Cross-Scale Residual Network for Multiple Tasks:Image Super-resolution, Denoising, and Deblocking
This work addresses the need for a unified network to handle correlated image restoration tasks, which is incremental as it builds on existing deep learning approaches.
The authors tackled the problem of performing multiple image restoration tasks (super-resolution, denoising, and deblocking) by proposing a cross-scale residual network that exploits scale-related features and inter-task correlations, and their experiments showed it outperforms state-of-the-art methods in quantitative and qualitative evaluations.
In general, image restoration involves mapping from low quality images to their high-quality counterparts. Such optimal mapping is usually non-linear and learnable by machine learning. Recently, deep convolutional neural networks have proven promising for such learning processing. It is desirable for an image processing network to support well with three vital tasks, namely, super-resolution, denoising, and deblocking. It is commonly recognized that these tasks have strong correlations. Therefore, it is imperative to harness the inter-task correlations. To this end, we propose the cross-scale residual network to exploit scale-related features and the inter-task correlations among the three tasks. The proposed network can extract multiple spatial scale features and establish multiple temporal feature reusage. Our experiments show that the proposed approach outperforms state-of-the-art methods in both quantitative and qualitative evaluations for multiple image restoration tasks.