[CVPR 2023] OrienterNet: Visual Localization in 2D Public Maps with Neural Matching 

There are works that can predict the intrinsics of an image using a deep network, for example: jinlinyi.github.io/PerspectiveFields/ This is what we use in our demo: skydes-orienternet.hf.space/

We combine multi-session SLAM poses with GPS and OrienterNet predictions. See section B.3 of the paper for more details: arxiv.org/pdf/2304.02009.pdf

@@pesarlin Thanks! Great work!