Towards Unsupervised Deep Image Enhancement With Generative Adversarial Network

• Published in: IEEE transactions on image processing Vol. 29; pp. 9140 - 9151
• Main Authors: Ni, Zhangkai, Yang, Wenhan, Wang, Shiqi, Ma, Lin, Kwong, Sam
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Gallium nitride; generative adversarial network; Generative adversarial networks; Generators; global attention; Histograms; Image color analysis; Image enhancement; Image quality; Machine learning; Mapping; Regularization; Task analysis; Unsupervised learning
• ISSN: 1057-7149; 1941-0042; 1941-0042
• DOI: 10.1109/TIP.2020.3023615

Improving the aesthetic quality of images is challenging and eager for the public. To address this problem, most existing algorithms are based on supervised learning methods to learn an automatic photo enhancer for paired data, which consists of low-quality photos and corresponding expert-retouched versions. However, the style and characteristics of photos retouched by experts may not meet the needs or preferences of general users. In this paper, we present an unsupervised image enhancement generative adversarial network (UEGAN), which learns the corresponding image-to-image mapping from a set of images with desired characteristics in an unsupervised manner, rather than learning on a large number of paired images. The proposed model is based on single deep GAN which embeds the modulation and attention mechanisms to capture richer global and local features. Based on the proposed model, we introduce two losses to deal with the unsupervised image enhancement: (1) fidelity loss , which is defined as a <inline-formula> <tex-math notation="LaTeX">\ell 2 </tex-math></inline-formula> regularization in the feature domain of a pre-trained VGG network to ensure the content between the enhanced image and the input image is the same, and (2) quality loss that is formulated as a relativistic hinge adversarial loss to endow the input image the desired characteristics. Both quantitative and qualitative results show that the proposed model effectively improves the aesthetic quality of images. Our code is available at: https://github.com/eezkni/UEGAN .