2026· IEEE Signal Processing Letters· Vol 33, pp. 2934-2938· 0 citations· 38 references
Computer Science
Abstract
Most existing low-light image enhancement methods mainly rely on feature modeling in a single domain, making it difficult to simultaneously achieve global illumination correction, local detail restoration, and noise suppression. To overcome this limitation, we propose a low-light image enhancement network(MPNet) that leverages multi-domain prior attention, and introduce MPGSA (Multi-domain Prior Guided Self-Attention) as its core module. Specifically, MPGSA incorporates priors from the spatial, Fourier, and wavelet domains into the attention mechanism. Through complementary multi-domain modeling, it improves global illumination restoration, local texture reconstruction, and noise suppression. Extensive experimental results demonstrate that the proposed method not only achieves outstanding visual quality and competitive quantitative metrics on multiple public datasets, but also performs excellently on downstream tasks, showcasing strong generalization ability and broad application potential.
This work introduces a Multi-Domain Attention Module (MDAM) to integrate spatial features with frequency-domain global context, and a Dynamic Frequency-domain Fusion Module (DFFM) that employs dynamic filters for detail refinement, noise suppression, and local brightness correction.
Yi-Fan Wang, Si-Bao Chen· International Conference on...· 0 citations
The framework first performs illumination-aware self-supervised denoising to generate a cleaner reference image, which is then used to guide diffusion-based enhancement with a pre-trained backbone, and uses pairwise downsampling together with the proposed illumination prior to suppress noise in dark regions.
The Edge-guided Hybrid Enhancement Network (EHENet), an efficient network integrating structural priors and spatial-angular extraction, is proposed, which significantly outperforms state-of-the-art methods in both quality and efficiency.
Hao Wu, Bing-Jie Zhu, Shizheng Li et al.· International Conference on...· 0 citations
Existing methods typically require training a separate model for each dataset, making them difficult to generalize across diverse illumination conditions. To address this limitation, we propose a novel low-light image enhancement method based on a Mixture of Experts (MoE) mechanism with fast adaptation. In our framewor...
Yi Wang, Haonan Su, Zhao-Lin Xiao· IEEE Signal Processing Lette...· 0 citations
A Progressive Prompt-Guided Enhancement Network (PPGENet) for unsupervised low-light image enhancement that leverages multimodal priors from CLIP and achieves superior performance in both quantitative metrics and visual quality.
Ming-Tong Chen, Xiaowen Shi, Yongqiang Tang et al.· International Conference on...· 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.
