Resolution Booster: Global Structure Preserving Stitching Method For Ultra-High Resolution Image Translation

Current image translation networks (for instance image to image translation, style transfer et al.) have strict limitation on input image resolution due to high spatial complexity, which results in a wide gap to their usage in practice. In this paper we propose a novel patch-based auxiliary architecture, called Resolution Booster, to endow a trained image translation network ability to process ultra high resolution images. Different from previous methods which compute the results with the entire image, our network processes resized global image at low resolution as well as high-resolution local patches to save the memory. To increase the quality of generated image, we exploit the rough global information with global branch and high resolution information with local branch then combine the results with a designed reconstruction network. Then a joint global/local stitching result is produced. Our network is flexible to be deployed on any exiting image translation method to endow the new network to process larger images. Experimental results show the both capability of processing much higher resolution images while not decreasing the generating quality compared with baseline methods and generality of our model for flexible deployment.