在影像處理中（例如人臉識別），圖像去模糊和超分辨率是非常重要的。但是在戶外時，我們經常取得模糊且低解析度的圖像。為了解決該問題，我們提出了一種深度融合之注意網路（DGFAN）來生成清晰且高解析度的圖像。我們分別對模糊且低解析度圖像萃取去模糊和超分辨率的特徵，以避免串連方式時所導致的誤差傳播。我們還在網絡中添加注意模塊，透過此機制讓網路能得到更有意義的特徵，並提出edge loss，使模型專注於臉部特徵，如眼睛和鼻子等。 DGFAN在PSNR和SSIM上與相較現有方法表現出色，並且使用DGFAN生成的清晰圖像可以提高面部驗證的準確性。

Image deblurring and super-resolution are very important in image processing such as face verification. However, when in the outdoors, we often get blurry and low resolution images. To solve the problem, we propose a deep gated fusion attention network (DGFAN) to generate a high resolution image without blurring artifacts. We extract features from two task-independent structures for deburring and super-resolution to avoid the error propagation in the cascade structure of deblurring and super-resolution. We also add an attention module in our network by using channel-wise and spatial-wise features for better features and propose an edge loss function to make the model focus on facial features like eyes and nose. DGFAN performs favorably against the state-of-arts methods in terms of PSNR and SSIM. Also, using the clear images generated by DGFAN can improve the accuracy on face verification.

[1] Xinyi Zhang, Hang Dong, Zhe Hu, Wei-Sheng Lai, Fei Wang, and Ming-Hsuan Yang. Gated fusion network for joint image deblurring and super-resolution. arXiv preprint arXiv:1807.10806, 2018.
[2] Yulun Zhang, Kunpeng Li, Kai Li, Lichen Wang, Bineng Zhong, and Yun Fu. Image super-resolution using very deep residual channel attention networks. In ECCV, 2018.
[3] Bee Lim, Sanghyun Son, Heewon Kim, Seungjun Nah, and Kyoung Mu Lee. Enhanced deep residual networks for single image super-resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 136–144, 2017.
[4] Xin Tao, Hongyun Gao, Xiaoyong Shen, Jue Wang, and Jiaya Jia. Scale-recurrent network for deep image deblurring. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 8174– 8182, 2018.
[5] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
[6] Jie Hu, Li Shen, and Gang Sun. Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 7132–7141, 2018.
[7] Max Jaderberg, Karen Simonyan, Andrew Zisserman, et al. Spatial transformer networks. In Advances in neural information processing systems, pages 2017–2025, 2015.
[8] Xin Yu, Basura Fernando, Bernard Ghanem, Fatih Porikli, and Richard Hartley. Face super-resolution guided by facial component heatmaps. In Proceedings of the European Conference on Computer Vision (ECCV), pages 217–233, 2018.
[9] Ziyi Shen, Wei-Sheng Lai, Tingfa Xu, Jan Kautz, and Ming-Hsuan Yang. Deep semantic face deblurring. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 8260–8269, 2018.
[10] Michal Hradiš, Jan Kotera, Pavel Zemcık, and Filip Šroubek. Convolutional neural networks for direct text deblurring. In Proceedings of BMVC, volume 10, page 2, 2015.
[11] Rob Fergus, Barun Singh, Aaron Hertzmann, Sam T Roweis, and William T Freeman. Removing camera shake from a single photograph. In ACM transactions on graphics (TOG), volume 25, pages 787–794. ACM, 2006.
[12] Christian J Schuler, Michael Hirsch, Stefan Harmeling, and Bernhard Schölkopf. Learning to deblur. IEEE transactions on pattern analysis and machine intelligence, 38(7):1439–1451, 2016.
[13] Ziwei Liu, Ping Luo, Xiaogang Wang, and Xiaoou Tang. Deep learning face attributes in the wild. In Proceedings of International Conference on Computer Vision (ICCV), 2015.
[14] Xiangyu Xu, Jinshan Pan, Yu-Jin Zhang, and Ming-Hsuan Yang. Motion blur kernel estimation via deep learning. IEEE Transactions on Image Processing, 27(1):194–205, 2018.
[15] Mehdi Noroozi, Paramanand Chandramouli, and Paolo Favaro. Motion deblurring in the wild. In German conference on pattern recognition, pages 65–77. Springer, 2017.
[16] Orest Kupyn, Volodymyr Budzan, Mykola Mykhailych, Dmytro Mishkin, and Jiˇrí Matas. Deblurgan: Blind motion deblurring using conditional adversarial networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 8183–8192, 2018.
[17] Wenzhe Shi, Jose Caballero, Ferenc Huszár, Johannes Totz, Andrew P Aitken, Rob Bishop, Daniel Rueckert, and Zehan Wang. 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, pages 1874–1883, 2016.
[18] Ying Tai, Jian Yang, and Xiaoming Liu. Image super-resolution via deep recursive residual network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3147–3155, 2017.
[19] Christian Ledig, Lucas Theis, Ferenc Huszár, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, et al. Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4681–4690, 2017.
[20] Yanting Hu, Jie Li, Yuanfei Huang, and Xinbo Gao. Channel-wise and spatial feature modulation network for single image super-resolution. arXiv preprint arXiv:1809.11130, 2018.
[21] Sanghyun Woo, Jongchan Park, Joon-Young Lee, and In So Kweon. Cbam: Convolutional block attention module. In Proceedings of the European Conference on Computer Vision (ECCV), pages 3–19, 2018.
[22] Jun-Hyuk Kim, Jun-Ho Choi, Manri Cheon, and Jong-Seok Lee. Ram: Residual attention module for single image super-resolution. arXiv preprint arXiv:1811.12043, 2018.
[23] Xiangyu Xu, Deqing Sun, Jinshan Pan, Yujin Zhang, Hanspeter Pfister, and Ming-Hsuan Yang. Learning to super-resolve blurry face and text images. In Proceedings of the IEEE International Conference on Computer Vision, pages 251–260, 2017.
[24] Takuma Yamaguchi, Hisato Fukuda, Ryo Furukawa, Hiroshi Kawasaki, and Peter Sturm. Video deblurring and super-resolution technique for multiple moving objects. In Asian conference on computer vision, pages 127–140. Springer, 2010.
[25] Haesol Park and Kyoung Mu Lee. Joint estimation of camera pose, depth, deblurring, and super-resolution from a blurred image sequence. In The IEEE International Conference on Computer Vision (ICCV), Oct 2017.
[26] John Canny. A computational approach to edge detection. In Readings in computer vision, pages 184–203. Elsevier, 1987.
[27] Erik Learned-Miller, Gary B Huang, Aruni RoyChowdhury, Haoxiang Li, and Gang Hua. Labeled faces in the wild: A survey. In Advances in face detection and facial image analysis, pages 189–248. Springer, 2016.
[28] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.

[29] Florian Schroff, Dmitry Kalenichenko, and James Philbin. Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 815–823, 2015.

[30] Lai, W. S., Huang, J. B., Hu, Z., Ahuja, N., & Yang, M. H. (2016). A comparative study for single image blind deblurring. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 1701-1709).