Open Access iconOpen Access

ARTICLE

crossmark

Towards Robust Rain Removal with Unet++

Boxia Hu1,2,*, Yaqi Sun3, Yufei Yang1,4, 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: email

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

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


Cite This Article

APA Style
Hu, B., Sun, Y., Yang, Y., Ouyang, Z., Zhang, F. (2023). Towards robust rain removal with unet++. Computers, Materials & Continua, 75(1), 879-890. https://doi.org/10.32604/cmc.2023.035858
Vancouver Style
Hu B, Sun Y, Yang Y, Ouyang Z, Zhang F. Towards robust rain removal with unet++. Comput Mater Contin. 2023;75(1):879-890 https://doi.org/10.32604/cmc.2023.035858
IEEE Style
B. Hu, Y. Sun, Y. Yang, Z. Ouyang, and F. Zhang "Towards Robust Rain Removal with Unet++," Comput. Mater. Contin., vol. 75, no. 1, pp. 879-890. 2023. https://doi.org/10.32604/cmc.2023.035858



cc This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 879

    View

  • 654

    Download

  • 0

    Like

Share Link