Abstract
Dynamic relocalization of 6D camera pose from single reference image is a costly and challenging task that requires delicate hand-eye calibration and precision positioning platform to do 3D mechanical rotation and translation. In this paper, we show that high-quality camera relocalization can be achieved in a much less expensive way. Based on inexpensive platform with unreliable absolute reposi-tioning accuracy (ARA), we propose a hand-eye calibra-tion free strategy to actively relocate camera into the same 6D pose that produces the input reference image, by sequentially correcting 3D relative rotation and translation. We theoretically prove that, by this strategy, both rotational and translational relative pose can be effectively reduced tozero, with bounded unknown hand-eye pose displacement. To conquer 3D rotation and translation ambiguity, this theoretical strategy is further revised to a practical relocaliza-tion algorithm with faster convergence rate and more reliability by jointly adjusting 3D relative rotation and trans-lation. Extensive experiments validate the effectiveness and superior accuracy of the proposed approach on laboratorytests and challenging real-world applications.