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.
@article{arxiv.2004.13388,
title = {Multi-Scale Boosted Dehazing Network with Dense Feature Fusion},
author = {Hang Dong and Jinshan Pan and Lei Xiang and Zhe Hu and Xinyi Zhang and Fei Wang and Ming-Hsuan Yang},
journal= {arXiv preprint arXiv:2004.13388},
year = {2020}
}
Comments
Accepted by CVPR 2020. The code are available at https://github.com/BookerDeWitt/MSBDN-DFF