Image Restoration by Matching Gradient Distributions Essay

9246 WordsMar 22, 201537 Pages
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 20XX 1 Image restoration by matching gradient distributions Taeg Sang Cho, Student Member, IEEE, C. Lawrence Zitnick, Member, IEEE, Neel Joshi, Member, IEEE Sing Bing Kang, Senior Member, IEEE, Richard Szeliski, Fellow, IEEE, and William. T. Freeman, Fellow, IEEE, Abstract—The restoration of a blurry or noisy image is commonly performed with a MAP estimator, which maximizes a posterior probability to reconstruct a clean image from a degraded image. A MAP estimator, when used with a sparse gradient image prior, reconstructs piecewise smooth images and typically removes textures that are important for visual realism. We present an alternative deconvolution method called iterative distribution reweighting (IDR) which imposes a global constraint on gradients so that a reconstructed image should have a gradient distribution similar to a reference distribution. In natural images, a reference distribution not only varies from one image to another, but also within an image depending on texture. We estimate a reference distribution directly from an input image for each texture segment. Our algorithm is able to restore rich mid-frequency textures. A large scale user study supports the conclusion that our algorithm improves the visual realism of reconstructed images compared to those of MAP estimators. Index Terms—Non-blind deconvolution, image prior, image deblurring, image denoising ✦ 1 I NTRODUCTION MAP estimate 10 0 Gradient profiles Images captured with today’s cameras typically contain some degree of noise and blur. In low-light situations, blur due to camera shake can ruin a photograph. If the exposure time is reduced to remove blur due to

More about Image Restoration by Matching Gradient Distributions Essay

Open Document