Recent research on learned visual descriptors has shown promising improvements in
correspondence estimation, a key component of many 3D vision tasks. However, existing
descriptor learning frameworks typically require ground-truth correspondences between
feature points for training, which are challenging to acquire at scale. In this paper we
propose a novel weakly-supervised framework that can learn feature descriptors solely from
relative camera poses between images. To do so, we devise both a new loss function that …

In this supplemental material, we provide additional experimental results, visualizations, and
implementation details. In Sec. 2, we demonstrate the performance of our learned
descriptors on a standard visual localization benchmark. In Sec. 3, we investigate the
robustness of our method to the errors in camera poses. In Sec. 4, we visualize the
probabilistic distribution of correspondences for given query points in example image pairs.
In Sec. 5, we show more qualitative results for dense feature matching. In Sec. 6, we …