Presented at 2010 IEEE CVPR
1 Massachusetts Institute of Technology
2 Microsoft Research
In image restoration tasks, the 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 the 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.
This work was mostly done while the first author was an intern at MSR. This research is partially funded by NGA NEGI-1582-04-0004, by ONR-MURI Grant N00014-06-1-0734, and by gift from Microsoft, Google, Adobe. The first author is partially supported by Samsung Scholarship Foundation. Authors would like to thank Wonyoung Kim for being a great model.
Last update: Aug. 18. 2010