A higher-order MRF based variational model for multiplicative noise reduction

TL;DR

This paper introduces a novel variational model using higher-order Markov Random Fields for effective multiplicative noise reduction, achieving state-of-the-art results with extremely fast GPU-based inference.

Contribution

It proposes a new FoE-based variational model for despeckling that is both highly effective and computationally efficient, leveraging non-convex optimization.

Findings

Performance comparable to leading despeckling algorithms

GPU implementation reduces processing time to under 1 second

Effective on synthetic speckle and SAR images

Abstract

The Fields of Experts (FoE) image prior model, a filter-based higher-order Markov Random Fields (MRF) model, has been shown to be effective for many image restoration problems. Motivated by the successes of FoE-based approaches, in this letter, we propose a novel variational model for multiplicative noise reduction based on the FoE image prior model. The resulted model corresponds to a non-convex minimization problem, which can be solved by a recently published non-convex optimization algorithm. Experimental results based on synthetic speckle noise and real synthetic aperture radar (SAR) images suggest that the performance of our proposed method is on par with the best published despeckling algorithm. Besides, our proposed model comes along with an additional advantage, that the inference is extremely efficient. {Our GPU based implementation takes less than 1s to produce state-of-the-art despeckling performance.}