Xu Yu, Wang Yi
School of Computer and Control Engineering, Yantai University, Yantai 264005, China.
Sensors (Basel). 2025 Jun 28;25(13):4044. doi: 10.3390/s25134044.
Image super-resolution (SR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs. It plays a crucial role in applications such as medical imaging, surveillance, and remote sensing. However, due to the ill-posed nature of the task and the inherent limitations of imaging sensors, obtaining accurate HR images remains challenging. While numerous methods have been proposed, the traditional approaches suffer from oversmoothing and limited generalization; CNN-based models lack the ability to capture long-range dependencies; and Transformer-based solutions, although effective in modeling global context, are computationally intensive and prone to texture loss. To address these issues, we propose a hybrid CNN-Transformer architecture that cascades a pixel-wise self-attention non-local means module (PSNLM) and an adaptive dual-path multi-scale fusion block (ADMFB). The PSNLM is inspired by the non-local means (NLM) algorithm. We use weighted patches to estimate the similarity between pixels centered at each patch while limiting the search region and constructing a communication mechanism across ranges. The ADMFB enhances texture reconstruction by adaptively aggregating multi-scale features through dual attention paths. The experimental results demonstrate that our method achieves superior performance on multiple benchmarks. For instance, in challenging ×4 super-resolution, our method outperforms the second-best method by 0.0201 regarding the Structural Similarity Index (SSIM) on the BSD100 dataset. On the texture-rich Urban100 dataset, our method achieves a 26.56 dB Peak Signal-to-Noise Ratio (PSNR) and 0.8133 SSIM.
图像超分辨率（SR）旨在从低分辨率（LR）输入重建高分辨率（HR）图像。它在医学成像、监控和遥感等应用中起着至关重要的作用。然而，由于该任务的不适定性以及成像传感器的固有局限性，获得准确的HR图像仍然具有挑战性。虽然已经提出了许多方法，但传统方法存在过度平滑和泛化能力有限的问题；基于卷积神经网络（CNN）的模型缺乏捕捉长距离依赖关系的能力；基于Transformer的解决方案虽然在建模全局上下文方面有效，但计算量很大且容易出现纹理损失。为了解决这些问题，我们提出了一种混合CNN-Transformer架构，该架构级联了逐像素自注意力非局部均值模块（PSNLM）和自适应双路径多尺度融合块（ADMFB）。PSNLM受到非局部均值（NLM）算法的启发。我们使用加权补丁来估计以每个补丁为中心的像素之间的相似度，同时限制搜索区域并构建跨范围的通信机制。ADMFB通过双注意力路径自适应地聚合多尺度特征来增强纹理重建。实验结果表明，我们的方法在多个基准测试中取得了优异的性能。例如，在具有挑战性的×4超分辨率中，我们的方法在BSD100数据集上的结构相似性指数（SSIM）方面比第二好的方法高出0.0201。在纹理丰富的Urban100数据集上，我们的方法实现了26.56 dB的峰值信噪比（PSNR）和0.8133的SSIM。
