Visual localization is a fundamental problem in computer vision
and robotics. Recently, deep learning has shown to be effective
for robust monocular localization. Most deep learningbased
methods utilize convolution neural network (CNN) to
regress global 6 degree-of-freedom (Dof) pose. However,
these methods suffer from pose sparsity, leading to over-fitting
during training and poor localization performance on unseen
data. In this paper, we try to alleviate this issue by implementing
randomly geometric augmentation (RGA) during training.
Specifically, we firstly estimate the depth map using a depth
estimation network for the initial training image. Combing
the estimated depth, RGB image and its corresponding pose,
we can randomly synthesize new images of different views.
The synthesized and initial images are used to train the pose
regression network. Experiment results show our geometric
augmentation strategy can significantly improve the localization
accuracy.