Abstract: A method for performing privacy-preserving visual localization includes: determining a query segmentation map based on a query image; accessing a privacy preserved scene representation that includes labeled three dimensional (3D) representations of a scene selected from one or more segmentation classes; determining a predicted pose based on a starting pose; generating, from the predicted pose, a predicted segmentation map; and refining the predicted pose after aligning the predicted segmentation map with a query segmentation map. The above may be repeated. The refined predicted pose of the query image is output.

Abstract: A training system includes: a pose module configured to: receive an image captured using a camera; and determine a 6 degree of freedom (DoF) pose of the camera; and a training module configured to: input training images to the pose module from a training dataset; and train a segmentation module of the pose module by alternating between: updating a target distribution with parameters of the segmentation module fixed based on minimizing a first loss determined based on a label distribution determined based on prototype distributions determined by the pose module based on input of ones of the training images; updating the parameters of the segmentation module with the target distribution fixed based on minimizing a second loss determined based on a second loss that is different than the first loss; and updating the parameters of the segmentation module based on a ranking loss using a global representation.