DepthMaster: Taming Diffusion Models for Monocular Depth Estimation

Understand

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.