Journal
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
Volume -, Issue -, Pages 2154-2164Publisher
IEEE
DOI: 10.1109/CVPR42600.2020.00223
Keywords
-
Categories
Funding
- 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]
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available