{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NF2YCBN6EMOJEPEDHUPOWLIQEA","short_pith_number":"pith:NF2YCBN6","schema_version":"1.0","canonical_sha256":"69758105be231c923c833d1eeb2d102037bc45d51ebf6cb5d6519c1b8af465cf","source":{"kind":"arxiv","id":"2412.09072","version":1},"attestation_state":"computed","paper":{"title":"Cross-View Completion Models are Zero-shot Correspondence Estimators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Honggyu An, Jaewoo Jung, Jinhyeon Kim, Jisang Han, Seonghoon Park, Seungryong Kim, Sunghwan Hong","submitted_at":"2024-12-12T08:58:20Z","abstract_excerpt":"In this work, we explore new perspectives on cross-view completion learning by drawing an analogy to self-supervised correspondence learning. Through our analysis, we demonstrate that the cross-attention map within cross-view completion models captures correspondence more effectively than other correlations derived from encoder or decoder features. We verify the effectiveness of the cross-attention map by evaluating on both zero-shot matching and learning-based geometric matching and multi-frame depth estimation. Project page is available at https://cvlab-kaist.github.io/ZeroCo/."},"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":"2412.09072","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T08:58:20Z","cross_cats_sorted":[],"title_canon_sha256":"4a840878d3a622fb66aa66ca2f5acc8c5c42164f352795ded405b76944512e8e","abstract_canon_sha256":"adcf4c4663f7919fd628ea0599effd3bc6ce63ba9e73b935314f795e3e96657c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:19.192881Z","signature_b64":"jbdMB4xpXRn399vz+jaLMtBOk+xH5eF9YbYQTYSJksJHDPB2BNLQDhcbrD1qzRRSsmGVa4c/URBw5THnq4WUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69758105be231c923c833d1eeb2d102037bc45d51ebf6cb5d6519c1b8af465cf","last_reissued_at":"2026-07-05T09:48:19.192495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:19.192495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-View Completion Models are Zero-shot Correspondence Estimators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Honggyu An, Jaewoo Jung, Jinhyeon Kim, Jisang Han, Seonghoon Park, Seungryong Kim, Sunghwan Hong","submitted_at":"2024-12-12T08:58:20Z","abstract_excerpt":"In this work, we explore new perspectives on cross-view completion learning by drawing an analogy to self-supervised correspondence learning. Through our analysis, we demonstrate that the cross-attention map within cross-view completion models captures correspondence more effectively than other correlations derived from encoder or decoder features. We verify the effectiveness of the cross-attention map by evaluating on both zero-shot matching and learning-based geometric matching and multi-frame depth estimation. Project page is available at https://cvlab-kaist.github.io/ZeroCo/."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09072","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/2412.09072/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":"2412.09072","created_at":"2026-07-05T09:48:19.192548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09072v1","created_at":"2026-07-05T09:48:19.192548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09072","created_at":"2026-07-05T09:48:19.192548+00:00"},{"alias_kind":"pith_short_12","alias_value":"NF2YCBN6EMOJ","created_at":"2026-07-05T09:48:19.192548+00:00"},{"alias_kind":"pith_short_16","alias_value":"NF2YCBN6EMOJEPED","created_at":"2026-07-05T09:48:19.192548+00:00"},{"alias_kind":"pith_short_8","alias_value":"NF2YCBN6","created_at":"2026-07-05T09:48:19.192548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26230","citing_title":"Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22190","citing_title":"No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2509.26645","citing_title":"TTT3R: 3D Reconstruction as Test-Time Training","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NF2YCBN6EMOJEPEDHUPOWLIQEA","json":"https://pith.science/pith/NF2YCBN6EMOJEPEDHUPOWLIQEA.json","graph_json":"https://pith.science/api/pith-number/NF2YCBN6EMOJEPEDHUPOWLIQEA/graph.json","events_json":"https://pith.science/api/pith-number/NF2YCBN6EMOJEPEDHUPOWLIQEA/events.json","paper":"https://pith.science/paper/NF2YCBN6"},"agent_actions":{"view_html":"https://pith.science/pith/NF2YCBN6EMOJEPEDHUPOWLIQEA","download_json":"https://pith.science/pith/NF2YCBN6EMOJEPEDHUPOWLIQEA.json","view_paper":"https://pith.science/paper/NF2YCBN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09072&json=true","fetch_graph":"https://pith.science/api/pith-number/NF2YCBN6EMOJEPEDHUPOWLIQEA/graph.json","fetch_events":"https://pith.science/api/pith-number/NF2YCBN6EMOJEPEDHUPOWLIQEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NF2YCBN6EMOJEPEDHUPOWLIQEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NF2YCBN6EMOJEPEDHUPOWLIQEA/action/storage_attestation","attest_author":"https://pith.science/pith/NF2YCBN6EMOJEPEDHUPOWLIQEA/action/author_attestation","sign_citation":"https://pith.science/pith/NF2YCBN6EMOJEPEDHUPOWLIQEA/action/citation_signature","submit_replication":"https://pith.science/pith/NF2YCBN6EMOJEPEDHUPOWLIQEA/action/replication_record"}},"created_at":"2026-07-05T09:48:19.192548+00:00","updated_at":"2026-07-05T09:48:19.192548+00:00"}