Tensor Super-Resolution with Generative Adversarial Nets: A Large Image Generation Approach

Abstract

Deep generative models have been successfully applied to many applications. However, existing methods experience limitations when generating large images (the literature usually generates small images, e.g., 32\32 or 128\128). In this paper, we propose a novel scheme using tensor super-resolution with adversarial generative nets (TSRGAN), to generate large high-quality images by exploring tensor structures. Essentially, the super resolution process of TSRGAN is based on tensor representation. First, we impose tensor structures for concise image representation, which is superior in capturing the pixel proximity information and the spatial patterns of elementary objects in images, over the vectorization preprocess in existing works. Secondly, we propose TSRGAN that integrates deep convolutional generative adversarial networks and tensor super-resolution in a cascading manner, to generate high-quality images from random distributions. More specifically, we design a tensor super-resolution process that consists of tensor dictionary learning and tensor coefficients learning. Finally, on three datasets, the proposed TSRGAN generates images with more realistic textures, compared with state-of-the-art adversarial autoencoders and super-resolution methods. The size of the generated images is increased by over 8.5 times, namely in PASCAL2.