2019/05/07 by Kinoshita, Yuma, Kiya, Hitoshi
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Multimedia (cs.MM) #electronic engineering #information engineering
paper · doi:10.48550/arxiv.1905.02899
In this paper, we propose a novel convolutional neural network (CNN) architecture considering both local and global features for image enhancement. Most conventional image enhancement methods, including Retinex-based methods, cannot restore lost pixel values caused by clipping and quantizing. CNN-based methods have recently been proposed to solve the problem, but they still have a limited performance due to network architectures not handling global features. To handle both local and global features, the proposed architecture consists of three networks: a local encoder, a global encoder, and a decoder. In addition, high dynamic range (HDR) images are used for generating training data for our networks. The use of HDR images makes it possible to train CNNs with better-quality images than images directly captured with cameras. Experimental results show that the proposed method can produce higher-quality images than conventional image enhancement methods including CNN-based methods, in terms of various objective quality metrics: TMQI, entropy, NIQE, and BRISQUE.