Blind Image Deconvolution using Deep Generative Priors
This addresses the ill-posed problem of blind deblurring for image processing applications, but it is incremental as it builds on existing generative priors.
The paper tackles blind image deconvolution by using deep generative networks as priors, proposing an alternating gradient descent scheme in latent spaces, and reports promising deblurring results on images with large blurs and heavy noise, with performance depending on generator range.
This paper proposes a novel approach to regularize the \textit{ill-posed} and \textit{non-linear} blind image deconvolution (blind deblurring) using deep generative networks as priors. We employ two separate 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 promising deblurring results on images even under large blurs, and heavy noise. To address the shortcomings of generative models such as mode collapse, we augment our generative priors with classical image priors and report improved performance on complex image datasets. The deblurring performance depends on how well the range of the generator spans the image class. Interestingly, our experiments show that even an untrained structured (convolutional) generative networks acts as an image prior in the image deblurring context allowing us to extend our results to more diverse natural image datasets.