Paper
8 June 2023 URformer: a rain removal network integrating channel features and spatial features
Baohong Zhou, Zhiliang Huang, Youyan Zhang, Shuihong Zhou, Zongsheng Jiang
Author Affiliations +
Proceedings Volume 12707, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023); 127071Z (2023) https://doi.org/10.1117/12.2681381
Event: International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023), 2023, Changsha, China
Abstract
With the development of intelligent monitoring and autonomous driving technology, the adverse effects of rainy weather are receiving increasing attention. The current image de-raining techniques have two main drawbacks: first, they easily lose local features and channel features, and second, the computational cost of global calculations on large feature maps is staggering. In this paper, we propose a self-attention network called URformer, which integrates spatial features and channel features. We introduce a novel feature extraction module that effectively combines local self-attention and channel self-attention mechanisms. URformer significantly reduces the computational cost of traditional global Transformers while extracting and preserving channel and spatial features. Experimental results demonstrate that the URformer network exhibits excellent performance on the RGB image de-raining task.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Baohong Zhou, Zhiliang Huang, Youyan Zhang, Shuihong Zhou, and Zongsheng Jiang "URformer: a rain removal network integrating channel features and spatial features", Proc. SPIE 12707, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023), 127071Z (8 June 2023); https://doi.org/10.1117/12.2681381
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Rain

RGB color model

Windows

Feature extraction

Transformers

Image fusion

Image processing

Back to Top