Open Access

ARTICLE

Towards Robust Rain Removal with Unet++

Boxia Hu^1,2,*, Yaqi Sun³, Yufei Yang^1,4, Ze Ouyang³, Feng Zhang³

1 School of Mathematics, Hunan University, Changsha, 410082, China
2 College of Mathematics and Statistics, Hengyang Normal University, Hengyang, 421002, China
3 College of Computer Science and Technology, Hengyang Normal University, Hengyang, 421002, China
4 School of Mathematics, Changsha University, Changsha, 410022, China

* Corresponding Author: Boxia Hu. Email:

Computers, Materials & Continua 2023, 75(1), 879-890. https://doi.org/10.32604/cmc.2023.035858

Received 07 September 2022; Accepted 23 November 2022; Issue published 06 February 2023

Abstract

Image deraining has become a hot topic in the field of computer vision. It is the process of removing rain streaks from an image to reconstruct a high-quality background. This study aims at improving the performance of image rain streak removal and reducing the disruptive effects caused by rain. To better fit the rain removal task, an innovative image deraining method is proposed, where a kernel prediction network with Unet++ is designed and used to filter rainy images, and rainy-day images are used to estimate the pixel-level kernel for rain removal. To minimize the gap between synthetic and real data and improve the performance in real rainy image handling, a loss function and an effective data optimization method are suggested. In contrast with other methods, the loss function consists of Structural Similarity Index loss, edge loss, and L1 loss, and it is adopted to improve performance. The proposed algorithm can improve the Peak Signal-to-Noise ratio by 1.3% when compared to conventional approaches. Experimental results indicate that the proposed method can achieve a better efficiency and preserve more image structure than several classical methods.

---

Keywords

---