This article proposes a novel approach to regularize the ill-posed and non-linear blind image deconvolution (blind deblurring) using deep generative networks as priors. We employ two separate pretrained generative networks — given lower-dimensional Gaussian vectors as input, one of the generative models samples from the distribution of sharp images, while the other from that of the blur kernels. To deblur, we find a sharp image and a blur kernel in the range of the respective generators that best explain the blurred image. Our experiments show promising deblurring results on images even under large blurs, and heavy measurement noise. Generative models often manifest a representation error to fit arbitrary samples from the learned distribution. This may be due to multiple factors such as mode collapse, architectural choices, or training caveats. To improve the generalizability of the proposed approach, we present a modification of the proposed scheme that governs the deblurring process under both generative, and classical priors. Training generative models is computationally expensive on larger and more diverse image datasets. Our experiments also show that even an untrained structured (convolutional) network acts as an image prior. We leverage this fact to deblur diverse/complex images for which a trained generative network might not be available.

中文翻译：

---

使用深度生成先验进行盲图像反卷积


本文提出了一种使用深度生成网络作为先验来正则化不适定和非线性盲图像反卷积（盲去模糊）的新方法。我们采用两个独立的预训练生成网络——给定低维高斯向量作为输入，其中一个生成模型样本来自清晰图像的分布，而另一个来自模糊内核的样本。为了去模糊，我们在各自的生成器范围内找到一个清晰的图像和一个模糊内核，最能解释模糊图像。我们的实验表明，即使在大模糊和严重测量噪声的情况下，图像去模糊效果也有希望。生成模型通常会表现出表示误差，以​​适应学习分布中的任意样本。这可能是由于多种因素造成的，例如模式崩溃、架构选择或训练注意事项。为了提高所提出方法的普遍性，我们提出了对所提出方案的修改，该方案在生成先验和经典先验下控制去模糊过程。在更大、更多样化的图像数据集上训练生成模型的计算成本很高。我们的实验还表明，即使是未经训练的结构化（卷积）网络也可以充当图像先验。我们利用这一事实对可能无法使用训练有素的生成网络的多样化/复杂图像进行去模糊。