{"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/depthmaster-taming-diffusion-models-for","title":"DepthMaster: Taming Diffusion Models for Monocular Depth Estimation","arxiv_id":"2501.02576","date":"2025-01-05","proceeding":null,"authors":["Ziyang Song","Zerong Wang","Bo Li","Hao Zhang","Ruijie Zhu","Li Liu","Peng-Tao Jiang","Tianzhu Zhang"],"abstract":"Monocular depth estimation within the diffusion-denoising paradigm demonstrates impressive generalization ability but suffers from low inference speed. Recent methods adopt a single-step deterministic paradigm to improve inference efficiency while maintaining comparable performance. However, they overlook the gap between generative and discriminative features, leading to suboptimal results. In this work, we propose DepthMaster, a single-step diffusion model designed to adapt generative features for the discriminative depth estimation task. First, to mitigate overfitting to texture details introduced by generative features, we propose a Feature Alignment module, which incorporates high-quality semantic features to enhance the denoising network's representation capability. Second, to address the lack of fine-grained details in the single-step deterministic framework, we propose a Fourier Enhancement module to adaptively balance low-frequency structure and high-frequency details. We adopt a two-stage training strategy to fully leverage the potential of the two modules. In the first stage, we focus on learning the global scene structure with the Feature Alignment module, while in the second stage, we exploit the Fourier Enhancement module to improve the visual quality. Through these efforts, our model achieves state-of-the-art performance in terms of generalization and detail preservation, outperforming other diffusion-based methods across various datasets. Our project page can be found at https://indu1ge.github.io/DepthMaster_page.","url_abs":"https://arxiv.org/abs/2501.02576v1","url_pdf":"https://arxiv.org/pdf/2501.02576v1.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":"depthmaster-taming-diffusion-models-for","repo_url":"https://github.com/indu1ge/DepthMaster","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"}],"methods":[{"method_slug":"adopt","method_name":"ADOPT"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-eth3d","task":"Monocular Depth Estimation","dataset":"ETH3D","model":"DepthMaster","rank_in_archive_order":2,"of":10,"metrics":{"Delta < 1.25":"0.974","absolute relative error":"0.053"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split","model":"DepthMaster","rank_in_archive_order":48,"of":79,"metrics":{"Delta < 1.25":"0.937","absolute relative error":"0.082"},"uses_additional_data":true},{"leaderboard":"/sota/monocular-depth-estimation-on-nyu-depth-v2","task":"Monocular Depth Estimation","dataset":"NYU-Depth V2","model":"DepthMaster","rank_in_archive_order":7,"of":85,"metrics":{"Delta < 1.25":"0.972","absolute relative error":"0.050"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2501.02576","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}