A Comparative Study for Single Image Blind Deblurring

Numerous single image blind deblurring algorithms have been proposed to restore latent sharp images under camera motion. However, these algorithms are mainly evaluated using either synthetic datasets or few selected real blurred images. It is thus unclear how these algorithms would perform on images acquired "in the wild" and how we could gauge the progress in the field. In this paper, we aim to bridge this gap. We present the first comprehensive perceptual study and analysis of single image blind deblurring using real-world blurred images. First, we collect a dataset of real blurred images and a dataset of synthetically blurred images. Using these datasets, we conduct a large-scale user study to quantify the performance of several representative state-of-the-art blind deblurring algorithms. Second, we systematically analyze subject preferences, including the level of agreement, significance tests of score differences, and rationales for preferring one method over another. Third, we study the correlation between human subjective scores and several full-reference and noreference image quality metrics. Our evaluation and analysis indicate the performance gap between synthetically blurred images and real blurred image and sheds light on future research in single image blind deblurring.

[1]  Adam Finkelstein,et al.  A no-reference metric for evaluating the quality of motion deblurring , 2013, ACM Trans. Graph..

[2]  Rob Fergus,et al.  Blind deconvolution using a normalized sparsity measure , 2011, CVPR 2011.

[3]  Seungyong Lee,et al.  Fast motion deblurring , 2009, ACM Trans. Graph..

[4]  Li Xu,et al.  Two-Phase Kernel Estimation for Robust Motion Deblurring , 2010, ECCV.

[5]  H. A. David,et al.  The method of paired comparisons , 1966 .

[6]  Sunghyun Cho,et al.  Edge-based blur kernel estimation using patch priors , 2013, IEEE International Conference on Computational Photography (ICCP).

[7]  Christophe Charrier,et al.  Blind Image Quality Assessment: A Natural Scene Statistics Approach in the DCT Domain , 2012, IEEE Transactions on Image Processing.

[8]  M. Kendall Statistical Methods for Research Workers , 1937, Nature.

[9]  Alan C. Bovik,et al.  No-Reference Image Quality Assessment in the Spatial Domain , 2012, IEEE Transactions on Image Processing.

[10]  Alan Chalmers,et al.  Evaluation of tone mapping operators using a High Dynamic Range display , 2005, ACM Trans. Graph..

[11]  Daniele Perrone,et al.  Total Variation Blind Deconvolution: The Devil Is in the Details , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Seungyong Lee,et al.  Handling outliers in non-blind image deconvolution , 2011, 2011 International Conference on Computer Vision.

[13]  R. A. Bradley,et al.  Rank Analysis of Incomplete Block Designs: I. The Method of Paired Comparisons , 1952 .

[14]  Chih-Yuan Yang,et al.  Single-Image Super-Resolution: A Benchmark , 2014, ECCV.

[15]  Bernhard Schölkopf,et al.  Fast removal of non-uniform camera shake , 2011, 2011 International Conference on Computer Vision.

[16]  Ming-Hsuan Yang,et al.  Joint Depth Estimation and Camera Shake Removal from Single Blurry Image , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  P. Moran On the method of paired comparisons. , 1947, Biometrika.

[18]  E. N. Gilbert,et al.  Review: H. A. David, The Method of Paired Comparisons , 1964 .

[19]  Frédo Durand,et al.  Understanding and evaluating blind deconvolution algorithms , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Zhou Wang,et al.  Multi-scale structural similarity for image quality assessment , 2003 .

[21]  Rob Fergus,et al.  Fast Image Deconvolution using Hyper-Laplacian Priors , 2009, NIPS.

[22]  Bernhard Schölkopf,et al.  Recording and Playback of Camera Shake: Benchmarking Blind Deconvolution with a Real-World Database , 2012, ECCV.

[23]  Gustavo de Veciana,et al.  An information fidelity criterion for image quality assessment using natural scene statistics , 2005, IEEE Transactions on Image Processing.

[24]  Olga Sorkine-Hornung,et al.  A comparative study of image retargeting , 2010, ACM Trans. Graph..

[25]  A. Bovik,et al.  A universal image quality index , 2002, IEEE Signal Processing Letters.

[26]  Sundaresh Ram,et al.  Removing Camera Shake from a Single Photograph , 2009 .

[27]  Alan C. Bovik,et al.  Blind Image Quality Assessment: From Natural Scene Statistics to Perceptual Quality , 2011, IEEE Transactions on Image Processing.

[28]  E. S. Pearson Biometrika tables for statisticians , 1967 .

[29]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[30]  Andrew Zisserman,et al.  Deblurring shaken and partially saturated images , 2011, ICCV Workshops.

[31]  Zhou Wang,et al.  Multiscale structural similarity for image quality assessment , 2003, The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003.

[32]  Michal Irani,et al.  Blind Deblurring Using Internal Patch Recurrence , 2014, ECCV.

[33]  Alan C. Bovik,et al.  Making a “Completely Blind” Image Quality Analyzer , 2013, IEEE Signal Processing Letters.

[34]  Ming-Hsuan Yang,et al.  Deblurring Low-Light Images with Light Streaks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[35]  Jean Ponce,et al.  Non-uniform Deblurring for Shaken Images , 2012, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[36]  Jiaya Jia,et al.  High-quality motion deblurring from a single image , 2008, ACM Trans. Graph..

[37]  Sylvain Paris,et al.  Handling Noise in Single Image Deblurring Using Directional Filters , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[38]  Yanning Zhang,et al.  Multi-image Blind Deblurring Using a Coupled Adaptive Sparse Prior , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[39]  Sebastian Nowozin,et al.  Discriminative Non-blind Deblurring , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[40]  Alan C. Bovik,et al.  Image information and visual quality , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[41]  Ming-Hsuan Yang,et al.  Deblurring Text Images via L0-Regularized Intensity and Gradient Prior , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[42]  Li Xu,et al.  Unnatural L0 Sparse Representation for Natural Image Deblurring , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[43]  Frédo Durand,et al.  Efficient marginal likelihood optimization in blind deconvolution , 2011, CVPR 2011.

[44]  Ankit Gupta,et al.  Single Image Deblurring Using Motion Density Functions , 2010, ECCV.

[45]  R. A. Bradley,et al.  RANK ANALYSIS OF INCOMPLETE BLOCK DESIGNS THE METHOD OF PAIRED COMPARISONS , 1952 .

[46]  Wilson S. Geisler,et al.  Image quality assessment based on a degradation model , 2000, IEEE Trans. Image Process..

[47]  David S. Doermann,et al.  Unsupervised feature learning framework for no-reference image quality assessment , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[48]  Theophano Mitsa,et al.  Evaluation of contrast sensitivity functions for the formulation of quality measures incorporated in halftoning algorithms , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[49]  Alan C. Bovik,et al.  A Two-Step Framework for Constructing Blind Image Quality Indices , 2010, IEEE Signal Processing Letters.

[50]  Ming-Hsuan Yang,et al.  Deblurring Face Images with Exemplars , 2014, ECCV.

[51]  Hua Huang,et al.  No-reference image quality assessment based on spatial and spectral entropies , 2014, Signal Process. Image Commun..

[52]  H. J. Arnold Introduction to the Practice of Statistics , 1990 .