{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:INU3AD2O4IJIX3SR7NC4JBGWDZ","short_pith_number":"pith:INU3AD2O","schema_version":"1.0","canonical_sha256":"4369b00f4ee2128bee51fb45c484d61e65a5c34dd1cd10bad0f32ee4c2fee68a","source":{"kind":"arxiv","id":"1905.02706","version":2},"attestation_state":"computed","paper":{"title":"Learning Unsupervised Multi-View Stereopsis via Robust Photometric Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Christoph Mertz, Martial Hebert, Shubham Agrawal, Shubham Tulsiani, Simon Lucey, Tejas Khot","submitted_at":"2019-05-07T17:45:22Z","abstract_excerpt":"We present a learning based approach for multi-view stereopsis (MVS). While current deep MVS methods achieve impressive results, they crucially rely on ground-truth 3D training data, and acquisition of such precise 3D geometry for supervision is a major hurdle. Our framework instead leverages photometric consistency between multiple views as supervisory signal for learning depth prediction in a wide baseline MVS setup. However, naively applying photo consistency constraints is undesirable due to occlusion and lighting changes across views. To overcome this, we propose a robust loss formulation"},"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":"1905.02706","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-07T17:45:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9d2eb658856a5480418bed9cf048c94bfc78df1f39c9c53030d013f88c8cce82","abstract_canon_sha256":"116ee1be8f9db9d0be08781da4cc325ada19408255034406c296bfa38ef8252c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:02.184442Z","signature_b64":"V0O+k8n9FVs978DU1mpgWRPw7B+AIV4Z78aOlHRTKeNM2DWZ0JCjS8YXwRpz42mtzywGu7bZzkeLuBQMZMbEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4369b00f4ee2128bee51fb45c484d61e65a5c34dd1cd10bad0f32ee4c2fee68a","last_reissued_at":"2026-05-17T23:44:02.183863Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:02.183863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Unsupervised Multi-View Stereopsis via Robust Photometric Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Christoph Mertz, Martial Hebert, Shubham Agrawal, Shubham Tulsiani, Simon Lucey, Tejas Khot","submitted_at":"2019-05-07T17:45:22Z","abstract_excerpt":"We present a learning based approach for multi-view stereopsis (MVS). While current deep MVS methods achieve impressive results, they crucially rely on ground-truth 3D training data, and acquisition of such precise 3D geometry for supervision is a major hurdle. Our framework instead leverages photometric consistency between multiple views as supervisory signal for learning depth prediction in a wide baseline MVS setup. However, naively applying photo consistency constraints is undesirable due to occlusion and lighting changes across views. To overcome this, we propose a robust loss formulation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02706","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":""},"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":"1905.02706","created_at":"2026-05-17T23:44:02.183966+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.02706v2","created_at":"2026-05-17T23:44:02.183966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02706","created_at":"2026-05-17T23:44:02.183966+00:00"},{"alias_kind":"pith_short_12","alias_value":"INU3AD2O4IJI","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"INU3AD2O4IJIX3SR","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"INU3AD2O","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2511.16428","citing_title":"CylinderDepth: Cylindrical Spatial Attention for Multi-View Consistent Self-Supervised Surround Depth Estimation","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INU3AD2O4IJIX3SR7NC4JBGWDZ","json":"https://pith.science/pith/INU3AD2O4IJIX3SR7NC4JBGWDZ.json","graph_json":"https://pith.science/api/pith-number/INU3AD2O4IJIX3SR7NC4JBGWDZ/graph.json","events_json":"https://pith.science/api/pith-number/INU3AD2O4IJIX3SR7NC4JBGWDZ/events.json","paper":"https://pith.science/paper/INU3AD2O"},"agent_actions":{"view_html":"https://pith.science/pith/INU3AD2O4IJIX3SR7NC4JBGWDZ","download_json":"https://pith.science/pith/INU3AD2O4IJIX3SR7NC4JBGWDZ.json","view_paper":"https://pith.science/paper/INU3AD2O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.02706&json=true","fetch_graph":"https://pith.science/api/pith-number/INU3AD2O4IJIX3SR7NC4JBGWDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/INU3AD2O4IJIX3SR7NC4JBGWDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INU3AD2O4IJIX3SR7NC4JBGWDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INU3AD2O4IJIX3SR7NC4JBGWDZ/action/storage_attestation","attest_author":"https://pith.science/pith/INU3AD2O4IJIX3SR7NC4JBGWDZ/action/author_attestation","sign_citation":"https://pith.science/pith/INU3AD2O4IJIX3SR7NC4JBGWDZ/action/citation_signature","submit_replication":"https://pith.science/pith/INU3AD2O4IJIX3SR7NC4JBGWDZ/action/replication_record"}},"created_at":"2026-05-17T23:44:02.183966+00:00","updated_at":"2026-05-17T23:44:02.183966+00:00"}