Abstract
Recent research on image super-resolution (SR) task has greatly progressed with the development of convolutional neural networks (CNNs). Most previous studies with single-scale feature enhance expressiveness by increasing network depth. However, most of them do not adequately extract and utilize multi-scale features. In this paper, we propose a novel residual aggregation U-shaped network (RAU), which fully utilizes multi-scale features to help reconstruct high-quality images. First, we use progressive downsampling structure to obtain multi-scale features and capture context information, and use progressive upsampling structure to fuse multi-scale features and fill detail texture. Second, we introduce auxiliary supervision in the middle layer to provide additional regularization and accelerate the convergence speed. Third, we propose a lightweight model for our network, and we replace the traditional convolution with the Ghost module in multiple locations of network. Extensive experiments on the challenge datasets confirmed the effectiveness of the proposed network. Our algorithm can restore high-quality high-resolution (HR) images and outperform other methods by a large margin.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-14875-3/MediaObjects/11042_2023_14875_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-14875-3/MediaObjects/11042_2023_14875_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-14875-3/MediaObjects/11042_2023_14875_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-14875-3/MediaObjects/11042_2023_14875_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-14875-3/MediaObjects/11042_2023_14875_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-14875-3/MediaObjects/11042_2023_14875_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-14875-3/MediaObjects/11042_2023_14875_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-14875-3/MediaObjects/11042_2023_14875_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-14875-3/MediaObjects/11042_2023_14875_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-14875-3/MediaObjects/11042_2023_14875_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-14875-3/MediaObjects/11042_2023_14875_Fig11_HTML.png)
Similar content being viewed by others
Data availability
The datasets analysed during the current study are available from the corresponding author on reasonable request.
References
Agustsson E, Timofte R (2017) NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study.
Ahn N, Kang B, Sohn KA (2018) Fast, accurate, and lightweight super-resolution with cascading residual network
Chao D, Chen CL, He K, Tang X (2014) Learning a deep convolutional network for image super-resolution
Chao D, Chen CL, Tang X (2016) Accelerating the super-resolution convolutional neural network
Choi JH, Kim JH, Cheon M, Lee JS (2021) Volatile-Nonvolatile Memory Network for Progressive Image Super-Resolution. IEEE Access PP(99):1–1
Chollet F (2017) Xception: deep learning with Depthwise separable convolutions
Dai T, Cai J, Zhang Y, **a ST, Zhang L (2019) Second-order attention network for single image super-resolution
Ding X, Guo Y, Ding G, Han J (2019) ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks
Guo Y et al. (2020) Closed-loop matters: dual regression networks for single image super-resolution
Guo Y et al. (2020) Closed-loop matters: Dual regression networks for single image super-resolution. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 5407–5416
Han K, Wang Y, Tian Q, Guo J, Xu C (2020) GhostNet: more features from cheap operations
Haris M, Shakhnarovich G, Ukita N (2018) Deep Back-projection networks for super-resolution’, ar**v
Hu X, Naiel MA, Wong A, Lamm M, Fieguth P (2019) RUNet: A robust UNet architecture for image super-resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. pp. 0–0
Huang JB, Singh A, Ahuja N (2015) Single image super-resolution from transformed self-exemplars
Kim J, Lee JK, Lee KM (2016) Accurate image super-resolution using very deep convolutional networks
Kim J, Lee JK, Lee K M (2016) Deeply-recursive convolutional network for image super-resolution
Lai WS, Huang JB, Ahuja N, Yang MH (2017) Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution. In: IEEE Conference on Computer Vision & Pattern Recognition. pp. 5835–5843
Ledig C et al. (2016) Photo-realistic single image super-resolution using a generative adversarial network. IEEE Comput. Soc.
Li Z, Yang J, Liu Z, Yang X, Wu W (2019) Feedback network for image super-resolution. IEEE
Li C, Cong R, Kwong S, Hou J, Huang Q (2020) ASIF-Net: Attention Steered Interweave Fusion Network for RGB-D Salient Object Detection. IEEE Trans Cybern PP(99):1–13
Lim B, Son S, Kim H, Nah S, Lee KM (2017) Enhanced deep residual networks for single image super-resolution
Liu J, Zhang W, Tang Y, Tang J, Wu G (2020) Residual feature aggregation network for image super-resolution
Liu J, Zhang W, Tang Y, Tang J, Wu G (2020) Residual feature aggregation network for image super-resolution
Lu Z, Chen Y (2021) Single image super-resolution based on a modified U-net with mixed gradient loss. Sig Image Video Proc:1–9
Martin D, Fowlkes C, Tal D, Malik J (2002) A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
Odena A, Dumoulin V, Olah C (2016) Deconvolution and Checkerboard Artifacts, Distill. https://doi.org/10.23915/distill.00003
Qin X, Zhang Z, Huang C, Dehghan M, Jagersand M (2020) U2-net: going deeper with nested U-structure for salient object detection. Pattern Recogn 106:107404
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation
Shi W et al. (2016) Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network. https://doi.org/10.1109/CVPR.2016.207
Tian C et al. (2020) Lightweight image super-resolution with enhanced CNN. Knowl.-Based Syst.
Tian C, Xu Y, Zuo W, Lin CW, Zhang D (2021) Asymmetric CNN for Image Superresolution. IEEE Trans Syst Man Cybern Syst PP(99):1–13
Tong T, Li G, Liu X, Gao Q (2017) Image super-resolution using dense skip connections
Wang L, Dong X, Wang Y, Ying X, Guo Y (2020) ‘Exploring sparsity in image super-resolution for efficient inference (CVPR’2021)
Wang X, Zheng Z, He Y, Yan F, Zeng Z, Yang Y (2021) Soft person reidentification network pruning via blockwise adjacent filter decaying. IEEE Trans. Cybern
Zeyde R, Elad M, Protter M (2010) On single image scale-up using sparse-representations’, Int. Conf. Curves Surf.
Zhang T, Qi GJ, **ao B, Wang J (2017) Interleaved group convolutions for deep neural networks
Zhang Y, Tian Y, Kong Y, Zhong B, Fu Y (2018) Residual dense network for image super-resolution. IEEE
Zhang Y, Sun Y, Liu S (2021) Deformable and residual convolutional network for image super-resolution. Appl Intell:1–10
Zhang Y, Wang H, Qin C, Fu Y (2021) Aligned structured sparsity learning for efficient image super-resolution. Adv Neural Inf Proces Syst 34:2695–2706
Bevilacqua M, Roumy A, Guillemot C, Morel A (2012) ‘Low-complexity single image super-resolution based on nonnegative neighbor embedding’, bmvc
Acknowledgements
This work was supported by the Tian** Key Laboratory of Optoelectronic Detection Technology and System Open Project[2019LODTS006]. The authors also acknowledge the anonymous reviewers for their helpful comments on the manuscript.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interest.
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 (e.g. a society or other partner) 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
Yang, Z., Yuan, P., Zhang, Y. et al. Residual aggregation U-shaped network for image super-resolution. Multimed Tools Appl 83, 58141–58158 (2024). https://doi.org/10.1007/s11042-023-14875-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-14875-3