Fast ?0-norm-based single image blind deblurring: A comparative study

Single image blind deblurring has been intensively studied since Fergus et al.´s variational Bayes method in 2006. It is now commonly believed that the blur-kernel estimation accuracy is highly dependent on the pursed salient edge information from the blurred image, which stimulates numerous ℓ₀-approximating blind deblurring methods via kinds of techniques and tricks. This paper, however, focuses on the four recent daring attempts which are all based on the simple and direct ℓ₀-norm. A systematic comparative analysis is made towards those methods, clarifying their similarities and differences, and providing a benchmark evaluation on both the deblurring quality and computational efficiency. Results have demonstrated that the ℓ₀-norm alone is far enough to achieve top blind deblurring performance. Instead, details are to be paid with fairly more attention as working on the problem formulation as well as the algorithmic deduction. Besides, three possible extensions are analyzed on the most leading bi-ℓ₀-ℓ₂-norm regularization-based blind deblurring method.