Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software


  • Satoshi Kosugi The University of Tokyo
  • Toshihiko Yamasaki The University of Tokyo




This paper tackles unpaired image enhancement, a task of learning a mapping function which transforms input images into enhanced images in the absence of input-output image pairs. Our method is based on generative adversarial networks (GANs), but instead of simply generating images with a neural network, we enhance images utilizing image editing software such as Adobe® Photoshop® for the following three benefits: enhanced images have no artifacts, the same enhancement can be applied to larger images, and the enhancement is interpretable. To incorporate image editing software into a GAN, we propose a reinforcement learning framework where the generator works as the agent that selects the software's parameters and is rewarded when it fools the discriminator. Our framework can use high-quality non-differentiable filters present in image editing software, which enables image enhancement with high performance. We apply the proposed method to two unpaired image enhancement tasks: photo enhancement and face beautification. Our experimental results demonstrate that the proposed method achieves better performance, compared to the performances of the state-of-the-art methods based on unpaired learning.




How to Cite

Kosugi, S., & Yamasaki, T. (2020). Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 11296-11303. https://doi.org/10.1609/aaai.v34i07.6790



AAAI Technical Track: Vision