Structure-Texture Aware Network for Low-Light Image Enhancement
Structure-Texture Aware Network for Low-Light Image Enhancement
复制标题
用于低光图像增强的结构-纹理感知网络
DOI：
10.1109/tcsvt.2022.3141578
复制
发表时间：
2022
影响因子：
8.4
通讯作者：
C. Zhu
中科院分区：
文献类型：
--
作者：
Kai Xu;H. Chen;Chunmei Xu;Yi Jin;C. Zhu
全局结构和局部细节纹理对图像增强任务有不同的影响。然而，大多数现有作品以相同的方式处理这两个组件，没有充分考虑全局结构和局部细节纹理的特征。在这项工作中，我们提出了一种结构纹理感知网络（STANet），它成功地利用低光图像的结构和纹理特征来提高感知质量。为了构建 STANet，引入了精细尺度轮廓图引导滤波器将图像分解为结构分量和纹理分量。然后，设计结构注意和纹理注意子网络以充分利用这两个组件的特征。最后，利用具有注意机制的融合子网络来探索全局特征和局部特征之间的内部相关性。此外，为了优化所提出的 STANet 模型，我们提出了一种混合损失函数；具体来说，引入颜色损失函数来减轻增强图像中的颜色失真。大量实验表明，该方法提高了图像的视觉质量；此外，STANet 的性能优于大多数其他最先进的方法。
Global structure and local detailed texture have different effects on image enhancement tasks. However, most existing works treated these two components in the same way, without fully considering the characteristics of the global structure and local detailed texture. In this work, we propose a structure-texture aware network (STANet) that successfully exploits structure and texture features of low-light images to improve perceptual quality. To construct STANet, a fine-scale contour map guided filter is introduced to decompose the image into a structure component and a texture component. Then, structure-attention and texture-attention subnetworks are designed to fully exploit the characteristics of these two components. Finally, a fusion subnetwork with attention mechanisms is utilized to explore the internal correlations among the global and local features. Furthermore, to optimize the proposed STANet model, we propose a hybrid loss function; specifically, a color loss function is introduced to alleviate color distortion in the enhanced image. Extensive experiments demonstrate that the proposed method improves the visual quality of images; moreover, STANet outperforms most other state-of-the-art approaches.