AI RESEARCH
UniDAC: Universal Metric Depth Estimation for Any Camera
arXiv CS.CV
•
ArXi:2603.27105v1 Announce Type: new Monocular metric depth estimation (MMDE) is a core challenge in computer vision, playing a pivotal role in real-world applications that demand accurate spatial understanding. Although prior works have shown promising zero-shot performance in MMDE, they often struggle with generalization across diverse camera types, such as fisheye and $360^\circ$ cameras. Recent advances have addressed this through unified camera representations or canonical representation spaces, but they require either including large-FoV camera data during.