Aug 2026· 2026 IEEE International Conference on Mechatronics and Automation (ICMA)· pp. 1115-1120· 0 citations· 12 references
Abstract
Images captured under nighttime conditions often exhibit insufficient brightness, heavy noise contamination, and significant texture corruption. Existing Retinex-inspired enhancement frameworks mainly focus on spatial feature reconstruction while paying limited attention to the coupling between illumination structures and fine texture information. To alleviate this limitation, a dual-stream frequency-decoupled framework named DSFD-Net is developed. A Frequency Feature Decomposition (FFD) module is introduced to learn disentangled low- and high-frequency representations in a data-driven manner. Based on this, a dual-stream architecture jointly optimizes a frequency branch and an illumination enhancement branch to improve illumination estimation and detail preservation. Furthermore, a Dual-Stream Multidomain Fusion Block (DSMFB) is designed to effectively integrate frequency-aware and illumination-aware features during reconstruction. Experiments on LOLv1 and LOLv2 demonstrate superior performance in visual quality, noise suppression, and detail recovery, especially under challenging nighttime conditions.
Comprehensive experiments on four benchmarks demonstrate that LEFTNet achieves competitive performance across the evaluated Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Average Mean Brightness Error (AMBE), Gradient Magnitude Similarity Deviation (GMSD), and Visual Saliency-Induced Ind...
Low-light image enhancement is a fundamental computer-vision problem that affects downstream tasks such as object detection, surveillance, autonomous driving, and night-time photography. Existing learning-based solutions either rely on heavy generative models with hundreds of millions of parameters or on purely spatial...
M. Al-Azzawi, H. I. Wahhab, Safaa Aqeel Khazraji et al.· JOIV: International Journal...· 0 citations
Underwater image enhancement (UIE) is still difficult. This is mainly due to wavelength-dependent light absorption, scattering, and environmental noise, which lead to low visibility, color distortion, and loss of fine details. Most existing deep learning (DL) based models primarily operate on spatial-domain convolu...
Najmul Hassan, Munsif Ali, Abu Saleh Musa Miah et al.· Scientific Reports· 0 citations
The proposed AASFNet achieves competitive or leading performance across multiple key metrics under the evaluated experimental settings, yielding the best or second-best PSNR, SSIM, and NIQE values among the compared methods.
Yang Li, Xian-Guo Li, Dan He et al.· Electronics· 0 citations
DPSF-Net is proposed, a dual-prior spatial-frequency network built on MCAF-Net for real-world RSID that achieves state-of-the-art performance on the real-world RRSHID remote sensing image dehazing benchmark and remains competitive across multiple synthetic datasets.
Mei Lu, Shang-Liang Shao, Shan-Liang Yao· 0 citations
This work proposes a model-driven deep neural network to effectively handle the joint degradation of low light and blur and designs an illumination enhancement module (IEM) and a reflectance refinement module (RRM) to improve brightness, restore fine details, and suppress noise.
Yao Xiao, You-Shen Xia, Zhen-Yu Lu et al.· IEEE Transactions on Neural...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
