---
title: "Enhance Image as You Like with Unpaired Learning"
authors:
  - "Xiaopeng Sun"
  - "Muxingzi Li"
  - "Tianyu He"
  - "Lubin Fan"
doi: "10.24963/ijcai.2021/140"
url: "https://ijcai.org/proceedings/2021/140"
pdf: "https://ijcai.org/proceedings/2021/0140.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "1011-1017"
track: "Main Track"
keywords:
  - "Machine Learning Applications: Applications of Unsupervised Learning"
  - "Computer Vision: 2D and 3D Computer Vision"
---

# Enhance Image as You Like with Unpaired Learning

Xiaopeng Sun, Muxingzi Li, Tianyu He, Lubin Fan

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 1011-1017. DOI: [10.24963/ijcai.2021/140](https://doi.org/10.24963/ijcai.2021/140)

## 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.