Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network

TL;DR

This paper introduces an unsupervised GAN-based model for image enhancement that learns from unpaired images, effectively improving aesthetic quality without relying on expert-retouched paired data.

Contribution

The paper proposes UEGAN, an unsupervised deep GAN with modulation and attention mechanisms, introducing new loss functions for effective image enhancement without paired training data.

Findings

Effective aesthetic improvement demonstrated in experiments

Unsupervised learning achieves comparable results to supervised methods

Model captures both global and local image features

Abstract

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 L2 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.