Removing haze in images
Removing haze in images
Contrastive Learning for Compact Single Image Dehazing
arXiv paper abstract https://arxiv.org/abs/2104.09367v1
arXiv PDF paper https://arxiv.org/pdf/2104.09367v1.pdf
GitHub https://github.com/GlassyWu/AECR-Net
Single image dehazing is a challenging ill-posed problem due to the severe information degeneration.
… novel contrastive regularization (CR) built upon contrastive learning to exploit both the information of hazy images and clear images as negative and positive samples, respectively.
… we develop a compact dehazing network based on autoencoder-like (AE) framework. It involves an adaptive mixup operation and a dynamic feature enhancement module
… extensive experiments on synthetic and real-world datasets demonstrate that our AECR-Net surpass the state-of-the-art approaches.
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
