A Content-Aware Image Prior

DMCA

A Content-Aware Image Prior

Cached

Download Links

by Taeg Sang Cho , Neel Joshi , C. Lawrence Zitnick , Sing Bing Kang , Richard Szeliski , William T. Freeman

Citations:

21 - 2 self

BibTeX

@MISC{Cho_acontent-aware,
    author = {Taeg Sang Cho and Neel Joshi and C. Lawrence Zitnick and Sing Bing Kang and Richard Szeliski and William T. Freeman},
    title = {A Content-Aware Image Prior},
    year = {}
}

OpenURL

Abstract

In 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. Orthogonal gradients

Keyphrases

content-aware image prior visual quality image restoration sparse gradient piecewise smooth characteristic noise artifact orthogonal gradient mid-level textural characteristic image restoration task incorrect image gaussian distribution natural image sparse gradient prior remove low-level local structure underlying texture mid-frequency texture small gradient gradient profile fractal-like texture whole image heavy-tailed gradient distribution

DMCA