Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences

arXiv:2404.06337v1 Announce Type: new
Abstract: Given two images, we can estimate the relative camera pose between them by establishing image-to-image correspondences. Usually, correspondences are 2D-to-2D and the pose we estimate is defined only up to scale. Some applications, aiming at instant augmented reality anywhere, require scale-metric pose estimates, and hence, they rely on external depth estimators to recover the scale. We present MicKey, a keypoint matching pipeline that is able to predict metric correspondences in 3D camera space. By learning …

abstract applications arxiv augmented reality cs.cv image images image-to-image instant reality scale them type