ABSTRACT
In this paper, we present a compact and accurate super-resolution algorithm using the attention-augmented convolutional neural network, which can exploit and weight hierarchical features at multiple scales and levels to improve learning capability. The proposed network employs cascading U-net structure to allow the flow of low-frequency information to focus on learning high- and mid-level features. In addition, deep hierarchical channel attention is developed to help in learning from high-level complex features. Moreover, we propose a hierarchical pyramid attention to learn the inter and intra-level dependencies between the feature maps. Furthermore, the comprehensive quantitative and qualitative experiments on low-resolution and real image benchmark datasets illustrate that our algorithm performs favorably against the state-of-the-art methods.
- Chen R., Jia H. Z., Xie X. D., Gao W. 2015. Robust image/video super-resolution display. in Proc. ACM Symposium on Virtual Reality Software & Technology.Google ScholarDigital Library
- Chen R., Jia H. Z., Xie X. D., Gao W. 2017. Blind restoration for nonuniform aerial images using nonlocal Retinex model and shearlet-based higher-order regularization. J. Electronic Imaging, 26, 3, 1--18.Google ScholarCross Ref
- X. Li and M. T. Orchard, "New edge-directed interpolation," IEEE Trans. Image Process., vol. 10, no. 10, pp. 1521--1527, Oct. 2001.Google Scholar
- Zhang L., Wu X. 2006. An edge-guided image interpolation algorithm via directional filtering and data fusion. IEEE Trans. Image Process., 15, 8, 2226--2238.Google ScholarDigital Library
- Marquina A., Osher S. J. 2008. Image super-resolution by TV regularization and bregman iteration. J. Sci. Comput., 37, 3, 367--382.Google ScholarDigital Library
- Timofte R., De Smet V., Van Gool L. 2014. A+: Adjusted anchored neighborhood regression for fast super-resolution," in Proc. IEEE Asian Conf. Comput. Vis.Google Scholar
- Yang J., Wright J., Huang T. S., Ma Y. 2010. Image super-resolution via sparse representation. IEEE Trans. Image Process., 19, 11, 2861--2873.Google ScholarDigital Library
- Freeman W., Jones T., Pasztor E., 2002. Example-based super-resolution," IEEE Comput. Graph. Appl., 22, 2, 56--65.Google ScholarDigital Library
- Dong C., Loy C. C., He K., Tang X. 2016. Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell., 38, 2, 295--307.Google ScholarDigital Library
- Dong C., Loy C. C., He K., Tang X. 2016. Accelerating the super-resolution convolutional neural network. in Proc. European Conference on Computer Vision (ECCV).Google ScholarCross Ref
- Kim J., Lee J., Lee K. 2016. Accurate image superresolution using very deep convolutional networks," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR).Google Scholar
- Shi W., Caballero J., Huszár F., Totz J., Aitken A. P., Bishop R., Rueckert D., Wang Z. 2016. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR).Google ScholarCross Ref
- Tong T., Li G., Liu X., Gao Q. 2017. Image super-resolution using dense skip connections," in Proc. IEEE Int. Conf. Comput. Vis. (ICCV).Google Scholar
- Lim B., Son S., Kim H., Nah S., Lee K. M. 2017. Enhanced deep residual networks for single image super-resolution," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW).Google Scholar
- Zhang Y., Tian Y., Kong Y., Zhong B., Fu Y. 2018. Residual dense network for image super-resolution. in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR).Google ScholarCross Ref
- Yu J., Fan Y., Yang J., Xu N., Wang Z., Wang X., Huang T. 2018. Wide activation for efficient and accurate image super-resolution. in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR).Google Scholar
- Tai Y., Yang J., Liu X. 2017. Image super-resolution via deep recursive residual network. in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR).Google ScholarCross Ref
- Tai Y., Yang J., Liu X., Xu C. 2017. Memnet: A persistent memory network for image restoration," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR).Google ScholarCross Ref
- Li Z., Yang J., Liu Z., Yang X., Jeon G., Wu W. 2019. Feedback networks for image super-resolution. in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR).Google ScholarCross Ref
- Lai W., Huang J., Ahuja N., Yang M. 2017. Deep laplacian pyramid networks for fast and accurate superresolution. in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR).Google Scholar
- Lai W., Huang J., Ahuja N., Yang M. 2018. Fast and accurate image super-resolution with deep laplacian pyramid networks. IEEE Trans. Pattern Anal. Mach. Intell., 38, 2, 295--307.Google Scholar
- Li J., Fang F., Mei K., Zhang G. 2018. Multi-scale residual network for image super-resolution. in Proc. European Conference on Computer Vision (ECCV).Google ScholarCross Ref
- Haris M., Shakhnarovich G., Ukita N. 2018. Deep back projection networks for super-resolution. in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR).Google ScholarCross Ref
- Zhong Z., Shen T., Yang Y., Z Lin., Zhang C. 2018. Joint sub-bands learning with clique structures for wavelet domain super-Resolution. in Proc. Neural Information Processing Systems (NuerIPS).Google Scholar
- Hu J., Shen L., Samuel S., Sun G., Wu H. 2019. Squeeze-and-excitation networks. IEEE Trans. Pattern Anal. Mach. Intell.Google ScholarDigital Library
- Wang X., Girshick R., Gupta A., He K. 2018. Non-local neural networks. in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR).Google ScholarCross Ref
- Zhang Y., Li K., Wang L., Zhong B., Fu Y. 2018. Image superresolution using very deep residual channel attention networks. in Proc. European Conference on Computer Vision (ECCV).Google Scholar
- Dai T., Cai J., Zhang Y., Xia S., Zhang L. 2019. Second-order attention network for single image super-resolution. in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR).Google ScholarCross Ref
- Timofte R., Agustsson E., Van Gool L., Yang M. H., Zhang L., Lim B., Son S., Kim H., Nah S., Lee K. M. 2017. Ntire 2017 challenge on single image super-resolution: Methods and results. in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW).Google ScholarCross Ref
Index Terms
- Single image super-resolution using deep hierarchical attention network
Recommendations
Single-image super-resolution with multilevel residual attention network
AbstractRecently, a great variety of image super-resolution (SR) algorithms based on convolutional neural network (CNN) have been proposed and achieved significant improvement. But how to restore more high-frequency details such as edges and textures is ...
Attention-Aware Linear Depthwise Convolution for Single Image Super-Resolution
SMA 2020: The 9th International Conference on Smart Media and ApplicationsAlthough deep convolutional neural networks (CNNs) have obtained outstanding performance in image super-resolution (SR), their computational cost increases geometrically as CNN models get deeper and wider. Meanwhile, the features of intermediate layers ...
Lightweight group convolutional network for single image super-resolution
Highlights- A novel CNN-based SISR method with cascaded modules named Lightweight Group Convolution Network (LGCN) is proposed.
AbstractRecently, deep learning methods have demonstrated significant reconstruction performance on Single Image Super-Resolution (SISR). However, most of them demand a huge amount of computational and memory consumption and hard to be applied ...
Comments