Densely Residual Laplacian Super-Resolution

Super-Resolution convolutional neural networks have recently demonstrated high-quality restoration for single images. However, existing algorithms often require very deep architectures and long training times. Furthermore, current convolutional neural networks for super-resolution are unable to exploit features at multiple scales and weigh them equally or at only static scale only, limiting their learning capability. In this exposition, we present a compact and accurate super-resolution algorithm, namely, densely residual laplacian network (DRLN). The proposed network employs cascading residual on the residual structure to allow the flow of low-frequency information to focus on learning high and mid-level features. In addition, deep supervision is achieved via the densely concatenated residual blocks settings, which also helps in learning from high-level complex features. Moreover, we propose Laplacian attention to model the crucial features to learn the inter and intra-level dependencies between the feature maps. Furthermore, comprehensive quantitative and qualitative evaluations on low-resolution, noisy low-resolution, and real historical image benchmark datasets illustrate that our DRLN algorithm performs favorably against the state-of-the-art methods visually and accurately.

1 Introduction

In recent years, super-resolution (SR), a low-level vision task, became a research focus due to the high demand for better-resolution image quality. Super-resolution addresses the problem of reconstructing a high-resolution (HR) input from a low-resolution (LR) counterpart. We aim to super-resolve a single low-resolution image, a technique, commonly, known as single image super-resolution (SISR). Image SR is a challenging task to achieve as the process is ill-posed, which means that mapping between the output HR image to the input LR image is many-to-one. However, despite being a difficult problem, it is useful in many computer vision applications such as surveillance imaging [1], medical imaging [2], forensics [3], object classification [4] etc.