Blind Image Deconvolution using Pretrained Generative Priors
This addresses the ill-posed problem of blind image deblurring for image processing applications, with an incremental improvement through a hybrid approach.
The paper tackles blind image deconvolution by using pretrained generative priors to regularize the problem, achieving excellent deblurring results even under large blurs and heavy noise.
This paper proposes a novel approach to regularize the ill-posed blind image deconvolution (blind image deblurring) problem using deep generative networks. We employ two separate deep generative models - one trained to produce sharp images while the other trained to generate blur kernels from lower dimensional parameters. To deblur, we propose an alternating gradient descent scheme operating in the latent lower-dimensional space of each of the pretrained generative models. Our experiments show excellent deblurring results even under large blurs and heavy noise. To improve the performance on rich image datasets not well learned by the generative networks, we present a modification of the proposed scheme that governs the deblurring process under both generative and classical priors.