GeoDiff: Geometry-Guided Diffusion for Metric Depth Estimation
This addresses the problem of scale ambiguities in monocular depth estimation for applications in robotics and computer vision, though it is incremental as it builds on existing diffusion frameworks.
The paper tackles the challenge of estimating absolute metric depth from single images by enhancing pretrained diffusion-based models with stereo vision guidance, achieving state-of-the-art performance in diverse environments without retraining.
We introduce a novel framework for metric depth estimation that enhances pretrained diffusion-based monocular depth estimation (DB-MDE) models with stereo vision guidance. While existing DB-MDE methods excel at predicting relative depth, estimating absolute metric depth remains challenging due to scale ambiguities in single-image scenarios. To address this, we reframe depth estimation as an inverse problem, leveraging pretrained latent diffusion models (LDMs) conditioned on RGB images, combined with stereo-based geometric constraints, to learn scale and shift for accurate depth recovery. Our training-free solution seamlessly integrates into existing DB-MDE frameworks and generalizes across indoor, outdoor, and complex environments. Extensive experiments demonstrate that our approach matches or surpasses state-of-the-art methods, particularly in challenging scenarios involving translucent and specular surfaces, all without requiring retraining.