Adversarial Text Image Super-Resolution using Sinkhorn Distance

Abstract

Convolutional neural network-based methods have demonstrated promising results for single image super-resolution. However, existing methods usually approach the problem on natural scenes rather than texts, whereas the latter can provide more informative messages to viewers. In this paper, instead of using the L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> -norm as the supervision metric, we propose a novel one for better preserving semantic information in text images. Our new metric combines optimal transport in a primal form with Sinkhorn distance defined in an adversarially learned feature space. Since the Sinkhorn distance measures the similarity between two features in terms of both feature components and spatial locations, our metric can maintain the spatial structure of texts during network optimization. Experimental results on text datasets show that our method performs favorably against state-of-the-art approaches in both quantitative and qualitative evaluations. We will publish the code, datasets, and models upon acceptance.