{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YVNNK2JNFLR5LHIII6A7C2EZDI","short_pith_number":"pith:YVNNK2JN","schema_version":"1.0","canonical_sha256":"c55ad5692d2ae3d59d084781f168991a151151744a2777c879cb5d09b0432bf5","source":{"kind":"arxiv","id":"2203.01502","version":2},"attestation_state":"computed","paper":{"title":"NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ping Tan, Siyu Zhu, Weihao Yuan, Xiaodong Gu, Zuozhuo Dai","submitted_at":"2022-03-03T03:27:20Z","abstract_excerpt":"Estimating the accurate depth from a single image is challenging since it is inherently ambiguous and ill-posed. While recent works design increasingly complicated and powerful networks to directly regress the depth map, we take the path of CRFs optimization. Due to the expensive computation, CRFs are usually performed between neighborhoods rather than the whole graph. To leverage the potential of fully-connected CRFs, we split the input into windows and perform the FC-CRFs optimization within each window, which reduces the computation complexity and makes FC-CRFs feasible. To better capture 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":"2203.01502","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-03T03:27:20Z","cross_cats_sorted":[],"title_canon_sha256":"31ef364f9b8dd9ba2472f5840dcb6f7a6f002d2ece5e9152327fd3ac4b933522","abstract_canon_sha256":"5d7ba0409220d6471a435f73c821192f8f6261119b35f99dfd22633930e627b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:12.534104Z","signature_b64":"P4N3FPWUEAkRnWTy1VmVBLDLhhbPwdrzM2GkyesBptIK8ZX993lYiVDCsi/tX8oFrmogSsOmU6dqxoVixB9vCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c55ad5692d2ae3d59d084781f168991a151151744a2777c879cb5d09b0432bf5","last_reissued_at":"2026-07-05T04:29:12.533343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:12.533343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ping Tan, Siyu Zhu, Weihao Yuan, Xiaodong Gu, Zuozhuo Dai","submitted_at":"2022-03-03T03:27:20Z","abstract_excerpt":"Estimating the accurate depth from a single image is challenging since it is inherently ambiguous and ill-posed. While recent works design increasingly complicated and powerful networks to directly regress the depth map, we take the path of CRFs optimization. Due to the expensive computation, CRFs are usually performed between neighborhoods rather than the whole graph. To leverage the potential of fully-connected CRFs, we split the input into windows and perform the FC-CRFs optimization within each window, which reduces the computation complexity and makes FC-CRFs feasible. To better capture t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01502","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/2203.01502/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":"2203.01502","created_at":"2026-07-05T04:29:12.533432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.01502v2","created_at":"2026-07-05T04:29:12.533432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01502","created_at":"2026-07-05T04:29:12.533432+00:00"},{"alias_kind":"pith_short_12","alias_value":"YVNNK2JNFLR5","created_at":"2026-07-05T04:29:12.533432+00:00"},{"alias_kind":"pith_short_16","alias_value":"YVNNK2JNFLR5LHII","created_at":"2026-07-05T04:29:12.533432+00:00"},{"alias_kind":"pith_short_8","alias_value":"YVNNK2JN","created_at":"2026-07-05T04:29:12.533432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.02576","citing_title":"DepthMaster: Taming Diffusion Models for Monocular Depth Estimation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01765","citing_title":"Efficient Test-Time Optimization for Depth Completion via Low-Rank Decoder Adaptation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2302.12288","citing_title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2406.09414","citing_title":"Depth Anything V2","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07665","citing_title":"Adaptive Depth-converted-Scale Convolution for Self-supervised Monocular Depth Estimation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07664","citing_title":"Monocular Depth Estimation From the Perspective of Feature Restoration: A Diffusion Enhanced Depth Restoration Approach","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YVNNK2JNFLR5LHIII6A7C2EZDI","json":"https://pith.science/pith/YVNNK2JNFLR5LHIII6A7C2EZDI.json","graph_json":"https://pith.science/api/pith-number/YVNNK2JNFLR5LHIII6A7C2EZDI/graph.json","events_json":"https://pith.science/api/pith-number/YVNNK2JNFLR5LHIII6A7C2EZDI/events.json","paper":"https://pith.science/paper/YVNNK2JN"},"agent_actions":{"view_html":"https://pith.science/pith/YVNNK2JNFLR5LHIII6A7C2EZDI","download_json":"https://pith.science/pith/YVNNK2JNFLR5LHIII6A7C2EZDI.json","view_paper":"https://pith.science/paper/YVNNK2JN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.01502&json=true","fetch_graph":"https://pith.science/api/pith-number/YVNNK2JNFLR5LHIII6A7C2EZDI/graph.json","fetch_events":"https://pith.science/api/pith-number/YVNNK2JNFLR5LHIII6A7C2EZDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YVNNK2JNFLR5LHIII6A7C2EZDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YVNNK2JNFLR5LHIII6A7C2EZDI/action/storage_attestation","attest_author":"https://pith.science/pith/YVNNK2JNFLR5LHIII6A7C2EZDI/action/author_attestation","sign_citation":"https://pith.science/pith/YVNNK2JNFLR5LHIII6A7C2EZDI/action/citation_signature","submit_replication":"https://pith.science/pith/YVNNK2JNFLR5LHIII6A7C2EZDI/action/replication_record"}},"created_at":"2026-07-05T04:29:12.533432+00:00","updated_at":"2026-07-05T04:29:12.533432+00:00"}