# TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Images

arXiv: https://arxiv.org/abs/2004.04634 · HTML: https://mlsanity.com/paper/2004.04634/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2020.

## Built on by (most cited first, 23 of 23)

- [Splicing ViT Features for Semantic Appearance Transfer](https://mlsanity.com/paper/2201.00424/) (2022)
- [Diffusion-based Image Translation using Disentangled Style and Content Representation](https://mlsanity.com/paper/2209.15264/) (2022)
- [Cross-Image Attention for Zero-Shot Appearance Transfer](https://mlsanity.com/paper/2311.03335/) (2023)
- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [Single Motion Diffusion](https://mlsanity.com/paper/2302.05905/) (2023)
- [Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment](https://mlsanity.com/paper/2203.04121/) (2022)
- [Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models](https://mlsanity.com/paper/2103.15545/) (2021)
- [SinDiffusion: Learning a Diffusion Model from a Single Natural Image](https://mlsanity.com/paper/2211.12445/) (2022)
- [General Image-to-Image Translation with One-Shot Image Guidance](https://mlsanity.com/paper/2307.14352/) (2023)
- [Diverse Generation from a Single Video Made Possible](https://mlsanity.com/paper/2109.08591/) (2021)
- [Texture Reformer: Towards Fast and Universal Interactive Texture Transfer](https://mlsanity.com/paper/2112.02788/) (2021)
- [CharacterGAN: Few-Shot Keypoint Character Animation and Reposing](https://mlsanity.com/paper/2102.03141/) (2021)
- [TransferI2I: Transfer Learning for Image-to-Image Translation from Small Datasets](https://mlsanity.com/paper/2105.06219/) (2021)
- [Disentangling Structure and Appearance in ViT Feature Space](https://mlsanity.com/paper/2311.12193/) (2023)
- [Design Booster: A Text-Guided Diffusion Model for Image Translation with Spatial Layout Preservation](https://mlsanity.com/paper/2302.02284/) (2023)
- [Rethink Arbitrary Style Transfer with Transformer and Contrastive Learning](https://mlsanity.com/paper/2404.13584/) (2024)
- [SPAST: Arbitrary Style Transfer with Style Priors via Pre-trained Large-scale Model](https://mlsanity.com/paper/2505.08695/) (2025)
- [SITTA: Single Image Texture Translation for Data Augmentation](https://mlsanity.com/paper/2106.13804/) (2021)
- [ChildPredictor: A Child Face Prediction Framework with Disentangled Learning](https://mlsanity.com/paper/2204.09962/) (2022)
- [Jurassic World Remake: Bringing Ancient Fossils Back to Life via Zero-Shot Long Image-to-Image Translation](https://mlsanity.com/paper/2308.07316/) (2023)
- [Image Shape Manipulation from a Single Augmented Training Sample](https://mlsanity.com/paper/2109.06151/) (2021)
- [One-shot Detail Retouching with Patch Space Neural Transformation Blending](https://mlsanity.com/paper/2210.01217/) (2022)
- [Zero-Shot Visual Concept Blending Without Text Guidance](https://mlsanity.com/paper/2503.21277/) (2025)

## Abstract (arXiv)

An unsupervised image-to-image translation (UI2I) task deals with learning a mapping between two domains without paired images. While existing UI2I methods usually require numerous unpaired images from different domains for training, there are many scenarios where training data is quite limited. In this paper, we argue that even if each domain contains a single image, UI2I can still be achieved. To this end, we propose TuiGAN, a generative model that is trained on only two unpaired images and amounts to one-shot unsupervised learning. With TuiGAN, an image is translated in a coarse-to-fine manner where the generated image is gradually refined from global structures to local details. We conduct extensive experiments to verify that our versatile method can outperform strong baselines on a wide variety of UI2I tasks. Moreover, TuiGAN is capable of achieving comparable performance with the state-of-the-art UI2I models trained with sufficient data.