BAM: A Balanced Attention Mechanism for Single Image Super Resolution

TL;DR

This paper introduces BAM, a balanced attention mechanism for single image super resolution that improves texture detail recovery and noise suppression, enhancing existing networks' performance and speed.

Contribution

The paper proposes a novel parallel attention mechanism combining ACAM and MSAM to balance noise reduction and texture preservation in SISR.

Findings

BAM improves super-resolution performance on aliasing regions.

Replacing existing attention modules with BAM reduces parameters and increases speed.

BAM outperforms state-of-the-art methods on real scene datasets.

Abstract

Recovering texture information from the aliasing regions has always been a major challenge for Single Image Super Resolution (SISR) task. These regions are often submerged in noise so that we have to restore texture details while suppressing noise. To address this issue, we propose a Balanced Attention Mechanism (BAM), which consists of Avgpool Channel Attention Module (ACAM) and Maxpool Spatial Attention Module (MSAM) in parallel. ACAM is designed to suppress extreme noise in the large scale feature maps while MSAM preserves high-frequency texture details. Thanks to the parallel structure, these two modules not only conduct self-optimization, but also mutual optimization to obtain the balance of noise reduction and high-frequency texture restoration during the back propagation process, and the parallel structure makes the inference faster. To verify the effectiveness and robustness of BAM, we applied it to 10 SOTA SISR networks. The results demonstrate that BAM can efficiently improve the networks performance, and for those originally with attention mechanism, the substitution with BAM further reduces the amount of parameters and increases the inference speed. Moreover, we present a dataset with rich texture aliasing regions in real scenes, named realSR7. Experiments prove that BAM achieves better super-resolution results on the aliasing area.