Xinhao Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xinhao Wu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Naida Ding
The State Key Laboratory of Robotics and Intelligent System, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
1 shared publication - Qiang Wang
Key Laboratory of Manufacturing Industrial Integrated Automation, Shenyang University, Shenyang, China
1 shared publication - Sen Lin
School of Automation and Electrical Engineering, Shenyang Ligong University, Shenyang, China
1 shared publication - Wentao Li
The State Key Laboratory of Robotics and Intelligent System, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
1 shared publication - Yandong Tang
Shenyang Institute of Automation, Chinese Academy of Sciences
1 shared publication - Yu Guan
The State Key Laboratory of Robotics and Intelligent System, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
1 shared publication
Latest Publications
- Open Access
- 11 October 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (20) , 10931
GLMA: Global-to-Local Mamba Architecture for Low-Light Image Enhancement
In recent years, Mamba has gained increasing importance in the field of image restoration, gradually outperforming traditional convolutional neural networks (CNNs) and Transformers. However, the existing Mamba-based networks mainly focus on capturing global contextual relationships and neglect the crucial impact of local feature interactions on restoration performance in low-light environments. These environments inherently require the joint optimization of multi-scale spatial dependencies and frequency-domain characteristics. The traditional CNNs and Transformers face challenges in modeling long-range dependencies, while State Space Models (SSMs) in Mamba demonstrate proficiency in sequential modeling yet exhibit limitations in fine-grained feature extraction. To address the limitations of existing methods in capturing global degradation patterns, this paper proposes a novel global-to-local feature extraction framework through systematic Mamba integration. The Low-Frequency Mamba Block (LFMBlock) is introduced first to perform refined feature extraction in the low-frequency domain. The High-Frequency Guided Enhancement Block (HFGBlock) is used, which utilizes low-frequency priors to compensate for texture distortions in high-frequency components. Comprehensive experiments on multiple benchmark datasets show that the Global-to-Local Mamba architecture achieves superior performance in low-light restoration and image enhancement. It significantly outperforms state-of-the-art methods in both quantitative metrics and visual quality preservation, especially in recovering edge details and suppressing noise amplification under extreme illumination conditions. The hierarchical design effectively bridges global structural recovery with local texture refinement, setting a new paradigm for frequency-aware image restoration.
- 11 October 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (20) , 10931
Open AccessGLMA: Global-to-Local Mamba Architecture for Low-Light Image Enhancement
In recent years, Mamba has gained increasing importance in the field of image restoration, gradually outperforming traditional convolutional neural networks (CNNs) and Transformers. However, the existing Mamba-based networks mainly focus on capturing global contextual relationships and neglect the crucial impact of local feature interactions on restoration performance in low-light environments. These environments inherently require the joint optimization of multi-scale spatial dependencies and frequency-domain characteristics. The traditional CNNs and Transformers face challenges in modeling long-range dependencies, while State Space Models (SSMs) in Mamba demonstrate proficiency in sequential modeling yet exhibit limitations in fine-grained feature extraction. To address the limitations of existing methods in capturing global degradation patterns, this paper proposes a novel global-to-local feature extraction framework through systematic Mamba integration. The Low-Frequency Mamba Block (LFMBlock) is introduced first to perform refined feature extraction in the low-frequency domain. The High-Frequency Guided Enhancement Block (HFGBlock) is used, which utilizes low-frequency priors to compensate for texture distortions in high-frequency components. Comprehensive experiments on multiple benchmark datasets show that the Global-to-Local Mamba architecture achieves superior performance in low-light restoration and image enhancement. It significantly outperforms state-of-the-art methods in both quantitative metrics and visual quality preservation, especially in recovering edge details and suppressing noise amplification under extreme illumination conditions. The hierarchical design effectively bridges global structural recovery with local texture refinement, setting a new paradigm for frequency-aware image restoration.