Huang Feng, Liu Hongwei, Chen Liqiong, Shen Ying, Yu Min
College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, 350108, China.
Zhongyu (Fujian) Digital Technology Co., Ltd, Fuzhou, 350108, China.
Sci Rep. 2025 Jan 15;15(1):2051. doi: 10.1038/s41598-025-85548-4.
Attention mechanisms have been introduced to exploit deep-level information for image restoration by capturing feature dependencies. However, existing attention mechanisms often have limited perceptual capabilities and are incompatible with low-power devices due to computational resource constraints. Therefore, we propose a feature enhanced cascading attention network (FECAN) that introduces a novel feature enhanced cascading attention (FECA) mechanism, consisting of enhanced shuffle attention (ESA) and multi-scale large separable kernel attention (MLSKA). Specifically, ESA enhances high-frequency texture features in the feature maps, and MLSKA executes the further extraction. The rich and fine-grained high-frequency information are extracted and fused from multiple perceptual layers, thus improving super-resolution (SR) performance. To validate FECAN's effectiveness, we evaluate it with different complexities by stacking different numbers of high-frequency enhancement modules (HFEM) that contain FECA. Extensive experiments on benchmark datasets demonstrate that FECAN outperforms state-of-the-art lightweight SR networks in terms of objective evaluation metrics and subjective visual quality. Specifically, at a × 4 scale with a 121 K model size, compared to the second-ranked MAN-tiny, FECAN achieves a 0.07 dB improvement in average peak signal-to-noise ratio (PSNR), while reducing network parameters by approximately 19% and FLOPs by 20%. This demonstrates a better trade-off between SR performance and model complexity.
注意力机制已被引入，通过捕捉特征依赖关系来利用深层信息进行图像恢复。然而，现有的注意力机制通常感知能力有限，并且由于计算资源限制，与低功耗设备不兼容。因此，我们提出了一种特征增强级联注意力网络（FECAN），它引入了一种新颖的特征增强级联注意力（FECA）机制，该机制由增强型混洗注意力（ESA）和多尺度大分离内核注意力（MLSKA）组成。具体来说，ESA增强特征图中的高频纹理特征，MLSKA执行进一步提取。从多个感知层中提取并融合丰富且细粒度的高频信息，从而提高超分辨率（SR）性能。为了验证FECAN的有效性，我们通过堆叠不同数量包含FECA的高频增强模块（HFEM），以不同复杂度对其进行评估。在基准数据集上进行的大量实验表明，在客观评估指标和主观视觉质量方面，FECAN优于当前最先进的轻量级SR网络。具体而言，在121K模型大小的×4尺度下，与排名第二的MAN-tiny相比，FECAN的平均峰值信噪比（PSNR）提高了0.07dB，同时网络参数减少了约19%，浮点运算次数减少了20%。这表明在SR性能和模型复杂度之间实现了更好的权衡。
