Results 1  10
of
184
Fast Motion Deblurring
"... This paper presents a fast deblurring method that produces a deblurring result from a single image of moderate size in a few seconds. We accelerate both latent image estimation and kernel estimation in an iterative deblurring process by introducing a novel prediction step and working with image deri ..."
Abstract

Cited by 128 (12 self)
 Add to MetaCart
This paper presents a fast deblurring method that produces a deblurring result from a single image of moderate size in a few seconds. We accelerate both latent image estimation and kernel estimation in an iterative deblurring process by introducing a novel prediction step and working with image derivatives rather than pixel values. In the prediction step, we use simple image processing techniques to predict strong edges from an estimated latent image, which will be solely used for kernel estimation. With this approach, a computationally efficient Gaussian prior becomes sufficient for deconvolution to estimate the latent image, as small deconvolution artifacts can be suppressed in the prediction. For kernel estimation, we formulate the optimization function using image derivatives, and accelerate the numerical process by reducing the number of Fourier transforms needed for a conjugate gradient method. We also show that the formulation results in a smaller condition number of the numerical system than the use of pixel values, which gives faster convergence. Experimental results demonstrate that our method runs an order of magnitude faster than previous work, while the deblurring quality is comparable. GPU implementation facilitates further speedup, making our method fast enough for practical use.
TwoPhase Kernel Estimation for Robust Motion Deblurring
"... Abstract. We discuss a few new motion deblurring problems that are significant to kernel estimation and nonblind deconvolution. We found that strong edges do not always profit kernel estimation, but instead under certain circumstance degrade it. This finding leads to a new metric to measure the use ..."
Abstract

Cited by 92 (4 self)
 Add to MetaCart
(Show Context)
Abstract. We discuss a few new motion deblurring problems that are significant to kernel estimation and nonblind deconvolution. We found that strong edges do not always profit kernel estimation, but instead under certain circumstance degrade it. This finding leads to a new metric to measure the usefulness of image edges in motion deblurring and a gradient selection process to mitigate their possible adverse effect. We also propose an efficient and highquality kernel estimation method based on using the spatial prior and the iterative support detection (ISD) kernel refinement, which avoids hard threshold of the kernel elements to enforce sparsity. We employ the TVℓ1 deconvolution model, solved with a new variable substitution scheme to robustly suppress noise. 1
Nonuniform deblurring for shaken images
 In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2010. 8. Image taken with a Canon 1D Mark III, at 35mm f/4.5. Images
"... Blur from camera shake is mostly due to the 3D rotation of the camera, resulting in a blur kernel that can be significantly nonuniform across the image. However, most current deblurring methods model the observed image as a convolution of a sharp image with a uniform blur kernel. We propose a new p ..."
Abstract

Cited by 75 (4 self)
 Add to MetaCart
(Show Context)
Blur from camera shake is mostly due to the 3D rotation of the camera, resulting in a blur kernel that can be significantly nonuniform across the image. However, most current deblurring methods model the observed image as a convolution of a sharp image with a uniform blur kernel. We propose a new parametrized geometric model of the blurring process in terms of the rotational velocity of the camera during exposure. We apply this model to two different algorithms for camera shake removal: the first one uses a single blurry image (blind deblurring), while the second one uses both a blurry image and a sharp but noisy image of the same scene. We show that our approach makes it possible to model and remove a wider class of blurs than previous approaches, including uniform blur as a special case, and demonstrate its effectiveness with experiments on real images. 1.
Single image deblurring using motion density functions
 In Proceedings of European Conference on Computer Vision
, 2010
"... Abstract. We present a novel single image deblurring method to estimate spatially nonuniform blur that results from camera shake. We use existing spatially invariant deconvolution methods in a local and robust way to compute initial estimates of the latent image. The camera motion is represented as ..."
Abstract

Cited by 50 (2 self)
 Add to MetaCart
(Show Context)
Abstract. We present a novel single image deblurring method to estimate spatially nonuniform blur that results from camera shake. We use existing spatially invariant deconvolution methods in a local and robust way to compute initial estimates of the latent image. The camera motion is represented as a Motion Density Function (MDF) which records the fraction of time spent in each discretized portion of the space of all possible camera poses. Spatially varying blur kernels are derived directly from the MDF. We show that 6D camera motion is well approximated by 3 degrees of motion (inplane translation and rotation) and analyze the scope of this approximation. We present results on both synthetic and captured data. Our system outperforms current approaches which make the assumption of spatially invariant blur. 1
Fast Image/Video Upsampling
, 2008
"... We propose a simple but effective upsampling method for automatically enhancing the image/video resolution, while preserving the essential structural information. The main advantage of our method lies in a feedbackcontrol framework which faithfully recovers the highresolution image information f ..."
Abstract

Cited by 37 (1 self)
 Add to MetaCart
We propose a simple but effective upsampling method for automatically enhancing the image/video resolution, while preserving the essential structural information. The main advantage of our method lies in a feedbackcontrol framework which faithfully recovers the highresolution image information from the input data, without imposing additional local structure constraints learned from other examples. This makes our method independent of the quality and number of the selected examples, which are issues typical of learningbased algorithms, while producing highquality results without observable unsightly artifacts. Another advantage is that our method naturally extends to video upsampling, where the temporal coherence is maintained automatically. Finally, our method runs very fast. We demonstrate the effectiveness of our algorithm by experimenting with different image/video data.
B.: Fast removal of nonuniform camera shake
 In: ICCV
"... Camera shake leads to nonuniform image blurs. Stateoftheart methods for removing camera shake model the blur as a linear combination of homographically transformed versions of the true image. While this is conceptually interesting, the resulting algorithms are computationally demanding. In this p ..."
Abstract

