Total variation deblurring algorithm extension in third-order tensor space

The deblurring algorithm based on the total variation (TV) model can better preserve sharp edges. However, the existing algorithms could not really deal with the multichannel images. In this paper, we extend the general TV model in matrix space to tensor TV model in third-order tensor space, called as t-TV model, utilizing a new tensor product, t-product. And an efficient algorithm, based on alternating minimization, is adopted to solve the t-TV model. The proposed method retains the advantages of the general TV regularization. Meanwhile it could directly deal with the multichannel images in tensor framework. Experimental results show that the proposed method can achieve satisfactory performance on gray and color blurred images.