Inverse problem regularization with hierarchical variational autoencoders
arXiv:2303.11217 · doi:10.1109/ICCV51070.2023.02093
Abstract
In this paper, we propose to regularize ill-posed inverse problems using a deep hierarchical variational autoencoder (HVAE) as an image prior. The proposed method synthesizes the advantages of i) denoiser-based Plug \& Play approaches and ii) generative model based approaches to inverse problems. First, we exploit VAE properties to design an efficient algorithm that benefits from convergence guarantees of Plug-and-Play (PnP) methods. Second, our approach is not restricted to specialized datasets and the proposed PnP-HVAE model is able to solve image restoration problems on natural images of any size. Our experiments show that the proposed PnP-HVAE method is competitive with both SOTA denoiser-based PnP approaches, and other SOTA restoration methods based on generative models.
References in corpus (9)
- Denoising Diffusion Probabilistic Models
- Diffusion Models Beat GANs on Image Synthesis
- NVAE: A Deep Hierarchical Variational Autoencoder
- Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior
- PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularization
- Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problems
- Fast and Provable ADMM for Learning with Generative Priors
- Efficient-VDVAE: Less is more
- Optimizing Hierarchical Image VAEs for Sample Quality