Content-adaptive Representation Learning for Fast Image Super-resolution

TL;DR

This paper introduces a content-adaptive patch-wise rolling network for image super-resolution that improves efficiency by addressing image difficulty diversity, achieving faster processing while maintaining high quality.

Contribution

The paper proposes a novel patch-wise rolling network with a content-adaptive strategy and a flexible rolling mechanism for efficient and high-quality image super-resolution.

Findings

Significant acceleration in image super-resolution processing.

Maintains state-of-the-art performance in quality.

Effectively handles difficulty diversity across image regions.

Abstract

Deep convolutional networks have attracted great attention in image restoration and enhancement. Generally, restoration quality has been improved by building more and more convolutional block. However, these methods mostly learn a specific model to handle all images and ignore difficulty diversity. In other words, an area in the image with high frequency tend to lose more information during compressing while an area with low frequency tends to lose less. In this article, we adrress the efficiency issue in image SR by incorporating a patch-wise rolling network(PRN) to content-adaptively recover images according to difficulty levels. In contrast to existing studies that ignore difficulty diversity, we adopt different stage of a neural network to perform image restoration. In addition, we propose a rolling strategy that utilizes the parameters of each stage more flexible. Extensive experiments demonstrate that our model not only shows a significant acceleration but also maintain state-of-the-art performance.