Convolutional Neural Networks Considering Local and Global features for Image Enhancement
This work addresses image quality enhancement for applications like photography or computer vision, but it is incremental as it builds on existing CNN-based approaches by adding global feature handling.
The paper tackles the problem of image enhancement by proposing a CNN architecture that integrates local and global features to restore lost pixel values from clipping and quantizing, resulting in higher-quality images as shown by improved scores on metrics like TMQI, entropy, NIQE, and BRISQUE compared to conventional methods.
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.