DCGSD: Low-Light Image Enhancement With Dual-Conditional Guidance Sparse Diffusion Model
IEEE Transactions on Circuits and Systems for Video Technology · 2025-08 · 35 (8) · 7792-7806
DOI: 10.1109/tcsvt.2025.3544771 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-08. Verfasst von Haiyan Jin und 6 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 71 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
When restoring low-light images, most methods largely overlook the ambiguity due to dark noise and lack discrimination for region and shape representations, resulting in invalid feature enhancement. In this work, we propose a physically explainable and prior guidance model for low-light image enhancement, termed Dual-Conditional Guidance Sparse Diffusion (DCGSD). Specifically, we introduce an elaborately designed Luminance Structure Guidance Head, which can be easily plugged into the existing diffusion model to emphasize the value of the luminance and structural representation. Furthermore, for reliable noise analysis, we provide a novel Sparse Attention Enhancement Module that is adaptively empowered to exploit the most useful region-to-region dependencies. This dynamic selection makes the diffusion process from dense to sparse, thus improving the efficiency of the reasoning noise distributions. To avoid noise amplification, we further present a Skip Calibration Module, which can be used to refine the local neighborhood that contains noisy and structural information. Extensive experiments have been performed to verify the superiority of the proposed method. DCGSD shows that leveraging dual-conditional guidance can support the diffusion model to produce sharper and more realistic results.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Jin, H., Wang, J., Zuo, F., Su, H., Xiao, Z., Wang, B., & Zhang, Y. (2025). DCGSD: Low-Light Image Enhancement With Dual-Conditional Guidance Sparse Diffusion Model. IEEE Transactions on Circuits and Systems for Video Technology, 35(8), 7792-7806. https://doi.org/10.1109/tcsvt.2025.3544771
Vancouver
Jin H, Wang J, Zuo F, Su H, Xiao Z, Wang B, et al. DCGSD: Low-Light Image Enhancement With Dual-Conditional Guidance Sparse Diffusion Model. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(8):7792-7806. doi:10.1109/tcsvt.2025.3544771
BibTeX
@article{Jin2025,
author = {Jin, Haiyan and Wang, Jing and Zuo, Fengyuan and Su, Haonan and Xiao, Zhaolin and Wang, Bin and Zhang, Yuanlin},
title = {DCGSD: Low-Light Image Enhancement With Dual-Conditional Guidance Sparse Diffusion Model},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2025},
volume = {35},
number = {8},
pages = {7792--7806},
doi = {10.1109/tcsvt.2025.3544771}
}
EUVIMED