# Dual Generator Generative Adversarial Networks for Multi-Domain Image-to-Image Translation

arXiv: https://arxiv.org/abs/1901.04604 · HTML: https://mlsanity.com/paper/1901.04604/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jan 2019.

## Built on by (most cited first, 8 of 8)

- [Motion Representations for Articulated Animation](https://mlsanity.com/paper/2104.11280/) (2021)
- [A Unified Hyper-GAN Model for Unpaired Multi-contrast MR Image Translation](https://mlsanity.com/paper/2107.11945/) (2021)
- [Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes](https://mlsanity.com/paper/2106.10876/) (2021)
- [Learning Unsupervised Cross-domain Image-to-Image Translation Using a Shared Discriminator](https://mlsanity.com/paper/2102.04699/) (2021)
- [SAR2EO: A High-resolution Image Translation Framework with Denoising Enhancement](https://mlsanity.com/paper/2304.04760/) (2023)
- [VoloGAN: Adversarial Domain Adaptation for Synthetic Depth Data](https://mlsanity.com/paper/2207.09204/) (2022)
- [Image-to-Image Translation Framework Embedded with Rotation Symmetry Priors](https://mlsanity.com/paper/2604.12805/) (2026)
- [Image Animation with Keypoint Mask](https://mlsanity.com/paper/2112.10457/) (2021)

## Abstract (arXiv)

State-of-the-art methods for image-to-image translation with Generative Adversarial Networks (GANs) can learn a mapping from one domain to another domain using unpaired image data. However, these methods require the training of one specific model for every pair of image domains, which limits the scalability in dealing with more than two image domains. In addition, the training stage of these methods has the common problem of model collapse that degrades the quality of the generated images. To tackle these issues, we propose a Dual Generator Generative Adversarial Network (G2GAN), which is a robust and scalable approach allowing to perform unpaired image-to-image translation for multiple domains using only dual generators within a single model. Moreover, we explore different optimization losses for better training of G2GAN, and thus make unpaired image-to-image translation with higher consistency and better stability. Extensive experiments on six publicly available datasets with different scenarios, i.e., architectural buildings, seasons, landscape and human faces, demonstrate that the proposed G2GAN achieves superior model capacity and better generation performance comparing with existing image-to-image translation GAN models.