Adverse Weather Image Translation with Asymmetric and Uncertainty-aware GAN

Jeong Gi Kwak, Youngsaeng Jin, Yuanming Li, Dongsik Yoon, Donghyeon Kim, Hanseok Ko

Research output: Contribution to conferencePaperpeer-review

2 Citations (Scopus)

Abstract

Adverse weather image translation belongs to the unsupervised image-to-image (I2I) translation task which aims to transfer adverse condition domain (e.g., rainy night) to standard domain (e.g., day). It is a challenging task because images from adverse domains have some artifacts and insufficient information. Recently, many studies employing Generative Adversarial Networks (GANs) have achieved notable success in I2I translation but there are still limitations in applying them to adverse weather enhancement. Symmetric architecture based on bidirectional cycle-consistency loss is adopted as a standard framework for unsupervised domain transfer methods. However, it can lead to inferior translation result if the two domains have imbalanced information. To address this issue, we propose a novel GAN model, i.e., AU-GAN, which has an asymmetric architecture for adverse domain translation. We insert a proposed feature transfer network (T-net) in only a normal domain generator (i.e., rainy night → day) to enhance encoded features of the adverse domain image. In addition, we introduce asymmetric feature matching for disentanglement of encoded features. Finally, we propose uncertainty-aware cycle-consistency loss to address the regional uncertainty of a cyclic reconstructed image. We demonstrate the effectiveness of our method by qualitative and quantitative comparisons with state-of-the-art models.

Original languageEnglish
Publication statusPublished - 2021
Event32nd British Machine Vision Conference, BMVC 2021 - Virtual, Online
Duration: 2021 Nov 222021 Nov 25

Conference

Conference32nd British Machine Vision Conference, BMVC 2021
CityVirtual, Online
Period21/11/2221/11/25

Bibliographical note

Publisher Copyright:
© 2021. The copyright of this document resides with its authors.

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Adverse Weather Image Translation with Asymmetric and Uncertainty-aware GAN'. Together they form a unique fingerprint.

Cite this