HAIR: Hypernetworks-based All-in-One Image Restoration
This addresses a bottleneck in image restoration for computer vision applications by enabling models to adapt to specific degradations, though it is incremental as it builds on existing hypernetwork and All-in-One approaches.
The paper tackles the problem of All-in-One image restoration models using the same parameters for different degradations, which limits performance, by proposing HAIR, a hypernetworks-based plug-and-play method that dynamically adapts parameters based on input degradation, improving performance in both single-task and All-in-One settings with Res-HAIR achieving superior or comparable results to state-of-the-art methods.
Image restoration aims to recover a high-quality clean image from its degraded version. Recent progress in image restoration has demonstrated the effectiveness of All-in-One image restoration models in addressing various unknown degradations simultaneously. However, these existing methods typically utilize the same parameters to tackle images with different types of degradation, forcing the model to balance the performance between different tasks and limiting its performance on each task. To alleviate this issue, we propose HAIR, a Hypernetworks-based All-in-One Image Restoration plug-and-play method that generates parameters based on the input image and thus makes the model to adapt to specific degradation dynamically. Specifically, HAIR consists of two main components, i.e., Classifier and Hyper Selecting Net (HSN). The Classifier is a simple image classification network used to generate a Global Information Vector (GIV) that contains the degradation information of the input image, and the HSN is a simple fully-connected neural network that receives the GIV and outputs parameters for the corresponding modules. Extensive experiments demonstrate that HAIR can significantly improve the performance of existing image restoration models in a plug-and-play manner, both in single-task and All-in-One settings. Notably, our proposed model Res-HAIR, which integrates HAIR into the well-known Restormer, can obtain superior or comparable performance compared with current state-of-the-art methods. Moreover, we theoretically demonstrate that to achieve a given small enough error, our proposed HAIR requires fewer parameters in contrast to mainstream embedding-based All-in-One methods. The code is available at https://github.com/toummHus/HAIR.