Abstract
Blind image deblurring is a fundamental and important task in the field of computer vision. With the continuous progress of technology, blind image deblurring methods have achieved remarkable development and wide application. In early research, methods based on the \(L_0+X\) paradigm have successfully solved the blind image deblurring problem to some extent. Recently, a new method based on the redescending potential function has also come into prominence. This new method is formally more concise, but the general redescending potential function does not adapt to different regional features of the image. To address this issue, we introduce an adaptive redescending potential function. This function adapts to different structural features based on the magnitude of the total curvature in different regions of the image. Additionally, we introduce a local block fidelity term to consider the difference in gradient information, which is not involved in previous blind deblurring methods. The efficacy of the proposed method is demonstrated through experimental results on benchmark datasets and real blurred images. Our method achieved improvements in PSNR results by 0.28 dB and 0.79 dB on the Köhler and Levin datasets, respectively. Similarly, on the Lai dataset, our method enhanced the PSNR by 0.77 dB and the SSIM by 0.0374. Moreover, the self-supervised model induced by our proposed method achieved a PSNR result on the Levin dataset that is 0.47 dB higher than other advanced self-supervised models. These results indicate that the method is effective and produces notable results.













Similar content being viewed by others
Data Availibility Statement
No datasets were generated or analysed during the current study.
References
Cho, S., Lee, S.: Fast motion deblurring. In: ACM SIGGRAPH Asia 2009 Papers, 1–8 (2009). https://doi.org/10.1145/1618452.1618491
Xu, L., Jia, J.: Two-phase kernel estimation for robust motion deblurring. In: The European Conference on Computer Vision, pp. 157–170 (2010). Springer
Perrone, D., Favaro, P.: A clearer picture of total variation blind deconvolution. IEEE Trans. Pattern Anal. Mach. Intell. 38(6), 1041–1055 (2015). https://doi.org/10.1109/TPAMI.2015.2477819
Kotera, J., Šroubek, F., Milanfar, P.: Blind deconvolution using alternating maximum a posteriori estimation with heavy-tailed priors. In: Computer Analysis of Images and Patterns, pp. 59–66 (2013). Springer
Almeida, M.S., Almeida, L.B.: Blind and semi-blind deblurring of natural images. IEEE Trans. Image Process. 19(1), 36–52 (2009). https://doi.org/10.1109/TIP.2009.2031231
Krishnan, D., Tay, T., Fergus, R.: Blind deconvolution using a normalized sparsity measure. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 233–240 (2011). IEEE
Perrone, D., Favaro, P.: A logarithmic image prior for blind deconvolution. Int. J. Comput. Vis 117(2), 159–172 (2016)
Zuo, W., Ren, D., Zhang, D., Gu, S., Zhang, L.: Learning iteration-wise generalized shrinkage-thresholding operators for blind deconvolution. IEEE Trans. Image Process. 25(4), 1751–1764 (2016). https://doi.org/10.1109/TIP.2016.2531905
Xu, L., Zheng, S., Jia, J.: Unnatural l0 sparse representation for natural image deblurring. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1107–1114 (2013)
Pan, J., Su, Z.: Fast l0-regularized kernel estimation for robust motion deblurring. IEEE Signal Process. Lett. 20(9), 841–844 (2013). https://doi.org/10.1109/LSP.2013.2261986
Pan, J., Hu, Z., Su, Z., Yang, M.-H.: Deblurring text images via l0-regularized intensity and gradient prior. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2901–2908 (2014)
Pan, J., Sun, D., Pfister, H., Yang, M.-H.: Blind image deblurring using dark channel prior. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp 1628–1636 (2016)
Yan, Y., Ren, W., Guo, Y., Wang, R., Cao, X.: Image deblurring via extreme channels prior. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 4003–4011 (2017)
Wen, F., Ying, R., Liu, Y., Liu, P., Truong, T.-K.: A simple local minimal intensity prior and an improved algorithm for blind image deblurring. IEEE Trans. Circuits Syst. Video Technol. 31(8), 2923–2937 (2020). https://doi.org/10.1109/TCSVT.2020.3034137
