计算机技术与发展2024，Vol.34Issue(4)：48-54,7.DOI:10.20165/j.cnki.ISSN1673-629X.2024.0008
基于U形多尺度注意力方法的真实图像去噪
Real-world Image Denoising Based on U-shaped Multi-scale Attention Method
摘要
Abstract
To address the issue of subpar denoising results in existing algorithms for real-world image denoising,we propose an innovative solution called the U-Shape Pyramid Channel Attention(UPCA).The U-shape structure comprises a fusion of multi-scale feature modules and long-range channel attention modules,forming a pyramid attention module.Through concatenation operations,the U-shape structure allows for the fusion of output feature maps from each layer,minimizing the loss of fine-grained image details during the convolution and downsampling processes.The multi-scale feature pyramid module effectively leverages contextual information to restore clean images,while the long-range channel attention module establishes dependencies on global information,thereby enhancing the denoising performance of the network.Additionally,we introduce a noise term in the loss function to expedite convergence during training and improve denoising efficiency.Experimental comparisons on the SIDD and DND datasets demonstrate the feasibility and su-periority of the UPCA.Compared to RIDNet which also utilizes channel attention,UPCA achieves a remarkable improvement of 0.81 dB/0.044 in terms of PSNR/SSIM metrics.The visually enhanced denoised images produced by UPCA are superior,and it requires less computational power for training with the same set of parameters.关键词
图像去噪/计算机视觉/真实噪声/多尺度特征/长距离通道注意力Key words
image denoising/computer vision/real noise/multi-scale features/long-range channel attention分类
信息技术与安全科学引用本文复制引用
王新武,陈春雨..基于U形多尺度注意力方法的真实图像去噪[J].计算机技术与发展,2024,34(4):48-54,7.基金项目
国家自然科学基金资助项目(61871142) （61871142）
中央高校基本科研业务费项目(3072020CFT0803) （3072020CFT0803）
