Abstract
Recently, single image super-resolution (SISR) has made great progress due to the rapid development of deep convolutional neural networks (CNN), and the application of Generative Adversarial Networks (GAN ) has made super-resolution networks even more effective. However, GAN-based methods have many problems such as lengthy and unstable convergence. To solve these problems, this paper presents a mechanism that employs boundary equilibrium in the image super-resolution network to balance the convergence of the generator and the discriminator and improve the visual quality of the generated synthetic images. Furthermore, current methods often use perceptual loss based on the VGG network. However, experiments show that the visual quality improvement brought by this perceptual loss is very limited, so we propose an improved perceptual loss based on Learned Perceptual Image Patch Similarity (LPIPS) to acquire better human visual effects rather than adopting the traditional perceptual loss based on VGG. The experimental results clearly show that using our proposed method can considerably improve the performance of image super-resolution and obtain clearer details than state-of-the-arts.
Similar content being viewed by others
References
Agustsson E, Timofte R (2017) Ntire 2017 challenge on single image super-resolution: dataset and study. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 126–135
Bevilacqua M, Roumy A, Guillemot C et al (2012) Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: Proceedings of the british machine vision conference. BMVA Press, pp 135.1–135.10. https://doi.org/10.5244/C.26.135https://doi.org/10.5244/C.26.135
Chowdhuri D, SKK S, Babu MR et al (2012) Very low resolution face recognition in parallel environment. Int J Comput Sci Inform Technol 3(3):4408–4410
Dai T, Cai J, Zhang Y et al (2019) Second-order attention network for single image super-resolution. In: Conference on computer vision and pattern recognition, pp 11,057–11,066
Dong C, Loy CC, He K et al (2014) Learning a deep convolutional network for image super-resolution. In: European conference on computer vision. Springer, pp 184–199
Dong C, Loy CC, He K et al (2015) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38(2):295–307
Dong C, Loy CC, Tang X (2016) Accelerating the super-resolution convolutional neural network. In: ECCV, pp 391–407
Goodfellow IJ, Pouget-Abadie J, Mirza M et al (2014) Generative adversarial nets. In: Proceedings of the 27th international conference on neural information processing systems - vol 2 MIT Press, Cambridge, MA, USA, NIPS’14, pp 2672–2680
Huang JB, Singh A, Ahuja N (2015) Single image super-resolution from transformed self-exemplars. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 5197–5206
Jo Y, Yang S, Kim SJ (2020) Investigating loss functions for extreme super-resolution. In: 2020 IEEE/CVF conference on computer vision and pattern recognition workshops, pp 1705–1712
Johnson J, Alahi A, Fei-Fei L (2016) Perceptual losses for real-time style transfer and super-resolution. In: ECCV, pp 694–711
Kim J, Lee JK, Lee KM (2016) Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1646–1654
Ledig C, Theis L, Huszár F et al (2017) Photo-realistic single image super-resolution using a generative adversarial network. In: Conference on computer vision and pattern recognition, pp 105–114
Li Y, Xiao N, Ouyang W (2018) BEGAN: boundary equilibrium generative adversarial networks. IEEE Access 6:11,342– 11,348
Lim B, Son S, Kim H et al (2017) Enhanced deep residual networks for single image super-resolution. In: 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW), pp 1132–1140
Liu J, Zhang W, Tang Y et al (2020) Residual feature aggregation network for image super-resolution. In: Conference on computer vision and pattern recognition, pp 2356–2365
Martin D, Fowlkes C, Tal D et al (2001) A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: IEEE international conference on computer vision, IEEE, pp 416–423
Nasrollahi K, Moeslund TB (2014) Super-resolution: a comprehensive survey. Mach Vis Appl 25(6):1423–1468
Niu B, Wen W, Ren W et al (2020) Single image super-resolution via a holistic attention network. In: ECCV, pp 191–207
Radford A, Metz L, Chintala S (2015) Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:151106434
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention, pp 234–241
Shi W, Caballero J, Huszár F et al (2016) Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1874–1883
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:14091556
Wang X, Yu K, Wu S et al (2019) ESRGAN: enhanced super-resolution generative adversarial networks. In: ECCV 2018 workshops, pp 63–79
Xu J, Chae Y, Stenger B et al (2018) Dense bynet: residual dense network for image super resolution. In: 2018 25th IEEE international conference on image processing (ICIP). IEEE, pp 71-75
Zeyde R, Elad M, Protter M (2012) On single image scale-up using sparse-representations. In: Curves and surfaces, Berlin, Heidelberg, pp 711–730
Zhang J, Jia K, Jia J et al (2018a) An improved approach to infer protein-protein interaction based on a hierarchical vector space model. Bmc Bioinformatics 19(1):161
Zhang R, Isola P, Efros AA et al (2018b) The unreasonable effectiveness of deep features as a perceptual metric. Proc IEEE Comput Society Conf Comput Vis Pattern Recognit, (1):586–595
Zhang Y, Li K, Li K et al (2018c) Image super-resolution using very deep residual channel attention networks. In: ECCV, pp 294–310
Acknowledgements
This work has been supported by the Natural Science Foundation of Shandong Province (No. ZR2019MF011), and the Postdoctoral Science Foundation of China (No. 2017M622210). We also gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan V used for this research.
Author information
Authors and Affiliations
Corresponding author
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 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, Z., Lu, W., Chen, S. et al. Boundary equilibrium SR: effective loss functions for single image super-resolution. Appl Intell 53, 17128–17138 (2023). https://doi.org/10.1007/s10489-022-04162-3
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-04162-3