{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2XSBKUCL2A4DHBLK6RL5XFRVN6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"931d920492db2ceb4a27ef60a79cecca7c630a75ffa3434b62011323ef254ab2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T22:42:20Z","title_canon_sha256":"386f60539b565a925b362e7b02c790441f84bb996769af0d6bdfc7142633c60d"},"schema_version":"1.0","source":{"id":"2410.02073","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02073","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02073v2","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02073","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"pith_short_12","alias_value":"2XSBKUCL2A4D","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2XSBKUCL2A4DHBLK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2XSBKUCL","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:d524cbf74ea01f6e2d1cf73ec7e4dd133f4d6879923084667c108077c37ae00a","target":"graph","created_at":"2026-05-17T23:39:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We present a foundation model for zero-shot metric monocular depth estimation. Our model, Depth Pro, synthesizes high-resolution depth maps with unparalleled sharpness and high-frequency details. The predictions are metric, with absolute scale, without relying on the availability of metadata such as camera intrinsics. And the model is fast, producing a 2.25-megapixel depth map in 0.3 seconds on a standard GPU."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the training protocol combining real and synthetic datasets, together with the multi-scale vision transformer, achieves both high metric accuracy and fine boundary tracing in zero-shot settings without camera intrinsics."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Depth Pro is a fast foundation model for zero-shot metric monocular depth estimation that produces sharp high-resolution depth maps with absolute scale using a multi-scale vision transformer."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Depth Pro produces sharp, metric-scale depth maps from single images in 0.3 seconds without any camera metadata."}],"snapshot_sha256":"33fdaba0a1b0a6ef23567915298b3a0db14507139ad27ded34d4d371be6110a3"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4cc9cca9276f8fc2b11233da516301a0f5c9ce3c54c373a1221bbe6010c435d3"},"paper":{"abstract_excerpt":"We present a foundation model for zero-shot metric monocular depth estimation. Our model, Depth Pro, synthesizes high-resolution depth maps with unparalleled sharpness and high-frequency details. The predictions are metric, with absolute scale, without relying on the availability of metadata such as camera intrinsics. And the model is fast, producing a 2.25-megapixel depth map in 0.3 seconds on a standard GPU. These characteristics are enabled by a number of technical contributions, including an efficient multi-scale vision transformer for dense prediction, a training protocol that combines re","authors_text":"Aleksei Bochkovskii, Ama\\\"el Delaunoy, Hugo Germain, Marcel Santos, Stephan R. Richter, Vladlen Koltun, Yichao Zhou","cross_cats":["cs.LG"],"headline":"Depth Pro produces sharp, metric-scale depth maps from single images in 0.3 seconds without any camera metadata.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T22:42:20Z","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second"},"references":{"count":294,"internal_anchors":0,"resolved_work":294,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Defocus deblurring using dual-pixel data , author=. ECCV , year=","work_id":"276fd506-629e-4bb1-9f04-24451c334aef","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"RCA engineer , year=","work_id":"6ddc4f2f-28ac-4db4-a96d-9c30847ac9cb","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention , author=. 2022 , journal=","work_id":"421fc360-e547-40f6-afdd-a9c85f6761b6","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Unilmv2: Pseudo-masked language models for unified language model pre-training , author=. ICML , year=","work_id":"1a6b7713-24f1-43c5-a6d0-bb06b38e3ce8","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Hangbo Bao and Li Dong and Songhao Piao and Furu Wei , booktitle=","work_id":"4b07335e-a784-4b28-9333-b92fac5f3143","year":null}],"snapshot_sha256":"9efdf4becbb4f22097dd23350371fb98e22c0f162dd02a8c4bef9d60a70f2fe6"},"source":{"id":"2410.02073","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-14T20:40:37.299863Z","id":"8d9e293a-1ea3-44e4-97cf-b67cbd78cb18","model_set":{"reader":"grok-4.3"},"one_line_summary":"Depth Pro is a fast foundation model for zero-shot metric monocular depth estimation that produces sharp high-resolution depth maps with absolute scale using a multi-scale vision transformer.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Depth Pro produces sharp, metric-scale depth maps from single images in 0.3 seconds without any camera metadata.","strongest_claim":"We present a foundation model for zero-shot metric monocular depth estimation. Our model, Depth Pro, synthesizes high-resolution depth maps with unparalleled sharpness and high-frequency details. The predictions are metric, with absolute scale, without relying on the availability of metadata such as camera intrinsics. And the model is fast, producing a 2.25-megapixel depth map in 0.3 seconds on a standard GPU.","weakest_assumption":"That the training protocol combining real and synthetic datasets, together with the multi-scale vision transformer, achieves both high metric accuracy and fine boundary tracing in zero-shot settings without camera intrinsics."}},"verdict_id":"8d9e293a-1ea3-44e4-97cf-b67cbd78cb18"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1517f0c6367e33c22ebbcb5f9173bbffa5dd666a592cdf78b3012be30c4c0de8","target":"record","created_at":"2026-05-17T23:39:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"931d920492db2ceb4a27ef60a79cecca7c630a75ffa3434b62011323ef254ab2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T22:42:20Z","title_canon_sha256":"386f60539b565a925b362e7b02c790441f84bb996769af0d6bdfc7142633c60d"},"schema_version":"1.0","source":{"id":"2410.02073","kind":"arxiv","version":2}},"canonical_sha256":"d5e415504bd03833856af457db96356fb94c70ee224f334b887d6dd2ef091141","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5e415504bd03833856af457db96356fb94c70ee224f334b887d6dd2ef091141","first_computed_at":"2026-05-17T23:39:21.793339Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:21.793339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QO2aphEC8iEDS0LNu2vuTJTsUZ9Q1lCMyNKVzfcG5foaHUEqk95l0S2stWqUAG7a188KTxT3PmnW2yh1znpsCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:21.794110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02073","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1517f0c6367e33c22ebbcb5f9173bbffa5dd666a592cdf78b3012be30c4c0de8","sha256:d524cbf74ea01f6e2d1cf73ec7e4dd133f4d6879923084667c108077c37ae00a"],"state_sha256":"45216beed8cb601ea78ad04ea458b22020fe3624092fe19c731b5c77d93c64e1"}