Color-wise Attention Network for Low-light Image Enhancement

CVPR Workshops(2020)

引用 45|浏览447
暂无评分
摘要
Absence of nearby light sources while capturing an image will degrade the visibility and quality of the captured image, making computer vision tasks difficult. In this paper, a color-wise attention network (CWAN) is proposed for low-light image enhancement based on convolutional neural networks. Motivated by the human visual system when looking at dark images, CWAN learns an end-to-end mapping between low-light and enhanced images while searching for any useful color cues in the low-light image to aid in the color enhancement process. Once these regions are identified, CWAN attention will be mainly focused to synthesize these local regions, as well as the global image. Both quantitative and qualitative experiments on challenging datasets demonstrate the advantages of our method in comparison with state-of-the-art methods.
更多
查看译文
关键词
qualitative analysis,quantitative analysis,convolutional neural networks,captured image,nearby light sources,low-light image enhancement,color-wise attention network,global image,CWAN attention,color enhancement process,color cues,dark images
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要