English

DepthMaster: Taming Diffusion Models for Monocular Depth Estimation

Computer Vision and Pattern Recognition 2026-04-24 v2

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.

Keywords

Cite

@article{arxiv.2501.02576,
  title  = {DepthMaster: Taming Diffusion Models for Monocular Depth Estimation},
  author = {Ziyang Song and Zerong Wang and Bo Li and Hao Zhang and Ruijie Zhu and Li Liu and Peng-Tao Jiang and Tianzhu Zhang},
  journal= {arXiv preprint arXiv:2501.02576},
  year   = {2026}
}

Comments

11 pages, 6 figures, 6 tables

R2 v1 2026-06-28T20:56:49.220Z