臺灣博碩士論文加值系統

單張影像去模糊是非常困難的問題，這是由於手中的資訊相對遠少於要解的變數的
量。這個領域的專家提出了非常多種假設以及數學模型來幫助解這個問題。他們大部分專注於如何使用某些已為眾人所知的自然影像會有的性質，來減少要解的變數，其中最出名的便是利用一般影像中，大部分的區域都是低能量的平滑或平坦的變化，強烈影像邊界則相對較少，影像邊界的強度形成了一個冪定律分布曲線這樣的性質。雖然先前的研究看起來似乎已經把能夠運用的資訊都做了探討，但其實仍
然有許多資訊可以被納入來幫助解這個問題。這篇論文中我們提出了一個新的觀察，經過大量實驗的來驗證正確性，提出的這個方法的確能大致辨識一張影像的模糊程度，並且能被用於估計模糊路徑。為了解出清晰影像，我們採用最佳化的方式，並按照前人的建議將最佳化拆成兩個步驟來做，一步是估計清晰影像，一步用於估計模糊路徑，交替做到收斂為止。初步的影像去模糊結果相信具有一定的說服力。這篇論文的主要貢獻，即是提出一個可以用於去模糊的新的影像特質以及相關的分析。

Single image de-convolution is an ill-posed problem due to the number of unknowns to be estimated is far larger than the number of available observations given by the input data. Experts of this eld have proposed several assumptions on the prior to help solve the problem. Most of the previous approaches concentrate on how to use the heavy-tailed gradient magnitude distribution. Although it seems that previous approaches have already exploited all the information from a single image, there are indeed lots of issues worthy of investigation.
In this thesis, we present a new image-based characteristic which is believed to be discriminative in identifying blur and sharp image. We study this assumption with various kinds of natural images, and the criterion used to model it is proven to be useful throughout extensive experiments. The optimization strategy we employed follows the suggestion made by by many researchers in recent years: We separate the optimization into two steps, one for image prediction, and the other for blur kernel estimation. Preliminary results of kernel estimation have shown the potential power of this proposed natural image statistics. The primary contribution of this thesis is hence the introduction and analysis of a new image prior.

Abstract
Contents
List of Figures
1 Introduction
2 Image Prior
2.0.1 Image Formation
2.0.2 Prior Derivation
2.0.3 Image Prior Model
3 Optimization Scheme
3.0.4 Patch Selection
3.0.5 f Update
3.0.6 k Update
4 Experiment Results
5 Discussion
A The Integrated Graphical User Interface
A.1 The Purpose
A.2 How to Use
Bibliography

[1] Anat Levin, "Blind Motion Deblurring Using Image Statistics," in NIPS,2006
[2] Anat Levin, Robert Fergus, Fredo Durand, andWilliam T. Freeman, "Image and depth from a conventional camera with a coded aperture," in SIGGRAPH, 2007
[3] Anat Levin, Peter Sand, Taeg Sang Cho, Fredo Durand, and William T. Freeman, "Motion-invariant photography," in SIGGRAPH, 2008
[4] Anat Levin, Yair Weiss, Fredo Durand, and William T. Freeman, "Understanding and evaluating blind deconvolution algorithms," in CVPR, 2009
[5] Anat Levin, Yair Weiss, Fredo Durand, and William T. Freeman, "Efficient Marginal Likelihood Optimization in Blind Deconvolution," in CVPR, 2011
[6] Amit Agrawal, Yi Xu, and Ramesh Raskar, "Invertible Motion Blur in Video," in SIGGRAPH, 2009
[7] Ankit Gupta, Neel Joshi, C. Lawrence Zitnick, Michael F. Cohen, and Brian Curless, "Single Image Deblurring Using Motion Density Functions," in ECCV, 2010
[8] Ayan Chakrabarti, Todd Zickler, and William T. Freeman "Analying Spatially-varing Blur," in CVPR, 2010
[9] Dilip Krishnan, Terence Tay ,and Rob Fergus, "Blind Deconvolution using a Normalized Sparsity Measure," in CVPR, 2011
[10] Hai Ting Lin, Yu-Wing Tai, and Michael S. Brown, "Motion regularization for matting motion blurred objects," in SIGGRAPH, 2010
[11] Jiaya Jia, "Single Image Motion Deblurring Using Transparency," in CVPR, 2007
[12] Krishnan, D. and Fergus, R., "Fast Image Deconvolution using Hyper-Laplacian Priors," in NIPS, 2009
[13] Li Xu and Jiaya Jia, "Two-Phase Kernel Estimation for Robust Motion Deblurring," in ECCV, 2010
[14] Neel Joshi, Richard Szeliski, and David J. Kriegman, "PSF estimation using sharp edge prediction," in CVPR, 2008
[15] Neel Joshi, C. Lawrence Zitnick, Richard Szeliski, and David J. Kriegman, "Image deblurring and denoising using color priors," in CVPR, 2009
[16] Norbert Wiener "Extrapolation, Interpolation, and smoothing of Stationary Time Series," in MIT Press, 1964
[17] Oliver Whyte, Josef Sivic, Andrew Zisserman, and Jean Ponce, "Non-uniform deblurring for shaken images," in CVPR, 2010
[18] Qi Shan,Jiaya Jia, and Aseem Agarwala, "High-quality motion deblurring from a single image," in SIGGRAPH, 2008
[19] Rob Fergus, Barun Singh, Aaron Hertzmann, Sam T. Roweis and William T. Freeman, "Removing Camera Shake From A Single Photograph," in SIGGRAPH, 2006
[20] Sunghyun Cho and Seungyong Lee, "Fast Motion Deblurring," in SIGGRAPH, 2009
[21] Taeg Sang Cho, Neel Joshi , C. Lawrence Zitnick, Sing Bing Kang, Richard Szeliski, and William T. Freeman, "A content-aware image prior," in CVPR, 2010
[22] William Hadley Richardson, "Bayesian-Based Iterative Method of Image Restoration," in J. Opt. Soc. Am. 62, 55-59, 1972
[23] Yu-Wing Tai, Naejin Kong, Stephen Lin, and Sung Yong Shin, "Coded Exposure Imaging for Projective Motion Deblurring," in CVPR, 2010
[24] Per Christian Hansen, James G. Nagy, and Dianne P. OLeary, "Deblurring Images: Matrices, Spectra, and Filtering," SIAM, 2006