欠曝光图像增强的深度学习论文(CVPR2019)
深度学习
最后更新 2020-05-22 11:19 阅读 201
最后更新 2020-05-22 11:19
阅读 201
深度学习
Describe
•Input: Underexposed photo.
•Output: Full-res enhanced image.
•Dataset: MIT-Adobe FiveK ,a new dataset of 3,000 underexposed image pairs.
•Framework: TensorFlow
•Configuration: NVidia Titan X Pascal GPU
Major Contributions
•We propose a network for enhancing underexposed photos by estimating an image-to-illumination map- ping, and design a new loss function based on various illumination constraints and priors.
•We prepare a new dataset of 3,000 underexposed images, each with an expert-retouched reference.
•We perform evaluation on our method using existing and new datasets, and demonstrate the superiority of our method qualitatively and quantitatively.