Two-Phase Kernel Estimation for Robust Motion Deblurring

Liu, Xü; Jia, Jiaya

doi:10.1007/978-3-642-15549-9_12

Cited by 772 publications

(1,169 citation statements)

References 22 publications

Supporting

Mentioning

1,157

Contrasting

Unclassified

Order By: Relevance

“…y denotes the input blurry image, γ denotes the control parameter, and ∇x s denotes the shock filtered gradient image [14]. The regularization term, our focus in this work, is the second term, the square of the absolute, values of the estimated kernel, 2…”

Section: Motivationsmentioning

confidence: 99%

“…As mentioned in several papers, edge information found in the observed blurry image is useful for estimating the kernel. Several important characteristics of edges, including the, gradient magnitude, orientation angle, width, and straightness [3][4][5][6][7][8][9][10][11][12][13][14][15][16], are widely used in state-of-the-art blur-related methods. Traditional de-blurring approaches apply masks on top of the observed blurry image to build the kernel estimation algorithm and focus on the most informative region in the blurry image.…”

Section: Overall Algorithmmentioning

confidence: 99%

“…However, this method is not suitable for images that are sparse or not Gaussian. Xu et al [14] proposed an efficient and high-quality kernel estimation method based on using the spatial and iterative support detection (ISD) kernel refinement and the, TV-l 1 deconvolution model, solved with a new variable substitution scheme to robustly suppress noise. Yuan et al [10] proposed a different system using a pair of images, a blurry image and a noisy image, to reconstruct the latent sharp image.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fast Patch-based De-blurring with Directional-oriented Kernel Estimation

Min¹,

Chong²

2017

Journal of IKEEE

View full text Add to dashboard Cite

This paper proposes a fast patch-based de-blurring algorithm including kernel estimation based on the angle between the edge and the blur direction. For de-blurring, image patches from the most informative edges in the blurry image are used to estimate a kernel with low computational cost. Moreover, the kernels of each patch are estimated based on the correlation between the edge direction and the blur direction. This makes the final kernel more reliable and creates an accurate latent image from the blurry image. The combination of directionally oriented kernel estimation and patch-based de-blurring is faster and more accurate than existing state-of-the art methods. Experimental results using various test images show that the proposed method achieves its objectives: speed and accuracy. key words: de-blurring, edge direction, image restoration, kernel estimation, motion blur.

show abstract

Section: Motivationsmentioning

confidence: 99%

Section: Overall Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast Patch-based De-blurring with Directional-oriented Kernel Estimation

Min¹,

Chong²

2017

Journal of IKEEE

View full text Add to dashboard Cite

show abstract

“…There has been a quite steady progress in uniform motion deblurring [25,26,27,28,29] thanks to the modeling and exploitation of texture statistics. Although these methods deal with an unknown and general blur pattern, they assume that blur is not changing across the image domain.…”

Section: Motion Deblurring and Blind Deconvolutionmentioning

confidence: 99%

Single Image Blind Deconvolution with Higher-Order Texture Statistics

Martinello

Favaro

2011

Video Processing and Computational Video

View full text Add to dashboard Cite

Abstract. We present a novel method for solving blind deconvolution, i.e., the task of recovering a sharp image given a blurry one. We focus on blurry images obtained from a coded aperture camera, where both the camera and the scene are static, and allow blur to vary across the image domain. As most methods for blind deconvolution, we solve the problem in two steps: First, we estimate the coded blur scale at each pixel; second, we deconvolve the blurry image given the estimated blur. Our approach is to use linear high-order priors for texture and second-order priors for the blur scale map, i.e., constraints involving two pixels at a time. We show that by incorporating the texture priors in a least-squares energy minimization we can transform the initial blind deconvolution task in a simpler optimization problem. One of the striking features of the simplified optimization problem is that the parameters that define the functional can be learned offline directly from natural images via singular value decomposition. We also show a geometrical interpretation of image blurring and explain our method from this viewpoint. In doing so we devise a novel technique to design optimally coded apertures. Finally, our coded blur identification results in computing convolutions, rather than deconvolutions, which are stable operations. We will demonstrate in several experiments that this additional stability allows the method to deal with large blur. We also compare our method to existing algorithms in the literature and show that we achieve state-of-the-art performance with both synthetic and real data.

show abstract

“…As blind deconvolution is, in general, illposed, these approaches are restricted to spatially invariant point spread functions (PSF) [5,25,26] or a locally invariant PSF [27,28].…”

Section: Related Workmentioning

confidence: 99%

Two Algorithms for Motion Estimation from Alternate Exposure Images

Sellent¹,

Eisemann²,

Magnor³

2011

Video Processing and Computational Video

View full text Add to dashboard Cite

Abstract. Most algorithms for dense 2D motion estimation assume pairs of images that are acquired with an idealized, infinitively short exposure time. In this work we compare two approaches that use an additional, motion-blurred image of a scene to estimate highly accurate, dense correspondence fields. We consider video sequences that are acquired with alternating exposure times so that a short-exposure image is followed by a long-exposure image that exhibits motion-blur. For both motion estimation algorithms we employ an image formation model that relates the motion blurred image to two enframing short-exposure images. With this model we can decipher the motion information encoded in the long-exposure image, but also estimate occlusion timings which are a prerequisite for artifact-free frame interpolation. The first approach solves for the motion in a pointwise least squares formulation while the second formulates a global, total variation regularized problem. Both approaches are evaluated in detail and compared to each other and state-of-the-art motion estimation algorithms.

show abstract

Two-Phase Kernel Estimation for Robust Motion Deblurring

Cited by 772 publications

References 22 publications

Fast Patch-based De-blurring with Directional-oriented Kernel Estimation

Fast Patch-based De-blurring with Directional-oriented Kernel Estimation

Single Image Blind Deconvolution with Higher-Order Texture Statistics

Two Algorithms for Motion Estimation from Alternate Exposure Images

Contact Info

Product

Resources

About