在影像處理領域中，單張影像超解析一直以來都是重要且實用的問題。將低解析度圖片還原成高解析度圖片為不適定問題。深度卷積網路已經超越傳統演算法在還原影像上可以獲得更大的峰值信噪比。日新月異的架構在追求更高的表現同時，也增加了網路參數、計算量，而輕量化的設計思路變誕生了。為求可以在手機等受限運算資源、容量之輕量化終端上運行超解析，進而應用於日常生活。因此，我們在基於提出的雙遞迴架構Dual-Recurrent Backbone將前饋超解析模型RFANet (The Residual Feature Aggregation Network)改為遞迴模型，提出節省參數量的超解析模型—RRFANet，達到減少79%參數量的使用，且得到相近的高解析度還原效能。

In the field of image processing, single image super-resolution has been an important and practical problem. Restoring a low-resolution image to a high-resolution image is an ill-posed problem. Deep convolutional networks have surpassed traditional algorithms in constructing high-resolution images. In pursuit of higher performance of the network, its number of parameters and computational complexity are also increased. The lightweight design idea was born to save the space usage of parameters.
We proposed a share-weight dual-recurrent backbone for single image super-resolution. We combine the residual feature aggregation network (RFANet) with our dual-recurrent backbone and propose a super-resolution model. Our proposed dual-recurrent backbone reduces the use of about 79% of the parameters and obtains similar high-resolution recovery performance as the state-of-the-art methods.

[1] J. Liu, W. J. Zhang, Y. T. Tang, J. Tang, G. S. Wu, and Ieee, "Residual Feature Aggregation Network for Image Super-Resolution," in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Electr Network, Jun 14-19 2020, NEW YORK: Ieee, in IEEE Conference on Computer Vision and Pattern Recognition, 2020, pp. 2356-2365, doi: 10.1109/cvpr42600.2020.00243. [Online]. Available: <Go to ISI>://WOS:000620679502062
https://ieeexplore.ieee.org/document/9156371/
[2] N. Ahn, B. Kang, and K.-A. Sohn, "Fast, accurate, and lightweight super-resolution with cascading residual network," in Proceedings of the European conference on computer vision (ECCV), 2018, pp. 252-268.
[3] J. Kim, J. K. Lee, K. M. Lee, and Ieee, "Deeply-Recursive Convolutional Network for Image Super-Resolution," in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, Jun 27-30 2016, in IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 1637-1645, doi: 10.1109/cvpr.2016.181. [Online]. Available: <Go to ISI>://WOS:000400012301073
[4] Y. Tai, J. Yang, X. M. Liu, and Ieee, "Image Super-Resolution via Deep Recursive Residual Network," in 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, Jul 21-26 2017, in IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2790-2798, doi: 10.1109/cvpr.2017.298. [Online]. Available: <Go to ISI>://WOS:000418371402090
https://ieeexplore.ieee.org/document/8099781/
[5] B. Lim, S. Son, H. Kim, S. Nah, K. M. Lee, and Ieee, "Enhanced Deep Residual Networks for Single Image Super-Resolution," in 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, Jul 21-26 2017, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2017, pp. 1132-1140, doi: 10.1109/cvprw.2017.151. [Online]. Available: <Go to ISI>://WOS:000426448300144
[6] C. Dong, C. C. Loy, and X. Tang, "Accelerating the super-resolution convolutional neural network," in European conference on computer vision, 2016: Springer, pp. 391-407.
[7] Z. Hui, X. Wang, and X. Gao, "Fast and accurate single image super-resolution via information distillation network," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 723-731.
[8] Z. Hui, X. Gao, Y. Yang, and X. Wang, "Lightweight image super-resolution with information multi-distillation network," in Proceedings of the 27th acm international conference on multimedia, 2019, pp. 2024-2032.
[9] W.-S. Lai, J.-B. Huang, N. Ahuja, and M.-H. Yang, "Deep laplacian pyramid networks for fast and accurate super-resolution," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 624-632.
[10] Y. Tai, J. Yang, X. Liu, and C. Xu, "Memnet: A persistent memory network for image restoration," in Proceedings of the IEEE international conference on computer vision, 2017, pp. 4539-4547.
[11] J. Liu, J. Tang, and G. Wu, "Residual feature distillation network for lightweight image super-resolution," in European Conference on Computer Vision, 2020: Springer, pp. 41-55.
[12] K. Zhang, W. Zuo, and L. Zhang, "Learning a single convolutional super-resolution network for multiple degradations," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 3262-3271.
[13] Y. Wang, L. Zhao, L. Liu, H. Hu, and W. Tao, "URNet: A U-Shaped Residual Network for Lightweight Image Super-Resolution," Remote Sensing, vol. 13, no. 19, p. 3848, 2021.
[14] J. Kim, J. K. Lee, K. M. Lee, and Ieee, "Accurate Image Super-Resolution Using Very Deep Convolutional Networks," in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, Jun 27-30 2016, in IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 1646-1654, doi: 10.1109/cvpr.2016.182. [Online]. Available: <Go to ISI>://WOS:000400012301074
[15] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778.
[16] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, "Densely connected convolutional networks," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 4700-4708.
[17] C. Dong, C. C. G. Loy, K. M. He, and X. O. Tang, "Learning a Deep Convolutional Network for Image Super-Resolution," in 13th European Conference on Computer Vision (ECCV), Zurich, SWITZERLAND, Sep 06-12 2014, vol. 8692, in Lecture Notes in Computer Science, 2014, pp. 184-199, doi: 10.1007/978-3-319-10593-2_13. [Online]. Available: <Go to ISI>://WOS:000345525100013
[18] C. Ledig et al., "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network," in 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, Jul 21-26 2017, in IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 105-114, doi: 10.1109/cvpr.2017.19. [Online]. Available: <Go to ISI>://WOS:000418371400012
[19] Wikipedia contributors, "Function composition," in Wikipedia, The Free Encyclopedia., ed.
[20] R. Timofte, S. Gu, J. Wu, and L. Van Gool, "Ntire 2018 challenge on single image super-resolution: Methods and results," in Proceedings of the IEEE conference on computer vision and pattern recognition workshops, 2018, pp. 852-863.
[21] M. Bevilacqua, A. Roumy, C. Guillemot, and M. L. Alberi-Morel, "Low-complexity single-image super-resolution based on nonnegative neighbor embedding," 2012.
[22] R. Zeyde, M. Elad, and M. Protter, "On single image scale-up using sparse-representations," in International conference on curves and surfaces, 2010: Springer, pp. 711-730.
[23] P. Arbelaez, M. Maire, C. Fowlkes, and J. Malik, "Contour detection and hierarchical image segmentation," IEEE transactions on pattern analysis and machine intelligence, vol. 33, no. 5, pp. 898-916, 2010.
[24] J.-B. Huang, A. Singh, and N. Ahuja, "Single image super-resolution from transformed self-exemplars," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 5197-5206.
[25] X. Gao, W. Lu, D. Tao, and X. Li, "Image quality assessment based on multiscale geometric analysis," IEEE Transactions on Image Processing, vol. 18, no. 7, pp. 1409-1423, 2009.
[26] Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, "Image quality assessment: from error visibility to structural similarity," IEEE transactions on image processing, vol. 13, no. 4, pp. 600-612, 2004.