计算机科学
水准点(测量)
人工智能
图像(数学)
计算机视觉
图像编辑
人工神经网络
对比度(视觉)
深度学习
先验概率
图像复原
模式识别(心理学)
图像处理
大地测量学
贝叶斯概率
地理
作者
Ruixing Wang,Qing Zhang,Chi‐Wing Fu,Xiaoyong Shen,Wei Xing Zheng,Jiaya Jia
出处
期刊:Computer Vision and Pattern Recognition
日期:2019-06-01
被引量:606
标识
DOI:10.1109/cvpr.2019.00701
摘要
This paper presents a new neural network for enhancing underexposed photos. Instead of directly learning an image-to-image mapping as previous work, we introduce intermediate illumination in our network to associate the input with expected enhancement result, which augments the network's capability to learn complex photographic adjustment from expert-retouched input/output image pairs. Based on this model, we formulate a loss function that adopts constraints and priors on the illumination, prepare a new dataset of 3,000 underexposed image pairs, and train the network to effectively learn a rich variety of adjustment for diverse lighting conditions. By these means, our network is able to recover clear details, distinct contrast, and natural color in the enhancement results. We perform extensive experiments on the benchmark MIT-Adobe FiveK dataset and our new dataset, and show that our network is effective to deal with previously challenging images.
科研通智能强力驱动
Strongly Powered by AbleSci AI