This paper aims to address a common challenge in deep learning-based image transformation methods, such as image enhancement and super-resolution, which heavily rely on precisely aligned paired datasets with pixel-level alignments. However, creating precisely aligned paired images presents significant challenges and hinders the advancement of methods trained on such data. To overcome this challenge, this paper introduces a novel and simple Frequency Distribution Loss (FDL) for computing distribution distance within the frequency domain. Specifically, we transform image features into the frequency domain using Discrete Fourier Transformation (DFT). Subsequently, frequency components (amplitude and phase) are processed separately to form the FDL loss function. Our method is empirically proven effective as a training constraint due to the thoughtful utilization of global information in the frequency domain. Extensive experimental evaluations, focusing on image enhancement and super-resolution tasks, demonstrate that FDL outperforms existing misalignment-robust loss functions. Furthermore, we explore the potential of our FDL for image style transfer that relies solely on completely misaligned data. Our code is available at: https://github.com/eezkni/FDL

翻译：本文旨在解决基于深度学习的图像变换方法（如图像增强和超分辨率）中普遍存在的挑战——这些方法严重依赖像素级精确对齐的配对数据集。然而，构建精确对齐的配对图像面临重大困难，且阻碍了基于此类数据训练方法的发展。为克服这一挑战，本文提出一种新颖简洁的频率分布损失（FDL），用于计算频域内的分布距离。具体而言，我们通过离散傅里叶变换（DFT）将图像特征转换至频域，随后分别处理频率分量（振幅和相位）以构建FDL损失函数。由于巧妙利用了频域中的全局信息，我们的方法经实证证明可作为有效的训练约束。针对图像增强和超分辨率任务的广泛实验评估表明，FDL优于现有抗错位损失函数。此外，我们探索了FDL在完全依赖错位数据的图像风格迁移中的应用潜力。我们的代码开源在：https://github.com/eezkni/FDL