Views
No views yet
We present DepthMaster, a tamed single-step diffusion model that customizes generative features in diffusion models to suit the discriminative depth estimation task. We introduce a Feature Alignment module to mitigate overfitting to texture and a Fourier Enhancement module to refine fine-grained details. DepthMaster exhibits state-of-the-art zero-shot performance and superior detail preservation ability, surpassing other diffusion-based methods across various datasets.
1@article{song2025depthmaster,
2 title={DepthMaster: Taming Diffusion Models for Monocular Depth Estimation},
3 author={Song, Ziyang and Wang, Zerong and Li, Bo and Zhang, Hao and Zhu, Ruijie and Liu, Li and Jiang, Peng-Tao and Zhang, Tianzhu},
4 journal={arXiv preprint arXiv:2501.02576},
5 year={2025}
6}