AI RESEARCH
RAD: Retrieval-Augmented Monocular Metric Depth Estimation for Underrepresented Classes
arXiv CS.CV
•
ArXi:2602.09532v2 Announce Type: replace Monocular Metric Depth Estimation (MMDE) is essential for physically intelligent systems, yet accurate depth estimation for underrepresented classes in complex scenes remains a persistent challenge. To address this, we propose RAD, a retrieval-augmented framework that approximates the benefits of multi-view stereo by utilizing retrieved neighbors as structural geometric proxies.