# One-to-one Mapping for Unpaired Image-to-image Translation

arXiv: https://arxiv.org/abs/1909.04110 · HTML: https://mlsanity.com/paper/1909.04110/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Sep 2019.

## Built on by (most cited first, 7 of 7)

- [Memories are One-to-Many Mapping Alleviators in Talking Face Generation](https://mlsanity.com/paper/2212.05005/) (2022)
- [Leveraging Conditional Generative Models in a General Explanation Framework of Classifier Decisions](https://mlsanity.com/paper/2106.10947/) (2021)
- [Deformation-aware GAN for Medical Image Synthesis with Substantially Misaligned Pairs](https://mlsanity.com/paper/2408.09432/) (2024)
- [How Video Meetings Change Your Expression](https://mlsanity.com/paper/2406.00955/) (2024)
- [Cross Modality Medical Image Synthesis for Improving Liver Segmentation](https://mlsanity.com/paper/2503.00945/) (2025)
- [Hallucination Detection in Virtually-Stained Histology: A Latent Space Baseline](https://mlsanity.com/paper/2411.15060/) (2024)
- [UniCycleFlow: Bidirectional Unpaired Image Translation with a Shared Rectified Flow](https://mlsanity.com/paper/2608.06784/) (2026)

## Abstract (arXiv)

Recently image-to-image translation has attracted significant interests in the literature, starting from the successful use of the generative adversarial network (GAN), to the introduction of cyclic constraint, to extensions to multiple domains. However, in existing approaches, there is no guarantee that the mapping between two image domains is unique or one-to-one. Here we propose a self-inverse network learning approach for unpaired image-to-image translation. Building on top of CycleGAN, we learn a self-inverse function by simply augmenting the training samples by swapping inputs and outputs during training and with separated cycle consistency loss for each mapping direction. The outcome of such learning is a proven one-to-one mapping function. Our extensive experiments on a variety of datasets, including cross-modal medical image synthesis, object transfiguration, and semantic labeling, consistently demonstrate clear improvement over the CycleGAN method both qualitatively and quantitatively. Especially our proposed method reaches the state-of-the-art result on the cityscapes benchmark dataset for the label to photo unpaired directional image translation.