Image Restoration Using Conditional Random Fields and Scale Mixtures of Gaussians

TL;DR

This paper introduces a CRF-based framework for image restoration that employs novel scale-mixture of Gaussians priors, outperforming existing methods in denoising and inpainting tasks.

Contribution

It presents a new CRF model with scale-mixture Gaussian priors for image patches, improving restoration quality over previous Gaussian mixture approaches.

Findings

Outperforms Gaussian mixture models in denoising

Achieves state-of-the-art results in image inpainting

Introduces a novel prior for image patches

Abstract

This paper proposes a general framework for internal patch-based image restoration based on Conditional Random Fields (CRF). Unlike related models based on Markov Random Fields (MRF), our approach explicitly formulates the posterior distribution for the entire image. The potential functions are taken as proportional to the product of a likelihood and prior for each patch. By assuming identical parameters for similar patches, our approach can be classified as a model-based non-local method. For the prior term in the potential function of the CRF model, multivariate Gaussians and multivariate scale-mixture of Gaussians are considered, with the latter being a novel prior for image patches. Our results show that the proposed approach outperforms methods based on Gaussian mixture models for image denoising and state-of-the-art methods for image interpolation/inpainting.