A higher-order MRF based variational model for multiplicative noise reduction
This work addresses efficient despeckling for SAR images, but it is incremental as it builds on existing prior models and optimization methods.
The authors tackled multiplicative noise reduction in images, particularly for synthetic aperture radar (SAR), by proposing a variational model based on the Fields of Experts prior, achieving performance on par with the best despeckling algorithms with inference times under 1 second on GPU.
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.}