xyzNet: Towards Machine Learning Camera Relocalization by Using a Scene Coordinate Prediction Network

Camera relocalization is a common problem in several applications such as augmented reality or robot navigation. Especially, augmented reality requires fast, accurate and robust camera localization. However, it is still challenging to have a both real-time and accurate method. In this paper, we present our hybrid method combing machine learning approach and geometric approach for real-time camera relocalization from a single RGB image. We propose a light Convolutional Neural Network (CNN) called xyzNet to efficiently and robustly regress 3D world coordinates of key-points in an image. Then, the geometric information about 2D-3D correspondences allows the removal of ambiguous predictions and the calculation of more accurate camera pose. Moreover, we show favorable results compared to previous machine learning based approaches about the accuracy and the performance of our method on different datasets as well as the capacity to address challenges concerning dynamic scene.