Existing methods have demonstrated effective performance on a single degradation type. In practical applications, however, the degradation is often unknown, and the mismatch between the model and the degradation will result in a severe performance drop. In this paper, we propose an all-in-one image restoration network that tackles multiple degradations. Due to the heterogeneous nature of different types of degradations, it is difficult to process multiple degradations in a single network. To this end, we propose to learn a neural degradation representation (NDR) that captures the underlying characteristics of various degradations. The learned NDR decomposes different types of degradations adaptively, similar to a neural dictionary that represents basic degradation components. Subsequently, we develop a degradation query module and a degradation injection module to effectively recognize and utilize the specific degradation based on NDR, enabling the all-in-one restoration ability for multiple degradations. Moreover, we propose a bidirectional optimization strategy to effectively drive NDR to learn the degradation representation by optimizing the degradation and restoration processes alternately. Comprehensive experiments on representative types of degradations (including noise, haze, rain, and downsampling) demonstrate the effectiveness and generalization capability of our method.

本研究中，我们提出了一种全能图像恢复网络，能够处理多种退化问题，通过学习神经退化表示(NDR)来解决多种退化数据的挑战，进一步结合退化查询模块和退化注入模块，实现了多种退化的全能恢复能力，同时采用双向优化策略来驱动NDR学习退化表示，我们的实验证明了该方法的有效性和泛化能力。

全能图像恢复的神经退化表示学习