A content-aware image prior

• 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: Article
• Online Access: Get fulltext

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.
United States. National Geospatial-Intelligence Agency (NEGI- 1582-04-0004)
United States. Army Research Office. Multidisciplinary University Research Initiative. (Grant Number N00014-06-1-0734)
Samsung Scholarship Foundation
MIT Summer Research Program (Internship)