EUVIMEDEUVIMED entdecken
Crossref

WSAMF-Net: Wavelet Spatial Attention-Based MultiStream Feedback Network for Single Image Dehazing

Xibin Song, Dingfu Zhou, Wei Li, Haodong Ding, Yuchao Dai, Liangjun Zhang

IEEE Transactions on Circuits and Systems for Video Technology · 2023-02 · 33 (2) · 575-588

DOI: 10.1109/tcsvt.2022.3207020 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2023-02. Verfasst von Xibin Song und 5 weiteren Autor:innen. Die Arbeit wurde bisher 75-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: Baidu Research, National Key Research and Development Program of China, Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single image-based dehazing has achieved remarkable progress with the development of deep learning technologies. End-to-end neural networks have been proposed to learn a direct hazy-to-clear image translation to recover the clear structures and edges cues from the hazy inputs. However, the frequency domain information is explored insufficiently and lots of intermediate structure and texture related cues of current dehazing networks are ignored, which limits the performances of current approaches. To handle these limitations mentioned above, a wavelet spatial attention based multi-stream feedback network (WSAMF-Net) is proposed for effective single image dehazing. Specifically, the proposed wavelet spatial attention utilizes both frequency-domain and spatial-domain information to enhance the extracted features for better structures and edges. Meanwhile, an enhanced multi-stream based cross feature fusion strategy, including vertical and horizontal attentions, is proposed to reweight and fuse the intermediate features of each stream to acquire more meaningful aggregated features, while the weight sharing strategy is used to achieve a good trade-off between performance and parameters. Besides, feedback mechanism is also designed to provide strong reconstruction ability. Furthermore, we propose a critical real-world industrial dataset (IDS) with images captured in real-world industrial quarry scenarios for research uses. Extensive experiments on various benchmarking datasets, including both synthetic and real-world datasets, demonstrate the superiority of our WSAMF-Net over state-of-the-art single image dehazing methods. The IDS dataset will be available at https://github.com/XBSong/IDS-Datasethttps://github.com/XBSong/IDS-Dataset.

Förderung

  • Baidu Research, National Key Research and Development Program of China
  • Natural Science Foundation of China

Zitieren

APA

Song, X., Zhou, D., Li, W., Ding, H., Dai, Y., & Zhang, L. (2023). WSAMF-Net: Wavelet Spatial Attention-Based MultiStream Feedback Network for Single Image Dehazing. IEEE Transactions on Circuits and Systems for Video Technology, 33(2), 575-588. https://doi.org/10.1109/tcsvt.2022.3207020

Vancouver

Song X, Zhou D, Li W, Ding H, Dai Y, Zhang L. WSAMF-Net: Wavelet Spatial Attention-Based MultiStream Feedback Network for Single Image Dehazing. IEEE Transactions on Circuits and Systems for Video Technology. 2023;33(2):575-588. doi:10.1109/tcsvt.2022.3207020

BibTeX
@article{Song2023,
  author = {Song, Xibin and Zhou, Dingfu and Li, Wei and Ding, Haodong and Dai, Yuchao and Zhang, Liangjun},
  title = {WSAMF-Net: Wavelet Spatial Attention-Based MultiStream Feedback Network for Single Image Dehazing},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2023},
  volume = {33},
  number = {2},
  pages = {575--588},
  doi = {10.1109/tcsvt.2022.3207020}
}
Kostenlos starten →