Modelling Uncertainty in Deep Learning for Camera Relocalization
This addresses robust and real-time visual localization for robotics or AR/VR applications, representing an incremental advance with uncertainty estimation.
The paper tackles camera relocalization by using a Bayesian convolutional neural network to regress 6-DOF pose from a single RGB image, achieving real-time performance under 6ms and improving state-of-the-art accuracy with approximately 2m and 6 degrees outdoors and 0.5m and 10 degrees indoors.
We present a robust and real-time monocular six degree of freedom visual relocalization system. We use a Bayesian convolutional neural network to regress the 6-DOF camera pose from a single RGB image. It is trained in an end-to-end manner with no need of additional engineering or graph optimisation. The algorithm can operate indoors and outdoors in real time, taking under 6ms to compute. It obtains approximately 2m and 6 degrees accuracy for very large scale outdoor scenes and 0.5m and 10 degrees accuracy indoors. Using a Bayesian convolutional neural network implementation we obtain an estimate of the model's relocalization uncertainty and improve state of the art localization accuracy on a large scale outdoor dataset. We leverage the uncertainty measure to estimate metric relocalization error and to detect the presence or absence of the scene in the input image. We show that the model's uncertainty is caused by images being dissimilar to the training dataset in either pose or appearance.