Image Restoration by Matching Gradient Distributions
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...
Main Authors: | Cho, Taeg Sang, Zitnick, C. Lawrence, Joshi, Neel, Kang, Sing Bing, Szeliski, Richard, Freeman, William T. |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
Format: | Article |
Language: | en_US |
Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2012
|
Online Access: | http://hdl.handle.net/1721.1/72590 https://orcid.org/0000-0002-2231-7995 |
Similar Items
-
A content-aware image prior
by: Cho, Taeg Sang, et al.
Published: (2012) -
A probabilistic image jigsaw puzzle solver
by: Cho, Taeg Sang, et al.
Published: (2012) -
The Patch Transform
by: Avidan, Shai, et al.
Published: (2012) -
Image alignment and stitching : a tutorial /
by: 323129 Szeliski, Richard
Published: (2006) -
Heterogeneous scene matching based on the gradient direction distribution field
by: Qingge Li, et al.
Published: (2023-04-01)