We propose a new solution to the problem of obtaining a single high-resolution image from multiple blurred, noisy, and undersampled images. Our estimator, derived using the Bayesian stochastic framework, is novel in that it employs a new hierarchical non-stationary image prior. This prior adapts the restoration of the super-resolved image to the local spatial statistics of the image. Numerical experiments demonstrate the effectiveness of the proposed approach.
Non-stationary approximate Bayesian super-resolution using a hierarchical prior model
2005-01-01
398677 byte
Conference paper
Electronic Resource
English
Non-Stationary Approximate Bayesian Super-Resolution using a Hierarchical Prior Model
British Library Conference Proceedings | 2005
|Bayesian autofocus/super-resolution theory
Tema Archive | 1990
|Low-dose CT Image Super Resolution using a Model-based Framework with CNN Prior
British Library Conference Proceedings | 2019
|Approximate Bayesian Prediction Using State Space Model with Uniform Noise
Springer Verlag | 2019
|