A Bayesian Hyperprior Approach for Joint Image Denoising and Interpolation, with an Application to HDR Imaging

Abstract

Recently, impressive denoising results have been achieved by Bayesian approaches which assume Gaussian models for the image patches. This improvement in performance can be attributed to the use of per-patch models. Unfortunately such an approach is particularly unstable for most inverse problems beyond denoising. In this work, we propose the use of a hyperprior to model image patches, in order to stabilize the estimation procedure. There are two main advantages to the proposed restoration scheme: Firstly it is adapted to diagonal degradation matrices, and in particular to missing data problems (e.g. inpainting of missing pixels or zooming). Secondly it can deal with signal dependent noise models, particularly suited to digital cameras. As such, the scheme is especially adapted to computational photography. In order to illustrate this point, we provide an application to high dynamic range imaging from a single image taken with a modified sensor, which shows the effectiveness of the proposed scheme.

Some figures are reduced to comply with arxiv's size constraints. Full size images are available as HAL technical report hal-01107519v5, IEEE Transactions on Computational Imaging, 2017

References in corpus (1)

• Bayesian estimation of regularization and PSF parameters for Wiener-Hunt deconvolution

Cited by in corpus (7)

• Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior
• Optimal Threshold Design for Quanta Image Sensor
• Bayesian imaging using Plug & Play priors: when Langevin meets Tweedie
• Solving Inverse Problems by Joint Posterior Maximization with a VAE Prior
• Sparsity promoting reconstructions via hierarchical prior models in diffuse optical tomography
• Deep Snapshot HDR Imaging Using Multi-Exposure Color Filter Array
• Connecting Image Inpainting with Denoising in the Homogeneous Diffusion Setting