{"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/patchrefiner-leveraging-synthetic-data-for","title":"PatchRefiner: Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimation","arxiv_id":"2406.06679","date":"2024-06-10","proceeding":null,"authors":["Zhenyu Li","Shariq Farooq Bhat","Peter Wonka"],"abstract":"This paper introduces PatchRefiner, an advanced framework for metric single image depth estimation aimed at high-resolution real-domain inputs. While depth estimation is crucial for applications such as autonomous driving, 3D generative modeling, and 3D reconstruction, achieving accurate high-resolution depth in real-world scenarios is challenging due to the constraints of existing architectures and the scarcity of detailed real-world depth data. PatchRefiner adopts a tile-based methodology, reconceptualizing high-resolution depth estimation as a refinement process, which results in notable performance enhancements. Utilizing a pseudo-labeling strategy that leverages synthetic data, PatchRefiner incorporates a Detail and Scale Disentangling (DSD) loss to enhance detail capture while maintaining scale accuracy, thus facilitating the effective transfer of knowledge from synthetic to real-world data. Our extensive evaluations demonstrate PatchRefiner's superior performance, significantly outperforming existing benchmarks on the Unreal4KStereo dataset by 18.1% in terms of the root mean squared error (RMSE) and showing marked improvements in detail accuracy and consistent scale estimation on diverse real-world datasets like CityScape, ScanNet++, and ETH3D.","url_abs":"https://arxiv.org/abs/2406.06679v1","url_pdf":"https://arxiv.org/pdf/2406.06679v1.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":"patchrefiner-leveraging-synthetic-data-for","repo_url":"https://github.com/zhyever/PatchFusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"patchrefiner-leveraging-synthetic-data-for","repo_url":"https://github.com/zhyever/patchrefiner","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.06679","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}