DepthMaster: Taming Diffusion Models for Monocular Depth Estimation

ArXi:2501.02576v2 Announce Type: replace Monocular depth estimation within the diffusion-denoising paradigm nstrates 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.