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.

翻译：本文提出利用深层层次变分自编码器（HVAE）作为图像先验，对不适定逆问题进行正则化。该方法融合了两类方法的优势：基于去噪器的即插即用（Plug & Play）方法与基于生成模型的逆问题方法。首先，利用VAE特性设计高效算法，使其具备即插即用（PnP）方法的收敛保证优势；其次，本方法不受专用数据集限制，所提出的PnP-HVAE模型能够处理任意尺寸的自然图像恢复问题。实验表明，所提出的PnP-HVAE方法在性能上与基于去噪器的SOTA PnP方法以及其他基于生成模型的SOTA恢复方法均具有竞争力。