Abstract
Blind image super-resolution (Blind-SR) is the process of leveraging a low-resolution (LR) image, with unknown degradation, to generate its high-resolution (HR) version. Most of the existing blind SR techniques use a degradation estimator network to explicitly estimate the blur kernel to guide the SR network with the supervision of ground truth (GT) kernels. To solve this issue, it is necessary to design an implicit estimator network that can extract discriminative blur kernel representation without relying on the supervision of ground-truth blur kernels. We design a lightweight (LBKENet) approach for blind super-resolution (Blind-SR) that estimates the blur kernel and restores the HR image based on a deep convolutional neural network (CNN) and a deep super-resolution residual convolutional generative adversarial network. Since the blur kernel for blind image SR is unknown, following the image formation model of the blind super-resolution problem, we first introduce a neural network-based model to estimate the blur kernel. This is achieved by (i) a Super Resolver that, from a low-resolution input, generates the corresponding SR image; and (ii) an Estimator Network generating the blur kernel from the input datum. The output of both models is used in a novel loss formulation. The proposed network is end-to-end trainable. The methodology proposed is substantiated by both quantitative and qualitative experiments. Results on benchmarks demonstrate that our computationally efficient approach (12\(\times \) fewer parameters than the state-of-the-art models) performs favorably with respect to approaches that have less number of parameters and can be used on devices with limited computational capabilities.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Agustsson, E., Timofte, R.: Ntire 2017 challenge on single image super-resolution: dataset and study. In: IEEE CVPRW, pp. 126–135 (2017)
Ahn, N., Kang, B., Sohn, K.A.: Fast, accurate, and lightweight super-resolution with cascading residual network. In: ECCV, pp. 252–268 (2018)
Bansal, V., Foresti, G.L., Martinel, N.: Cloth-changing person re-identification with self-attention. In: WACVW, pp. 602–610 (2022)
Bell-Kligler, S., Shocher, A., Irani, M.: Blind super-resolution kernel estimation using an internal-gan. In: NeurIPS, vol. 32 (2019)
Bevilacqua, M., Roumy, A., Guillemot, C., Alberi-Morel, M.L.: Low-complexity single-image super-resolution based on nonnegative neighbor embedding (2012)
Bhat, G., et al.: Ntire 2021. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 613–626 (2021)
Bhat, G., Danelljan, M., Timofte, R., et al.: NTIRE 2021 challenge on burst super-resolution: methods and results. In: CVPRW (2021)
Dunnhofer, M., Martinel, N., Micheloni, C.: Improving MRI-based knee disorder diagnosis with pyramidal feature details. In: International Conference on Medical Imaging with Deep Learning, vol. 143, pp. 131–147. PMLR (2021)
Dunnhofer, M., Martinel, N., Micheloni, C.: Weakly-supervised domain adaptation of deep regression trackers via reinforced knowledge distillation. IEEE Rob. Autom. Let. 6(3), 5016–5023 (2021)
Figueiredo, M., Bioucas-Dias, J.M., Nowak, R.D.: Majorization-minimization algorithms for wavelet-based image restoration. IEEE Trans. Image Process. 16(12), 2980–2991 (2007)
Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139–144 (2020)
Gu, J., Lu, H., Zuo, W., Dong, C.: Blind super-resolution with iterative kernel correction. In: IEEE/CVF CVPR, pp. 1604–1613 (2019)
Haris, M., Shakhnarovich, G., Ukita, N.: Deep back-projection networks for super-resolution. In: IEEE, pp. 1664–1673 (2018)
Huang, J.B., Singh, A., Ahuja, N.: Single image super-resolution from transformed self-exemplars. In: CVPR, pp. 5197–5206 (2015)
Huang, S., Teo, R., Leong, W., Martinel, N., Foresti, G.L., Micheloni, C.: Coverage control of multiple unmanned aerial vehicles: a short review. Unmanned Syst. 6(2), 131–144 (2018)
Kim, J., Lee, J.K., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks. In: IEEE CVPR, pp. 1646–1654 (2016)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. ar**v preprint ar**v:1412.6980 (2014)
Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: IEEE CVPR, pp. 4681–4690 (2017)
Lefkimmiatis, S.: Universal denoising networks: a novel cnn architecture for image denoising. In: IEEE CVPR, pp. 3204–3213 (2018)
Leong, W.L., Martinel, N., Huang, S., Micheloni, C., Foresti, G.L., Teo, R.S.H.: An intelligent auto-organizing aerial robotic sensor network system for urban surveillance. J. Intell. Rob. Syst. 102(2), 33 (2021)
Liang, J., Zhang, K., Gu, S., Van Gool, L., Timofte, R.: Flow-based kernel prior with application to blind super-resolution. In: IEEE/CVF CVPR, pp. 10601–10610 (2021)
