2019/08/20 by Muhammad Asim, Asim, Muhammad, Fahad Shamshad +3 · 5 citations
Computer Science · Engineering · #Advanced Image Processing Techniques #Algorithm #Artificial intelligence #Bayesian probability #Blind deconvolution #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Deconvolution #FOS: Computer and information sciences #Generative grammar #Generative model #Image (mathematics) #Image Processing Techniques and Applications #Image and Signal Denoising Methods #Image processing #Image restoration #Pattern recognition (psychology) #Prior probability #cs.CV
paper · pdf · doi:10.48550/arxiv.1908.07404
published in arXiv (Cornell University) (Cornell University) · Accepted in BMVC 2019. Extended version of this paper can be found at arXiv:1802.04073
arxiv created 2019/08/20 · openalex publication_date 2019/08/20 · arxiv updated 2019/08/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.