期刊
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
卷 -, 期 -, 页码 2154-2164出版社
IEEE
DOI: 10.1109/CVPR42600.2020.00223
关键词
-
资金
- National Major Science and Technology Projects of China [2019ZX01008103]
- National Natural Science Foundation of China (NSFC) [61603291]
- Natural Science Basic Research Plan in Shaanxi Province of China [2018JM6057]
- Fundamental Research Funds for the Central Universities
- NSFC [61872421, 61922043]
- NSF of Jiangsu Province [BK20180471]
- NSF CAREER Grant [1149783]
In this paper, we propose a Multi-Scale Boosted Dehazing Network with Dense Feature Fusion based on the U-Net architecture. The proposed method is designed based on two principles, boosting and error feedback, and we show that they are suitable for the dehazing problem. By incorporating the Strengthen-Operate-Subtract boosting strategy in the decoder of the proposed model, we develop a simple yet effective boosted decoder to progressively restore the haze-free image. To address the issue of preserving spatial information in the U-Net architecture, we design a dense feature fusion module using the back-projection feedback scheme. We show that the dense feature fusion module can simultaneously remedy the missing spatial information from high-resolution features and exploit the non-adjacent features. Extensive evaluations demonstrate that the proposed model performs favorably against the state-of-the-art approaches on the benchmark datasets as well as real-world hazy images.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据