Blind hyperspectral denoising

In this work we propose a new formulation for hyperspectral denoising based on the Blind Compressed Sensing (BCS) framework. BCS learns the sparsifying basis during signal recovery combining the advantages of standard sparse recovery with dictionary learning. We show that our proposed formulation yields better results than a state-of-the- art technique hyperspectral denoising both in terms of PSNR (more than 1dB improvement) and visual quality.