Learning a Single Convolutional Super-Resolution Network for Multiple Degradations

TL;DR

This paper introduces a versatile convolutional neural network that can handle various image degradations in super-resolution tasks by incorporating degradation parameters as inputs, improving practicality and scalability over traditional methods.

Contribution

A novel framework with a dimensionality stretching strategy allowing a single CNN to address multiple and spatially varying degradations in super-resolution.

Findings

Effective on synthetic and real images

Handles multiple degradation types simultaneously

Computationally efficient and scalable

Abstract

Recent years have witnessed the unprecedented success of deep convolutional neural networks (CNNs) in single image super-resolution (SISR). However, existing CNN-based SISR methods mostly assume that a low-resolution (LR) image is bicubicly downsampled from a high-resolution (HR) image, thus inevitably giving rise to poor performance when the true degradation does not follow this assumption. Moreover, they lack scalability in learning a single model to non-blindly deal with multiple degradations. To address these issues, we propose a general framework with dimensionality stretching strategy that enables a single convolutional super-resolution network to take two key factors of the SISR degradation process, i.e., blur kernel and noise level, as input. Consequently, the super-resolver can handle multiple and even spatially variant degradations, which significantly improves the practicability. Extensive experimental results on synthetic and real LR images show that the proposed convolutional super-resolution network not only can produce favorable results on multiple degradations but also is computationally efficient, providing a highly effective and scalable solution to practical SISR applications.