{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AB4UIFQU3VD7XRFYIYAHHSWS74","short_pith_number":"pith:AB4UIFQU","schema_version":"1.0","canonical_sha256":"0079441614dd47fbc4b8460073cad2ff368a3213f30c89ce68415bf494779d77","source":{"kind":"arxiv","id":"2312.02284","version":1},"attestation_state":"computed","paper":{"title":"PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peter Wonka, Shariq Farooq Bhat, Zhenyu Li","submitted_at":"2023-12-04T19:03:12Z","abstract_excerpt":"Single image depth estimation is a foundational task in computer vision and generative modeling. However, prevailing depth estimation models grapple with accommodating the increasing resolutions commonplace in today's consumer cameras and devices. Existing high-resolution strategies show promise, but they often face limitations, ranging from error propagation to the loss of high-frequency details. We present PatchFusion, a novel tile-based framework with three key components to improve the current state of the art: (1) A patch-wise fusion network that fuses a globally-consistent coarse predict"},"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":"2312.02284","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T19:03:12Z","cross_cats_sorted":[],"title_canon_sha256":"c0fe552e53d7f778fcb9028e7050f9e5ac64550c69c44c27fe6ac0c9ff5ed81f","abstract_canon_sha256":"16850e2160ef4574f10d75f04fd6ed732690c1ae27699dca41c1be1eda4391ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:15.478766Z","signature_b64":"DOh/NJIK0hy0Y3SCOh2D085Rz3QZP1vrD1Khef44g4BfZxbqZXlYIhSycouweqX+/1jyM3EE6U81uICjFVM9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0079441614dd47fbc4b8460073cad2ff368a3213f30c89ce68415bf494779d77","last_reissued_at":"2026-07-05T07:20:15.478204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:15.478204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peter Wonka, Shariq Farooq Bhat, Zhenyu Li","submitted_at":"2023-12-04T19:03:12Z","abstract_excerpt":"Single image depth estimation is a foundational task in computer vision and generative modeling. However, prevailing depth estimation models grapple with accommodating the increasing resolutions commonplace in today's consumer cameras and devices. Existing high-resolution strategies show promise, but they often face limitations, ranging from error propagation to the loss of high-frequency details. We present PatchFusion, a novel tile-based framework with three key components to improve the current state of the art: (1) A patch-wise fusion network that fuses a globally-consistent coarse predict"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02284","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/2312.02284/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":"2312.02284","created_at":"2026-07-05T07:20:15.478271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.02284v1","created_at":"2026-07-05T07:20:15.478271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02284","created_at":"2026-07-05T07:20:15.478271+00:00"},{"alias_kind":"pith_short_12","alias_value":"AB4UIFQU3VD7","created_at":"2026-07-05T07:20:15.478271+00:00"},{"alias_kind":"pith_short_16","alias_value":"AB4UIFQU3VD7XRFY","created_at":"2026-07-05T07:20:15.478271+00:00"},{"alias_kind":"pith_short_8","alias_value":"AB4UIFQU","created_at":"2026-07-05T07:20:15.478271+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15321","citing_title":"BenchDepth: Are We on the Right Way to Evaluate Depth Foundation Models?","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AB4UIFQU3VD7XRFYIYAHHSWS74","json":"https://pith.science/pith/AB4UIFQU3VD7XRFYIYAHHSWS74.json","graph_json":"https://pith.science/api/pith-number/AB4UIFQU3VD7XRFYIYAHHSWS74/graph.json","events_json":"https://pith.science/api/pith-number/AB4UIFQU3VD7XRFYIYAHHSWS74/events.json","paper":"https://pith.science/paper/AB4UIFQU"},"agent_actions":{"view_html":"https://pith.science/pith/AB4UIFQU3VD7XRFYIYAHHSWS74","download_json":"https://pith.science/pith/AB4UIFQU3VD7XRFYIYAHHSWS74.json","view_paper":"https://pith.science/paper/AB4UIFQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.02284&json=true","fetch_graph":"https://pith.science/api/pith-number/AB4UIFQU3VD7XRFYIYAHHSWS74/graph.json","fetch_events":"https://pith.science/api/pith-number/AB4UIFQU3VD7XRFYIYAHHSWS74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AB4UIFQU3VD7XRFYIYAHHSWS74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AB4UIFQU3VD7XRFYIYAHHSWS74/action/storage_attestation","attest_author":"https://pith.science/pith/AB4UIFQU3VD7XRFYIYAHHSWS74/action/author_attestation","sign_citation":"https://pith.science/pith/AB4UIFQU3VD7XRFYIYAHHSWS74/action/citation_signature","submit_replication":"https://pith.science/pith/AB4UIFQU3VD7XRFYIYAHHSWS74/action/replication_record"}},"created_at":"2026-07-05T07:20:15.478271+00:00","updated_at":"2026-07-05T07:20:15.478271+00:00"}