计算机科学
卷积神经网络
人工智能
对比度(视觉)
图像(数学)
特征(语言学)
计算机视觉
对比度增强
模式识别(心理学)
图像增强
语言学
医学
放射科
哲学
磁共振成像
作者
Tao Li,Chuang Zhu,Guoqing Xiang,Yuan Li,Huizhu Jia,Xiaodong Xie
标识
DOI:10.1109/vcip.2017.8305143
摘要
In this paper, we propose a CNN based method to perform low-light image enhancement. We design a special module to utilize multiscale feature maps, which can avoid gradient vanishing problem as well. In order to preserve image textures as much as possible, we use SSIM loss to train our model. The contrast of low-light images can be adaptively enhanced using our method. Results demonstrate that our CNN based method outperforms other contrast enhancement methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI