vix.ing · top · new · best · stats · spec

Blind Image Deconvolution using Pretrained Generative Priors

2019/08/20 by Muhammad Asim, Asim, Muhammad, Fahad Shamshad +3
Computer Science · Engineering · #Advanced Image Processing Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing Techniques and Applications #Image and Signal Denoising Methods

paper · pdf · doi:10.48550/arxiv.1908.07404

openalex publication_date 2019/08/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

Related