Abstract:

Single image super-resolution (SISR) has been a very attractive research topic in recent years. Breakthroughs in SISR have been achieved due to deep learning and generative adversarial networks (GANs). However, the generated image still suffers from ndesired artifacts. In this paper, we propose a new method named GMGAN for SISR tasks. In this method, to generate images more in line with human vision system (HVS), we design a quality loss by integrating an image quality assessment (IQA) metric named gradient magnitude similarity deviation (GMSD). To our knowledge, it is the first time to truly integrate an IQA metric into SISR. Moreover, to overcome the instability of the original GAN, we use a variant of GANs named improved training of Wasserstein GANs (WGAN-GP). Besides GMGAN, we highlight the importance of training datasets. Experiments show that GMGAN with quality loss and WGAN-GP can generate visually appealing results and set a new state of the art. In addition, large quantity of high-quality training images with rich textures can benefit the results.

Problem Definition:

Image generation is not an easy problem. Trying to generate large scale images add complexity to the generation. Complex networks with high dimensionality inputs and outputs are not easy to train. In this work, we tackle this problem by providing a way to generate larger images. This is done by exploring the di_erent ways to integrate a super-resolution network with a GAN to enable training with smaller sized datasets.

OBJECTIVE:

The main objective is to create a fast and precise method for obtaining super-resolution vascular images from high-density contrast-enhanced ultrasound imaging data