去除動態模糊在電腦視覺中是一個被研究已久的課題。在卷積神經網路(CNN)開始被廣泛應用後，也被用來與傳統去模糊的方法結合，多半是用在找出模糊核或顯著的邊緣後再進行去模糊的處理。生成對抗網路(GAN)問世後，在風格轉換的問題上有優秀的表現，於是我們就想將去模糊化的問題也變成一種風格轉換的問題。
我們針對去模糊生成對抗網路(DeblurGAN)中的生成器(Generator)架構去做改善，提出了一個結合了起始塊(inception block)、殘缺塊(residual block)以及密集塊(dense block)的新的塊模型來對動態模糊進行去模糊的處理。也因為使用了密集網絡(DenseNet)的概念，可以有效的減少過度擬合(overfitting)的問題。
改善後的去模糊生成對抗網路所生成的去模糊圖片在結構相似度以及圖像視覺化中，效果都有顯著的進步。

Deblurring from a motion blurred image has been studied for some times. After convolution neural network(CNN) be used widely, it can be implemented on finding blur kernel or latent sharp edge from a blurred image. In recent years, the most popular network architecture called generative adversarial network (GAN) which performs well on style transformation. We consider that a deblurring problem as a style transformation problem, so we use GAN to do deblurring. We focus on improving the state-of-the-art deblur method DeblurGAN’s generator, and present a new kind of block which combined inception block, residual block and dense block to do deblurring from motion blur. By using the conception of dense net which can avoid overfitting. The improved DeblurGAN present better in both structural similarity measure and by visual effect.

[1] O. Kupyn, V. Budzan, M. Mykhailych, D. Mishkin, J. Matas. “DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks,” arXiv:1711.07064v4, 2018.
[2] C. Szegedy, S. Ioffe, V. Vanhoucke, A. Alemi. “Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning,” arXiv: 1602.07261v2, 2016.
[3] K. He, X. Zhang, S. Ren, J. Sun. “Deep Residual Learning for Image Recognition,” arXiv: 1512.00385, 2015.
[4] G. Huang, Z. Liu, L. van der Maaten. “Densely Connected Convolutional Networks,” arXiv: 1608.06993, Jan. 2018.
[5] L. Wang, Y. Li, S. Wang. “DeepDeblur: Fast one-step blurry face images restoration,” arXiv: 1711.09515v1, 2017.
[6] S. Ramakrishnan, S. Pachori, A. Gangopadhyay, S. Raman. “Deep Generative Filter for Motion Deblurring,” arXiv: 1709.03481v1, 2017.
[7] T. M. Nimisha, A. K. Singh, A. N. Rajagopalan. “Blur-Invariant Deep Learning for Blind-Deblurring,” IEEE International Conference on Computer Vision (ICCV), pp. 4762-4770, Oct 2017.
[8] G. G. Chrysos, S. Zafeiriou. “Deep Face Deblurring,” arXiv: 1704.08772v2, 2017.
[9] R. Fergus, B. Singh, A. Hertzmann, S. T. Roweis, W. T. Freeman. “Removing Camera Shake from a Single Photograph,” ACM Transactions on Graphics, vol. 25, no.3, pp. 787-794, 2006.
[10] D. Krishnan, T. Tay, R. Fergus. “Blind Deconvolution Using a Normalized Sparsity Measure,” In Proceedings of the IEEE Computer Vision and Pattern Recognition (CVPR), pp. 233-240, June 2011.
[11] J. Pan, D. Sun, H. Pfister, M. “Yang. Blind Image Deblurring Using Dark Channel Prior,” In Proceedings of the IEEE Computer Vision and Pattern Recognition (CVPR), pp. 1-9, June 2016.
[12] J. Pan, Z. Hu, Z. Su, M. Yang. “Deblurring Text Images via L0-Regularized Intensity and Gradient Prior,” In Proceedings of the IEEE Computer Vision and Pattern Recognition (CVPR), pp. 2901-2908, June 2014.
[13] M. Noroozi, P. Chandramouli, P. Favaro. “Motion Deblurring in the Wild,” arXiv: 1701.01486v2, Jan 2017.
[14] A. Chakrabarti. “A Neural Approach to Blind Motion Deblurring,” arXiv: 1603.04771v2, Aug 2016.
[15] H. Son, S. Lee. “Fast Non-blind Deconvolution via Regularized Residual Networks with Long/Short Skip-Connections,” IEEE International Conference on Conference Photography (ICCP), pp. 1-10, May 2017.
