{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZVKH5C5NXKEPS4GWP2QB3CYAED","short_pith_number":"pith:ZVKH5C5N","schema_version":"1.0","canonical_sha256":"cd547e8badba88f970d67ea01d8b0020e82d3038af44a9b45df2b80f3781785d","source":{"kind":"arxiv","id":"2312.13252","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Charles Herrmann, David J. Fleet, Deqing Sun, Junhwa Hur, Saurabh Saxena","submitted_at":"2023-12-20T18:27:47Z","abstract_excerpt":"While methods for monocular depth estimation have made significant strides on standard benchmarks, zero-shot metric depth estimation remains unsolved. Challenges include the joint modeling of indoor and outdoor scenes, which often exhibit significantly different distributions of RGB and depth, and the depth-scale ambiguity due to unknown camera intrinsics. Recent work has proposed specialized multi-head architectures for jointly modeling indoor and outdoor scenes. In contrast, we advocate a generic, task-agnostic diffusion model, with several advancements such as log-scale depth parameterizati"},"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":"2312.13252","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-20T18:27:47Z","cross_cats_sorted":[],"title_canon_sha256":"33d276f7ccd837df4d0297e2250c1c6ac623613dd903440583f8a89d04ebd488","abstract_canon_sha256":"b10fd828ac6fbbb137d74cf362b16b69e278343744f02ae9f591d1382f3dd2d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:33.896343Z","signature_b64":"xTjJqvBEP/TovEaYn8hrGoI1i0+lhuACATaYilO9tbKAdbL1y1cK3F5ZKgSbUC2l4mxWBrFvHI6NUS/JWZSVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd547e8badba88f970d67ea01d8b0020e82d3038af44a9b45df2b80f3781785d","last_reissued_at":"2026-07-05T07:26:33.895816Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:33.895816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Charles Herrmann, David J. Fleet, Deqing Sun, Junhwa Hur, Saurabh Saxena","submitted_at":"2023-12-20T18:27:47Z","abstract_excerpt":"While methods for monocular depth estimation have made significant strides on standard benchmarks, zero-shot metric depth estimation remains unsolved. Challenges include the joint modeling of indoor and outdoor scenes, which often exhibit significantly different distributions of RGB and depth, and the depth-scale ambiguity due to unknown camera intrinsics. Recent work has proposed specialized multi-head architectures for jointly modeling indoor and outdoor scenes. In contrast, we advocate a generic, task-agnostic diffusion model, with several advancements such as log-scale depth parameterizati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13252","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/2312.13252/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":"2312.13252","created_at":"2026-07-05T07:26:33.895878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.13252v1","created_at":"2026-07-05T07:26:33.895878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13252","created_at":"2026-07-05T07:26:33.895878+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZVKH5C5NXKEP","created_at":"2026-07-05T07:26:33.895878+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZVKH5C5NXKEPS4GW","created_at":"2026-07-05T07:26:33.895878+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZVKH5C5N","created_at":"2026-07-05T07:26:33.895878+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.03825","citing_title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZVKH5C5NXKEPS4GWP2QB3CYAED","json":"https://pith.science/pith/ZVKH5C5NXKEPS4GWP2QB3CYAED.json","graph_json":"https://pith.science/api/pith-number/ZVKH5C5NXKEPS4GWP2QB3CYAED/graph.json","events_json":"https://pith.science/api/pith-number/ZVKH5C5NXKEPS4GWP2QB3CYAED/events.json","paper":"https://pith.science/paper/ZVKH5C5N"},"agent_actions":{"view_html":"https://pith.science/pith/ZVKH5C5NXKEPS4GWP2QB3CYAED","download_json":"https://pith.science/pith/ZVKH5C5NXKEPS4GWP2QB3CYAED.json","view_paper":"https://pith.science/paper/ZVKH5C5N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.13252&json=true","fetch_graph":"https://pith.science/api/pith-number/ZVKH5C5NXKEPS4GWP2QB3CYAED/graph.json","fetch_events":"https://pith.science/api/pith-number/ZVKH5C5NXKEPS4GWP2QB3CYAED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZVKH5C5NXKEPS4GWP2QB3CYAED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZVKH5C5NXKEPS4GWP2QB3CYAED/action/storage_attestation","attest_author":"https://pith.science/pith/ZVKH5C5NXKEPS4GWP2QB3CYAED/action/author_attestation","sign_citation":"https://pith.science/pith/ZVKH5C5NXKEPS4GWP2QB3CYAED/action/citation_signature","submit_replication":"https://pith.science/pith/ZVKH5C5NXKEPS4GWP2QB3CYAED/action/replication_record"}},"created_at":"2026-07-05T07:26:33.895878+00:00","updated_at":"2026-07-05T07:26:33.895878+00:00"}