{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NDWVCOCMLIQEAKAST6LC53TVPS","short_pith_number":"pith:NDWVCOCM","schema_version":"1.0","canonical_sha256":"68ed51384c5a204028129f962eee757c9f7a3d948938c20c8147a923ace0e0bd","source":{"kind":"arxiv","id":"2503.08219","version":1},"attestation_state":"computed","paper":{"title":"CL-MVSNet: Unsupervised Multi-view Stereo with Dual-level Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Feng Gao, Jianbo Jiao, Kaiqiang Xiong, Ronggang Wang, Rui Peng, Tianxing Feng, Zhe Zhang","submitted_at":"2025-03-11T09:39:06Z","abstract_excerpt":"Unsupervised Multi-View Stereo (MVS) methods have achieved promising progress recently. However, previous methods primarily depend on the photometric consistency assumption, which may suffer from two limitations: indistinguishable regions and view-dependent effects, e.g., low-textured areas and reflections. To address these issues, in this paper, we propose a new dual-level contrastive learning approach, named CL-MVSNet. Specifically, our model integrates two contrastive branches into an unsupervised MVS framework to construct additional supervisory signals. On the one hand, we present an imag"},"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":"2503.08219","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T09:39:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9e837fe800857a5d212f67e9538c4055ba85417eb321aab77b6740b9a9e8576c","abstract_canon_sha256":"e27f7a4b4de55e1a1aa83febe77b6304e9e3e4661a352160c9bea6a22c54035d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:54.110177Z","signature_b64":"QtHpfNc3H9eBMMwmCtq1aa+wWB5PVBwHIVJVITLQe0Ma1UhDrqr+Ay4GwC+kAbZrCwtGQCcop6iNzh4pz0/dBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68ed51384c5a204028129f962eee757c9f7a3d948938c20c8147a923ace0e0bd","last_reissued_at":"2026-07-05T10:28:54.109728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:54.109728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CL-MVSNet: Unsupervised Multi-view Stereo with Dual-level Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Feng Gao, Jianbo Jiao, Kaiqiang Xiong, Ronggang Wang, Rui Peng, Tianxing Feng, Zhe Zhang","submitted_at":"2025-03-11T09:39:06Z","abstract_excerpt":"Unsupervised Multi-View Stereo (MVS) methods have achieved promising progress recently. However, previous methods primarily depend on the photometric consistency assumption, which may suffer from two limitations: indistinguishable regions and view-dependent effects, e.g., low-textured areas and reflections. To address these issues, in this paper, we propose a new dual-level contrastive learning approach, named CL-MVSNet. Specifically, our model integrates two contrastive branches into an unsupervised MVS framework to construct additional supervisory signals. On the one hand, we present an imag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08219","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/2503.08219/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":"2503.08219","created_at":"2026-07-05T10:28:54.109800+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.08219v1","created_at":"2026-07-05T10:28:54.109800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08219","created_at":"2026-07-05T10:28:54.109800+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDWVCOCMLIQE","created_at":"2026-07-05T10:28:54.109800+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDWVCOCMLIQEAKAS","created_at":"2026-07-05T10:28:54.109800+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDWVCOCM","created_at":"2026-07-05T10:28:54.109800+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/NDWVCOCMLIQEAKAST6LC53TVPS","json":"https://pith.science/pith/NDWVCOCMLIQEAKAST6LC53TVPS.json","graph_json":"https://pith.science/api/pith-number/NDWVCOCMLIQEAKAST6LC53TVPS/graph.json","events_json":"https://pith.science/api/pith-number/NDWVCOCMLIQEAKAST6LC53TVPS/events.json","paper":"https://pith.science/paper/NDWVCOCM"},"agent_actions":{"view_html":"https://pith.science/pith/NDWVCOCMLIQEAKAST6LC53TVPS","download_json":"https://pith.science/pith/NDWVCOCMLIQEAKAST6LC53TVPS.json","view_paper":"https://pith.science/paper/NDWVCOCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.08219&json=true","fetch_graph":"https://pith.science/api/pith-number/NDWVCOCMLIQEAKAST6LC53TVPS/graph.json","fetch_events":"https://pith.science/api/pith-number/NDWVCOCMLIQEAKAST6LC53TVPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDWVCOCMLIQEAKAST6LC53TVPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDWVCOCMLIQEAKAST6LC53TVPS/action/storage_attestation","attest_author":"https://pith.science/pith/NDWVCOCMLIQEAKAST6LC53TVPS/action/author_attestation","sign_citation":"https://pith.science/pith/NDWVCOCMLIQEAKAST6LC53TVPS/action/citation_signature","submit_replication":"https://pith.science/pith/NDWVCOCMLIQEAKAST6LC53TVPS/action/replication_record"}},"created_at":"2026-07-05T10:28:54.109800+00:00","updated_at":"2026-07-05T10:28:54.109800+00:00"}