[16] M. Hradiš, J. Kotera, P. Zemcík, F. Šroubek. “Convolutional Neural Networks for Direct Text Deblurring,” In Proceedings of the British Machine Vision Conference (BMVC), pp. 6.1-6.13, Sept 2015.
[17] X. Xu, J. Pan, Y. Zhang, M. Yang. “Motion Blur Kernel Estimation via Deep Learning,” IEEE Transaction on Image Processing, pp. 194-205, Sept 2017.
[18] I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio. “Generative Adversarial Nets,” In Advances in Neural Information Proceeding Systems (NIPS), pp. 2672-2680, 2014.
[19] T. Salimans, I. J. Goodfellow, W. Zaremba, V. Cheung, A. Radford, X. Chen. “Improved Techniques for Training GANs,” arXiv: 1606.03498, June 2016.
[20] M. Arjovsky, S. Chintala, L. Bottou. “Wasserstein GAN,” arXiv: 1701.07875, Dec 2017.
[21] I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, Aaron Courville. “Improved Training of Wasserstein GANs,” arXiv: 1704.00028, Dec 2017.
[22] J. Zhu, T. Park, P. Isola, A. A. Efros. “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks,” arXiv: 1703.10593, Feb 2018.
[23] C. Ledig, L. Theis, F. Huszar, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, Z. Wang, W. Shi. “Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network,” arXiv: 1609.04802, May 2017.
[24] P. Luc, C. Couprie, S. Chintala, J. Verbeek. “Semantic Segmentation using Adversarial Networks,” arXiv: 1611.08408, Nov 2016.
[25] P. Isola, J. Zhu, T. Zhou, A. A. Efros. “Image-to-Image Translation with Conditional Adversarial Networks,” arXiv: 1611.07004, Nov 2017.
[26] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich. “Going deeper with convolutions,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.1-9, June 2015.
[27] S. Ioffe, C. Szegedy. “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” arXiv: 1502.03167, Mar 2015.
[28] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, Z. Wojna. “Rethinking the Inception Architecture for Computer Vision,” arXiv: 1512.00567, Dec 2015.
[29] D. Ulyanov, A. Vedaldi, V. Lempitsky. “Instance Normalization: The Missing Ingredient for Fast Stylization,” arXiv: 1607.08022, Nov 2017.
[30] V. Nair, G. E. Hinton. “Rectified Linear Units Improve Restricted Boltzmann Machines,” In Proceedings of the 27th International Conference on Machine Learning, Haifa, Israel, 2010.
[31] A. L. Maas, A. Y. Hannun, A. Y. Ng. “Rectifier Nonlinearities Improve Neural Network Acoustic Models,” In Proceedings of the 30th International Conference on Machine Learning, Atlanta, Georgia, USA, 2013.
[32] Z. Shen, W. Lai, T. Xu, J. Kautz, M. Yang. “Deep Semantic Face Deblurring,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
[33] J. Johnson, A. Alahi, Li Fei-Fei. “Perceptual Losses for Real-Time Style Transfer and Super-Resolution,” arXiv: 1603.08155, Mar 2016.
[34] J. Deng, W. Dong, R. Socher, L. Li, K. Li and Li Fei-Fei. “ImageNet: A Large-Scale Hierarchical Image Database,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 248-255, June 2009.
[35] D. P. Kingma, J. L. Ba. “ADAM: A METHOD FOR STOCHASTIC OPTIMIZATION,” Conference paper at the 3rd International Conference for Learning Representations (ICLR), 2015.
[36] G. Huang, Z. Liu, L. van der Maaten, K. Q. Weinberger. “Densely Connected Convolutional Networks,” arXiv: 1608.06993v5, Jan 2018.
[37] R. Yan and L. Shao. “Blind Image Blur Estimation via Deep Learning,” IEEE Transaction on Image Processing, vol. 25, no. 4, pp. 1910-1921, Apr 2016.
[38] C. Li and M. Wand. “Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks,” arXiv: 1604.04382v1, Apr 2016.
[39] R. Köhler, M. Hirsch, B. Mohler, B. Schölkopf, S. Harmeling. “Recording and playback of camera shake: benchmarking blind deconvolution with a real-world database,” In ECCV, pp. 27-40, 2012.
[40] S. Nah, T. H. Kim, K. M. Lee. “Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.