UCL-Dehaze: Toward Real-World Image Dehazing via Unsupervised Contrastive Learning.

Yongzhen WANG, Xuefeng YAN, Fu Lee WANG, Haoran XIE, Wenhan YANG, Xiao-Ping ZHANG, Jing QIN, Mingqiang WEI

Research output: Journal PublicationsJournal Article (refereed)peer-review


While the wisdom of training an image dehazing model on synthetic hazy data can alleviate the difficulty of collecting real-world hazy/clean image pairs, it brings the well-known domain shift problem. From a different yet new perspective, this paper explores contrastive learning with an adversarial training effort to leverage unpaired real-world hazy and clean images, thus alleviating the domain shift problem and enhancing the network’s generalization ability in real-world scenarios. We propose an effective unsupervised contrastive learning paradigm for image dehazing, dubbed UCL-Dehaze. Unpaired real-world clean and hazy images are easily captured, and will serve as the important positive and negative samples respectively when training our UCL-Dehaze network. To train the network more effectively, we formulate a new self-contrastive perceptual loss function, which encourages the restored images to approach the positive samples and keep away from the negative samples in the embedding space. Besides the overall network architecture of UCL-Dehaze, adversarial training is utilized to align the distributions between the positive samples and the dehazed images. Compared with recent image dehazing works, UCL-Dehaze does not require paired data during training and utilizes unpaired positive/negative data to better enhance the dehazing performance. We conduct comprehensive experiments to evaluate our UCL-Dehaze and demonstrate its superiority over the state-of-the-arts, even only 1,800 unpaired real-world images are used to train our network. Source code is publicly available at https://github.com/yz-wang/UCL-Dehaze.
Original languageEnglish
Pages (from-to)1361-1374
Number of pages14
JournalIEEE Transactions on Image Processing
Early online date9 Feb 2024
Publication statusPublished - 2024

Bibliographical note

Publisher Copyright:
© 1992-2012 IEEE.


  • UCL-Dehaze
  • adversarial training
  • image dehazing
  • unpaired data
  • unsupervised contrastive learning


Dive into the research topics of 'UCL-Dehaze: Toward Real-World Image Dehazing via Unsupervised Contrastive Learning.'. Together they form a unique fingerprint.

Cite this