# Unpaired Image Enhancement with Quality-Attention Generative Adversarial Network

arXiv: https://arxiv.org/abs/2012.15052 · HTML: https://mlsanity.com/paper/2012.15052/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Dec 2020.

## Built on by (most cited first, 10 of 10)

- [Very Lightweight Photo Retouching Network with Conditional Sequential Modulation](https://mlsanity.com/paper/2104.06279/) (2021)
- [CSformer: Bridging Convolution and Transformer for Compressive Sensing](https://mlsanity.com/paper/2112.15299/) (2021)
- [ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field](https://mlsanity.com/paper/2312.09095/) (2023)
- [Learning Diverse Tone Styles for Image Retouching](https://mlsanity.com/paper/2207.05430/) (2022)
- [Gap-closing Matters: Perceptual Quality Evaluation and Optimization of Low-Light Image Enhancement](https://mlsanity.com/paper/2302.11464/) (2023)
- [Cycle-Interactive Generative Adversarial Network for Robust Unsupervised Low-Light Enhancement](https://mlsanity.com/paper/2207.00965/) (2022)
- [The Loop Game: Quality Assessment and Optimization for Low-Light Image Enhancement](https://mlsanity.com/paper/2202.09738/) (2022)
- [Region-Aware Portrait Retouching with Sparse Interactive Guidance](https://mlsanity.com/paper/2304.04017/) (2023)
- [Invertible Network for Unpaired Low-light Image Enhancement](https://mlsanity.com/paper/2112.13107/) (2021)
- [Just Noticeable Difference Modeling for Face Recognition System](https://mlsanity.com/paper/2209.05856/) (2022)

## Abstract (arXiv)

In this work, we aim to learn an unpaired image enhancement model, which can enrich low-quality images with the characteristics of high-quality images provided by users. We propose a quality attention generative adversarial network (QAGAN) trained on unpaired data based on the bidirectional Generative Adversarial Network (GAN) embedded with a quality attention module (QAM). The key novelty of the proposed QAGAN lies in the injected QAM for the generator such that it learns domain-relevant quality attention directly from the two domains. More specifically, the proposed QAM allows the generator to effectively select semantic-related characteristics from the spatial-wise and adaptively incorporate style-related attributes from the channel-wise, respectively. Therefore, in our proposed QAGAN, not only discriminators but also the generator can directly access both domains which significantly facilitates the generator to learn the mapping function. Extensive experimental results show that, compared with the state-of-the-art methods based on unpaired learning, our proposed method achieves better performance in both objective and subjective evaluations.