# Rethinking the Truly Unsupervised Image-to-Image Translation

arXiv: https://arxiv.org/abs/2006.06500 · HTML: https://mlsanity.com/paper/2006.06500/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2020.

## Built on by (most cited first, 30 of 56)

- [Zero-shot Image-to-Image Translation](https://mlsanity.com/paper/2302.03027/) (2023)
- [Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning](https://mlsanity.com/paper/2205.09542/) (2022)
- [DG-Font: Deformable Generative Networks for Unsupervised Font Generation](https://mlsanity.com/paper/2104.03064/) (2021)
- [The Spatially-Correlative Loss for Various Image Translation Tasks](https://mlsanity.com/paper/2104.00854/) (2021)
- [TAPE: Task-Agnostic Prior Embedding for Image Restoration](https://mlsanity.com/paper/2203.06074/) (2022)
- [Diff-Font: Diffusion Model for Robust One-Shot Font Generation](https://mlsanity.com/paper/2212.05895/) (2022)
- [DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network](https://mlsanity.com/paper/2103.07893/) (2021)
- [Training-free Content Injection using h-space in Diffusion Models](https://mlsanity.com/paper/2303.15403/) (2023)
- [Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2106.09016/) (2021)
- [Few-Shot Font Generation by Learning Fine-Grained Local Styles](https://mlsanity.com/paper/2205.09965/) (2022)
- [Reinforcement Learning-Based Black-Box Model Inversion Attacks](https://mlsanity.com/paper/2304.04625/) (2023)
- [General Image-to-Image Translation with One-Shot Image Guidance](https://mlsanity.com/paper/2307.14352/) (2023)
- [InstaFormer: Instance-Aware Image-to-Image Translation with Transformer](https://mlsanity.com/paper/2203.16248/) (2022)
- [CoMoGAN: continuous model-guided image-to-image translation](https://mlsanity.com/paper/2103.06879/) (2021)
- [CF-Font: Content Fusion for Few-shot Font Generation](https://mlsanity.com/paper/2303.14017/) (2023)
- [A Style-aware Discriminator for Controllable Image Translation](https://mlsanity.com/paper/2203.15375/) (2022)
- [DiffV2IR: Visible-to-Infrared Diffusion Model via Vision-Language Understanding](https://mlsanity.com/paper/2503.19012/) (2025)
- [A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learning](https://mlsanity.com/paper/2303.12710/) (2023)
- [Deep Transfer Learning for Intelligent Vehicle Perception: a Survey](https://mlsanity.com/paper/2306.15110/) (2023)
- [Physics-informed Guided Disentanglement in Generative Networks](https://mlsanity.com/paper/2107.14229/) (2021)
- [Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2203.12707/) (2022)
- [Few shot font generation via transferring similarity guided global style and quantization local style](https://mlsanity.com/paper/2309.00827/) (2023)
- [C-DiffSET: Leveraging Latent Diffusion for SAR-to-EO Image Translation with Confidence-Guided Reliable Object Generation](https://mlsanity.com/paper/2411.10788/) (2024)
- [Contrastive Learning for Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2105.03117/) (2021)
- [Exploring Generative AI for Sim2Real in Driving Data Synthesis](https://mlsanity.com/paper/2404.09111/) (2024)
- [Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Data](https://mlsanity.com/paper/2204.04950/) (2022)
- [Exploring Negatives in Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2204.11018/) (2022)
- [Progressive Text-to-Image Diffusion with Soft Latent Direction](https://mlsanity.com/paper/2309.09466/) (2023)
- [One-for-All: Towards Universal Domain Translation with a Single StyleGAN](https://mlsanity.com/paper/2310.14222/) (2023)
- [Learning Temporally and Semantically Consistent Unpaired Video-to-video Translation Through Pseudo-Supervision From Synthetic Optical Flow](https://mlsanity.com/paper/2201.05723/) (2022)

## Abstract (arXiv)

Every recent image-to-image translation model inherently requires either image-level (i.e. input-output pairs) or set-level (i.e. domain labels) supervision. However, even set-level supervision can be a severe bottleneck for data collection in practice. In this paper, we tackle image-to-image translation in a fully unsupervised setting, i.e., neither paired images nor domain labels. To this end, we propose a truly unsupervised image-to-image translation model (TUNIT) that simultaneously learns to separate image domains and translates input images into the estimated domains. Experimental results show that our model achieves comparable or even better performance than the set-level supervised model trained with full labels, generalizes well on various datasets, and is robust against the choice of hyperparameters (e.g. the preset number of pseudo domains). Furthermore, TUNIT can be easily extended to semi-supervised learning with a few labeled data.