Liu, X., Tanaka, M., Okutomi, M.: Single-image noise level estimation for blind denoising. IEEE TIP 22(12), 5226–5237 (2013)
Lugmayr, A., Danelljan, M., Timofte, R.: NTIRE 2020 challenge on real-world image super-resolution: methods and results. In: CVPRW (2020)
Luo, Z., Huang, Y., Li, S., Wang, L., Tan, T.: Unfolding the alternating optimization for blind super resolution. In: NeurIPS, vol. 33 (2020)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: ICCV, vol. 2, pp. 416–423. IEEE (2001)
Martinel, N., Dunnhofer, M., Foresti, G.L., Micheloni, C.: Person re-identification via unsupervised transfer of learned visual representations. In: Proceedings of the 11th International Conference on Distributed Smart Cameras, pp. 151–156. ACM (2017)
Martinel, N., Dunnhofer, M., Pucci, R., Foresti, G.L., Micheloni, C.: Lord of the rings: hanoi pooling and self-knowledge distillation for fast and accurate vehicle reidentification. IEEE Trans. Ind. Inf. 18(1), 87–96 (2022)
Martinel, N., Foresti, G.L., Micheloni, C.: Deep pyramidal pooling with attention for person re-identification. IEEE Trans. Image Process. 29, 7306–7316 (2020)
Martinel, N., Micheloni, C., Foresti, G.L.: A pool of multiple person re-identification experts. Pattern Recogn. Lett. 71, 23–30 (2016)
Matsui, Y., et al.: Sketch-based manga retrieval using manga109 dataset. Multimedia Tools Appl. 76(20), 21811–21838 (2017)
Michaeli, T., Irani, M.: Nonparametric blind super-resolution. In: IEEE ICCV, pp. 945–952 (2013)
Muhammad Umer, R., Luca Foresti, G., Micheloni, C.: Deep iterative residual convolutional network for single image super-resolution. In: ICPR (2021)
Umer, R.M., Micheloni, C.: Deep cyclic generative adversarial residual convolutional networks for real image super-resolution. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12537, pp. 484–498. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-67070-2_29
Shocher, A., Cohen, N., Irani, M: “Zero-shot” super-resolution using deep internal learning. In: IEEE CVPR, pp. 3118–3126 (2018)
Soh, J.W., Cho, S., Cho, N.I.: Meta-transfer learning for zero-shot super-resolution. In: IEEE/CVF CVPR, pp. 3516–3525 (2020)
Timofte, R., Agustsson, E., Van Gool, L., Yang, M.H., Zhang, L.: Ntire 2017 challenge on single image super-resolution: methods and results. In: CVPRW, pp. 114–125 (2017)
Umer, R.M., Foresti, G.L., Micheloni, C.: Deep super-resolution network for single image super-resolution with realistic degradations. In: ICDSC, pp. 21:1–21:7 (2019)
Umer, R.M., Foresti, G.L., Micheloni, C.: Deep generative adversarial residual convolutional networks for real-world super-resolution. In: IEEE/CVF CVPRW, pp. 438–439 (2020)
Umer, R.M., Micheloni, C.: Rbsricnn: raw burst super-resolution through iterative convolutional neural network. ar**v preprint ar**v:2110.13217 (2021)
Umer, R.M., Micheloni, C.: Real image super-resolution using gan through modeling of lr and hr process. In: AVSS, pp. 1–8. IEEE (2022)
Umer, R.M., Munir, A., Micheloni, C.: A deep residual star generative adversarial network for multi-domain image super-resolution. In: SpliTech, pp. 01–05. IEEE (2021)
Wang, L., Wang, Y., Dong, X., Xu, Q., Yang, J., An, W., Guo, Y.: Unsupervised degradation representation learning for blind super-resolution. In: IEEE/CVF CVPR, pp. 10581–10590 (2021)
Wang, X., et al.: Esrgan: enhanced super-resolution generative adversarial networks. In: ECCVW (2018)
Wei, P., Lu, H., Timofte, R., Lin, L., Zuo, W., et al.: AIM 2020 challenge on real image super-resolution: methods and results. In: ECCVW (2020)
Zeyde, R., Elad, M., Protter, M.: On single image scale-up using sparse-representations. In: Boissonnat, J.-D., Chenin, P., Cohen, A., Gout, C., Lyche, T., Mazure, M.-L., Schumaker, L. (eds.) Curves and Surfaces 2010. LNCS, vol. 6920, pp. 711–730. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-27413-8_47
Zhang, K., et al.: AIM 2020 challenge on efficient super-resolution: methods and results. In: ECCVW, pp. 5–40 (2020)
Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: IEEE CVPR, pp. 586–595 (2018)
Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., Fu, Y.: Image super-resolution using very deep residual channel attention networks. In: ECCV, pp. 286–301 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Khan, A.H., Umer, R.M., Dunnhofer, M., Micheloni, C., Martinel, N. (2023). LBKENet:Lightweight Blur Kernel Estimation Network for Blind Image Super-Resolution. In: Foresti, G.L., Fusiello, A., Hancock, E. (eds) Image Analysis and Processing – ICIAP 2023. ICIAP 2023. Lecture Notes in Computer Science, vol 14234. Springer, Cham. https://doi.org/10.1007/978-3-031-43153-1_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-43153-1_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43152-4
Online ISBN: 978-3-031-43153-1
eBook Packages: Computer ScienceComputer Science (R0)