Data to 7 Oct 2026

Rethinking the Truly Unsupervised Image-to-Image Translation

arXiv 2006.06500 ↗First posted 11 Jun 2020cs.CV cs.LGcited by 56

Not on the map. Why?

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.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 10; 2022: 22; 2023: 19; 2024: 3; 2025: 2.

56 papers.

Sort:

By area:

2023Zero-shot Image-to-Image Translationcited by 503
2022Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learningcited by 93
2021DG-Font: Deformable Generative Networks for Unsupervised Font Generationcited by 70
2021The Spatially-Correlative Loss for Various Image Translation Taskscited by 66
2022TAPE: Task-Agnostic Prior Embedding for Image Restorationcited by 54
2022Diff-Font: Diffusion Model for Robust One-Shot Font Generationcited by 40
2021DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Networkcited by 37
2023Training-free Content Injection using h-space in Diffusion Modelscited by 36
2021Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translationcited by 35
2022Few-Shot Font Generation by Learning Fine-Grained Local Stylescited by 34
2023Reinforcement Learning-Based Black-Box Model Inversion Attackscited by 33
2023General Image-to-Image Translation with One-Shot Image Guidancecited by 31

38 more

2022InstaFormer: Instance-Aware Image-to-Image Translation with Transformercited by 28
2021CoMoGAN: continuous model-guided image-to-image translationcited by 27
2023CF-Font: Content Fusion for Few-shot Font Generationcited by 26
2022A Style-aware Discriminator for Controllable Image Translationcited by 16
2025DiffV2IR: Visible-to-Infrared Diffusion Model via Vision-Language Understandingcited by 16
2023A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learningcited by 10
2023Deep Transfer Learning for Intelligent Vehicle Perception: a Surveycited by 10
2021Physics-informed Guided Disentanglement in Generative Networkscited by 9
2022Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translationcited by 8
2023Few shot font generation via transferring similarity guided global style and quantization local stylecited by 8
2024C-DiffSET: Leveraging Latent Diffusion for SAR-to-EO Image Translation with Confidence-Guided Reliable Object Generationcited by 8
2021Contrastive Learning for Unsupervised Image-to-Image Translationcited by 7
2024Exploring Generative AI for Sim2Real in Driving Data Synthesiscited by 7
2022Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Datacited by 6
2022Exploring Negatives in Contrastive Learning for Unpaired Image-to-Image Translationcited by 6
2023Progressive Text-to-Image Diffusion with Soft Latent Directioncited by 6
2023One-for-All: Towards Universal Domain Translation with a Single StyleGANcited by 6
2022Learning Temporally and Semantically Consistent Unpaired Video-to-video Translation Through Pseudo-Supervision From Synthetic Optical Flowcited by 5
2022LANIT: Language-Driven Image-to-Image Translation for Unlabeled Datacited by 5
2022Can We Find Strong Lottery Tickets in Generative Models?cited by 4
2023Few-shot Font Generation by Learning Style Difference and Similaritycited by 4
2023Human-Inspired Facial Sketch Synthesis with Dynamic Adaptationcited by 4
2022Polymorphic-GAN: Generating Aligned Samples across Multiple Domains with Learned Morph Mapscited by 3
2022HistoStarGAN: A Unified Approach to Stain Normalisation, Stain Transfer and Stain Invariant Segmentation in Renal Histopathologycited by 3
2022Smooth image-to-image translations with latent space interpolationscited by 2
2022DGFont++: Robust Deformable Generative Networks for Unsupervised Font Generationcited by 2
20233D-Aware Multi-Class Image-to-Image Translation with NeRFscited by 2
2023Weakly Supervised Scene Text Generation for Low-resource Languagescited by 2
2023Domain-Scalable Unpaired Image Translation via Latent Space Anchoringcited by 2
2021Leveraging Local Domains for Image-to-Image Translationcited by 1
2021Bridging the Gap between Label- and Reference-based Synthesis in Multi-attribute Image-to-Image Translationcited by 1
2022Swapping Semantic Contents for Mixing Imagescited by 1
2023ACE: Zero-Shot Image to Image Translation via Pretrained Auto-Contrastive-Encodercited by 1
2023UTSGAN: Unseen Transition Suss GAN for Transition-Aware Image-to-image Translationcited by 1
2023Progressive Energy-Based Cooperative Learning for Multi-Domain Image-to-Image Translationcited by 1
2024Shape-Preserving Generation of Food Images for Automatic Dietary Assessmentcited by 1
2025StyDeco: Unsupervised Style Transfer with Distilling Priors and Semantic Decouplingcited by 1
2021Few-Shot Unsupervised Image-to-Image Translation on complex scenescited by 0

50 most cited of 56 All 56 (JSON)