Image translation between aerial images and map images

Abstract

NTT summer internship gave me a great opportunity to work on the image translation problem between aerial images and map images . Out of all the state of the art methods, MUNIT proposed a framework to utilize disentangle learning in the image translation problem by decomposing the traditional feature space into the content sub space and style subspace As aerial images and map images are supposed to share the same content sub space, w e implement MUNIT on the problem of image translation between aerial images and map images and analyze the experimental results.