A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Filters
UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning
[article]
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