Cross-Scale Residual Network for Multiple Tasks:Image Super-resolution, Denoising, and Deblocking

TL;DR

This paper introduces a cross-scale residual network that leverages inter-task correlations and multi-scale features to improve image super-resolution, denoising, and deblocking, achieving superior results over existing methods.

Contribution

The novel cross-scale residual network effectively exploits scale-related features and inter-task correlations for multiple image restoration tasks.

Findings

Outperforms state-of-the-art methods in quantitative metrics.

Achieves better qualitative restoration results.

Supports multiple tasks with a unified network.

Abstract

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.