Gated Multiple Feedback Network for Image Super-Resolution

TL;DR

This paper introduces GMFN, a novel deep learning network with gated feedback connections that enhances low-level features with high-level information for improved image super-resolution, outperforming existing methods.

Contribution

The paper proposes a gated multiple feedback network with a feedback module that selectively refines low-level features using high-level features, advancing super-resolution techniques.

Findings

GMFN outperforms state-of-the-art SR methods in quantitative metrics.

The gated feedback module effectively enhances feature representation.

Extensive experiments validate the superiority of GMFN.

Abstract

The rapid development of deep learning (DL) has driven single image super-resolution (SR) into a new era. However, in most existing DL based image SR networks, the information flows are solely feedforward, and the high-level features cannot be fully explored. In this paper, we propose the gated multiple feedback network (GMFN) for accurate image SR, in which the representation of low-level features are efficiently enriched by rerouting multiple high-level features. We cascade multiple residual dense blocks (RDBs) and recurrently unfolds them across time. The multiple feedback connections between two adjacent time steps in the proposed GMFN exploits multiple high-level features captured under large receptive fields to refine the low-level features lacking enough contextual information. The elaborately designed gated feedback module (GFM) efficiently selects and further enhances useful information from multiple rerouted high-level features, and then refine the low-level features with the enhanced high-level information. Extensive experiments demonstrate the superiority of our proposed GMFN against state-of-the-art SR methods in terms of both quantitative metrics and visual quality. Code is available at https://github.com/liqilei/GMFN.