This paper proposes a new way of regularizing an inverse problem in imaging (e.g., deblurring or inpainting) by means of a deep generative neural network. Compared to end-to-end models, such approaches seem particularly interesting since the same network can be used for many different problems and experimental conditions, as soon as the generative model is suited to the data. Previous works proposed to use a synthesis framework, where the estimation is performed on the latent vector, the solution being obtained afterwards via the decoder. Instead, we propose an analysis formulation where we directly optimize the image itself and penalize the latent vector. We illustrate the interest of such a formulation by running experiments of inpainting, deblurring and super-resolution. In many cases our technique achieves a clear improvement of the performance and seems to be more robust, in particular with respect to initialization.

中文翻译：

---

通过深度生成模型进行正则化：一种分析观点

本文提出了一种通过深度生成神经网络对成像中反问题进行正则化的新方法（例如，去模糊或修复）。与端到端模型相比，这种方法似乎特别有趣，因为只要生成模型适合数据，就可以将同一网络用于许多不同的问题和实验条件。先前的工作提出使用综合框架，其中对潜矢量进行估计，然后通过解码器获得解决方案。取而代之的是，我们提出一种分析公式，在该公式中，我们直接优化图像本身并惩罚潜在矢量。我们通过进行修复，去模糊和超分辨率实验来说明这种配方的兴趣。