文献类型：期刊文献

英文题名：LapECNet: Laplacian Pyramid Networks for Image Exposure Correction

作者：Li, Yongchang[1];Jiang, Jing[1]

第一作者：Li, Yongchang

通讯作者：Jiang, J[1]

机构：[1]Beijing Union Univ, Coll Informat Technol, Beijing 100101, Peoples R China

第一机构：北京联合大学智慧城市学院

通讯机构：[1]corresponding author), Beijing Union Univ, Coll Informat Technol, Beijing 100101, Peoples R China.|[1141734]北京联合大学智慧城市学院;[11417]北京联合大学;

年份：2025

卷号：15

期号：16

外文期刊名：APPLIED SCIENCES-BASEL

收录：;WOS:【SCI-EXPANDED(收录号:WOS:001557256000001)】；

基金：This research was funded by the Horizontal General Project (Science and Technology Category) of Beijing Union University, titled "Development of Video-Based Extensometry Technology Using Digital Image Correlation (DIC)".

语种：英文

外文关键词：exposure correction; frequency disentanglement; Laplacian pyramid networks; dynamic aggregation

摘要：Images captured under complex lighting conditions often suffer from local under/ overexposure and detail loss. Existing methods typically process illumination and texture information in a mixed manner, making it difficult to simultaneously achieve precise exposure adjustment and preservation of detail. To address this challenge, we propose LapECNet, an enhanced Laplacian pyramid network architecture for image exposure correction and detail reconstruction. Specifically, it decomposes the input image into different frequency bands of a Laplacian pyramid, enabling separate handling of illumination adjustment and detail enhancement. The framework first decomposes the image into three feature levels. At each level, we introduce a feature enhancement module that adaptively processes image features across different frequency bands using spatial and channel attention mechanisms. After enhancing the features at each level, we further propose a dynamic aggregation module that learns adaptive weights to hierarchically fuse multi-scale features, achieving context-aware recombination of the enhanced features. Extensive experiments with public benchmarks on the MSEC dataset demonstrated that our method gave improvements of 15.4% in PSNR and 7.2% in SSIM over previous methods. On the LCDP dataset, our method demonstrated improvements of 7.2% in PSNR and 13.9% in SSIM over previous methods.