Papers › DepthMaster: Taming Diffusion Models for Monocular Depth Estimation

DepthMaster: Taming Diffusion Models for Monocular Depth Estimation

5 Jan 2025arXiv:2501.02576archive 2025-07-28

Ziyang Song, Zerong Wang, Bo Li, Hao Zhang, Ruijie Zhu, Li Liu, Peng-Tao Jiang, Tianzhu Zhang

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

indu1ge/DepthMaster officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DenoisingDepth EstimationMonocular Depth Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation ETH3D DepthMaster Delta < 1.25 0.974 #2 of 10 Archive leaderboard report
Monocular Depth Estimation ETH3D DepthMaster absolute relative error 0.053 #2 of 10 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split DepthMaster Delta < 1.25 0.937 #48 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split DepthMaster absolute relative error 0.082 #48 of 79 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 DepthMaster Delta < 1.25 0.972 #7 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 DepthMaster absolute relative error 0.050 #7 of 85 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ADOPTDiffusionFocus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections