# Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks

arXiv: https://arxiv.org/abs/1807.08536 · HTML: https://mlsanity.com/paper/1807.08536/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2018.

## Built on by (most cited first, 10 of 10)

- [EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations](https://mlsanity.com/paper/2207.06635/) (2022)
- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [Breaking the Dilemma of Medical Image-to-image Translation](https://mlsanity.com/paper/2110.06465/) (2021)
- [Mutually improved endoscopic image synthesis and landmark detection in unpaired image-to-image translation](https://mlsanity.com/paper/2107.06941/) (2021)
- [UCDFormer: Unsupervised Change Detection Using a Transformer-driven Image Translation](https://mlsanity.com/paper/2308.01146/) (2023)
- [Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment](https://mlsanity.com/paper/2603.17655/) (2026)
- [A Framework for Generalizing Critical Heat Flux Detection Models Using Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2212.09107/) (2022)
- [Image-to-Image Translation Framework Embedded with Rotation Symmetry Priors](https://mlsanity.com/paper/2604.12805/) (2026)
- [Regularized Distribution Matching Distillation for One-step Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2406.14762/) (2024)
- [Source-Agnostic Image Translation Based on Latent Aware Adaptive Masking](https://mlsanity.com/paper/2608.14046/) (2026)

## Abstract (arXiv)

Recent studies on unsupervised image-to-image translation have made a remarkable progress by training a pair of generative adversarial networks with a cycle-consistent loss. However, such unsupervised methods may generate inferior results when the image resolution is high or the two image domains are of significant appearance differences, such as the translations between semantic layouts and natural images in the Cityscapes dataset. In this paper, we propose novel Stacked Cycle-Consistent Adversarial Networks (SCANs) by decomposing a single translation into multi-stage transformations, which not only boost the image translation quality but also enable higher resolution image-to-image translations in a coarse-to-fine manner. Moreover, to properly exploit the information from the previous stage, an adaptive fusion block is devised to learn a dynamic integration of the current stage's output and the previous stage's output. Experiments on multiple datasets demonstrate that our proposed approach can improve the translation quality compared with previous single-stage unsupervised methods.