Deep Mean-Shift Priors for Image Restoration
Abstract
In this paper we introduce a natural image prior that directly represents a Gaussian-smoothed version of the natural image distribution. We include our prior in a formulation of image restoration as a Bayes estimator that also allows us to solve noise-blind image restoration problems. We show that the gradient of our prior corresponds to the mean-shift vector on the natural image distribution. In addition, we learn the mean-shift vector field using denoising autoencoders, and use it in a gradient descent approach to perform Bayes risk minimization. We demonstrate competitive results for noise-blind deblurring, super-resolution, and demosaicing.
Cite
Text
Bigdeli et al. "Deep Mean-Shift Priors for Image Restoration." Neural Information Processing Systems, 2017.Markdown
[Bigdeli et al. "Deep Mean-Shift Priors for Image Restoration." Neural Information Processing Systems, 2017.](https://mlanthology.org/neurips/2017/bigdeli2017neurips-deep/)BibTeX
@inproceedings{bigdeli2017neurips-deep,
title = {{Deep Mean-Shift Priors for Image Restoration}},
author = {Bigdeli, Siavash Arjomand and Zwicker, Matthias and Favaro, Paolo and Jin, Meiguang},
booktitle = {Neural Information Processing Systems},
year = {2017},
pages = {763-772},
url = {https://mlanthology.org/neurips/2017/bigdeli2017neurips-deep/}
}