EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HLCNet: An HVI-Guided Cross-Branch Network with Large-Small Convolutions for Practical Low-Light Image Enhancement

Yuantao Zhang, Cairang Sanzhi, Dongcai Zhao, Zhicheng Dong, Jie Li, Bowen Liu

Applied Sciences · 02.08.2026 · 16 (15) · 7678

DOI: 10.3390/app16157678 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 02.08.2026. Verfasst von Yuantao Zhang und 5 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Innovation and Development Joint Fund of the Chongqing Natural Science Foundation, Science and Technology Plan Project of the Tibet Autonomous Region, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Images captured under practical low-light conditions typically suffer from insufficient brightness, color distortion, noise, and blur, and the enhancement process itself may further introduce overexposed highlights. This paper presents HLCNet, an HVI-guided Large-Small Convolutional Cross-Branch Network for low-light restoration. RGB inputs are transformed into the HVI space so that chromatic and intensity information can be enhanced in two complementary branches. Each branch applies LSConv to couple broad illumination context with local structural modeling, followed by SE channel recalibration and an LCA-based encoder–decoder, while a soft overexposure constraint suppresses excessive responses without hard clipping. To ensure a controlled comparison, CIDNet is reproduced in the same Tesla T4 environment, whereas the published CIDNet results and other previously reported values are explicitly marked as external references. On LOL-Blur, HLCNet raises the PSNR of the reproduced CIDNet baseline from 26.5438 dB to 27.6260 dB, increases the SSIM from 0.8839 to 0.8863, and reduces the LPIPS from 0.1224 to 0.1056. On LOL-v2 Real and Synthetic, it attains 23.843 dB and 25.991 dB PSNR, respectively. Ablation, sensitivity, qualitative, and perceptual color-space analyses indicate that HLCNet is particularly effective for low-light images containing blur and weak structural details.

Förderung

  • Innovation and Development Joint Fund of the Chongqing Natural Science Foundation
  • Science and Technology Plan Project of the Tibet Autonomous Region, China

Zitieren

APA

Zhang, Y., Sanzhi, C., Zhao, D., Dong, Z., Li, J., & Liu, B. (2026). HLCNet: An HVI-Guided Cross-Branch Network with Large-Small Convolutions for Practical Low-Light Image Enhancement. Applied Sciences, 16(15), 7678. https://doi.org/10.3390/app16157678

Vancouver

Zhang Y, Sanzhi C, Zhao D, Dong Z, Li J, Liu B. HLCNet: An HVI-Guided Cross-Branch Network with Large-Small Convolutions for Practical Low-Light Image Enhancement. Applied Sciences. 2026;16(15):7678. doi:10.3390/app16157678

BibTeX
@article{Zhang2026,
  author = {Zhang, Yuantao and Sanzhi, Cairang and Zhao, Dongcai and Dong, Zhicheng and Li, Jie and Liu, Bowen},
  title = {HLCNet: An HVI-Guided Cross-Branch Network with Large-Small Convolutions for Practical Low-Light Image Enhancement},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {15},
  pages = {7678},
  doi = {10.3390/app16157678}
}
Kostenlos starten →