In recent years, we have witnessed the great advancement of Deep neural networks (DNNs) in image restoration. However, a critical limitation is that they cannot generalize well to real-world degradations with different degrees or types. In this paper, we are the first to propose a novel training strategy for image restoration from the causality perspective, to improve the generalization ability of DNNs for unknown degradations. Our method, termed Distortion Invariant representation Learning (DIL), treats each distortion type and degree as one specific confounder, and learns the distortion-invariant representation by eliminating the harmful confounding effect of each degradation. We derive our DIL with the back-door criterion in causality by modeling the interventions of different distortions from the optimization perspective. Particularly, we introduce counterfactual distortion augmentation to simulate the virtual distortion types and degrees as the confounders. Then, we instantiate the intervention of each distortion with a virtual model updating based on corresponding distorted images, and eliminate them from the meta-learning perspective. Extensive experiments demonstrate the effectiveness of our DIL on the generalization capability for unseen distortion types and degrees. Our code will be available at https://github.com/lixinustc/Casual-IRDIL.

翻译：近年来，深度神经网络（DNN）在图像复原领域取得了显著进展。然而，其关键局限性在于无法有效泛化至不同程度或类型的真实环境退化。本文首次从因果视角提出新型图像复原训练策略，旨在提升DNN对未知退化的泛化能力。我们提出的畸变不变表征学习（DIL）方法，将每个畸变类型与程度视为特定混杂因子，通过消除各退化因素的有害混杂效应来学习畸变不变表征。基于因果理论的后门准则，我们从优化角度对不同畸变的干预过程进行建模，从而推导出DIL方法。具体而言，我们引入反事实畸变增强技术来模拟作为混杂因子的虚拟畸变类型与程度，随后通过相应畸变图像的虚拟模型更新实例化各畸变的干预操作，并从元学习视角消除其影响。大量实验证明，DIL方法在未知畸变类型与程度的泛化能力上具有显著效果。相关代码将发布于https://github.com/lixinustc/Casual-IRDIL。