Home
Publications
Photo Gallery
Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions
Yi Zhu, Tianyu Wang, Xueyang Fu, Xin Yang, Xuejin Guo, Jiabin Dai, Yu Qiao, Xiaowei Hu
CVPR · 2023
Xueyang Fu: Corresponding author; Xiaowei Hu: Corresponding author
Research summary
A unified framework for image restoration that learns both weather-general and weather-specific features to handle multiple adverse conditions.
Abstract
Image restoration under multiple adverse weather conditions aims to remove weather-related artifacts by using the single set of network parameters. In this paper, we find that distorted images under different weather conditions contain general characteristics as well as their specific characteristics. Inspired by this observation, we design an efficient unified framework with a two-stage training strategy to explore the weather-general and weather-specific features. The first training stage aims to learn the weather-general features by taking the images under various weather conditions as the inputs and outputting the coarsely restored results. The second training stage aims to learn to adaptively expand the specific parameters for each weather type in the deep model, where requisite positions for expansion of weather-specific parameters are learned automatically. Hence, we can obtain an efficient and unified model for image restoration under multiple adverse weather conditions. Moreover, we build the first real-world benchmark dataset with multiple weather conditions to better deal with real-world weather scenarios. Experimental results show that our method achieves superior performance on all the synthetic and real-world benchmark datasets.
Key insight
Disentangles weather-general and weather-specific features for image restoration, enabling a single model to handle multiple adverse weather conditions (rain, haze, snow) instead of requiring separate task-specific networks.
Paper & resources
BibTeX
@inproceedings{zhu2023weather,
title={Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions},
author={Zhu, Yi and Wang, Tianyu and Fu, Xueyang and Yang, Xin and Guo, Xuejin and Dai, Jiabin and Qiao, Yu and Hu, Xiaowei},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2023}
}