Going Much Wider with Deep Networks for Image Super-Resolution

Divide and Conquer is a well-established approach in the literature that has efficiently solved a variety of problems. However, it is yet to be explored in full in solving image super-resolution. To predict a sharp up-sampled image, this work proposes a divide and conquer approach based wide and deep network (WDN) that divides the 4× up-sampling problem into 32 disjoint subproblems that can be solved simultaneously and independently of each other Half of these subproblems deal with predicting the overall features of the high-resolution image, while the remaining are exclusively for predicting the finer details. Additionally, a technique that is found to be more effective in calibrating the pixel intensities has been proposed. Results obtained on multiple datasets demonstrate the improved performance of the proposed wide and deep network over state-of-the-art methods.

1. Introduction

Image Super-Resolution refers to those set of techniques that increase the resolution of an image while maintaining its quality that is commonly measured in terms of Peak Signal to Noise Ratio (PSNR [29]), and Structural Similarity (SSIM [97]) w.r.t. the ground-truth. Recent advances in display device technologies (Full HD and higher resolutions) have brought a surge in the application of super-resolution thus making it a prominent Computer Vision problem that is gaining immense academic and commercial research interests.