摘要
针对图像去噪特征提取单一化以及特征利用率低,不能生成更清晰图像的问题,提出了级联多尺度特征融合残差真实图像去噪网络。该网络双分支自适应密集残差块采用双路非对称扩张卷积扩展图像感受野,在水平尺度上选择性地提取丰富的纹理特征。在多尺度空间U-Net模块中,利用多尺度空间融合块增强网络对图像整体结构的学习能力,学习不同层次的信息,获取基于图像空间和上下文信息的多级特征。跳跃连接促进结构之间的参数共享,使不同尺度的特征充分融合,保证信息的完整性。最后,采用双残差学习构建出清晰的去噪图像。结果表明,该算法在真实噪声数据集(DND和SIDD)上的峰值信噪比分别为39.68 dB和39.50 dB,结构相似性分别为0.953和0.957,优于主流去噪算法。所提算法在增强去噪性能的同时,也保留了更详细的信息,使图像质量进一步提升。
In order to address the problems of singularization of image denoising feature extraction and low feature utilization,which cannot generate clearer images,a cascaded multi-scale feature fusion residual real image denoising network is proposed.The network’s dual-branch adaptive dense residual block uses dual-path asymmetric dilation convolution to expand the image receptive field to selectively extract rich texture features on the horizontal scale.In the multi-scale space U-Net module,the multi-scale space fusion block is used to enhance the network’s learning ability of the overall image structure,learn different levels of information,and acquire multi-level features based on image space and context information.Skip connections facilitates parameter sharing among structures,fully integrating features at different scales and ensuring the integrity of information.Finally,dual residual learning is used to generate clear denoised images.Results show that the peak signal-to-noise ratio of the proposed algorithm on real noise datasets(DND and SIDD)is 39.68 dB and 39.50 dB respectively,and the structural similarity is 0.953 and 0.957 respectively,which is better than the mainstream denoising algorithm.The proposed algorithm enhances denoising performance while retaining more detailed information,further improving image quality.
作者
郭业才
胡晓伟
毛湘南
GUO Yecai;HU Xiaowei;MAO Xiangnan(College of Electronic and Information Engineering,Nanjing University of Information Science and Technology,Nanjing 210044,China;College of Electronic Information Engineering,Wuxi University,Wuxi 214105,China)
出处
《计算机科学》
北大核心
2025年第6期239-246,共8页
Computer Science
基金
国家自然科学基金(61673222)。
关键词
图像去噪
真实噪声
卷积神经网络
多尺度特征融合
密集残差
Image denoising
Real noise
Convolutional neural network
Multi-scale feature fusion
Dense residual
