Image Restoration Using Conditional Random Fields and Scale Mixtures of Gaussians
This work addresses image quality enhancement for applications like photography and medical imaging, representing an incremental improvement over prior non-local and model-based techniques.
The paper tackles image restoration by proposing a Conditional Random Fields framework with a novel scale-mixture of Gaussians prior for patches, achieving superior performance in denoising and interpolation/inpainting compared to existing methods.
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.