{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/depth-pro-sharp-monocular-metric-depth-in","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","arxiv_id":"2410.02073","date":"2024-10-02","proceeding":null,"authors":["Aleksei Bochkovskii","Amaël Delaunoy","Hugo Germain","Marcel Santos","Yichao Zhou","Stephan R. Richter","Vladlen Koltun"],"abstract":"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 real and synthetic datasets to achieve high metric accuracy alongside fine boundary tracing, dedicated evaluation metrics for boundary accuracy in estimated depth maps, and state-of-the-art focal length estimation from a single image. Extensive experiments analyze specific design choices and demonstrate that Depth Pro outperforms prior work along multiple dimensions. We release code and weights at https://github.com/apple/ml-depth-pro","url_abs":"https://arxiv.org/abs/2410.02073v2","url_pdf":"https://arxiv.org/pdf/2410.02073v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"depth-pro-sharp-monocular-metric-depth-in","repo_url":"https://github.com/apple/ml-depth-pro","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2410.02073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02073"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/apple/ml-depth-pro","reach":null}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":6,"samples":[{"code_sha256_prefix":"797f67c4a606ecf8","entry":"FeatureFusionBlock2d","repo":"apple/ml-depth-pro","repo_kind":"official","path":"src/depth_pro/depth_pro.py","file_url":"https://github.com/apple/ml-depth-pro/blob/HEAD/src/depth_pro/depth_pro.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"797f67c4a606ecf8"}},{"code_sha256_prefix":"cb63d133b895bb33","entry":"MultiresConvDecoder","repo":"apple/ml-depth-pro","repo_kind":"official","path":"src/depth_pro/depth_pro.py","file_url":"https://github.com/apple/ml-depth-pro/blob/HEAD/src/depth_pro/depth_pro.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"cb63d133b895bb33"}},{"code_sha256_prefix":"4a40681365be9dab","entry":"ResidualBlock","repo":"apple/ml-depth-pro","repo_kind":"official","path":"src/depth_pro/depth_pro.py","file_url":"https://github.com/apple/ml-depth-pro/blob/HEAD/src/depth_pro/depth_pro.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4a40681365be9dab"}},{"code_sha256_prefix":"b95622fc8f1b40b5","entry":"DepthPro","repo":"apple/ml-depth-pro","repo_kind":"official","path":"src/depth_pro/depth_pro.py","file_url":"https://github.com/apple/ml-depth-pro/blob/HEAD/src/depth_pro/depth_pro.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b95622fc8f1b40b5"}},{"code_sha256_prefix":"dfbf916e11fefcb1","entry":"DepthProEncoder","repo":"apple/ml-depth-pro","repo_kind":"official","path":"src/depth_pro/depth_pro.py","file_url":"https://github.com/apple/ml-depth-pro/blob/HEAD/src/depth_pro/depth_pro.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"dfbf916e11fefcb1"}},{"code_sha256_prefix":"99044ba6da60afa4","entry":"FOVNetwork","repo":"apple/ml-depth-pro","repo_kind":"official","path":"src/depth_pro/depth_pro.py","file_url":"https://github.com/apple/ml-depth-pro/blob/HEAD/src/depth_pro/depth_pro.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"99044ba6da60afa4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}