{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2XSBKUCL2A4DHBLK6RL5XFRVN6","short_pith_number":"pith:2XSBKUCL","schema_version":"1.0","canonical_sha256":"d5e415504bd03833856af457db96356fb94c70ee224f334b887d6dd2ef091141","source":{"kind":"arxiv","id":"2410.02073","version":2},"attestation_state":"computed","paper":{"title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Depth Pro produces sharp, metric-scale depth maps from single images in 0.3 seconds without any camera metadata.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aleksei Bochkovskii, Ama\\\"el Delaunoy, Hugo Germain, Marcel Santos, Stephan R. Richter, Vladlen Koltun, Yichao Zhou","submitted_at":"2024-10-02T22:42:20Z","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"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2410.02073","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T22:42:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"386f60539b565a925b362e7b02c790441f84bb996769af0d6bdfc7142633c60d","abstract_canon_sha256":"931d920492db2ceb4a27ef60a79cecca7c630a75ffa3434b62011323ef254ab2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:21.794110Z","signature_b64":"QO2aphEC8iEDS0LNu2vuTJTsUZ9Q1lCMyNKVzfcG5foaHUEqk95l0S2stWqUAG7a188KTxT3PmnW2yh1znpsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5e415504bd03833856af457db96356fb94c70ee224f334b887d6dd2ef091141","last_reissued_at":"2026-05-17T23:39:21.793339Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:21.793339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Depth Pro produces sharp, metric-scale depth maps from single images in 0.3 seconds without any camera metadata.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aleksei Bochkovskii, Ama\\\"el Delaunoy, Hugo Germain, Marcel Santos, Stephan R. Richter, Vladlen Koltun, Yichao Zhou","submitted_at":"2024-10-02T22:42:20Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Depth Pro produces sharp, metric-scale depth maps from single images in 0.3 seconds without any camera metadata.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"33fdaba0a1b0a6ef23567915298b3a0db14507139ad27ded34d4d371be6110a3"},"source":{"id":"2410.02073","kind":"arxiv","version":2},"verdict":{"id":"8d9e293a-1ea3-44e4-97cf-b67cbd78cb18","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:40:37.299863Z","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.","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","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.","pith_extraction_headline":"Depth Pro produces sharp, metric-scale depth maps from single images in 0.3 seconds without any camera metadata."},"references":{"count":294,"sample":[{"doi":"","year":null,"title":"Defocus deblurring using dual-pixel data , author=. ECCV , year=","work_id":"276fd506-629e-4bb1-9f04-24451c334aef","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"RCA engineer , year=","work_id":"6ddc4f2f-28ac-4db4-a96d-9c30847ac9cb","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention , author=. 2022 , journal=","work_id":"421fc360-e547-40f6-afdd-a9c85f6761b6","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Unilmv2: Pseudo-masked language models for unified language model pre-training , author=. ICML , year=","work_id":"1a6b7713-24f1-43c5-a6d0-bb06b38e3ce8","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Hangbo Bao and Li Dong and Songhao Piao and Furu Wei , booktitle=","work_id":"4b07335e-a784-4b28-9333-b92fac5f3143","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":294,"snapshot_sha256":"9efdf4becbb4f22097dd23350371fb98e22c0f162dd02a8c4bef9d60a70f2fe6","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4cc9cca9276f8fc2b11233da516301a0f5c9ce3c54c373a1221bbe6010c435d3"},"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":"2410.02073","created_at":"2026-05-17T23:39:21.793476+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02073v2","created_at":"2026-05-17T23:39:21.793476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02073","created_at":"2026-05-17T23:39:21.793476+00:00"},{"alias_kind":"pith_short_12","alias_value":"2XSBKUCL2A4D","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"2XSBKUCL2A4DHBLK","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"2XSBKUCL","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":42,"internal_anchor_count":42,"sample":[{"citing_arxiv_id":"2411.14295","citing_title":"DissolveStereo: Coarse Depth Injection for Zero-Shot Stereo Video Generation","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2501.02576","citing_title":"DepthMaster: Taming Diffusion Models for Monocular Depth