文献类型：期刊文献

英文题名：Lightweight and Fast Low-Light Image Enhancement Method Based on PoolFormer

作者：Hu, Xin[1];Wang, Jinhua[1];Xu, Sunhan[1]

第一作者：Hu, Xin

通讯作者：Wang, JH[1]

机构：[1]Beijing Union Univ, Smart City Coll, Beijing 100101, Peoples R China

第一机构：北京联合大学继续教育学院

通讯机构：[1]corresponding author), Beijing Union Univ, Smart City Coll, Beijing 100101, Peoples R China.|[1141733]北京联合大学继续教育学院;[11417]北京联合大学;

年份：2024

卷号：E107D

期号：1

起止页码：157-160

外文期刊名：IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS

收录：;EI(收录号：20240415420039);Scopus(收录号：2-s2.0-85182709182);WOS:【SCI-EXPANDED(收录号:WOS:001137449200011)】；

基金：This work was supported by National Nature Science Foundation of China (No.62172045 and No.62272049) and Projects of Beijing Union University (No.ZKZD202301).

语种：英文

外文关键词：key computer vision; low-light image enhancement; transformer; poolformer; lightweight

摘要：Images captured in low-light environments have low visibility and high noise, which will seriously affect subsequent visual tasks such as target detection and face recognition. Therefore, low-light image enhancement is of great significance in obtaining high-quality images and is a challenging problem in computer vision tasks. A low-light enhancement model, LLFormer, based on the Vision Transformer, uses axis-based multi head self-attention and a cross-layer attention fusion mechanism to reduce the complexity and achieve feature extraction. This algorithm can enhance images well. However, the calculation of the attention mechanism is complex and the number of parameters is large, which limits the application of the model in practice. In response to this problem, a lightweight module, PoolFormer, is used to replace the attention module with spatial pooling, which can increase the parallelism of the network and greatly reduce the number of model parameters. To suppress image noise and improve visual effects, a new loss function is constructed for model optimization. The experiment results show that the proposed method not only reduces the number of parameters by 49%, but also performs better in terms of image detail restoration and noise suppression compared with the baseline model. On the LOL dataset, the PSNR and SSIM were 24.098 dB and 0.8575 respectively. On the MIT-Adobe FiveK dataset, the PSNR and SSIM were 27.060 dB and 0.9490. The evaluation results on the two datasets are better than the current mainstream low-light enhancement algorithms.