English

Enhance Images as You Like with Unpaired Learning

Computer Vision and Pattern Recognition 2021-10-05 v1 Image and Video Processing

Abstract

Low-light image enhancement exhibits an ill-posed nature, as a given image may have many enhanced versions, yet recent studies focus on building a deterministic mapping from input to an enhanced version. In contrast, we propose a lightweight one-path conditional generative adversarial network (cGAN) to learn a one-to-many relation from low-light to normal-light image space, given only sets of low- and normal-light training images without any correspondence. By formulating this ill-posed problem as a modulation code learning task, our network learns to generate a collection of enhanced images from a given input conditioned on various reference images. Therefore our inference model easily adapts to various user preferences, provided with a few favorable photos from each user. Our model achieves competitive visual and quantitative results on par with fully supervised methods on both noisy and clean datasets, while being 6 to 10 times lighter than state-of-the-art generative adversarial networks (GANs) approaches.

Keywords

Cite

@article{arxiv.2110.01161,
  title  = {Enhance Images as You Like with Unpaired Learning},
  author = {Xiaopeng Sun and Muxingzi Li and Tianyu He and Lubin Fan},
  journal= {arXiv preprint arXiv:2110.01161},
  year   = {2021}
}

Comments

7 pages; IJCAI 2021