# Asymmetric GAN for Unpaired Image-to-image Translation

arXiv: https://arxiv.org/abs/1912.11660 · HTML: https://mlsanity.com/paper/1912.11660/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Dec 2019.

## Built on by (most cited first, 14 of 14)

- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [Auto-Exposure Fusion for Single-Image Shadow Removal](https://mlsanity.com/paper/2103.01255/) (2021)
- [StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation](https://mlsanity.com/paper/2403.20142/) (2024)
- [A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends](https://mlsanity.com/paper/2402.15490/) (2024)
- [Adverse Weather Image Translation with Asymmetric and Uncertainty-aware GAN](https://mlsanity.com/paper/2112.04283/) (2021)
- [PeaceGAN: A GAN-based Multi-Task Learning Method for SAR Target Image Generation with a Pose Estimator and an Auxiliary Classifier](https://mlsanity.com/paper/2103.15469/) (2021)
- [EvoMakeup: High-Fidelity and Controllable Makeup Editing with MakeupQuad](https://mlsanity.com/paper/2508.05994/) (2025)
- [BioGAN: An unpaired GAN-based image to image translation model for microbiological images](https://mlsanity.com/paper/2306.06217/) (2023)
- [CSHNet: A Novel Information Asymmetric Image Translation Method](https://mlsanity.com/paper/2501.10197/) (2025)
- [D3T-GAN: Data-Dependent Domain Transfer GANs for Few-shot Image Generation](https://mlsanity.com/paper/2205.06032/) (2022)
- [Shadow Removal by High-Quality Shadow Synthesis](https://mlsanity.com/paper/2212.04108/) (2022)
- [CycleGANAS: Differentiable Neural Architecture Search for CycleGAN](https://mlsanity.com/paper/2311.07162/) (2023)
- [Mechanisms of Generative Image-to-Image Translation Networks](https://mlsanity.com/paper/2411.10368/) (2024)
- [Diffusion Based Unpaired Data Learning for Inverse Problems](https://mlsanity.com/paper/2609.01370/) (2026)

## Abstract (arXiv)

Unpaired image-to-image translation problem aims to model the mapping from one domain to another with unpaired training data. Current works like the well-acknowledged Cycle GAN provide a general solution for any two domains through modeling injective mappings with a symmetric structure. While in situations where two domains are asymmetric in complexity, i.e., the amount of information between two domains is different, these approaches pose problems of poor generation quality, mapping ambiguity, and model sensitivity. To address these issues, we propose Asymmetric GAN (AsymGAN) to adapt the asymmetric domains by introducing an auxiliary variable (aux) to learn the extra information for transferring from the information-poor domain to the information-rich domain, which improves the performance of state-of-the-art approaches in the following ways. First, aux better balances the information between two domains which benefits the quality of generation. Second, the imbalance of information commonly leads to mapping ambiguity, where we are able to model one-to-many mappings by tuning aux, and furthermore, our aux is controllable. Third, the training of Cycle GAN can easily make the generator pair sensitive to small disturbances and variations while our model decouples the ill-conditioned relevance of generators by injecting aux during training. We verify the effectiveness of our proposed method both qualitatively and quantitatively on asymmetric situation, label-photo task, on Cityscapes and Helen datasets, and show many applications of asymmetric image translations. In conclusion, our AsymGAN provides a better solution for unpaired image-to-image translation in asymmetric domains.