Chen, L., Fang, F., Wang, T., Zhang, G.: Blind image deblurring with local maximum gradient prior. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1742–1750 (2019)
Liu, J., Yan, M., Zeng, T.: Surface-aware blind image deblurring. IEEE Trans. Pattern Anal. Mach. Intell. 43(3), 1041–1055 (2019). https://doi.org/10.1109/tpami.2019.2941472
Zhang, M., Fang, Y., Ni, G., Zeng, T.: Pixel screening based intermediate correction for blind deblurring. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 5892–5900 (2022)
Shao, W.-Z.: Revisiting the regularizers in blind image deblurring with a new one. IEEE Trans. Image Process. (2023). https://doi.org/10.1109/TIP.2023.3280358
Ren, D., Zhang, K., Wang, Q., Hu, Q., Zuo, W.: Neural blind deconvolution using deep priors. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3341–3350 (2020)
Tran, P., Tran, A.T., Phung, Q., Hoai, M.: Explore image deblurring via encoded blur kernel space. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 11956–11965 (2021)
Chen, M., Quan, Y., Xu, Y., Ji, H.: Self-supervised blind image deconvolution via deep generative ensemble learning. IEEE Trans. Circuits Syst. Video Technol. 33(2), 634–647 (2022). https://doi.org/10.1109/TCSVT.2022.3207279
Bredell, G., Erdil, E., Weber, B., Konukoglu, E.: Wiener guided dip for unsupervised blind image deconvolution. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3047–3056 (2023)
Li, J., Wang, W., Nan, Y., Ji, H.: Self-supervised blind motion deblurring with deep expectation maximization. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 13986–13996 (2023)
Zhuang, Z., Li, T., Wang, H., Sun, J.: Blind image deblurring with unknown kernel size and substantial noise. Int. J. Comput. Vis. 132(2), 319–348 (2024)
Zhang, M., Yang, Y., Ni, G., Wu, T., Zeng, T.: Self-supervised multi-scale neural network for blind deblurring. Inverse Problems Imaging 18(3), 623–641 (2024). https://doi.org/10.3934/ipi.2023046
Yu, X., Luo, X., Luo, S., Huang, Y.: A regularized restoration model based on geometrical features and noise evaluation. In: International Conference on Signal Processing, pp. 1016–1021 (2014). IEEE
Zhong, Q., Li, Y., Yang, Y., Duan, Y.: Minimizing discrete total curvature for image processing. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 9474–9482 (2020)
Lai, W., Huang, J., Hu, Z., Ahuja, N., Yang, M.: A comparative study for single image blind deblurring. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1701–1709 (2016)
Michaeli, T., Irani, M.: Blind deblurring using internal patch recurrence. In: Lecture Notes in Computer Science, pp. 783–798 (2014)
Köhler, R., Hirsch, M., Mohler, B., Schölkopf, B., Harmeling, S.: Recording and playback of camera shake: Benchmarking blind deconvolution with a real-world database. In: The European Conference on Computer Vision, pp. 27–40 (2012)
Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: Understanding and evaluating blind deconvolution algorithms. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1964–1971 (2009)
Shan, Q., Jia, J., Agarwala, A.: High-quality motion deblurring from a single image. ACM Trans. Graph. 27(3), 1–10 (2008). https://doi.org/10.1145/1360612.1360672
Whyte, O., Sivic, J., Zisserman, A.: Deblurring shaken and partially saturated images. Int. J. Comput. Vis. 110, 185–201 (2014)
Acknowledgements
The research is supported by the Natural Science Foundation of Inner Mongolia Autonomous Region (2024MS01002) and the network information center of Inner Mongolia University.
Author information
Authors and Affiliations
Contributions
Lulu Zhang wrote the main content of the paper, and Professors Qiyu Jin, Guoliang Zhao, and Caiying Wu revised the paper.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
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
Zhang, L., Jin, Q., Zhao, G. et al. Blind image deblurring based on adaptive redescending potential function and local patch fidelity term. SIViP 18, 8847–8857 (2024). https://doi.org/10.1007/s11760-024-03512-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-024-03512-7