Removing rain from images via combining detection and removal

Wen Li; Kangying Wang; Chao Xiong; Xiaochuan Guo

doi:10.1117/12.2636786

29 April 2022 Removing rain from images via combining detection and removal

Wen Li, Kangying Wang, Chao Xiong, Xiaochuan Guo

Proceedings Volume 12247, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2022); 1224706 (2022) https://doi.org/10.1117/12.2636786
Event: 2022 International Conference on Image, Signal Processing, and Pattern Recognition, 2022, Guilin, China

Abstract

The performance of rain removal methods which are based on deep learning is largely affected by the designed models and training datasets for the image rain removal tasks. Most of current state-of-the-art focus on how to construct powerful deep models. But in this paper, we start from two perspectives of training dataset and model. We propose a novel rain model that includes a rain layer, a background layer and and a way how rainy image is generated. Based on this model, we develop a multi-task deep learning architecture that learns features of both the rain layer and the clean background layer. The additional information of rain layer is important because its loss function can provide additional powerful information to the network. Then we collected a large number of images of real rain streaks and outdoor scenes, and produced datasets for training. The effectiveness of our model and architecture was shown in tests on synthetic datasets.

Citation Download Citation

Wen Li, Kangying Wang, Chao Xiong, and Xiaochuan Guo "Removing rain from images via combining detection and removal", Proc. SPIE 12247, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2022), 1224706 (29 April 2022); https://doi.org/10.1117/12.2636786

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available