Motion-Based Motion Deblurring
IEEE Transactions on Pattern Analysis and Machine Intelligence
Two motion-blurred images are better than one
Pattern Recognition Letters - Special issue: In memoriam Azriel Rosenfeld
Removing camera shake from a single photograph
ACM SIGGRAPH 2006 Papers
Coded exposure photography: motion deblurring using fluttered shutter
ACM SIGGRAPH 2006 Papers
Image deblurring with blurred/noisy image pairs
ACM SIGGRAPH 2007 papers
Image and depth from a conventional camera with a coded aperture
ACM SIGGRAPH 2007 papers
ACM SIGGRAPH 2008 papers
High-quality motion deblurring from a single image
ACM SIGGRAPH 2008 papers
ACM SIGGRAPH Asia 2009 papers
Image deblurring using inertial measurement sensors
ACM SIGGRAPH 2010 papers
Two-phase kernel estimation for robust motion deblurring
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Single image deblurring using motion density functions
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Blind deconvolution using a normalized sparsity measure
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Efficient marginal likelihood optimization in blind deconvolution
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Blur kernel estimation using the radon transform
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
A regularization approach to joint blur identification and image restoration
IEEE Transactions on Image Processing
Total variation blind deconvolution
IEEE Transactions on Image Processing
PSF Estimation via Gradient Domain Correlation
IEEE Transactions on Image Processing
A no-reference metric for evaluating the quality of motion deblurring
ACM Transactions on Graphics (TOG)
Kernel estimation from salient structure for robust motion deblurring
Image Communication
| Hi-index | 0.00 |
We describe a new method for recovering the blur kernel in motion-blurred images based on statistical irregularities their power spectrum exhibits. This is achieved by a power-law that refines the one traditionally used for describing natural images. The new model better accounts for biases arising from the presence of large and strong edges in the image. We use this model together with an accurate spectral whitening formula to estimate the power spectrum of the blur. The blur kernel is then recovered using a phase retrieval algorithm with improved convergence and disambiguation capabilities. Unlike many existing methods, the new approach does not perform a maximum a posteriori estimation, which involves repeated reconstructions of the latent image, and hence offers attractive running times. We compare the new method with state-of-the-art methods and report various advantages, both in terms of efficiency and accuracy.