Timezone: »

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

Tue Dec 05 05:35 PM -- 05:40 PM (PST) @ Hall A

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. The gradient of a bound of our estimator involves the gradient of the logarithm of our prior. This gradient corresponds to the mean-shift vector on the natural image distribution, and we learn the mean-shift vector field using denoising autoencoders. We demonstrate competitive results for noise-blind deblurring, super-resolution, and demosaicing.

Author Information

Siavash Arjomand Bigdeli (Universit├Ąt 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)