Loading [MathJax]/extensions/TeX/euler_ieee.js
USCFormer: Unified Transformer With Semantically Contrastive Learning for Image Dehazing | IEEE Journals & Magazine | IEEE Xplore

USCFormer: Unified Transformer With Semantically Contrastive Learning for Image Dehazing

Publisher: IEEE

Abstract:

Haze severely degrades the visibility of scene objects and deteriorates the performance of autonomous driving, traffic monitoring, and other vision-based intelligent tran...View more

Abstract:

Haze severely degrades the visibility of scene objects and deteriorates the performance of autonomous driving, traffic monitoring, and other vision-based intelligent transportation systems. As a potential remedy, we propose a novel unified Transformer with semantically contrastive learning for image dehazing, dubbed USCFormer. USCFormer has three key contributions. First, USCFormer absorbs the respective strengths of CNN and Transformer by incorporating them into a unified Transformer format. Thus, it allows the simultaneous capture of global-local dependency features for better image dehazing. Second, by casting clean/hazy images as the positive/negative samples, the contrastive constraint encourages the restored image to be closer to the ground-truth images (positives) and away from the hazy ones (negatives). Third, we regard the semantic information as important prior knowledge to help USCFormer mitigate the effects of haze on the scene and preserve image details and colors by leveraging intra-object semantic correlation. Experiments on synthetic datasets and real-world hazy photos fully validate the superiority of USCFormer in both perceptual quality assessment and subjective evaluation. Code is available at https://github.com/yz-wang/USCFormer .
Published in: IEEE Transactions on Intelligent Transportation Systems ( Volume: 24, Issue: 10, October 2023)
Page(s): 11321 - 11333
Date of Publication: 02 June 2023

ISSN Information:

Publisher: IEEE

Funding Agency:


References

References is not available for this document.