Name
Abstract | ||
|---|---|---|
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. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/CVPR42600.2020.00223 | 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) |
DocType | ISSN | Citations |
Conference | 1063-6919 | 7 |
PageRank | References | Authors |
0.42 | 39 | 7 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hang Dong | 1 | 43 | 10.03 |
| Jin-shan Pan | 2 | 567 | 30.84 |
| Lei Xiang | 3 | 7 | 1.10 |
| Zhe Hu | 4 | 291 | 19.58 |
| Xinyi Zhang | 5 | 14 | 2.19 |
| Fei Wang | 6 | 55 | 13.07 |
| Yang Ming-Hsuan | 7 | 15303 | 620.69 |