Abstract
Deep generative prior (DGP) is recently proposed for image restoration and manipulation, obtaining compelling results for recovering missing semantics. In this paper, we exploit a general solution for single image deblurring using DGP as the image prior. To this end, two aspects of this object are investigated. One is modeling the process of latent image degradation, corresponding to the estimation of blur kernels in conventional deblurring methods. In this regard, a Reblur2Deblur network is proposed and trained on large-scale datasets. In this way, the proposed structure can simulate the degradation of latent sharp images. The other is encouraging deblurring results faithful to the content of latent images, and matching the appearance of blurry observations. As the generative adversarial network (GAN)-based methods often result in mismatched reconstruction, a deblurring framework with the relaxation strategy is implemented to tackle this problem. The pre-trained GAN and pre-trained ReblurNet are allowed to be fine-tuned on the fly in a self-supervised manner. Finally, we demonstrate empirically that the proposed model can perform favorably against the state-of-the-art methods.
Similar content being viewed by others
References
NAH S, SON S, LEE S, et al. NTIRE 2021 challenge on image deblurring[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 19–25, 2021, virtual. New York: IEEE, 2021: 149–165.
SUN L, CHO S, WANG J, et al. Edge-based blur kernel estimation using patch priors[C]//IEEE International Conference on Computational Photography (ICCP), April 19–21, 2013, Cambridge, MA, USA. New York: IEEE, 2013: 1–8.
WHYTE O, SIVIC J, ZISSERMAN A, et al. Non-uniform deblurring for shaken images[J]. International journal of computer vision, 2012, 98(2): 168–186.
ZHOU Y, KOMODAKIS N. A map-estimation framework for blind deblurring using high-level edge priors[C]//European Conference on Computer Vision, September 6–12, 2014, Zurich, Switzerland. Berlin, Heidelberg: Springer-Verlag, 2014: 142–157.
ULYANOV D, VEDALDI A, LEMPITSKY V. Deep image prior[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 18–23, 2018, Salt Lake City, UT, USA. New York: IEEE, 2018: 9446–9454.
REN D, ZHANG K, WANG Q, et al. Neural blind deconvolution using deep priors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 13–19, 2020, Seattle, WA, USA. New York: IEEE, 2020: 3341–3350.
PAN X G, ZHAN X H, DAI B, et al. Exploiting deep generative prior for versatile image restoration and manipulation[C]//European Conference on Computer Vision, August 23–28, 2020, Glasgow, UK. Berlin, Heidelberg: Springer-Verlag, 2020: 262–277.
LIU Z, LUO P, WANG X, et al. Deep learning face attributes in the wild[C]//Proceedings of the IEEE International Conference on Computer Vision, December 7–13, 2015, Santiago, Chile. New York: IEEE, 2015: 3730–3738.
DENG J, DONG W, SOCHER R, et al. Imagenet: a large-scale hierarchical image database[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition, June 20–25, 2009, Miami, FL, USA. New York: IEEE, 2009: 248–255.
LU B, CHEN J C, CHELLAPPA R. Unsupervised domain-specific deblurring via disentangled representations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 15–20, 2019, Long Beach, USA. New York: IEEE, 2019: 10225–10234.
DU W, CHEN H, YANG H. Learning invariant representation for unsupervised image restoration[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 13–19, 2020, Seattle, WA, USA. New York: IEEE, 2020: 14483–14492.
KUPYN O, BUDZAN V, MYKHAILYCH M, et al. Deblurgan: blind motion deblurring using conditional adversarial networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 18–23, 2018, Salt Lake City, UT, USA. New York: IEEE, 2018: 8183–8192.
LAI W S, HUANG J B, HU Z, et al. A comparative study for single image blind deblurring[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 27–30, 2016, Las Vegas, NV, USA. New York: IEEE, 2016: 1701–1709.
KRISHNAN D, TAY T, FERGUS R. Blind deconvolution using a normalized sparsity measure[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 20–25, 2011, Colorado Springs, CO, USA. New York: IEEE, 2011: 233–240.
PAN J, SUN D, PFISTER H, et al. Deblurring images via dark channel prior[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 40(10): 2315–2328.
Author information
Authors and Affiliations
Corresponding author
Additional information
This work has been supported by the National Natural Science Foundation of China (No.61273251).
Statements and Declarations
The authors declare that there are no conflicts of interest related to this article.
Rights and permissions
About this article
Cite this article
Li, Y., Wang, S. & Chen, L. Self-supervised image blind deblurring using deep generator prior. Optoelectron. Lett. 18, 187–192 (2022). https://doi.org/10.1007/s11801-022-1111-0
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11801-022-1111-0