Low-light images often suffer from uneven illumination, resulting in reduced brightness, low contrast, and increased noise interference. However, existing enhancement methods frequently lead to over- or under-enhancement, frequency domain distortion, or insufficient noise suppression, which adversely affect both visual quality and the performance of downstream vision tasks. To address these issues, we propose AASFNet, a novel low-light image enhancement network that integrates spatial and frequency domain features through amplitude enhancement and dual-domain fusion. The framework consists of a Frequency-domain Enhancement Network (FreqEnhanceNet) with an illumination-guided Amplitude Module (AmpModule) for adaptive brightness adjustment and a Spatial-Frequency Fusion Network (SpatFreqFusionNet) incorporating a Dual-Domain Fusion Module (DDFModule) for noise suppression and illumination correction via multi-scale feature interaction. This design enables the network to simultaneously adjust global illumination, restore local details, and suppress noise. Additionally, a joint spatial-frequency loss function is introduced, including an illumination-guided amplitude loss and a cosine phase loss, to enhance structural consistency and amplitude fidelity. Comprehensive experiments on the LOL-v2 Real and Synthetic datasets demonstrate that 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. Moreover, when applied as a preprocessing module, it achieves improved detection accuracy across multiple low-light benchmarks, with mAP scores of 78.63% on ExDark, 78.2% on DarkFace, and 80.32% on LoLI-Street. These results suggest the potential applicability of the model in real-world scenarios such as autonomous driving and surveillance, although further validation under actual deployment conditions is still required.
Yang Li, Xian-Guo Li, Dan He et al.· Electronics· 0 citations
Nourishing Xinjiang with culture (wenhua runjiang) represents a key practice of the Party’s Xinjiang governance strategy in the educational domain in the new era, while curriculum-based ideological and political education constitutes a strategic initiative for implementing the fundamental task of fostering virtue through education. Confronted with the distinctive ideological and political education ecology and the demand for application-oriented talent cultivation in the Xinjiang region, local higher education institutions face an urgent imperative: how to construct a systematic ideological-political cultivation framework through computing curricula, with nourishing Xinjiang with culture serving as the value compass and computing courses functioning as the disciplinary vehicle. Grounded in cultural identity theory and the consciousness of the community for the Chinese nation, this study elucidates the unique role of computing education in transmitting Chinese culture and safeguarding ideological security in border regions. It proposes an integrated “value–knowledge–competence” framework. Centering on the design of instructional objectives, content restructuring, methodological innovation, and evaluation and feedback, the study transforms discipline-specific features—such as cybersecurity, artificial intelligence, digital preservation of ethnic cultures, and algorithmic ethics—into focal points for ideological and political education, and substantiates them through concrete teaching cases. Furthermore, the article constructs a safeguarding closed-loop encompassing faculty capacity building, organizational leadership, and quality evaluation, with the aim of developing a replicable and scalable system of ideological-political cultivation through computing curricula, thereby providing intellectual and talent support for the initiative of nourishing Xinjiang with culture.
Yufeng Jia, Dan He· Journal of Contemporary Educ...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
