Map-Relative Pose Regression for Visual Re-Localization

arXiv:2404.09884v1 Announce Type: cross
Abstract: Pose regression networks predict the camera pose of a query image relative to a known environment. Within this family of methods, absolute pose regression (APR) has recently shown promising accuracy in the range of a few centimeters in position error. APR networks encode the scene geometry implicitly in their weights. To achieve high accuracy, they require vast amounts of training data that, realistically, can only be created using novel view synthesis in a days-long process. …

arxiv cs.cv cs.lg localization map regression type visual