EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HLFDehazeNet: Direction-Aware Cross-Frequency Gating for High-Resolution Image Dehazing

Chongyao Yan, Yumo Shen, Yangjie Zhang, Boyu Lu, Lei Pan

Electronics · 16.11.2026 · 15 (22) · 5314

DOI: 10.3390/electronics15225314 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 16.11.2026. Verfasst von Chongyao Yan und 4 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universitie, Henan Province Key R&D Special Fund, Civil Aviation Information Technology Research Center, Civil Aviation Flight University of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-resolution image dehazing requires the recovery of broad scene structure together with fine directional details. We propose HLFDehazeNet, a wavelet-based network that regulates information exchange between these complementary representations. A discrete wavelet transform separates shallow features into one low-frequency band and three directional high-frequency bands, which are processed by parallel encoder–decoder branches with attentive state-space modules. Residual directional cross-frequency interaction (RDCI) uses a separate learned gate for each high-frequency band to modulate bidirectional exchange with the low-frequency branch before decoding. After inverse wavelet reconstruction, edge-conditioned residual compensation (ECRC) uses edge-related features to modulate an image-space residual correction. HLFDehazeNet obtains PSNR/SSIM values of 33.26 dB/0.9882 on 8KDehaze, 28.74 dB/0.9365 on 4KID, and 24.01 dB/0.7844 on O-HAZE. On RESIDE6K, the joint configuration improves PSNR by 2.56 dB over the same network with both modules disabled. The contribution of each module depends on the presence of the other, and internal ablations favor direction-specific gate predictors and residual modulation in the tested configurations. Without fine-tuning, HLFDehazeNet trained on RESIDE6K achieves PSNR/SSIM values of 28.97 dB/0.9773 on SOTS-Outdoor and 13.13 dB/0.5307 on NH-HAZE. Qualitative comparisons on the real-world subset of HSTS illustrate the restoration results on real hazy scenes.

Förderung

  • Fundamental Research Funds for the Central Universitie
  • Henan Province Key R&D Special Fund
  • Civil Aviation Information Technology Research Center, Civil Aviation Flight University of China

Zitieren

APA

Yan, C., Shen, Y., Zhang, Y., Lu, B., & Pan, L. (2026). HLFDehazeNet: Direction-Aware Cross-Frequency Gating for High-Resolution Image Dehazing. Electronics, 15(22), 5314. https://doi.org/10.3390/electronics15225314

Vancouver

Yan C, Shen Y, Zhang Y, Lu B, Pan L. HLFDehazeNet: Direction-Aware Cross-Frequency Gating for High-Resolution Image Dehazing. Electronics. 2026;15(22):5314. doi:10.3390/electronics15225314

BibTeX
@article{Yan2026,
  author = {Yan, Chongyao and Shen, Yumo and Zhang, Yangjie and Lu, Boyu and Pan, Lei},
  title = {HLFDehazeNet: Direction-Aware Cross-Frequency Gating for High-Resolution Image Dehazing},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {22},
  pages = {5314},
  doi = {10.3390/electronics15225314}
}
Kostenlos starten →