Superresolution and blind deconvolution of video

Šroubek, Filip; Flusser, Jan; Šorel, Michal

doi:10.1109/icpr.2008.4760989

Cited by 9 publications

(17 citation statements)

References 6 publications

(5 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method assumes that the kernel has a single peak, which is a restrictive assumption in the presence of motion blur. In [18,9], methods for jointly estimating the high-res image and a nonparametric kernel were developed. This joint estimation strategy, however, was shown to lead to erroneous results [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Nonparametric Blind Super-resolution

Michaeli

Irani

2013

2013 IEEE International Conference on Computer Vision

299

295

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

“…Our last contribution is a proof that our algorithm computes the MAP estimate of the kernel, as opposed to the joint MAP (over the kernel and high-res image) strategy of [19,10,18,9]. The benefit of this approach has been studied and demonstrated in the context of blind deblurring [13].…”

Section: Introductionmentioning

confidence: 99%

Nonparametric Blind Super-resolution

Michaeli

Irani

2013

2013 IEEE International Conference on Computer Vision

299

295

View full text Add to dashboard Cite

show abstract

“…Using registration parameters inside the algorithm instead of registering input images gives better results and paves the way for including methods of making registration parameters more accurate during reconstruction of the HR image. 34,57 The second method was based on the application of scattered-point interpolation on projected sequence data, followed by a filtering operation to restore …”

Section: Discussionmentioning

confidence: 99%

Superresolution imaging: a survey of current techniques

et al. 2008

View full text Add to dashboard Cite

Imaging plays a key role in many diverse areas of application, such as astronomy, remote sensing, microscopy, and tomography. Owing to imperfections of measuring devices (e.g., optical degradations, limited size of sensors) and instability of the observed scene (e.g., object motion, media turbulence), acquired images can be indistinct, noisy, and may exhibit insufficient spatial and temporal resolution. In particular, several external effects blur images. Techniques for recovering the original image include blind deconvolution (to remove blur) and superresolution (SR). The stability of these methods depends on having more than one image of the same frame. Differences between images are necessary to provide new information, but they can be almost unperceivable. State-of-the-art SR techniques achieve remarkable results in resolution enhancement by estimating the subpixel shifts between images, but they lack any apparatus for calculating the blurs. In this paper, after introducing a review of current SR techniques we describe two recently developed SR methods by the authors. First, we introduce a variational method that minimizes a regularized energy function with respect to the high resolution image and blurs. In this way we establish a unifying way to simultaneously estimate the blurs and the high resolution image. By estimating blurs we automatically estimate shifts with subpixel accuracy, which is inherent for good SR performance. Second, an innovative learning-based algorithm using a neural architecture for SR is described. Comparative experiments on real data illustrate the robustness and utilization of both methods.

show abstract

“…Nguyen et al [19] used the generalized cross-correlation method to identify the blur kernel using quadratic formulations. Sroubek et al [24] estimated the image and the blur kernel under translational motion models by joint MAP estimation. However, their models can barely generalize to real videos due to the oversimplified motion models.…”

Section: Related Workmentioning

confidence: 99%