Abstract
Deblurring is a classical image restoration problem. Although recent methods have shown promising deblurring performance, most methods still cannot effectively balance the texture details restoration and model complexity. In order to improve the performance of deblurring, some models are designed to be more complex. In this work, a simple and efficient Wiener deconvolution and multi-scale transformer-based U-Net (WTransU-Net) is proposed to tackle these problems. First, the proposed Wiener feature extraction module uses explicit Wiener deconvolution to extract the Wiener features in the deep feature space. Then, the obtained Wiener features are input into a multi-scale feature reconstruction module which only embeds one transformer refining block in each scale of the U-Net to deblur the image from local and global perspectives. In addition, a multi-scale hybrid loss function is designed to train the WTransU-Net in an end-to-end manner to better learn the content and texture details. The experimental results on benchmark datasets show that compared with the state-of-the-art deblurring methods, the proposed WTransU-Net can achieve better performance with fewer artifacts in terms of quantitatively and qualitatively.
Similar content being viewed by others
Data availability
This article uses public datasets, which are available on their official website
References
Karacan, K., Uyar, T., Tunga, B., et al.: A novel multistage CAD system for breast cancer diagnosis. Signal Image Video Process. 17, 1–10 (2023)
Nie, C., Qadar, M.A., Zhou, S., et al.: Transnational image object detection datasets from nighttime driving. Signal Image Video Process. 17, 1–9 (2022)
Chong Mou, Qian Wang, and Jian Zhang., et al. (2022): Deep generalized unfolding networks for image restoration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2204–13348 (2022)
Rim, J., Kim, G., Kim, J., et al.: Realistic blur synthesis for learning image deblurring. In: European Conference Computer Vision LNCS,v13667, pp. 487–503( 2022)
Shyam, P., Kim, K.S., Yoon, K.J.: GIQE: Generic image quality enhancement via Nth order iterative degradation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2077–2087(2022)
Kaufman, A., Fattal, R.: Deblurring using analysis-synthesis networks pair. In: IEEE Conference Computer Vision Pattern Recognition, pp. 5811–5820 (2020)
Fang, Y., Zhang, H., Wong, H.S., et al.: A robust non-blind deblurring method using deep denoiser prior. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 735–744 (2022)
Guan, Z., Tsai, E.H.R., Huang, X., et al.: Non-blind deblurring for fluorescence: A deformable latent space approach with Kernel parameterization. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision ,pp. 711–719 (2022)
Dong, J., Pan, J., Sun, D., et al.: Learning data terms for non-blind deblurring. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 748–763 (2018)
Vasu, S., Maligireddy, V.R., Rajagopalan, A.N.: Non-blind deblurring: Handling Kernel uncertainty with CNNs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3272-3281 (2018)
Son, H., Lee, S.: Fast non-blind deconvolution via regularized residual networks with long/short skip-connections, In: 2017 IEEE International Conference on Computational Photography (ICCP), 1–10 (2017)
Chakrabarti A.: A neural approach to blind motion deblurring. In: Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, 11-14, 2016, Proceedings, Part III 14 2016 , pp. 221–235(2016)
Sun, J., Cao, W., Xu, Z., et al.: Learning a convolutional neural network for non-uniform motion blur removal. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 769–777 (2015)
Sankhe, P.D., Patil, M., Margaret, M.: Deblurring of grayscale images using inverse and Wiener filter. In: Proceedings of the International Conference and Workshop on Emerging Trends in Technology, 145–148 (2011)
Mbarki, Z., Seddik, H., Braiek, E.B.: Non blind image restoration scheme combining parametric wiener filtering and BM3D denoising technique. In: 2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), pp. 1–5 (2018)
Wiener, N., Mathematician, C., et al.: Extrapolation, interpolation, and smoothing of stationary time series: with engineering applications. MIT press, Cambridge (1949)
Krishnan, D., Fergus, R.: Fast image deconvolution using hyper-Laplacian priors. Adv. Neural Inf. Process. Syst. 22, 1033–1041 (2009)
Levin, A., Weiss, Y., Durand, F., et al.: Understanding and evaluating blind deconvolution algorithms. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1964–1971 (2009)
Levin, A., Fergus, R., Durand, F., et al.: Image and depth from a conventional camera with a coded aperture. Proc ACM SIGGRAPH Conf Computer Graph. 26(3), 70 (2007)
Schmidt, U., Jancsary, J., Nowozin, S., et al.: Cascades of regression tree fields for image restoration. IEEE Trans. Pattern Anal. Mach. Intell. 38(4), 677–689 (2015)
Roth, S., Black, M.J.: Fields of experts. Int. J. Comput. Vis. 82(2), 205–229 (2009)
