Multi-Scale and U-shaped Networks are widely used in various image restoration problems, including deblurring. Keeping in mind the wide range of applications, we present a comparison of these architectures and their effects on image deblurring. We also introduce a new block called as NFResblock. It consists of a Fast Fourier Transformation layer and a series of modified Non-Linear Activation Free Blocks. Based on these architectures and additions, we introduce NFResnet and NFResnet+, which are modified multi-scale and U-Net architectures, respectively. We also use three different loss functions to train these architectures: Charbonnier Loss, Edge Loss, and Frequency Reconstruction Loss. Extensive experiments on the Deep Video Deblurring dataset, along with ablation studies for each component, have been presented in this paper. The proposed architectures achieve a considerable increase in Peak Signal to Noise (PSNR) ratio and Structural Similarity Index (SSIM) value.

翻译：多尺度网络与U形网络被广泛用于包括去模糊在内的各类图像恢复问题中。鉴于其广泛的应用场景，本文对比了这两种架构及其对图像去模糊的影响。我们提出了一种名为NFResblock的新型模块，它由一个快速傅里叶变换层和一系列改进的无非线性激活模块组成。基于上述架构与改进，我们分别提出了改进的多尺度网络NFResnet和改进的U-Net架构NFResnet+。同时，我们采用三种不同的损失函数训练这些网络：Charbonnier损失、边缘损失和频率重建损失。本文在Deep Video Deblurring数据集上进行了大量实验，并对每个组件进行了消融研究。所提出的架构在峰值信噪比（PSNR）和结构相似性指数（SSIM）上均实现了显著提升。