结合视觉显著性与注意力机制的低光照图像增强

Combining Visual Saliency and Attention Mechanism for Low-Light Image Enhancement

低光照图像增强是解决低光照环境下各种视觉分析任务的基础和核心步骤,但现有主流方法由于普遍未能对结构信息进行有效刻画,往往存在曝光不均衡、颜色失真等问题.针对上述问题,文中提出结合视觉显著性与注意力机制的低光照图像增强方法.首先,构建基于注意力机制的低光照图像增强网络,在引入注意力机制的同时考虑局部细节和全局信息,正确刻画增强结果中的颜色信息.再遵循由粗到细的逐步优化理念,设计渐进式注意力机制,将增强过程分阶段细化,实现精细化建设.然后,引入显著性引导的特征融合,增强网络对图像中显著性目标的感知能力,从更符合视觉认知需求的角度提升对于结构信息的表达,有效避免产生噪声/伪影等问题.实验表明,文中方法有效解决现有工作存在的曝光不足与颜色失真等问题,性能较优.

Low-light image enhancement is the foundation and core step for solving various visual analysis tasks in low-light environments.However,the existing mainstream methods generally fail to characterize structural information effectively,resulting in some problems,such as unbalanced exposure and color distortion.Therefore,a low-light image enhancement network combining visual saliency and attention mechanism is proposed in this paper.A low-light image enhancement framework based on attention mechanism is firstly constructed by introducing attention mechanism with consideration of both local details and global information to characterize the color information in the enhancement results correctly.To achieve refined construction,a progressive process is designed to refine the enhancement process in stages following the concept of gradual optimization from coarse to fine.The feature fusion module guided by visual saliency is introduced to enhance the ability of the network to perceive salient objects in images and improve the expression of structural information from a perspective of being more in line with visual cognitive needs.Thus,noise/artifacts and other problems are avoided effectively.Experiments show that the proposed method solves the problems of unbalanced exposure and color distortion effectively with superior performance.