Abstract
Recent image rescaling methods adopt invertible bijective transformations to model downscaling and upscaling simultaneously, where the high-frequency information learned in the downscaling process is used to recover the high-resolution image by inversely passing the model. However, less attention has been paid to exploiting the high-frequency information when upscaling. In this paper, an efficient end-to-end learning model for image rescaling, based on a newly designed neural network, is developed. The network consists of a downscaling generation sub-network (DSNet) and a super-resolution sub-network (SRNet), and learns to recover high-frequency signals. Concretely, we introduce dense attention blocks to the DSNet to produce the visually-pleasing low resolution (LR) image and model the distribution of the high-frequency information using a latent variable following a specified distribution. For the SRNet, we adapt an enhanced deep residual network by using residual attention blocks and adding a long skip connection, which transforms the predicted LR image and the random samples of the latent variable back during upscaling. Finally, we define a joint loss and adopt a multi-stage training strategy to optimize the whole network. Experimental results demonstrate that the superior performance of our model over existing methods in terms of both quantitative metrics and visual quality.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhang, Y., Zhao, D., Zhang, J., Xiong, R., Gao, W.: Interpolation-dependent image downsampling. IEEE Trans. Image Process. 20(11), 3291–3296 (2011)
Kim, H., Choi, M., Lim, B., Lee, K.M.: Task-aware image downscaling. In: Proceedings of the 15th European Conference Computer Vision, Munich, Germany, 8–14 September, Part IV, vol. 11208, pp. 419–434 (2018)
Li, Y., Liu, D., Li, H., Li, L., Li, Z., Wu, F.: Learning a convolutional neural network for image compactresolution. IEEE Trans. Image Process. 28(3), 1092–1107 (2019)
Sun, W., Chen, Z.: Learned image downscaling for upscaling using content adaptive resampler. IEEE Trans. Image Process. 29, 4027–4040 (2020)
Jiang, F., Tao, W., Liu, S., Ren, J., Guo, X., Zhao, D.: An end-to-end compression framework based on convolutional neural networks. IEEE Trans. Circuits Syst. Video Technol. 28(10), 3007–3018 (2018)
Fang, L., Au, O.C., Tang, K., Wen, X., Wang, H.: Novel 2-d MMSE subpixel-based image down-sampling. IEEE Trans. Circuits Syst. Video Technol. 22(5), 740–753 (2012)
Rubinstein, M., Gutierrez, D., Sorkine, O., Shamir, A.: A comparative study of image retargeting. ACM Trans. Graph. 29(6), 160 (2010)
Liu, J., He, S., Lau, R.W.H.: L0-regularized image downscaling. IEEE Trans. Image Process. 27(3), 1076–1085 (2018)
Shannon, C.E.: Communication in the presence of noise. Proc. IEEE 86(2), 447–457 (1998)
Mitchell, D.P., Netravali, A.N.: Reconstruction filters in computer-graphics. In: Proceedings of the 15th Annual Conference on Computer Graphics and Interactive Techniques, Atlanta, Georgia, USA, 1–5 August, pp. 221–228 (1988)
Schultz, R.R., Stevenson, R.L.: A Bayesian approach to image expansion for improved definition. IEEE Trans. Image Process. 3(3), 233–242 (1994)
Glasner, D., Bagon, S., Irani, M.: Super-resolution from a single image. In: Proceedings of the IEEE 12th International Conference on Computer Vision, Kyoto, Japan, 27 September–4 October, pp. 349–356 (2009)
Yang, J., Wright, J., Huang, T.S., Ma, Y.: Image super-resolution via sparse representation. IEEE Trans. Image Process. 19(11), 2861–2873 (2010)
Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295–307 (2016)
Kim, J., Lee, J.K., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June, pp. 1646–1654 (2016)
Lim, B., Son, S., Kim, H., Nah, S., Lee, K.M.: Enhanced deep residual networks for single image super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA, 21–26 July, pp. 1132–1140 (2017)
