EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DCAF-Net: Density-Conditioned Attention Fusion Network for Single-Image Dehazing

Nianfeng Li iD, Shaojie Liu iD, Hongjie Ding iD, Shenyan Gao iD, Zhiguo Xiao iD, Qian Liu iD

Sensors · 22.07.2026 · 26 (14) · 4656

DOI: 10.3390/s26144656 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 22.07.2026. Verfasst von Nianfeng Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, Changchun University, Changchun 130022, China. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jilin Provincial Scientific and Technological Department.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single-image dehazing aims to recover clear scenes from degraded images affected by atmospheric scattering, serving as a critical preprocessing technique for improving the imaging quality of visual sensors. Existing deep learning-based dehazing methods exhibit limited generalization ability in real-world scenarios, primarily due to the spatial non-uniformity of haze and its coupling with illumination and texture degradation, as well as the scarcity of real paired data. To address these issues, this paper proposes a haze-density conditional attention fusion network (DCAF-Net). The network employs an adaptive haze density perception module to fuse priors such as the dark channel, local contrast, and saturation, generating a spatial haze density guidance map. This map is then embedded as conditional information into the multi-scale feature modulation and attention fusion process, enabling adaptive restoration of regions with different degradation levels. Furthermore, a residual dense cascaded feature enhancement module is designed to leverage feature reuse, gated fusion, and residual learning to enhance the representational capacity of deep features. Training adopts a joint optimization objective combining Charbonnier reconstruction loss, perceptual contrast loss, and structural similarity loss. Experimental results demonstrate that DCAF-Net achieves competitive performance against representative methods on multiple synthetic and real-world hazy datasets, and shows promising restoration performance on representative real-world hazy scenes, and can provide high-quality image preprocessing support for visual-sensor-based intelligent perception systems.

Schlagwörter

Stichwörter der Autor:innen

density-conditioned attentionimage dehazingmulti-prior fusionnon-homogeneous fog distribution

Autor:innen und Institutionen

  • College of Computer Science and Technology, Changchun University, Changchun 130022, China.
  • School of Computer Science & Technology, Beijing Institute of Technology, Beijing 100811, China.

ORCID-Profile: Nianfeng Li, Shaojie Liu, Hongjie Ding, Shenyan Gao, Zhiguo Xiao, Qian Liu

Förderung

  • Jilin Provincial Scientific and Technological Department

Zitieren

APA

Li, N., Liu, S., Ding, H., Gao, S., Xiao, Z., & Liu, Q. (2026). DCAF-Net: Density-Conditioned Attention Fusion Network for Single-Image Dehazing. Sensors, 26(14), 4656. https://doi.org/10.3390/s26144656

Vancouver

Li N, Liu S, Ding H, Gao S, Xiao Z, Liu Q. DCAF-Net: Density-Conditioned Attention Fusion Network for Single-Image Dehazing. Sensors. 2026;26(14):4656. doi:10.3390/s26144656

BibTeX
@article{Li2026,
  author = {Li, Nianfeng and Liu, Shaojie and Ding, Hongjie and Gao, Shenyan and Xiao, Zhiguo and Liu, Qian},
  title = {DCAF-Net: Density-Conditioned Attention Fusion Network for Single-Image Dehazing},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {14},
  pages = {4656},
  doi = {10.3390/s26144656}
}
Kostenlos starten →