{"ID":2852044,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.18291","arxiv_id":"2510.18291","title":"GeoDiff: Geometry-Guided Diffusion for Metric Depth Estimation","abstract":"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.","short_abstract":"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 s...","url_abs":"https://arxiv.org/abs/2510.18291","url_pdf":"https://arxiv.org/pdf/2510.18291v1","authors":"[\"Tuan Pham\",\"Thanh-Tung Le\",\"Xiaohui Xie\",\"Stephan Mandt\"]","published":"2025-10-21T04:47:36Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}