAKK7DGXSIYOEDYFD7VDSMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BLISAKK7DGXSIYOEDYFD7VDSMP/action/storage_attestation","attest_author":"https://pith.science/pith/BLISAKK7DGXSIYOEDYFD7VDSMP/action/author_attestation","sign_citation":"https://pith.science/pith/BLISAKK7DGXSIYOEDYFD7VDSMP/action/citation_signature","submit_replication":"https://pith.science/pith/BLISAKK7DGXSIYOEDYFD7VDSMP/action/replication_record"}},"created_at":"2026-07-05T07:37:11.402824+00:00","updated_at":"2026-07-05T07:37:11.402824+00:00"}