Timezone: »

Deep Mean-Shift Priors for Image Restoration
Siavash Arjomand Bigdeli · Matthias Zwicker · Paolo Favaro · Meiguang Jin

Tue Dec 05 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #86

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.

Author Information

Siavash Arjomand Bigdeli (Universität Bern)
Matthias Zwicker (University of Maryland, College Park)
Paolo Favaro (University of Bern)
Meiguang Jin (University of Bern)

Related Events (a corresponding poster, oral, or spotlight)