Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network
This addresses a more realistic scenario in image restoration for applications like photography or medical imaging, though it is incremental as it builds on existing deep learning methods for distortion tasks.
The paper tackles the problem of restoring images with spatially-heterogeneous distortions, where multiple corruptions affect different parts of an image, by proposing a mixture of experts network that learns common and distortion-specific representations, and experimentally shows it outperforms other models for both single and multiple distortions.
In recent years, deep learning-based methods have been successfully applied to the image distortion restoration tasks. However, scenarios that assume a single distortion only may not be suitable for many real-world applications. To deal with such cases, some studies have proposed sequentially combined distortions datasets. Viewing in a different point of combining, we introduce a spatially-heterogeneous distortion dataset in which multiple corruptions are applied to the different locations of each image. In addition, we also propose a mixture of experts network to effectively restore a multi-distortion image. Motivated by the multi-task learning, we design our network to have multiple paths that learn both common and distortion-specific representations. Our model is effective for restoring real-world distortions and we experimentally verify that our method outperforms other models designed to manage both single distortion and multiple distortions.