{"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/a-two-streamed-network-for-estimating-fine","title":"A Two-Streamed Network for Estimating Fine-Scaled Depth Maps from Single RGB Images","arxiv_id":"1607.00730","date":"2016-07-04","proceeding":"ICCV 2017 10","authors":["Jun Li","Reinhard Klein","Angela Yao"],"abstract":"Estimating depth from a single RGB image is an ill-posed and inherently\nambiguous problem. State-of-the-art deep learning methods can now estimate\naccurate 2D depth maps, but when the maps are projected into 3D, they lack\nlocal detail and are often highly distorted. We propose a fast-to-train\ntwo-streamed CNN that predicts depth and depth gradients, which are then fused\ntogether into an accurate and detailed depth map. We also define a novel set\nloss over multiple images; by regularizing the estimation between a common set\nof images, the network is less prone to over-fitting and achieves better\naccuracy than competing methods. Experiments on the NYU Depth v2 dataset shows\nthat our depth predictions are competitive with state-of-the-art and lead to\nfaithful 3D projections.","url_abs":"http://arxiv.org/abs/1607.00730v4","url_pdf":"http://arxiv.org/pdf/1607.00730v4.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":[],"tasks":[{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-nyu-depth-v2","task":"Monocular Depth Estimation","dataset":"NYU-Depth V2","model":"Li et al.","rank_in_archive_order":84,"of":85,"metrics":{"RMSE":"0.635"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}