Wang, X., et al.: ESRGAN: enhanced super-resolution generative adversarial networks. In: Leal-Taixé, L., Roth, S. (eds.) ECCV 2018, Part V. LNCS, vol. 11133, pp. 63–79. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11021-5_5
Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., Fu, Y.: Image super-resolution using very deep residual channel attention networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018, Part VII. LNCS, vol. 11211, pp. 294–310. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_18
Hashemzadeh, M., Asheghi, B., Farajzadeh, N.: Content-aware image resizing: an improved and shadow-preserving seam carving method. Sig. Process. 155, 233–246 (2019)
Li, L., Tang, J., Ye, Z., Sheng, B., Mao, L., Ma, L.: Unsupervised face super-resolution via gradient enhancement and semantic guidance. Vis. Comput. 37(9–11), 2855–2867 (2021)
Liu, Y., Yang, D., Zhang, F., Xie, Q., Zhang, C.: Deep recurrent residual channel attention network for single image super-resolution. Vis. Comput. (2023)
Xiao, M., et al.: Invertible image rescaling. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part I. LNCS, vol. 12346, pp. 126–144. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_8
Li, S., Zhang, G., Luo, Z., Liu, J., Zeng, Z., Zhang, S.: Approaching the limit of image rescaling via flow guidance. In: Proceedings of 32nd British Machine Vision Conference, Online, 22–25 November, p. 13 (2021)
Liang, J., Lugmayr, A., Zhang, K., Danelljan, M., Gool, L.V., Timofte, R.: Hierarchical conditional flow: a unified framework for image super-resolution and image rescaling. In: Proceedings of IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada, 10–17 October, pp. 4056–4065 (2021)
Zhang, M., Pan, Z., Zhou, X., Kuo, C.J.: Enhancing image rescaling using dual latent variables in invertible neural network. CoRR abs/2207.11844 (2022)
Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real NVP. In: Proceedings of 5th International Conference on Learning Representations, Toulon, France, 24–26 April (2017)
Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Honolulu, HI, USA, 21–26 July, pp. 2261–2269 (2017)
Agustsson, E., Timofte, R.: NTIRE 2017 challenge on single image super-resolution: dataset and study. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA, 21–26 July, pp. 1122–1131 (2017)
Bevilacqua, M., Roumy, A., Guillemot, C., Alberi-Morel, M.: Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: Proceedings of British Machine Vision Conference, Surrey, UK, 3–7 September, pp. 1–10 (2012)
Zeyde, R., Elad, M., Protter, M.: On single image scaleup using sparse-representations. In: Proceedings of the 7th International Conference on Curves and Surfaces, Avignon, France, 24–30 June, vol. 6920, pp. 711–730 (2010)
Martin, D.R., Fowlkes, C.C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceedings of the Eighth International Conference on Computer Vision, Vancouver, British Columbia, Canada, 7–14 July, vol. 2, pp. 416–425 (2001)
Huang, J., Singh, A., Ahuja, N.: Single image super-resolution from transformed self-exemplars. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 7–12 June, pp. 5197–5206 (2015)
Acknowledgements
This work was supported by the National Natural Science Foundation of China (Project Nos. 62272164, 61402053), the Hunan Provincial Natural Science Foundation of China (Grant No. 2023JJ30050) and the Scientific Research Fund of Education Department of Hunan Province (Grant No. 21B0287).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gui, Y., Xie, Y., Kuang, L., Chen, Z., Zhang, J. (2024). Enhancing Image Rescaling Using High Frequency Guidance and Attentions in Downscaling and Upscaling Network. In: Sheng, B., Bi, L., Kim, J., Magnenat-Thalmann, N., Thalmann, D. (eds) Advances in Computer Graphics. CGI 2023. Lecture Notes in Computer Science, vol 14495. Springer, Cham. https://doi.org/10.1007/978-3-031-50069-5_35
Download citation
DOI: https://doi.org/10.1007/978-3-031-50069-5_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-50068-8
Online ISBN: 978-3-031-50069-5
eBook Packages: Computer ScienceComputer Science (R0)