Book contents
- Frontmatter
- Contents
- List of contributors
- Preface
- 1 Mathematical models and practical solvers for uniform motion deblurring
- 2 Spatially-varying image deblurring
- 3 Hybrid-imaging for motion deblurring
- 4 Efficient, blind, spatially-variant deblurring for shaken images
- 5 Removing camera shake in smartphones without hardware stabilization
- 6 Multi-sensor fusion for motion deblurring
- 7 Motion deblurring using fluttered shutter
- 8 Richardson–Lucy deblurring for scenes under a projective motion path
- 9 HDR imaging in the presence of motion blur
- 10 Compressive video sensing to tackle motion blur
- 11 Coded exposure motion deblurring for recognition
- 12 Direct recognition of motion-blurred faces
- 13 Performance limits for motion deblurring cameras
- Index
- References
2 - Spatially-varying image deblurring
Published online by Cambridge University Press: 05 June 2014
Book contents
- Frontmatter
- Contents
- List of contributors
- Preface
- 1 Mathematical models and practical solvers for uniform motion deblurring
- 2 Spatially-varying image deblurring
- 3 Hybrid-imaging for motion deblurring
- 4 Efficient, blind, spatially-variant deblurring for shaken images
- 5 Removing camera shake in smartphones without hardware stabilization
- 6 Multi-sensor fusion for motion deblurring
- 7 Motion deblurring using fluttered shutter
- 8 Richardson–Lucy deblurring for scenes under a projective motion path
- 9 HDR imaging in the presence of motion blur
- 10 Compressive video sensing to tackle motion blur
- 11 Coded exposure motion deblurring for recognition
- 12 Direct recognition of motion-blurred faces
- 13 Performance limits for motion deblurring cameras
- Index
- References
Summary
Camera shake is one of the most common causes of image blur. This type of blur arises when a long exposure is required (due to low light levels, for example), and the camera is not held still.
Removing blur due to camera shake is a very active area of research. With just a single photograph as input, this blur removal is known as the blind deconvolution problem, i.e. simultaneously recovering both the blurring function (point spread function or PSF) and the deblurred, latent image. Unfortunately, the blind deconvolution problem is inherently ill-posed, as the observed blurred image provides only a partial constraint on the solution. Therefore, the problem cannot be solved without assuming constraints or priors on the blur or the deblurred image. The most common assumption is that the blur is spatially invariant, but this can handle only a limited set of camera motions. The deblurred image is typically assumed to have natural image statistics (Fergus, Singh, Hertzmann, Roweis & Freeman 2006). A key open problem is to model general camera motions, which are quite common and can cause the blur kernels to vary spatially.
Review of image deblurring methods
Image deblurring has received a lot of attention in the computer vision community. Deblurring is the combination of two tightly coupled sub-problems: PSF estimation and non-blind image deconvolution. These problems have been addressed both independently and jointly (Richardson 1972).
- Type
- Chapter
- Information
- Motion DeblurringAlgorithms and Systems, pp. 31 - 56Publisher: Cambridge University PressPrint publication year: 2014
References
, & (2009). Invertible motion blur in video. In ACM Special Interest Group on Graphics and Interactive Techniques, 28(3), 95:1–8.Google Scholar
, , , , & (2007). A database and evaluation methodology for optical flow. In IEEE International Conference on Computer Vision, pp. 1-8.
, & (1996). Motion deblurring and super-resolution from an image sequence. In European Conference on Computer Vision, pp. 571–82.
& (2004). Motion-based motion deblurring. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(6), 689–98.Google Scholar
, & (2007). Removing non-uniform motion blur from images. In IEEE International Conference on Computer Vision, pp. 1-8.
& (2008). Motion from blur. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8.
, , , & (2006). Removing camera shake from a single photograph. ACM Special Interest Group on Graphics and Interactive Techniques, 25(3), 787–94.Google Scholar
, , , & (2010). Single image deblurring using motion density functions. In European Conference on Computer Vision, pp. 171–84.
, , & (2010). Efficient filter flow for space-variant multiframe blind deconvolution. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 607–14.
(2007). Single image motion deblurring using transparency. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8.
, & (2005). Visual tracking in the presence of motion blur. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 18-25.
, , & (2010). Image deblurring using inertial measurement sensors. ACM Transactions on Graphics, 29, 30:1–30:9.Google Scholar
, & (2008). PSF estimation using sharp edge prediction. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8.
, , & (2009). Image deblurring and denoising using color priors. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 1550–7.
(2007). Blind motion deblurring using image statistics. In Neural Information Processing Systems Conference, pp. 841–8.
, , & (2007). Image and depth from a conventional camera with a coded aperture. ACM Special Interest Groupon Graphics and Interactive Techniques, 26(3), 70:1–10.Google Scholar
, , , & (2010). Generating sharp panoramas from motion-blurre dvideos. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 2424–31.
& (2004). A variational approach for bayesian blind image deconvolution. IEEE Transactions on Signal Processing, 52(8), 2222–33.Google Scholar
, , ., & (2008). Automatic estimation and removal of noise from asingle image. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(2), 299–314.Google Scholar
& (1981). An iterative image registration technique with an application to stereo vision. In International Joint Conference on Artificial Intelligence, 81, 674–9.Google Scholar
(1980). Updating quasi-newton matrices with limited storage. Mathematics of Computation, 35, 773–82.Google Scholar
& (2005). Mosaicing and restoration from blurred image sequence taken with moving camera. In IEEE International Conference on Advances in Pattern Recognition, pp. 598–607.
(1972). Bayesian-based iterative method of image restoration. Journal of the Optical Society of America, 62(1), 55–9.Google Scholar
& (2009). Filter flow. In IEEE International Conference on Computer Vision, pp. 143–50.
, & (2008). High-quality motion deblurring from a single image. ACM Special Interest Group on Graphics and Interactive Techniques, 27(3), 73:1–10.Google Scholar
, & (2007). Rotational motion deblurring of a rigid object from a single image. In IEEE International Conference on Computer Vision, pp. 1-8.
(1999). Robust parametere stimation in computer vision. Society for Industrial and Applied Mathematics Review, 41(3), 513–37.Google Scholar
, , & (2009). Richardson–Lucy deblurring for scenes under projective motion path, Technical report, Korea Advanced Institute of Science and Technology.
, , & (2008). Image/video deblurring using a hybrid camera. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8.
, , & (2010). Coded exposure imaging for projective motion deblurring. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 2408–15.
& (2007). What makes a good model of natural images? In IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8.
, , & (2010). Non-uniform deblurring for shaken images. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 491–8.
, , & (2007). Image deblurring with blurred/noisy image pairs. ACM Transactions on Graphics, 26, pp. 1-10.Google Scholar