Cited by 37 (3 self)
 Add to MetaCart
(Show Context)
Camera shake leads to nonuniform image blurs. Stateoftheart methods for removing camera shake model the blur as a linear combination of homographically transformed versions of the true image. While this is conceptually interesting, the resulting algorithms are computationally demanding. In this paper we develop a forward model based on the efficient filter flow framework, incorporating the particularities of camera shake, and show how an efficient algorithm for blur removal can be obtained. Comprehensive comparisons on a number of realworld blurry images show that our approach is not only substantially faster, but it also leads to better deblurring results. 1.
Invertible motion blur in video
 ACM Trans. Graph
, 2009
"... Figure 1: By simply varying the exposure time for video frames, multiimage deblurring can be made invertible. (Left) Varying exposure photos of a moving car. Notice the change in illumination and the blur size in the captured photos. (Right) The foreground object is automatically rectified, segment ..."
Abstract

Cited by 29 (2 self)
 Add to MetaCart
Figure 1: By simply varying the exposure time for video frames, multiimage deblurring can be made invertible. (Left) Varying exposure photos of a moving car. Notice the change in illumination and the blur size in the captured photos. (Right) The foreground object is automatically rectified, segmented, deblurred, and composed onto the background using the varying exposure video. Novel renderings, such as motion streaks, can be generated by linear combination of the deblurred image and the captured photos. We show that motion blur in successive video frames is invertible even if the pointspread function (PSF) due to motion smear in a single photo is noninvertible. Blurred photos exhibit nulls in the frequency transform of the PSF, leading to an illposed deconvolution. Hardware solutions to avoid this require specialized devices such as the coded exposure camera or accelerating sensor motion. We employ ordinary video cameras and introduce the notion of nullfilling along with jointinvertibility of multiple blurfunctions. The key idea is to record the same object with varying PSF’s, so that the nulls in the frequency component of one frame can be filled by other frames. The combined frequency transform becomes nullfree, making deblurring wellposed. We achieve jointlyinvertible blur simply by changing the exposure time of successive frames. We address the problem of automatic deblurring of objects moving with constant velocity by solving its critical components: preservation of all spatial frequencies, segmentation and motion estimation of moving parts, and nondegradation of the static parts of the scene. We demonstrate several challenging cases of object motion blur including textured backgrounds and partial occluders.
Handling outliers in nonblind image deconvolution
 In ICCV
, 2011
"... Nonblind deconvolution is a key component in image deblurring systems. Previous deconvolution methods assume a linear blur model where the blurred image is generated by a linear convolution of the latent image and the blur kernel. This assumption often does not hold in practice due to various types ..."
Abstract

Cited by 28 (5 self)
 Add to MetaCart
(Show Context)
Nonblind deconvolution is a key component in image deblurring systems. Previous deconvolution methods assume a linear blur model where the blurred image is generated by a linear convolution of the latent image and the blur kernel. This assumption often does not hold in practice due to various types of outliers in the imaging process. Without proper outlier handling, previous methods may generate results with severe ringing artifacts even when the kernel is estimated accurately. In this paper we analyze a few common types of outliers that cause previous methods to fail, such as pixel saturation and nonGaussian noise. We propose a novel blur model that explicitly takes these outliers into account, and build a robust nonblind deconvolution method upon it, which can effectively reduce the visual artifacts caused by outliers. The effectiveness of our method is demonstrated by experimental results on both synthetic and realworld examples. 1.
An augmented Lagrangian method for total variation video restoration,”
 IEEE Trans. Image Process.,
, 2011
"... AbstractThis paper presents a fast algorithm for restoring video sequences. The proposed algorithm, as opposed to existing methods, does not consider video restoration as a sequence of image restoration problems. Rather, it treats a video sequence as a spacetime volume and poses a spacetime tota ..."
Abstract

Cited by 25 (6 self)
 Add to MetaCart
(Show Context)
AbstractThis paper presents a fast algorithm for restoring video sequences. The proposed algorithm, as opposed to existing methods, does not consider video restoration as a sequence of image restoration problems. Rather, it treats a video sequence as a spacetime volume and poses a spacetime total variation regularization to enhance the smoothness of the solution. The optimization problem is solved by transforming the original unconstrained minimization problem to an equivalent constrained minimization problem. An augmented Lagrangian method is used to handle the constraints, and an alternating direction method (ADM) is used to iteratively find solutions of the subproblems. The proposed algorithm has a wide range of applications, including video deblurring and denoising, video disparity refinement, and hotair turbulence effect reduction.
SpaceVariant SingleImage Blind Deconvolution for Removing Camera Shake
"... Modelling camera shake as a spaceinvariant convolution simplifies the problem of removing camera shake, but often insufficiently models actual motion blur such as those due to camera rotation and movements outside the sensor plane or when objects in the scene have different distances to the camera. ..."
Abstract

Cited by 23 (4 self)
 Add to MetaCart
(Show Context)
Modelling camera shake as a spaceinvariant convolution simplifies the problem of removing camera shake, but often insufficiently models actual motion blur such as those due to camera rotation and movements outside the sensor plane or when objects in the scene have different distances to the camera. In an effort to address these limitations, (i) we introduce a taxonomy of camera shakes, (ii) we build on a recently introduced framework for spacevariant filtering by Hirsch et al. and a fast algorithm for single image blind deconvolution for spaceinvariant filters by Cho and Lee to construct a method for blind deconvolution in the case of spacevariant blur, and (iii), we present an experimental setup for evaluation that allows us to take images with real camera shake while at the same time recording the spacevariant point spread function corresponding to that blur. Finally, we demonstrate that our method is able to deblur images degraded by spatiallyvarying blur originating from real camera shake, even without using additionally motion sensor information. 1