Abstract
Deep neural networks with attention mechanism for super-resolution (SR) have achieved good SR performance by focusing on the high-frequency components of images. However, during the SR process, it is difficult for these networks to obtain multi-level high-frequency features with different extraction difficulties from low-resolution images, resulting in the lack of textures and details in the reconstructed SR images. To solve this problem, we propose an attention hierarchical network (AHN) for SR. The proposed AHN separates and extracts high-frequency features with different extraction difficulties in a hierarchical way to obtain multi-level high-frequency features. In the process of separation and extraction, we separate high-frequency features into easy-to-extract features and difficult-to-extract features by attention block and extract the separated features by dense-residual module. Extensive experiments demonstrate that the proposed AHN is superior to the state-of-the-art SR methods and reconstructs better SR images that contain more textures and details.
Similar content being viewed by others
Data availability
Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.
References
Agustsson E, Ntire TR (2017) 2017 challenge on single image super-resolution: Dataset and study. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 126–135
Anwar S, Khan S, Barnes N (2020) A deep journey into super-resolution: A survey. ACM Comput Surv 53(3):1–34. https://doi.org/10.1145/3390462
Bevilacqua M, Roumy A, Guillemot C et al (2012) Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: Proceedings of the 23rd British Machine Vision Conference pp 1–10
Chen Y C, Li L, Yu L et al (2020) Uniter: Universal image-text representation learning. In: Proceedings of the European Conference on Computer Vision. Springer, pp 104–120
Chen L, Zhang H, Xiao J, et al (2017) Sca-cnn: Spatial and channel-wise attention in convolutional networks for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 5659–5667
Choi J S, Kim M (2017) A deep convolutional neural network with selection units for super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 154–160
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. https://doi.org/10.1109/TPAMI.2015.2439281
Dong C, Loy CC, Tang X et al (2016) Accelerating the Super-Resolution Convolutional Neural Network. In: Proceeding of the European Conference on Computer Vision. Springer, pp 391–407
Garcia-Garcia JM, Lozano MD, Penichet VM et al (2022) Building a three-level multimodal emotion recognition framework. Multimedia Tools and Applications 1–31. https://doi.org/10.1007/s11042-022-13254-8
Guo K, Guo H, Ren S et al (2020) Towards efficient motion-blurred public security video super-resolution based on back-projection networks. J Netw Comput Appl 166:102691. https://doi.org/10.1016/j.jnca.2020.102691
Hu Y, Gao X, Li J et al (2021) Single image super-resolution with multi-scale information cross-fusion network. Signal Process 179:107831. https://doi.org/10.1016/j.sigpro.2020.107831
Hu H, Gu J, Zhang Z et al (2018) Relation networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 3588–3597
Hu Y, Li J, Huang Y et al (2019) Channel-wise and spatial feature modulation network for single image super-resolution. IEEE Trans Circuits Syst Video Technol 30(11):3911–3927. https://doi.org/10.1109/TCSVT.2019.2915238
Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 7132–7141
Huang JB, Singh A, Ahuja N (2015) Single image super-resolution from transformed self-exemplars. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 5197–5206
Kim JH, Choi JH, Cheon M et al (2018) Ram: Residual attention module for single image super-resolution. arXiv:1811.12043
Kim J, Lee JK, Lee KM et al (2016) Deeply-Recursive Convolutional Network for Image Super-Resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 1637–1645
Kim J, Lee JK, Lee KM et al (2016) Accurate Image Super-Resolution Using Very Deep Convolutional Networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 1646–1654
Kingma D P, Ba J (2014) Adam: A method for stochastic optimization. arXiv:14126980
Lai WS, Huang JB, Ahuja N et al (2017) Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 5835–5843
Ledig C, Theis L, Huszár F et al (2017) Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 4681–4690
Lin Z, Feng M, Santos CND et al (2017) A structured self-attentive sentence embedding. arXiv:1703.03130
Liu H, Gu Y (2022) Deep Joint Estimation Network for Satellite Video Super-Resolution With Multiple Degradations. IEEE Trans Geosci Remote Sens 60:1–15. https://doi.org/10.1109/TGRS.2022.3163790
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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 416–423
Shi W, Caballero J, Huszar 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. IEEE, pp 1874–1883
Song Z, Zhao X, Hui Y et al (2021) Progressive back-projection network for COVID-CT super-resolution. Computer Methods and Programs in Biomedicine 106193. https://doi.org/10.1016/j.cmpb.2021.106193
Song Z, Zhao X, Hui Y et al (2022) Fusing Attention Network based on Dilated Convolution for Super Resolution. IEEE Trans Cogn Dev Syst. https://doi.org/10.1109/TCDS.2022.3153090
Song Z, Zhao X, Jiang H (2021) Gradual deep residual network for super-resolution. Multimed Tools Appl 80(7):9765–9778. https://doi.org/10.1007/s11042-020-10152-9
Tai Y, Yang J, Liu X et al (2017) Memnet: A persistent memory network for image restoration. In: Proceedings of the IEEE International Conference on Computer Vision. IEEE, pp 4539–4547
Tai Y, Yang J, Liu X (2017) Image super-resolution via deep recursive residual network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 3147–3155
Tong T, Li G, Liu X et al (2017) Image super-resolution using dense skip connections. In: Proceedings of the IEEE International Conference on Computer Vision. IEEE, pp 4799–4807
Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. arXiv:1706.03762
Wang Z, Bovik AC, Sheikh HR et al (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612. https://doi.org/10.1109/TIP.2003.819861
Wang Z, Chen J, Hoi SCH (2020) Deep Learning for Image Super-resolution: A Survey. IEEE Trans Pattern Anal Mach Intell 43(10):3365–3387. https://doi.org/10.1109/TPAMI.2020.2982166
Wang X, Yu K, Dong C et al (2018) Recovering realistic texture in image super-resolution by deep spatial feature transform. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 606–615
Wang X, Yu K, Wu S et al (2018) Esrgan: Enhanced super-resolution generative adversarial networks. In: Proceedings of the European Conference on Computer Vision. Springer, pp 1–10
Wei D, Wang Z (2022) Channel rearrangement multi-branch network for image super-resolution. Digital Signal Process 120:103254. https://doi.org/10.1016/j.dsp.2021.103254
Yang J, Wright J, Huang TS et al (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19(11):2861–2873. https://doi.org/10.1109/TIP.2010.2050625
Zeyde R, Elad M, Protter M et al (2010) On single image scale-up using sparse-representations. In: International Conference on Curves and Surfaces. Springer, pp 711–730
Zhang H, Goodfellow I, Metaxas D et al (2019) Self-attention generative adversarial networks. In: International Conference on Machine Learning. IEEE, pp 7354–7363
Zhang Y, Li K, Li K et al (2018) Image super-resolution using very deep residual channel attention networks. In: Proceedings of the European Conference on Computer Vision. Springer, pp 286–301
Zhang Y, Tian Y, Kong Y et al (2018) Residual dense network for image super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 2472–2481
Acknowledgements
This work is supported by the National Key R&D Program (2020YFB1713600), the National Natural Science Foundation of China (61763029), the Science and Technology Program of Gansu Province (21YF5GA072, 21JR7RA206), the Education Industry Support Program of Gansu Provincial Department (2021CYZC-02), and the Natural Science Foundation of Gansu Province (21JR7RA206).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interests
The authors declare that they have no conflict of interests.
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
Song, Z., Zhao, X., Hui, Y. et al. Attention hierarchical network for super-resolution. Multimed Tools Appl 82, 46351–46369 (2023). https://doi.org/10.1007/s11042-023-15782-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15782-3