Zoran, D., Weiss, Y.: From learning models of natural image patches to whole image restoration. In: 2011 International Conference on Computer Vision , pp. 479–486 (2011)
Xu, L., Ren, J.S., Liu, C., et al.: Deep convolutional neural network for image deconvolution. Adv. Neural Inf. Process. Syst. 27, 1790–1798 (2014)
Ren, W., Zhang, J., Ma, L., et al.: Deep non-blind deconvolution via generalized low-rank approximation. Adv. Neural Inf. Process. Syst. 31, 297–307 (2018)
Zamir, S.W., Arora, A., Khan, S., et al.: Multi-stage progressive image restoration. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 14816–14826 (2021)
Zhang, Z., Cheng, Y., Suo, J., et al.: INFWIDE: Image and feature space Wiener deconvolution network for non-blind image deblurring in low-light conditions. IEEE Trans. Image Process. 32, 1390–1402 (2023)
Nah, S., Hyun Kim, T., Mu Lee, K.: Deep multi-scale convolutional neural network for dynamic scene deblurring. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3883–3891 (2017)
Dong, J., Roth, S., Schiele, B.: Deep wiener deconvolution: Wiener meets deep learning for image deblurring. Adv. Neural Inf. Process. Syst. 33, 1048–1059 (2020)
Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. Adv. Neural Inf. Process, Syst (2017)
Zamir, S.W., Arora, A., Khan, S., et al.: Restormer: Efficient transformer for high-resolution image restoration. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5728–5739 (2022)
Corbineau, M.C., Bertocchi, C., Chouzenoux, E., et al.: Learned image deblurring by unfolding a proximal interior point algorithm. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 4664–4668(2019)
Leung, C., Lu, W.S.: A modified Wiener filter for the restoration of blurred images. In: Proceedings of IEEE Pacific Rim Conference on Communications Computers and Signal Processing, PACRIM - Proc., 1: 166–169(1993)
Cho, S.J., Ji, S.W., Hong, J.P., et al.: Rethinking coarse-to-fine approach in single image deblurring. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4641–4650 (2021)
Wang, Z., Cun, X., Bao, J., et al.: Uformer: A general u-shaped transformer for image restoration. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.17683–17693(2022)
Abuolaim, A., Brown, M.S.: Defocus deblurring using dual-pixel data. In: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part X 16, pp. 111–126(2020)
Suin, M., Purohit, K., Rajagopalan, A.N.: Spatially-attentive patch-hierarchical network for adaptive motion deblurring. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3606–3615 (2020)
Zhang, D., Wang, X.: Dynamic multi-scale network for dual-pixel images defocus deblurring with transformer. In: 2022 IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6 (2022)
Wang, Z., Simoncelli, E.P., Bovik, A.C.: Multiscale structural similarity for image quality assessment. In: The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, Vol. 2, pp. 1398–1402 (2003)
Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Lecture Notes Computer Science, pp. 234–241 (2015)
Ma, K., Duanmu, Z., Wu, Q., et al.: Waterloo exploration database: New challenges for image quality assessment models. IEEE Trans. Image Process. 26(2), 1004–1016 (2016)
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. IEEE Int. Conf. Comput. Vis. 2, 416–423 (2001)
Shen, Z., Wang, W., Lu, X., et al.: Human-aware motion deblurring. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 5572–5581 (2019)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, (2014)
Tao, X., Gao, H., Shen, X., et al.: Scale-recurrent network for deep image deblurring. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8174–8182 (2018)
Zhang, H., Dai, Y., Li, H., et al.: Deep stacked hierarchical multi-patch network for image deblurring. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5978–5986 (2019)
Kim, K., Lee, S., Cho, S.: MSSNet: Multi-scale-stage network for single image deblurring. LNCS 13802, 524–539 (2023)
Gong, D., Zhang, Z., Shi, Q., et al.: Learning deep gradient descent optimization for image deconvolution. IEEE Trans. Neural Netw. Learn. Syst. 31(12), 5468–5482 (2020)
Acknowledgements
This work was supported by Foundation of HubeiKey Laboratory of Metallurgical Industry Process System Science (No. Y202008) and National Natural Science Foundation of China (No. 61671338).
Author information
Authors and Affiliations
Contributions
SZ and YX proposed the algorithm and wrote the main manuscript, and HX participated in the design of the network. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
This article does not involve ethical issues.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhao, S., Xing, Y. & Xu, H. WTransU-Net: Wiener deconvolution meets multi-scale transformer-based U-net for image deblurring. SIViP 17, 4265–4273 (2023). https://doi.org/10.1007/s11760-023-02659-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-023-02659-z