Single-image de-raining with feature-supervised generative adversarial network

Peng Xiang, Lei Wang, Fuxiang Wu, Jun Cheng, Mengchu Zhou

Research output: Contribution to journalArticlepeer-review

54 Scopus citations


De-raining, which aims at rain-steak removal from images, is a practical task in computer vision. However, it is difficult due to its ill-posed nature. In this letter, we propose a deep neural network architecture, feature-supervised generative adversarial network (FS-GAN) for single-image rain removal. Its main idea is to train a generative adversarial network (GAN) for which the supervision from ground truth is imposed on different layers of the generator network. We design a feature-supervised generator, a discriminator, an optimization target, as well as the detailed structure of FS-GAN. Experiments show that the proposed FS-GAN achieves better performance than state-of-the-art de-raining methods on both synthetic and real-world images in terms of quantitative and visual quality.

Original languageEnglish (US)
Article number8663315
Pages (from-to)650-654
Number of pages5
JournalIEEE Signal Processing Letters
Issue number5
StatePublished - May 2019

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics


  • Rain removal
  • convolutional neural networks
  • generative adversarial network


Dive into the research topics of 'Single-image de-raining with feature-supervised generative adversarial network'. Together they form a unique fingerprint.

Cite this