[1]鲁正威,张笃振.一种基于Uniformer Transformer与UNet的图像降噪模型[J].南京师范大学学报(工程技术版),2023,23(01):039-45,65.[doi:10.3969/j.issn.1672-1292.2023.01.006]
　Lu Zhengwei,Zhang Duzhen.An Image Denoising Model Based on Uniformer Transformer and UNet[J].Journal of Nanjing Normal University(Engineering and Technology),2023,23(01):039-45,65.[doi:10.3969/j.issn.1672-1292.2023.01.006]
点击复制

一种基于Uniformer Transformer与UNet的图像降噪模型
分享到：

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
23卷
期数:
2023年01期
页码:
039-45,65
栏目:
计算机科学与技术
出版日期:
2023-03-15

文章信息/Info

Title:
An Image Denoising Model Based on Uniformer Transformer and UNet
文章编号:
1672-1292(2023)01-0039-07
作者:
鲁正威; 张笃振
(江苏师范大学计算机科学与技术学院,江苏 徐州 221116)
Author(s):
Lu Zhengwei; Zhang Duzhen
(School of Computer Science and Technology,Jiangsu Normal University,Xuzhou 221116,China)
关键词:
卷积神经网络(CNNs); Uniformer Transformer; 图像降噪; UNet
Keywords:
Convolutional Neural Networks(CNNs); Uniformer Transformer; image denoising; UNet
分类号:
TP391.41
DOI:
10.3969/j.issn.1672-1292.2023.01.006
文献标志码:
A
摘要:
卷积神经网络(CNNs)在图像降噪任务中取得了较大的成功. 基于Vision Transformer模型表现出较好的效果. 计算机视觉领域利用Transformer方法其性能超过了卷积神经网络方法. 提出了一种名为UUNet(Uniformer Transformer-UNet)的图像降噪模型,该模型使用Uniformer Transformer作为骨干网络,并融入UNet网络来提取图像的深层特征,使用PSNR、SSIM等指标对图像降噪效果进行评估. 实验结果表明,使用UUNet网络对图像降噪的整体性最优.
Abstract:
Convolutional Neural Networks(CNNs)have achieved a great success in image denoising task. The Vision Transformer-based model has also demonstrated superior results. In previous experimental results, the performance of using the Transformer methods in the field of computer vision outperformed that of the CNNs-based methods. A UUNet(Uniformer Transformer-UNet)image denoising model is proposed in this paper which uses the Uniformer Transformer as the backbone network and integrates the UNet network structure to extract the deep feature information of the images. PSNR and SSIM are used in this study to evaluate the image denoising effects. The experimental results show that the UUNet network has a better performance than other five models.

参考文献/References:

