Abstract
Single image deblurring is a typical ill-posed problem. Although a lot of effective algorithms have been proposed, there is a lack of blind evaluation metrics for the perceptual quality of deblurred images. In this paper, we introduce a new, low-cost and lightweight dataset, called Deblurred image Quality Assessment (DeblurQA). Next, we design an extendable model named DeBlurred Quality Assessment NETwork (DBQA-NET) based on multi-resolution deep feature aggregation, and train it by a two-stage training method of classification combined with quality prediction, along with a joint loss function of ranking and regression. Finally, we demonstrate the superiority of the method and show that it can assist the existing deblurring algorithms: in the hyperparameter selection experiment, it can find the best and worst results that match human perception; when applied to the training of deep-learning-based methods, it can significantly improve the abnormal results. The model, code and the dataset are available at https://github.com/weidelongdongqiang/deblurQA/tree/IQA.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Pan, J., Liu, R., Su, Z., Gu, X.: Kernel estimation from salient structure for robust motion deblurring. Signal Process. Image Commun. 28(9), 1156–1170 (2013)
Kupyn, O., Budzan, V., Mykhailych, M., Mishkin, D., Matas, J.: DeblurGAN: blind motion deblurring using conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8183–8192 (2018)
Pan, J., Sun, D., Pfister, H., Yang, M.H.: Blind image deblurring using dark channel prior. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1628–1636 (2016)
Zhang, L., Zhang, L., Bovik, A.C.: A feature-enriched completely blind image quality evaluator. IEEE Trans. Image Process. (TIP) 24(8), 2579–2591 (2015)
Fang, Y., Zhu, H., Zeng, Y., Ma, K., Wang, Z.: Perceptual quality assessment of smartphone photography. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3677–3686 (2020)
Li, L., Lin, W., Wang, X., Yang, G., Bahrami, K., Kot, A.C.: No-reference image blur assessment based on discrete orthogonal moments. IEEE Trans. Cybernet. 46(1), 39–50 (2015)
Zhu, H., Li, L., Wu, J., Dong, W., Shi, G.: MetaIQA: deep meta-learning for no-reference image quality assessment. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14143–14152 (2020)
Su, S., et al.: Blindly assess image quality in the wild guided by a self-adaptive hyper network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3667–3676 (2020)
Michaeli, T., Irani, M.: Blind deblurring using internal patch recurrence. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 783–798. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10578-9_51
Ren, D., Zhang, K., Wang, Q., Hu, Q., Zuo, W.: Neural blind deconvolution using deep priors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3341–3350 (2020)
Zhang, X., Dong, H., Hu, Z., Lai, W.S., Wang, F., Yang, M.H.: Gated fusion network for joint image deblurring and super-resolution. In: 29th British Machine Vision Conference (BMVC) (2019)
Lee, D.H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning (ICML), vol. 3, no. 2 (2013)
Ding, K., Ma, K., Wang, S., Simoncelli, E.P.: Image quality assessment: unifying structure and texture similarity. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMT) 44, 2567–2581 (2020)
Wu, J., Ma, J., Liang, F., Dong, W., Shi, G., Lin, W.: End-to-end blind image quality prediction with cascaded deep neural network. IEEE Trans. Image Process. (TIP) 29, 7414–7426 (2020)
Liu, X., van de Weijer, J., Bagdanov, A.D.: RankIQA: learning from rankings for no-reference image quality assessment. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 1040–1049 (2017)
Ma, K., Liu, W., Liu, T., Wang, Z., Tao, D.: dipIQ: blind image quality assessment by learning-to-rank discriminable image pairs. IEEE Trans. Image Process. (TIP) 26(8), 3951–3964 (2017)
Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: Efficient marginal likelihood optimization in blind deconvolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2657–2664 (2011)
Krishnan, D., Tay, T., Fergus, R.: Blind deconvolution using a normalized sparsity measure. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 233–240 (2011)
Xu, L., Zheng, S., Jia, J.: Unnatural l0 sparse representation for natural image deblurring. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1107–1114 (2013)
Kupyn, O., Martyniuk, T., Wu, J., Wang, Z.: DeblurGAN-V2: deblurring (orders-of-magnitude) faster and better. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 8878–8887 (2019)
Zhang, W., Ma, K., Yan, J., Deng, D., Wang, Z.: Blind image quality assessment using a deep bilinear convolutional neural network. IEEE Trans. Circ. Syst. Video Technol. (TCSVT) 30(1), 36–47 (2020)
Temel, D., Prabhushankar, M., AlRegib, G.: UNIQUE: unsupervised image quality estimation. IEEE Signal Process. Lett. 23(10), 1414–1418 (2016)
Wang, Z., Bovik, A.C., Sheikh, H.R., et al.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, C., Xu, C., Chen, C., Xu, C., Wei, Z. (2022). Blind Perceptual Quality Assessment for Single Image Motion Deblurring. In: Deng, W., et al. Biometric Recognition. CCBR 2022. Lecture Notes in Computer Science, vol 13628. Springer, Cham. https://doi.org/10.1007/978-3-031-20233-9_54
Download citation
DOI: https://doi.org/10.1007/978-3-031-20233-9_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20232-2
Online ISBN: 978-3-031-20233-9
eBook Packages: Computer ScienceComputer Science (R0)