{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:V6WJQECWORASIHYVC4TBWTXWHL","short_pith_number":"pith:V6WJQECW","schema_version":"1.0","canonical_sha256":"afac9810567441241f1517261b4ef63ae68ee7bca2682f03cb2f3bc71afbe542","source":{"kind":"arxiv","id":"1902.10556","version":1},"attestation_state":"computed","paper":{"title":"Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Long Quan, Shiwei Li, Tian Fang, Tianwei Shen, Yao Yao, Zixin Luo","submitted_at":"2019-02-27T14:34:50Z","abstract_excerpt":"Deep learning has recently demonstrated its excellent performance for multi-view stereo (MVS). However, one major limitation of current learned MVS approaches is the scalability: the memory-consuming cost volume regularization makes the learned MVS hard to be applied to high-resolution scenes. In this paper, we introduce a scalable multi-view stereo framework based on the recurrent neural network. Instead of regularizing the entire 3D cost volume in one go, the proposed Recurrent Multi-view Stereo Network (R-MVSNet) sequentially regularizes the 2D cost maps along the depth direction via the ga"},"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":"1902.10556","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-27T14:34:50Z","cross_cats_sorted":[],"title_canon_sha256":"df699358daf102c92699c8160a015e63c6eee2044aaaaa460e309c686d551f33","abstract_canon_sha256":"9b480d8f76a80e7eb4f88589ae184ccf8158580157d408e1ecf8fc6eb479caa2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:30.532558Z","signature_b64":"TW2Ks6aLvr/Yk6S7Guq/9PSyjLLtHW2gsT5GKodKVHRVPHmePfU4U4T2zTR0tV4gt0jPNp0+fTCq2aBymNX5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afac9810567441241f1517261b4ef63ae68ee7bca2682f03cb2f3bc71afbe542","last_reissued_at":"2026-05-17T23:52:30.532033Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:30.532033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Long Quan, Shiwei Li, Tian Fang, Tianwei Shen, Yao Yao, Zixin Luo","submitted_at":"2019-02-27T14:34:50Z","abstract_excerpt":"Deep learning has recently demonstrated its excellent performance for multi-view stereo (MVS). However, one major limitation of current learned MVS approaches is the scalability: the memory-consuming cost volume regularization makes the learned MVS hard to be applied to high-resolution scenes. In this paper, we introduce a scalable multi-view stereo framework based on the recurrent neural network. Instead of regularizing the entire 3D cost volume in one go, the proposed Recurrent Multi-view Stereo Network (R-MVSNet) sequentially regularizes the 2D cost maps along the depth direction via the ga"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10556","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":""},"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":"1902.10556","created_at":"2026-05-17T23:52:30.532122+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.10556v1","created_at":"2026-05-17T23:52:30.532122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10556","created_at":"2026-05-17T23:52:30.532122+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6WJQECWORAS","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6WJQECWORASIHYV","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6WJQECW","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.18052","citing_title":"Efficient 3D Content Reconstruction and Generation","ref_index":297,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V6WJQECWORASIHYVC4TBWTXWHL","json":"https://pith.science/pith/V6WJQECWORASIHYVC4TBWTXWHL.json","graph_json":"https://pith.science/api/pith-number/V6WJQECWORASIHYVC4TBWTXWHL/graph.json","events_json":"https://pith.science/api/pith-number/V6WJQECWORASIHYVC4TBWTXWHL/events.json","paper":"https://pith.science/paper/V6WJQECW"},"agent_actions":{"view_html":"https://pith.science/pith/V6WJQECWORASIHYVC4TBWTXWHL","download_json":"https://pith.science/pith/V6WJQECWORASIHYVC4TBWTXWHL.json","view_paper":"https://pith.science/paper/V6WJQECW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.10556&json=true","fetch_graph":"https://pith.science/api/pith-number/V6WJQECWORASIHYVC4TBWTXWHL/graph.json","fetch_events":"https://pith.science/api/pith-number/V6WJQECWORASIHYVC4TBWTXWHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6WJQECWORASIHYVC4TBWTXWHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6WJQECWORASIHYVC4TBWTXWHL/action/storage_attestation","attest_author":"https://pith.science/pith/V6WJQECWORASIHYVC4TBWTXWHL/action/author_attestation","sign_citation":"https://pith.science/pith/V6WJQECWORASIHYVC4TBWTXWHL/action/citation_signature","submit_replication":"https://pith.science/pith/V6WJQECWORASIHYVC4TBWTXWHL/action/replication_record"}},"created_at":"2026-05-17T23:52:30.532122+00:00","updated_at":"2026-05-17T23:52:30.532122+00:00"}