Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network

Abstract

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.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• scikit-image: Image processing in Python
• An Overview of Multi-Task Learning in Deep Neural Networks
• Path-Restore: Learning Network Path Selection for Image Restoration
• Learning Implicitly Recurrent CNNs Through Parameter Sharing
• Restoring Images with Unknown Degradation Factors by Recurrent Use of a Multi-branch Network