Estimation","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2503.12844","citing_title":"GuideDog: A Real-World Egocentric Multimodal Dataset for Blind and Low-Vision Accessibility-Aware Guidance","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22629","citing_title":"H-Flow: Self-supervised Human Scene Flow via Physics-inspired Joint Multi-modal Learning","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2508.13977","citing_title":"ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Driving","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2601.00678","citing_title":"Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15876","citing_title":"Unlocking Dense Metric Depth Estimation in VLMs","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20461","citing_title":"Understanding Model Behavior in Monocular Polyp Sizing","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15876","citing_title":"Unlocking Dense Metric Depth Estimation in VLMs","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18599","citing_title":"Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19797","citing_title":"Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth","ref_index":76,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16807","citing_title":"DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusion","ref_index":95,"is_internal_anchor":true},{"citing_arxiv_id":"2507.00209","citing_title":"SurgiSR4K: A High-Resolution Endoscopic Video Dataset for Robotic-Assisted Minimally Invasive Procedures","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2510.08278","citing_title":"A Multimodal Depth-Aware Method For Embodied Reference Understanding","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2510.17568","citing_title":"PAGE-4D: VGGT-4D Perception via Disentangled Pose and Geometry Estimation","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2502.20110","citing_title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2601.00678","citing_title":"Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2508.10934","citing_title":"ViPE: Video Pose Engine for 3D Geometric Perception","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2603.01765","citing_title":"Efficient Test-Time Optimization for Depth Completion via Low-Rank Decoder Adaptation","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2603.10584","citing_title":"Need for Speed: Zero-Shot Depth Completion with Single-Step Diffusion","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20329","citing_title":"Image Generators are Generalist Vision Learners","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12608","citing_title":"A Data Efficiency Study of Synthetic Fog for Object Detection Using the Clear2Fog Pipeline","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13140","citing_title":"Multi-Modal Guided Multi-Source Domain Adaptation for Object Detection","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02867","citing_title":"HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraits","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03841","citing_title":"Training a Student Expert via Semi-Supervised Foundation Model Distillation","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2XSBKUCL2A4DHBLK6RL5XFRVN6","json":"https://pith.science/pith/2XSBKUCL2A4DHBLK6RL5XFRVN6.json","graph_json":"https://pith.science/api/pith-number/2XSBKUCL2A4DHBLK6RL5XFRVN6/graph.json","events_json":"https://pith.science/api/pith-number/2XSBKUCL2A4DHBLK6RL5XFRVN6/events.json","paper":"https://pith.science/paper/2XSBKUCL"},"agent_actions":{"view_html":"https://pith.science/pith/2XSBKUCL2A4DHBLK6RL5XFRVN6","download_json":"https://pith.science/pith/2XSBKUCL2A4DHBLK6RL5XFRVN6.json","view_paper":"https://pith.science/paper/2XSBKUCL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02073&json=true","fetch_graph":"https://pith.science/api/pith-number/2XSBKUCL2A4DHBLK6RL5XFRVN6/graph.json","fetch_events":"https://pith.science/api/pith-number/2XSBKUCL2A4DHBLK6RL5XFRVN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2XSBKUCL2A4DHBLK6RL5XFRVN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2XSBKUCL2A4DHBLK6RL5XFRVN6/action/storage_attestation","attest_author":"https://pith.science/pith/2XSBKUCL2A4DHBLK6RL5XFRVN6/action/author_attestation","sign_citation":"https://pith.science/pith/2XSBKUCL2A4DHBLK6RL5XFRVN6/action/citation_signature","submit_replication":"https://pith.science/pith/2XSBKUCL2A4DHBLK6RL5XFRVN6/action/replication_record"}},"created_at":"2026-05-17T23:39:21.793476+00:00","updated_at":"2026-05-17T23:39:21.793476+00:00"}