[1]DABOV K,FOI A,KATKOVNIK V,et al. Image denoising with block-matching and 3D filtering[C]//International Society for Optics and Photonics.Washington,USA,2006:6064-6078.
[2]GU S,ZHANG L,ZUO W,et al. Weighted nuclear norm minimization with application to image denoising[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Columbus,Ohio,USA,2014:2862-2869.
[3]RONNEBERGER O,FISCHER P,BROX T. U-Net:Convolutional networks for biomedical image segmentation[C]//Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Switzerland:Springer. 2015:234-241.
[4]ZHANG K,ZUO W,CHEN Y,et al. Beyond a Gaussian denoiser:residual learning of deep CNN for image denoising[J]. IEEE Transactions on Image Processing,2017,26(7):3142-3155.
[5]ZHANG K,ZUO W,ZHANG L. FFDNet:Toward a fast and flexible solution for CNN-based image denoising[J]. IEEE Transactions on Image Processing,2018,27(9):4608-4622.
[6]PARK B,YU S,JEONG J. Densely connected hierarchical network for image denoising[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Long Beach,CA,USA,2019.
[7]GURROLA-RAMOS J,DALMAU O,ALARCÓN T E. A residual dense U-Net neural network for image denoising[J]. IEEE Access,2021,9:31742-31754.
[8]AGUSTSSON E,TIMOFTE R. Ntire 2017 challenge on single image super-resolution:Dataset and study[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. Honolulu,Hawaii,USA,2017:126-135.
[9]LIU Z,LIN Y,CAO Y,et al. Swin transformer:Hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. USA:IEEE,2021:10012-10022.
[10]LIANG J Y,CAO J Z,SUN G L,et al. SwinIR:Image restoration using swin transformer[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. USA:IEEE,2021:1833-1844.
[11]NIKLAUS S,MAI L,LIU F. Video frame interpolation via adaptive convolution[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu,Hawaii,USA,2017:670-679.
[12]WU H,QU Y,LIN S,et al. Contrastive learning for compact single image dehazing[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. USA:IEEE,2021:10551-10560.
[13]WANG X,GIRSHICK R,GUPTA A,et al. Non-local neural net-works[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City,Utah,USA,2018:7794-7803.
[14]ZHANG Y,LI K,LI K,et al. Image super-resolution using very deep residual channel attention networks[C]//Proceedings of the European Conference on Computer Vision. Berlin:Springer Science,2018:286-301.
[15]LI K,WANG Y,ZHANG J,et al. Uniformer:Unifying convolution and self-attention for visual recognition[J]. arXiv Preprint arXiv:2201.09450,2022.
[16]FAN C M,LIU T J,LIU K H. Selective residual M-Net for real image denoising[J]. arXiv Preprint arXiv:2203.01645,2022.
[17]FAN C M,LIU T J,LIU K H. SUNet:Swin transformer UNet for image denoising[J]. arXiv Preprint arXiv:2202.14009,2022.
[18]CHEN B X,LIU T J,LIU K H,et al. Image super-resolution using complex dense block on generative adversarial networks[C]//2019 IEEE International Conference on Image Processing. Taipei,China,2019:2866-2870.
[19]BUADES A,COLL B,MOREL J M. A non-local algorithm for image denoising[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego,CA,USA,2005,2:60-65.
[20]DONG W S,LI X,ZHANG L,et al. Sparsity-based image denoising via dictionary learning and structural clustering[C]//CVPR 2011. Colorado Springs,CO,USA,2011.
[21]XU L,ZHENG S,JIA J. Unnatural L0 sparse representation for natural image deblurring[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Oregon,Portland,2013.
[22]CHAN T F,WONG C K. Total variation blind deconvolution[J]. IEEE Transactions on Image Processing,1998,7(3):370-375.
[23]KRAHMER F,LIN Y Z,MCADOO B Z,et al. Blind image deconvolution:motion blur estimation[J/OL]. University of Minnesota,2006,9[2022-05-15]. http://purl.umn.edu/3685.
[24]WEN K Y,LIU T J,LIU K H,et al. Identifying poultry farms from satellite images with residual dense U-Net[C]//2020 IEEE International Conference on Systems,Man,and Cybernetics. Toronto,ON,Canada,2020.
[25]SHI M Z,XU T F,FENG L,et al. Single image deblurring using novel image prior constraints[J]. Optik,2013,124(20):4429-4434.
[26]XIAO X,LIAN S,LUO Z,et al. Weighted res-unet for high-quality retina vessel segmentation[C]//2018 9th International Conference on Information Technology in Medicine and Education. Hangzhou,China,2018
[27]GUAN S,KHAN A A,SIKDAR S,et al. Fully dense UNet for 2-D sparse photoacoustic tomography artifact removal[J]. IEEE Journal of Biomedical and Health Informatics,2019,24(2):568-576.
[28]JIN Q,MENG Z,SUN C,et al. RA-UNet:A hybrid deep attention-aware network to extract liver and tumor in CT scans[J]. Frontiers in Bioengineering and Biotechnology,2020,8:1471.
[29]YAN Q,ZHANG L,LIU Y,et al. Deep HDR imaging via a non-local network[J]. IEEE Transactions on Image Processing,2020,29:4308-4322.
[30]SHI W,CABALLERO J,HUSZAc'1R F,et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. USA:IEEE,2016:1874-1883.
[31]MARTIN D,FOWLKES C,TAL D,et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics[C]//Proceedings of the Eighth IEEE International Conference on Computer Vision. ICCV 2001. USA:IEEE,2002:416-423.

备注/Memo

备注/Memo:
收稿日期:2022-09-15.
基金项目:江苏省高校自然科学基金项目(19KJB520032)、江苏师范大学博士学位教师科研支持项目(20XSRS018)、江苏师范大学研究生科研与实践创新计划项目(2022XKT1535).
通讯作者:张笃振,博士,副教授,研究方向:目标检测、机器学习. E-mail:zhduzhen@jsnu.edu.cn
更新日期/Last Update: 2023-03-15