Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
This addresses the limitation of existing SISR methods that fail in real-world scenarios with varied degradations, offering a more practical solution for image processing applications.
The paper tackles the problem of single image super-resolution (SISR) by proposing a framework that enables a single convolutional network to handle multiple degradations, such as blur and noise, rather than assuming bicubic downsampling, resulting in improved performance and scalability for practical applications.
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.