Gradient-Guided Parameter Mask for Multi-Scenario Image Restoration Under Adverse Weather

TL;DR

This paper introduces a parameter masking technique guided by gradient variations to improve multi-scenario image restoration under adverse weather, achieving state-of-the-art results without adding extra parameters.

Contribution

It proposes a novel gradient-guided parameter masking method that adaptively segments model parameters for different weather scenarios without increasing model complexity.

Findings

Achieves state-of-the-art PSNR scores on multiple weather datasets.

Effectively isolates task-specific parameters using gradient fluctuation analysis.

Improves efficiency and effectiveness in multi-weather image restoration.

Abstract

Removing adverse weather conditions such as rain, raindrop, and snow from images is critical for various real-world applications, including autonomous driving, surveillance, and remote sensing. However, existing multi-task approaches typically rely on augmenting the model with additional parameters to handle multiple scenarios. While this enables the model to address diverse tasks, the introduction of extra parameters significantly complicates its practical deployment. In this paper, we propose a novel Gradient-Guided Parameter Mask for Multi-Scenario Image Restoration under adverse weather, designed to effectively handle image degradation under diverse weather conditions without additional parameters. Our method segments model parameters into common and specific components by evaluating the gradient variation intensity during training for each specific weather condition. This enables the model to precisely and adaptively learn relevant features for each weather scenario, improving both efficiency and effectiveness without compromising on performance. This method constructs specific masks based on gradient fluctuations to isolate parameters influenced by other tasks, ensuring that the model achieves strong performance across all scenarios without adding extra parameters. We demonstrate the state-of-the-art performance of our framework through extensive experiments on multiple benchmark datasets. Specifically, our method achieves PSNR scores of 29.22 on the Raindrop dataset, 30.76 on the Rain dataset, and 29.56 on the Snow100K dataset. Code is available at: \href{https://github.com/AierLab/MultiTask}{https://github.com/AierLab/MultiTask}.