EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

Variational Bayesian Inference Deraining Network Based on Latent Variable Grouping

Yan Shen, Zhenghang Chen, Jiange Xu, Xuanming Hu, Xiaotao Shao, Yanbing Li

IET Image Processing · 2026-01 · 20 (1)

DOI: 10.1049/ipr2.70420 ↗

At a glance

Journal article in IET Image Processing, published online on 2026-06-29. Written by Yan Shen and 5 co-authors. 53 references. The full text is freely available (open access, CC BY 4.0).

AbstraktBibliografické údajeCiteRelated studies

Abstract (original language)

Recently, data‐driven methods for image deraining have achieved remarkable progress. However, the scarcity of accurately paired real‐world rainy and clean images poses considerable challenges, which consequently hinders the generalization capability of existing networks to real‐world rainy scenarios. To tackle these problems, we propose a variational Bayesian inference deraining network (VBDNet) that integrates model‐driven and data‐driven approaches within a unified variational Bayesian framework. Specifically, we introduce a latent variable grouping strategy to enhance the expressive capacity of the prior and variational posterior for modelling complex rain distributions. To maintain distributional consistency across groups, a residual distribution mechanism is designed to stabilize the Kullback–Leibler divergence during optimization. Moreover, we redesign BNet with a multi‐scale feature fusion network, which enables it to better model the diverse and complex structures of rain streaks. VBDNet consists of BNet for background inference, RNet for rain streak generation with grouped latent variables and DNet as a discriminator for adversarial learning. Extensive experiments on both synthetic datasets and real‐world SPA‐Data demonstrate that VBDNet achieves superior deraining performance and exhibits stronger generalization capability compared with state‐of‐the‐art methods.

Cite

APA

Shen, Y., Chen, Z., Xu, J., Hu, X., Shao, X., & Li, Y. (2026). Variational Bayesian Inference Deraining Network Based on Latent Variable Grouping. IET Image Processing, 20(1). https://doi.org/10.1049/ipr2.70420

Vancouver

Shen Y, Chen Z, Xu J, Hu X, Shao X, Li Y. Variational Bayesian Inference Deraining Network Based on Latent Variable Grouping. IET Image Processing. 2026;20(1). doi:10.1049/ipr2.70420

BibTeX
@article{Shen2026,
  author = {Shen, Yan and Chen, Zhenghang and Xu, Jiange and Hu, Xuanming and Shao, Xiaotao and Li, Yanbing},
  title = {Variational Bayesian Inference Deraining Network Based on Latent Variable Grouping},
  journal = {IET Image Processing},
  year = {2026},
  volume = {20},
  number = {1},
  doi = {10.1049/ipr2.70420}
}
Start for free →