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.
Abstract (translated)
在本文中,我们提议通过使用 Deep hierarchical variational autoencoder (HVAE) 作为图像先验来 regularize 不完备反问题。该提议方法融合了基于去噪的插件和 Play (PnP)方法的优点,以及基于生成模型的反问题方法的优点。首先,我们利用 VAE 的特性设计了一个高效的算法,该算法从插件和 Play (PnP)方法的收敛保证中受益匪浅。其次,我们的 approach 不仅限于特定的数据集,而 proposed PnP-HVAE 模型能够在任何大小的自然图像上解决图像恢复问题。我们的实验结果表明,提出的 PnP-HVAE 方法与领先的基于插件和 Play (PnP)方法的 PnP 方法以及基于生成模型的其他领先的恢复方法竞争。
URL
https://arxiv.org/abs/2303.11217
