1 Hit in 4.0 sec

UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning [article]

Yongzhen Wang, Xuefeng Yan, Fu Lee Wang, Haoran Xie, Wenhan Yang, Mingqiang Wei, Jing Qin
2022 arXiv   pre-print
We propose an effective unsupervised contrastive learning paradigm for image dehazing, dubbed UCL-Dehaze.  ...  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 bridging the gap between synthetic  ...  Towards real-world image dehazing, we propose an unsupervised contrastive learning paradigm, called UCL-Dehaze.  ... 
arXiv:2205.01871v1 fatcat:4chy2dryivgzlnhitusd3ldxae