计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (4): 200-210.DOI: 10.3778/j.issn.1002-8331.2209-0470

• 图形图像处理 • 上一篇    下一篇

结合稠密小波变换的双分支低照度图像增强

陈俊杰,周永霞,祖佳贞,盛威,赵平   

  1. 1. 中国计量大学  信息工程学院,杭州  310018
    2. 中国计量大学  浙江省电磁波信息技术与计量检测重点实验室,杭州  310018
  • 出版日期:2024-02-15 发布日期:2024-02-15

Dual-Branch Low-Light Image Enhancement Combined with Dense Wavelet Transform

CHEN Junjie, ZHOU Yongxia, ZU Jiazhen, SHEN Wei, ZHAO Ping   

  1. 1. College of Information Engineering, China Jiliang University, Hangzhou 310018, China
    2. Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, China Jiliang University, Hangzhou 310018, China
  • Online:2024-02-15 Published:2024-02-15

摘要: 针对低照度图像存在低亮度、高噪声、色彩失真等问题,提出了一种结合稠密小波变换的双分支低照度图像增强方法。采用稠密小波网络进行多尺度特征信息融合,在减少信息丢失的同时使网络具有一定的去噪能力。在多尺度特征融合中嵌入全局注意力模块和特征提取模块,充分提取全局和局部特征。通过双分支结构对图像进行色彩增强和细节重建,使得低照度图像具有较好的增强效果。引入了新的联合损失函数从多方面指导网络训练,以增强网络性能。将所提方法与主流方法相比较,实验结果充分表明,所提方法有效提高了低照度图像的亮度,抑制了图像噪声,并取得了更丰富的细节和色彩信息,得到的增强图像更清晰自然,在峰值信噪比和结构相似度等图像质量客观评价指标方面也具有显著的优势。

关键词: 稠密小波变换, 低照度, 图像增强, 双分支, 联合损失函数

Abstract: A dual-branch image enhancement method combining dense wavelet transform is proposed to solve the problems of low brightness, high noise, and color distortion in low-light images. Firstly, dense wavelet networks are used for multi-scale feature information fusion to reduce information loss and provide denoising capability. Then, the global attention module and feature extraction module are embedded in the multi-scale feature fusion to fully extract global and local features. Finally, the effect of low-light images is enhanced by color enhancement and detail reconstruction with a dual-branch structure. In addition, a new joint loss function is introduced to guide the network training from multiple aspects to enhance its performance. The experimental results show that the proposed method effectively improves the brightness of low-light images, suppresses image noise, and obtains richer details and color information. The enhanced images are clearer and more natural, and the peak signal-to-noise ratio and structural similarity have significant advantages over the mainstream methods.

Key words: dense wavelet, low-light, image enhancement, dual-branch, joint loss function