AI RESEARCH
Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens
arXiv CS.AI
•
ArXi:2508.04928v4 Announce Type: replace-cross We propose a method to extend foundational monocular depth estimators (FMDEs), trained on perspective images, to fisheye images. Despite being trained on tens of millions of images, FMDEs are susceptible to the covariate shift