Image Restoration by Matching Gradient Distributions
Author(s)Cho, Taeg Sang; Zitnick, C. Lawrence; Joshi, Neel; Kang, Sing Bing; Szeliski, Richard; Freeman, William T.; ... Show more Show less
MetadataShow full item record
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.
DepartmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
IEEE Transactions on Pattern Analysis and Machine Intelligence
Institute of Electrical and Electronics Engineers (IEEE)
Taeg Sang Cho et al. “Image Restoration by Matching Gradient Distributions.” IEEE Transactions on Pattern Analysis and Machine Intelligence 34.4 (2012): 683–694.
Author's final manuscript