A content-aware image prior

n image restoration tasks, a heavy-tailed gradient distribution of natural images has been extensively exploited as an image prior. Most image restoration algorithms impose a sparse gradient prior on the whole image, reconstructing an image with piecewise smooth characteristics. While the sparse gra...

Full description

Bibliographic Details
Main Authors: Cho, Taeg Sang (Contributor), Joshi, Neel (Author), Zitnick, C. Lawrence (Author), Kang, Sing Bing (Author), Szeliski, Richard (Author), Freeman, William T. (Contributor)
Other Authors: Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor)
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers (IEEE), 2012-07-30T16:30:40Z.
Subjects:
Online Access:Get fulltext
LEADER 02255 am a22003013u 4500
001 71890
042 |a dc 
100 1 0 |a Cho, Taeg Sang  |e author 
100 1 0 |a Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science  |e contributor 
100 1 0 |a Freeman, William T.  |e contributor 
100 1 0 |a Cho, Taeg Sang  |e contributor 
100 1 0 |a Freeman, William T.  |e contributor 
700 1 0 |a Joshi, Neel  |e author 
700 1 0 |a Zitnick, C. Lawrence  |e author 
700 1 0 |a Kang, Sing Bing  |e author 
700 1 0 |a Szeliski, Richard  |e author 
700 1 0 |a Freeman, William T.  |e author 
245 0 0 |a A content-aware image prior 
260 |b Institute of Electrical and Electronics Engineers (IEEE),   |c 2012-07-30T16:30:40Z. 
856 |z Get fulltext  |u http://hdl.handle.net/1721.1/71890 
520 |a n image restoration tasks, a heavy-tailed gradient distribution of natural images has been extensively exploited as an image prior. Most image restoration algorithms impose a sparse gradient prior on the whole image, reconstructing an image with piecewise smooth characteristics. While the sparse gradient prior removes ringing and noise artifacts, it also tends to remove mid-frequency textures, degrading the visual quality. We can attribute such degradations to imposing an incorrect image prior. The gradient profile in fractal-like textures, such as trees, is close to a Gaussian distribution, and small gradients from such regions are severely penalized by the sparse gradient prior. To address this issue, we introduce an image restoration algorithm that adapts the image prior to the underlying texture. We adapt the prior to both low-level local structures as well as mid-level textural characteristics. Improvements in visual quality is demonstrated on deconvolution and denoising tasks. 
520 |a United States. National Geospatial-Intelligence Agency (NEGI- 1582-04-0004) 
520 |a United States. Army Research Office. Multidisciplinary University Research Initiative. (Grant Number N00014-06-1-0734) 
520 |a Samsung Scholarship Foundation 
520 |a MIT Summer Research Program (Internship) 
546 |a en_US 
655 7 |a Article 
773 |t 2010 IEEE Conference on Computer Vision and Pattern Recognition