计算机科学 ›› 2025, Vol. 52 ›› Issue (6): 239-246.doi: 10.11896/jsjkx.240300058

• 计算机图形学&多媒体 • 上一篇    下一篇

基于级联的多尺度特征融合残差去噪网络

郭业才1,2, 胡晓伟1, 毛湘南1   

  1. 1 南京信息工程大学电子与信息工程学院 南京 210044
    2 无锡学院电子信息工程学院 江苏 无锡 214105
  • 收稿日期:2024-03-11 修回日期:2024-07-18 出版日期:2025-06-15 发布日期:2025-06-11
  • 通讯作者: 郭业才(guo-yecai@163.com)
  • 基金资助:
    国家自然科学基金(61673222)

Multi-scale Feature Fusion Residual Denoising Network Based on Cascade

GUO Yecai1,2, HU Xiaowei1, MAO Xiangnan1   

  1. 1 College of Electronic and Information Engineering,Nanjing University of Information Science and Technology,Nanjing 210044,China
    2 College of Electronic Information Engineering,Wuxi University,Wuxi 214105,China
  • Received:2024-03-11 Revised:2024-07-18 Online:2025-06-15 Published:2025-06-11
  • About author:GUO Yecai,born in 1962,Ph.D,professor,is a member of CCF(No.P7150M).His main research interests include machine learning,meteorological communication technology,underwater communication theory and its applications.
  • Supported by:
    National Natural Science Foundation of China(61673222).

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。

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

Abstract: 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.

Key words: Image denoising, Real noise, Convolutional neural network, Multi-scale feature fusion, Dense residual

中图分类号: 

  • TP391
[1]SOLOMON C,BRECKON T.Fundamentals of Digital ImageProcessing:A Practical Approach with Examples in Matlab[M].Chichester:Wiley-Blackwell,2011:6-7.
[2]AFONSO M V,BIOUCAS-DIAS J M,FIGUEIREDO M A T.Fast Image Recovery using Variable Splitting and Constrained Optimization[J].IEEE transactions on image processing,2010,19(9):2345-2356.
[3]ANWARS S,BARNES N.Real Image Denoising with FeatureAttention[C]//IEEE/CVF International Conference on Computer Vision.Korea:IEEE,2019:3155-3164.
[4]WU W C.Research on Image Denoising Method Based on Convolutional Neural Network[D].Kunming:Yunnan Normal University,2023.
[5]FENG Y Z,LIU J X,WANG H Y,et al.Real Image Denoising Method Based on Multi-Level Residual Information Distillation[J].Computer Engineering,2024,50(3):216-223.
[6]KIM Y,SOH J W,PARK G Y,et al.Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition.Seattle,USA:IEEE,2020:3479- 3489.
[7]YUE Z,ZHAO Q,ZHANG L,et al.Dual Adversarial Network:Toward Real-World Noise Removal and Noise Generation[C]//Proceedings of the European Conference on Computer Vision.Cham:Springer International Publishing,2020:41-58.
[8]FOI A,TRIMECHE M,KATKOVNIK V,et al.Practical Poissonian-Gaussian Noise modeling and fitting for Single-Image Raw-Data[J].IEEE Transactions on Image Processing,2008,17(10):1737-1754.
[9]HEIDE F,STEINBERGER M,TSAI Y T,et al.Flexisp:AFlexible Camera Image Processing Framework[J].ACM Tran-sactions on Graphics,2014,33(6):1-13.
[10]DABOV K,FOI A,KATKOVNIK V,et al.Image Denoising by Sparse 3D Transform-Domain Collaborative Filtering[J].IEEE Transactions onImage Processing,2007,16(8):2080-2095.
[11]HUANG G,LIU Z,VAN DER MAATEN L,et al.Densely connected Convolutional Networks[C]//IEEE Conference on Computer Vision and Pattern Recognition.New York:IEEE,2017:2261-2269.
[12]WOO S,PARK J,LEE J Y,et al.CBAM:Convolutional Block Attention Module[C]//Proceedings of the European Conference on Computer Vision.Switzerland:Springer International Publishing,2018:3-19.
[13]KOMATSU R,GONSALVES T.Comparing U-Net based Mo-dels for Denoising Color Images[J].AI,2020,1(4):465-486.
[14]YIN H T,WANG T Y.Image Denoising Algorithm Based on DeepMulti-Scale Convolutional Sparse Coding [J].Computer Science.2023,50(4):133-140.
[15]CRNJANSKI J,KRSTIC M,TOTOVIC A,et al.Adaptive Sig-moid-Like and PReLU Activation Functions for All-Optical Perceptron[J].Optics letters,2021,46(9):2003-2006.
[16]JIANG D,QU H,ZHAO J,et al.Aggregating Multi-Scale Contextual Features from Multiple Stages for Semantic Image Segmentation[J].Connection Science,2021,33(3):605-622.
[17]PALUBINSKAS G.Image Similarity/Distance Measures:What is really behind MSE and SSIM?[J].International Journal of Image and Data Fusion,2017,8(1):32-53.
[18]CHARBONNIER P,BLANC-FERAUD L,AUBERT G,et al.Two Deterministic Half-Quadratic Regularization Algorithms for Computed Imaging[C]//Proceedings of 1st International Conference on Image Processing.New York:IEEE,1994:168-172.
[19]JIANG K,WANG Z,YI P,et al.Multi-Scale Progressive Fusion Network for Single Image Deraining[C]//IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition.New York:IEEE,2020:8343-8352.
[20]ABDELHAMED A,LIN S,BROWN M S.A High-Quality Denoising Dataset for Smartphone Cameras[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition.New York:IEEE,2018:1692-1700.
[21]PLOTZ T,ROTH S.Benchmarking Denoising Algorithms with Real Photographs[C]//IEEE Conference on Computer Vision and Pattern Recognition.New York:IEEE,2017:2750- 2759.
[22]LEBRUN M,COLOM M,MOREL J M.The Noise Clinic:A Blind Image Denoising Algorithm[J].Image Processing on Line,2015(5):1-54.
[23]TONG Y B,ZHANG Q S,QI Y P.Image Quality Assessing by Combining PSNR with SSIM[J].Journal of Image and Gra-phics,2006,11(12):1758-1763.
[24]CAZENAV T,SENTUC J,VIDEAU M.Cosine Annealing,Mixnet and Swish Activation for Computer Go[M].Cham:Springer International Publishing,2021:53-60.
[25]KINGMA D,BA J.Adam:A Method for Stochastic Optimization[C]//International Conference for Learning Representations.New York:IEEE,2014:1-15.
[26]YU X,FU Z,GE C.A Multi-Scale Generative Adversarial Network for Real-World Image Denoising[J].Signal,Image and Video Processing,2022,16(1):257-264.
[27]SOH J W,CHO N I.Variational Deep Image Restoration [J].IEEE Transactions on Image Processing,2022,31:4363-4376.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!