在影像處理中，影像去模糊是一個很重要而且很有挑戰性的任務。在未知點擴散函數的情況下，大部分的單一影像去模糊都採用使用整張影像去疊代估計出誤差最小的點擴散函數值，然而，使用整張影像去去模糊的方法通常會因為反覆估計點擴散函數而造成很大的計算量。我們觀察到利用整張影像去還原清晰影像並不是永遠都能有比較好的效果，相反的，使用一個擁有足夠資訊去估計點擴散函數的區塊，不但能減少計算時間，同時也因為減少了平滑區域和重複邊緣的影響而使得效能更好。
在這篇論文中，我們一開始利用模糊影像的資訊對影像進行二次偏微計算出有用的資訊點以保留強邊資訊，並以分群的方式讓這些資訊點自動形成群集以避免固定的區塊大小或錯誤的區塊形成，並將這些群集視為初始的區塊，然而單一區塊的資訊是不足以估計出點擴散函數的，因此我們在這裡使用了合作賽局去讓這些區塊進行聯集已選出最好的區塊，我們將每個區塊的中心點視為玩家去找出最好的聯盟。在我們的實驗中，我們將我們的演算法套在兩篇著名的去模糊方法上，結果顯示出運用我們的方法可以在真實影像和合成影像上都達到時間上的進步和準確率的改善。

Image deblurring is an important and challenging task in image processing. The main goal of blind deconvolution is to recover latent image from blurry image without knowing blur kernel. To estimate the blur kernel, a typical method is MAP (Maximum a Posteriori) approach which uses the predicted latent image and the blur kernel it estimated to minimize the error iteratively. However, the method has complex computation and takes long time if a whole image is used to recover the latent image.
In our research, we find out that it is not necessary to use whole image to predict the blur kernel. By using a patch of the image with enough edge information can efficiently reduces the computational time and improves the results for image deblurring since it eliminates the smooth regions and repetition edges’ influence. In our method, we use an anisotropic Partial Differential Equation which can keep strong edges’ information to find out informative points, patch them by clustering points to avoid fix patch size and wrong patch’s center location, and treat every patch center as a player to use a coalitional game to find out the best patch. In our experiment, we use our algorithm to modify two blind deconvolution methods and the results show improvement with our method both on real world and synthetic images.

[1] Lucy, L. (1974). Bayesian-based iterative method of image restoration. In Journal of Astronomy (Vol. 79, pp. 745-754).
[2] Rav-acha. A., & Peleg, S. (2005). Two motion blurred images are better than one. In Pattern Recognition Letters (Vol. 26, pp. 311-317).
[3] Yuan, L., Sun, J., Quan, L., & Shum, H.-Y. (2007). Image Deblurring with Blurred/Noisy Image Pairs. In SIGGRAPH.
[4] Fergus, R., Singh, B., Hertzmann, A., Roweis, S. T., & Freeman, W. T. (2006, July). Removing camera shake from a single photograph. In ACM Transactions on Graphics (TOG) (Vol. 25, No. 3, pp. 787-794).
[5] Krishnan, D., Tay, T., & Fergus, R. (2011, June). Blind deconvolution using a normalized sparsity measure. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on (pp. 233-240).
[6] Xie, J., Lin, W., Li, H., Guo, K., Jin, B., Zhang, Y., & Liu, D. (2011, October). A new algorithm for improving deblurring effects and addressing spatially-variant blur problems for image motion deblurring. In Image and Signal Processing (CISP), 2011 4th International Congress on (pp. 651-655).
[7] Donatelli, M., Estatico, C., Martinelli, A., & Serrazapizzano, S. (2006). Improved image deblurring with antireflective boundary conditions and re-blurring. In Inverse Problems (Vol. 22, No. 6, pp. 2035-2053).
[8] Shan, Q., Jia, J., & Agarwala, A. (2008, August). High-quality motion deblurring from a single image. In ACM Transactions on Graphics (TOG) (Vol. 27, No. 3, p. 73).
[9] Xu, L., & Jia, J. (2010). Two-phase kernel estimation for robust motion deblurring. In Computer Vision–ECCV 2010 (pp. 157-170).
[10] Bae, H., Fowlkes, C. C., & Chou, P. H. (2013). Patch mosaic for fast motion deblurring. In Computer Vision–ACCV 2012 (pp. 322-335).
[11] Hu, Z., & Yang, M, (2012). Good regions to deblur. In ECCV'12 Proceedings of the 12th European conference on Computer Vision (Vol. 5, pp. 59-72).
[12] Jia, J. (2007, June). Single image motion deblurring using transparency. In Computer Vision and Pattern Recognition, 2007. CVPR'07. IEEE Conference on (pp. 1-8).
[13] Krishnan, D., & Fergus, R (2009). Fast image deconvolution using hyper-laplacian priors. In NIPS (pp. 1033-1041).
[14] Joshi, N., Szeliski, R., & Kriegman, D. J. (2008, June). PSF estimation using sharp edge prediction. In Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on (pp. 1-8).
[15] Frey, B., & Dueck, D., (2007, February). Clustering by Passing Messages between Data Points. In Science (Vol. 315, No. 5814, pp. 972-976).
[16] Levin, A., Fergus, R., Durand, F., & Freeman, W. T., (2007) Image and depth from a conventional camera with a coded aperture. In ACM Transaction on Graphics (Vol. 26, No. 3, Article no. 70).
[17] Tschumperle, D., & Deriche, R., (2005, April) Vector-valued image regularization with PDEs: a common framework for different applications. In IEEE transaction on Pattern Analysis Machine Intelligence (Vol. 2, No. 4, pp. 506-517).
[18] Köhler, R., Hirsch, M., Mohler, B., Schölkopf, B., & Harmeling, S. (2012). Recording and playback of camera shake: Benchmarking blind deconvolution with a real-world database. In Computer Vision–ECCV 2012 (pp. 27-40).