Feedback Network for Image Super-Resolution

TL;DR

This paper introduces a feedback network for image super-resolution that refines low-level features using high-level information through a recurrent feedback mechanism, improving reconstruction quality.

Contribution

It proposes a novel feedback-based deep network architecture for image super-resolution, incorporating RNN-based feedback and curriculum learning for degraded images.

Findings

Outperforms state-of-the-art super-resolution methods

Demonstrates strong early reconstruction ability

Effective on images with multiple types of degradation

Abstract

Recent advances in image super-resolution (SR) explored the power of deep learning to achieve a better reconstruction performance. However, the feedback mechanism, which commonly exists in human visual system, has not been fully exploited in existing deep learning based image SR methods. In this paper, we propose an image super-resolution feedback network (SRFBN) to refine low-level representations with high-level information. Specifically, we use hidden states in an RNN with constraints to achieve such feedback manner. A feedback block is designed to handle the feedback connections and to generate powerful high-level representations. The proposed SRFBN comes with a strong early reconstruction ability and can create the final high-resolution image step by step. In addition, we introduce a curriculum learning strategy to make the network well suitable for more complicated tasks, where the low-resolution images are corrupted by multiple types of degradation. Extensive experimental results demonstrate the superiority of the proposed SRFBN in comparison with the state-of-the-art methods. Code is avaliable at https://github.com/Paper99/SRFBN_CVPR19.