{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BEAA3KLJSYQD427FK3TVVFBRJX","short_pith_number":"pith:BEAA3KLJ","schema_version":"1.0","canonical_sha256":"09000da96996203e6be556e75a94314dcfe651bf1357364fbffb411f5c0a3486","source":{"kind":"arxiv","id":"2108.08943","version":1},"attestation_state":"computed","paper":{"title":"PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuhang Zou, Derek Hoiem, Jae Yong Lee, Joseph DeGol","submitted_at":"2021-08-19T23:14:48Z","abstract_excerpt":"Recent learning-based multi-view stereo (MVS) methods show excellent performance with dense cameras and small depth ranges. However, non-learning based approaches still outperform for scenes with large depth ranges and sparser wide-baseline views, in part due to their PatchMatch optimization over pixelwise estimates of depth, normals, and visibility. In this paper, we propose an end-to-end trainable PatchMatch-based MVS approach that combines advantages of trainable costs and regularizations with pixelwise estimates. To overcome the challenge of the non-differentiable PatchMatch optimization t"},"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":"2108.08943","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-19T23:14:48Z","cross_cats_sorted":[],"title_canon_sha256":"f554962d4307b80fd9aa15aa2d1405d851d8f1ff213a26647b01c2b316aaf2ea","abstract_canon_sha256":"95a65f25d88c69d4ef8ba6c25975e0316fe1ae16d3338f99e925943115400d66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:32.143334Z","signature_b64":"72H7YAKQIWBTyqsTarOAjzOCl6SsyZWuxRV2dH+UZLKcX20PX5Oi7yiBrXeJEDxc/UnzjBi7fQdo2YYS964FDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09000da96996203e6be556e75a94314dcfe651bf1357364fbffb411f5c0a3486","last_reissued_at":"2026-07-05T03:07:32.142910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:32.142910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuhang Zou, Derek Hoiem, Jae Yong Lee, Joseph DeGol","submitted_at":"2021-08-19T23:14:48Z","abstract_excerpt":"Recent learning-based multi-view stereo (MVS) methods show excellent performance with dense cameras and small depth ranges. However, non-learning based approaches still outperform for scenes with large depth ranges and sparser wide-baseline views, in part due to their PatchMatch optimization over pixelwise estimates of depth, normals, and visibility. In this paper, we propose an end-to-end trainable PatchMatch-based MVS approach that combines advantages of trainable costs and regularizations with pixelwise estimates. To overcome the challenge of the non-differentiable PatchMatch optimization t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08943","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/2108.08943/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":"2108.08943","created_at":"2026-07-05T03:07:32.142965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.08943v1","created_at":"2026-07-05T03:07:32.142965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08943","created_at":"2026-07-05T03:07:32.142965+00:00"},{"alias_kind":"pith_short_12","alias_value":"BEAA3KLJSYQD","created_at":"2026-07-05T03:07:32.142965+00:00"},{"alias_kind":"pith_short_16","alias_value":"BEAA3KLJSYQD427F","created_at":"2026-07-05T03:07:32.142965+00:00"},{"alias_kind":"pith_short_8","alias_value":"BEAA3KLJ","created_at":"2026-07-05T03:07:32.142965+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/BEAA3KLJSYQD427FK3TVVFBRJX","json":"https://pith.science/pith/BEAA3KLJSYQD427FK3TVVFBRJX.json","graph_json":"https://pith.science/api/pith-number/BEAA3KLJSYQD427FK3TVVFBRJX/graph.json","events_json":"https://pith.science/api/pith-number/BEAA3KLJSYQD427FK3TVVFBRJX/events.json","paper":"https://pith.science/paper/BEAA3KLJ"},"agent_actions":{"view_html":"https://pith.science/pith/BEAA3KLJSYQD427FK3TVVFBRJX","download_json":"https://pith.science/pith/BEAA3KLJSYQD427FK3TVVFBRJX.json","view_paper":"https://pith.science/paper/BEAA3KLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.08943&json=true","fetch_graph":"https://pith.science/api/pith-number/BEAA3KLJSYQD427FK3TVVFBRJX/graph.json","fetch_events":"https://pith.science/api/pith-number/BEAA3KLJSYQD427FK3TVVFBRJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BEAA3KLJSYQD427FK3TVVFBRJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BEAA3KLJSYQD427FK3TVVFBRJX/action/storage_attestation","attest_author":"https://pith.science/pith/BEAA3KLJSYQD427FK3TVVFBRJX/action/author_attestation","sign_citation":"https://pith.science/pith/BEAA3KLJSYQD427FK3TVVFBRJX/action/citation_signature","submit_replication":"https://pith.science/pith/BEAA3KLJSYQD427FK3TVVFBRJX/action/replication_record"}},"created_at":"2026-07-05T03:07:32.142965+00:00","updated_at":"2026-07-05T03:07:32.142965+00:00"}