{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Y6FSZHOC5W4TDZROA35POMVLWL","short_pith_number":"pith:Y6FSZHOC","schema_version":"1.0","canonical_sha256":"c78b2c9dc2edb931e62e06faf732abb2e6f780d2c3954cc33456cc838a30465f","source":{"kind":"arxiv","id":"1911.10127","version":2},"attestation_state":"computed","paper":{"title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingyang Zhang, Lei Zhou, Long Quan, Shiwei Li, Tian Fang, Yao Yao, Yufan Ren, Zixin Luo","submitted_at":"2019-11-22T16:29:12Z","abstract_excerpt":"While deep learning has recently achieved great success on multi-view stereo (MVS), limited training data makes the trained model hard to be generalized to unseen scenarios. Compared with other computer vision tasks, it is rather difficult to collect a large-scale MVS dataset as it requires expensive active scanners and labor-intensive process to obtain ground truth 3D structures. In this paper, we introduce BlendedMVS, a novel large-scale dataset, to provide sufficient training ground truth for learning-based MVS. To create the dataset, we apply a 3D reconstruction pipeline to recover high-qu"},"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":"1911.10127","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-22T16:29:12Z","cross_cats_sorted":[],"title_canon_sha256":"5558c54ee7d6d605b8fc8261648532e767f40a5d5cfffb9c8a91cb440998f972","abstract_canon_sha256":"cf9e43e9bd43efc34fa3988ebf9393c2f9faf8e19b6e2fb4dceb918001bfbc4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:31.383581Z","signature_b64":"r8KggOUEuJNVURkucRyS6UO9f5UdMJnX047x7PPZzcMyR5x0x5qMdYF1azpSkJyp1a0JxRNSQ98ufOdcs21FCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c78b2c9dc2edb931e62e06faf732abb2e6f780d2c3954cc33456cc838a30465f","last_reissued_at":"2026-07-05T00:54:31.383124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:31.383124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingyang Zhang, Lei Zhou, Long Quan, Shiwei Li, Tian Fang, Yao Yao, Yufan Ren, Zixin Luo","submitted_at":"2019-11-22T16:29:12Z","abstract_excerpt":"While deep learning has recently achieved great success on multi-view stereo (MVS), limited training data makes the trained model hard to be generalized to unseen scenarios. Compared with other computer vision tasks, it is rather difficult to collect a large-scale MVS dataset as it requires expensive active scanners and labor-intensive process to obtain ground truth 3D structures. In this paper, we introduce BlendedMVS, a novel large-scale dataset, to provide sufficient training ground truth for learning-based MVS. To create the dataset, we apply a 3D reconstruction pipeline to recover high-qu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.10127","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/1911.10127/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":"1911.10127","created_at":"2026-07-05T00:54:31.383181+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.10127v2","created_at":"2026-07-05T00:54:31.383181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.10127","created_at":"2026-07-05T00:54:31.383181+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6FSZHOC5W4T","created_at":"2026-07-05T00:54:31.383181+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6FSZHOC5W4TDZRO","created_at":"2026-07-05T00:54:31.383181+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6FSZHOC","created_at":"2026-07-05T00:54:31.383181+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06560","citing_title":"Vision as Unified Multimodal Generation","ref_index":209,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y6FSZHOC5W4TDZROA35POMVLWL","json":"https://pith.science/pith/Y6FSZHOC5W4TDZROA35POMVLWL.json","graph_json":"https://pith.science/api/pith-number/Y6FSZHOC5W4TDZROA35POMVLWL/graph.json","events_json":"https://pith.science/api/pith-number/Y6FSZHOC5W4TDZROA35POMVLWL/events.json","paper":"https://pith.science/paper/Y6FSZHOC"},"agent_actions":{"view_html":"https://pith.science/pith/Y6FSZHOC5W4TDZROA35POMVLWL","download_json":"https://pith.science/pith/Y6FSZHOC5W4TDZROA35POMVLWL.json","view_paper":"https://pith.science/paper/Y6FSZHOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.10127&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6FSZHOC5W4TDZROA35POMVLWL/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6FSZHOC5W4TDZROA35POMVLWL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6FSZHOC5W4TDZROA35POMVLWL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6FSZHOC5W4TDZROA35POMVLWL/action/storage_attestation","attest_author":"https://pith.science/pith/Y6FSZHOC5W4TDZROA35POMVLWL/action/author_attestation","sign_citation":"https://pith.science/pith/Y6FSZHOC5W4TDZROA35POMVLWL/action/citation_signature","submit_replication":"https://pith.science/pith/Y6FSZHOC5W4TDZROA35POMVLWL/action/replication_record"}},"created_at":"2026-07-05T00:54:31.383181+00:00","updated_at":"2026-07-05T00:54:31.383181+00:00"}