Papers › UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation

UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation

4 Mar 2022arXiv:2203.02557archive 2025-07-28

Dmitrii Torbunov, Yi Huang, Haiwang Yu, Jin Huang, Shinjae Yoo, MeiFeng Lin, Brett Viren, Yihui Ren

Unpaired image-to-image translation has broad applications in art, design, and scientific simulations. One early breakthrough was CycleGAN that emphasizes one-to-one mappings between two unpaired image domains via generative-adversarial networks (GAN) coupled with the cycle-consistency constraint, while more recent works promote one-to-many mapping to boost diversity of the translated images. Motivated by scientific simulation and one-to-one needs, this work revisits the classic CycleGAN framework and boosts its performance to outperform more contemporary models without relaxing the cycle-consistency constraint. To achieve this, we equip the generator with a Vision Transformer (ViT) and employ necessary training and regularization techniques. Compared to previous best-performing models, our model performs better and retains a strong correlation between the original and translated image. An accompanying ablation study shows that both the gradient penalty and self-supervised pre-training are crucial to the improvement. To promote reproducibility and open science, the source code, hyperparameter configurations, and pre-trained model are available at https://github.com/LS4GAN/uvcgan.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ls4gan/benchmarking officialmentioned in papermentioned on GitHubpytorch report
ls4gan/uvcgan officialmentioned in papermentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DiversityImage-to-Image TranslationTranslation

Datasets

Introduced by this paper, per the archive.

Pretrained Models of the Benchmarking Algorithms for UVCGAN

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEBatch NormalizationConvolutionCycle Consistency LossDense ConnectionsDropoutGAN Least Squares LossInstance NormalizationLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPatchGANPosition-Wise Feed-Forward LayerReLUResidual BlockResidual ConnectionSigmoid ActivationSoftmaxTanh ActivationTransformerVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections