Deep neural networks (DNNs) have shown very promising results for various image restoration (IR) tasks. However, the design of network architectures remains a major challenging for achieving further improvements. While most existing DNN-based methods solve the IR problems by directly mapping low quality images to desirable high-quality images, the observation models characterizing the image degradation processes have been largely ignored. In this paper, we first propose a denoising-based IR algorithm, whose iterative steps can be computed efficiently. Then, the iterative process is unfolded into a deep neural network, which is composed of multiple denoisers modules interleaved with back-projection (BP) modules that ensure the observation consistencies. A convolutional neural network (CNN) based denoiser that can exploit the multi-scale redundancies of natural images is proposed. As such, the proposed network not only exploits the powerful denoising ability of DNNs, but also leverages the prior of the observation model. Through end-to-end training, both the denoisers and the BP modules can be jointly optimized. Experimental results on several IR tasks, e.g., image denoisig, super-resolution and deblurring show that the proposed method can lead to very competitive and often state-of-the-art results on several IR tasks, including image denoising, deblurring, and super-resolution.

中文翻译：

---

用于图像恢复的去噪先验驱动深度神经网络


深度神经网络 (DNN) 在各种图像恢复 (IR) 任务中显示出非常有前景的结果。然而，网络架构的设计仍然是实现进一步改进的主要挑战。虽然大多数现有的基于 DNN 的方法通过直接将低质量图像映射到所需的高质量图像来解决红外问题，但表征图像劣化过程的观测模型在很大程度上被忽略了。在本文中，我们首先提出了一种基于去噪的IR算法，其迭代步骤可以有效地计算。然后，迭代过程被展开为一个深度神经网络，该网络由多个降噪模块与反投影（BP）模块交错组成，以确保观察的一致性。提出了一种基于卷积神经网络（CNN）的降噪器，可以利用自然图像的多尺度冗余。因此，所提出的网络不仅利用了 DNN 强大的去噪能力，而且还利用了观察模型的先验。通过端到端训练，可以联合优化降噪器和BP模块。图像去噪、超分辨率和去模糊等多项 IR 任务的实验结果表明，所提出的方法可以在图像去噪、去模糊和超模糊等多种 IR 任务上带来非常有竞争力且通常是最先进的结果。 -解决。