# Harmonic Unpaired Image-to-image Translation

arXiv: https://arxiv.org/abs/1902.09727 · HTML: https://mlsanity.com/paper/1902.09727/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Feb 2019.

## Built on by (most cited first, 18 of 18)

- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network](https://mlsanity.com/paper/2105.09188/) (2021)
- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2108.04547/) (2021)
- [Segmentation-Renormalized Deep Feature Modulation for Unpaired Image Harmonization](https://mlsanity.com/paper/2102.06315/) (2021)
- [Unaligned Image-to-Image Translation by Learning to Reweight](https://mlsanity.com/paper/2109.11736/) (2021)
- [Exploring Semantic Consistency in Unpaired Image Translation to Generate Data for Surgical Applications](https://mlsanity.com/paper/2309.03048/) (2023)
- [USIS: Unsupervised Semantic Image Synthesis](https://mlsanity.com/paper/2109.14715/) (2021)
- [FCR: Investigating Generative AI models for Forensic Craniofacial Reconstruction](https://mlsanity.com/paper/2508.18031/) (2025)
- [Wavelet-based Unsupervised Label-to-Image Translation](https://mlsanity.com/paper/2305.09647/) (2023)
- [Masked Discriminators for Content-Consistent Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2309.13188/) (2023)
- [A Semi-Paired Approach For Label-to-Image Translation](https://mlsanity.com/paper/2306.13585/) (2023)
- [Jurassic World Remake: Bringing Ancient Fossils Back to Life via Zero-Shot Long Image-to-Image Translation](https://mlsanity.com/paper/2308.07316/) (2023)
- [Effect of Instance Normalization on Fine-Grained Control for Sketch-Based Face Image Generation](https://mlsanity.com/paper/2207.08072/) (2022)
- [Microscopy Image Segmentation via Point and Shape Regularized Data Synthesis](https://mlsanity.com/paper/2308.09835/) (2023)
- [SemST: Semantically Consistent Multi-Scale Image Translation via Structure-Texture Alignment](https://mlsanity.com/paper/2310.04995/) (2023)
- [SCONE-GAN: Semantic Contrastive learning-based Generative Adversarial Network for an end-to-end image translation](https://mlsanity.com/paper/2311.03866/) (2023)
- [Towards Unsupervised Representation Learning: Learning, Evaluating and Transferring Visual Representations](https://mlsanity.com/paper/2312.00101/) (2023)

## Abstract (arXiv)

The recent direction of unpaired image-to-image translation is on one hand very exciting as it alleviates the big burden in obtaining label-intensive pixel-to-pixel supervision, but it is on the other hand not fully satisfactory due to the presence of artifacts and degenerated transformations. In this paper, we take a manifold view of the problem by introducing a smoothness term over the sample graph to attain harmonic functions to enforce consistent mappings during the translation. We develop HarmonicGAN to learn bi-directional translations between the source and the target domains. With the help of similarity-consistency, the inherent self-consistency property of samples can be maintained. Distance metrics defined on two types of features including histogram and CNN are exploited. Under an identical problem setting as CycleGAN, without additional manual inputs and only at a small training-time cost, HarmonicGAN demonstrates a significant qualitative and quantitative improvement over the state of the art, as well as improved interpretability. We show experimental results in a number of applications including medical imaging, object transfiguration, and semantic labeling. We outperform the competing methods in all tasks, and for a medical imaging task in particular our method turns CycleGAN from a failure to a success, halving the mean-squared error, and generating images that radiologists prefer over competing methods in 95% of cases.