2026-10-12T04:54:58Z https://www.scidb.cn/oai

10.57760/sciencedb.21394 2025-02-27T11:26:04Z

2025-02-27 Two-Stage Low-light Image Enhancement Based on Wavelet Transform doi:10.57760/sciencedb.21394 en In low-light environments, images often suffer from insufficient brightness, decreased contrast, and blurred details, leading to significant degradation of visual quality. To address these issues, this paper proposes a dual-stage wavelet transform-based method for low-light image enhancement. The method builds upon wavelet transform theory and employs a U-Net architecture to progressively achieve feature encoding, decoding, and enhancement through two sequential stages: preliminary restoration and fine-grained enhancement. For effective noise suppression and detail enhancement, we design an enhanced wavelet-domain feature fusion module that integrates discrete wavelet transform, inverse discrete wavelet transform, and dual attention mechanisms. Meanwhile, the proposed dynamic gated spatial attention and lightweight fusion-curve attention mechanisms collaborate within this feature fusion module to process image features with refined adaptability. Additionally, a fusion perceptual loss function is developed to guide the model in generating visually natural enhanced images with authentic details by jointly optimizing pixel-level errors and perceptual quality metrics. Experimental results demonstrate that our method achieves state-of-the-art performance on key metrics (e.g., PSNR, SSIM) across multiple public low-light datasets, exhibiting superior capabilities in both noise suppression and detail recovery. Image enhancement; U-Net; Wavelet transformation; Attention mechanism; Loss function Sun Jing Sun Fuqi Hao Shijie Sun Fuming PUBLIC https://api.github.com/licenses/apache-2.0 dataset Science Data Bank