LoginSign Up
Deep Mean-shift prior

Deep Mean-shift prior

A natural image restoration prior that represents natural image distribution smoothed with a Gaussian kernel.

Deep Mean-shift prior is an approach for image restoration developed based on the estimate of the natural image probability distribution smoothed by a Gaussian kernel.

It is created as a Bayes estimator that boost the Gaussian smoothed density of natural images. Its framework is an example of Bayesian inference using deep learning.

Deep Mean-shift prior allows users to solve noise-blind restoration problems. It builds on denoising

autoencoders (DAEs). It provides image restoration techniques based on gradient-descent risk minimization with competitive results for noise-blind image deblurring, super-resolution and demosaicing

Timeline

People

Name
Role
Related Golden topics

Further reading

Title
Author
Link
Type

Deep Mean-Shift Priors for Image Restoration

Siavash Arjomand Bigdeli, Meiguang Jin, Paolo Favaro and Matthias Zwicker

Academic paper

Documentaries, videos and podcasts

Title
Date
Link

Deep Mean-Shift Priors for Image Restoration (NIPS 2017 Spotlight)

24 November 2017

Companies

Company
CEO
Location
Products/Services