# A Unified Hyper-GAN Model for Unpaired Multi-contrast MR Image Translation

arXiv: https://arxiv.org/abs/2107.11945 · HTML: https://mlsanity.com/paper/2107.11945/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 26 Jul 2021.

## Builds on (most cited first, 17 of 17)

- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [A Learned Representation For Artistic Style](https://mlsanity.com/paper/1610.07629/) (2016)
- [Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1802.01221/) (2018)
- [ComboGAN: Unrestrained Scalability for Image Domain Translation](https://mlsanity.com/paper/1712.06909/) (2017)
- [Brain tumor segmentation with missing modalities via latent multi-source correlation representation](https://mlsanity.com/paper/2003.08870/) (2020)
- [Unified cross-modality feature disentangler for unsupervised multi-domain MRI abdomen organs segmentation](https://mlsanity.com/paper/2007.09669/) (2020)
- [Dual-cycle Constrained Bijective VAE-GAN For Tagged-to-Cine Magnetic Resonance Image Synthesis](https://mlsanity.com/paper/2101.05439/) (2021)
- [Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoders](https://mlsanity.com/paper/1712.02050/) (2017)
- [Latent Filter Scaling for Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1812.09877/) (2018)
- [Dual Generator Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1901.04604/) (2019)
- [Unified Attentional Generative Adversarial Network for Brain Tumor Segmentation From Multimodal Unpaired Images](https://mlsanity.com/paper/1907.03548/) (2019)
- [Flow-based Deformation Guidance for Unpaired Multi-Contrast MRI Image-to-Image Translation](https://mlsanity.com/paper/2012.01777/) (2020)
- [DOTE: Dual cOnvolutional filTer lEarning for Super-Resolution and Cross-Modality Synthesis in MRI](https://mlsanity.com/paper/1706.04954/) (2017)

## Built on by (most cited first, 15 of 15)

- [A Novel Unified Conditional Score-based Generative Framework for Multi-modal Medical Image Completion](https://mlsanity.com/paper/2207.03430/) (2022)
- [ModDrop++: A Dynamic Filter Network with Intra-subject Co-training for Multiple Sclerosis Lesion Segmentation with Missing Modalities](https://mlsanity.com/paper/2203.04959/) (2022)
- [FedMed-GAN: Federated Domain Translation on Unsupervised Cross-Modality Brain Image Synthesis](https://mlsanity.com/paper/2201.08953/) (2022)
- [Cross-Modality Neuroimage Synthesis: A Survey](https://mlsanity.com/paper/2202.06997/) (2022)
- [Toward Medical Deepfake Detection: A Comprehensive Dataset and Novel Method](https://mlsanity.com/paper/2509.15711/) (2025)
- [Multi-scale Super-resolution Magnetic Resonance Spectroscopic Imaging with Adjustable Sharpness](https://mlsanity.com/paper/2206.08984/) (2022)
- [HyperCoil-Recon: A Hypernetwork-based Adaptive Coil Configuration Task Switching Network for MRI Reconstruction](https://mlsanity.com/paper/2308.04821/) (2023)
- [Image-to-Image Translation Framework Embedded with Rotation Symmetry Priors](https://mlsanity.com/paper/2604.12805/) (2026)
- [K-Space-Aware Cross-Modality Score for Synthesized Neuroimage Quality Assessment](https://mlsanity.com/paper/2307.04296/) (2023)
- [Principled Feature Disentanglement for High-Fidelity Unified Brain MRI Synthesis](https://mlsanity.com/paper/2406.14954/) (2024)
- [Pretext Task Adversarial Learning for Unpaired Low-field to Ultra High-field MRI Synthesis](https://mlsanity.com/paper/2503.05339/) (2025)
- [AdaViT: Adaptive Vision Transformer for Flexible Pretrain and Finetune with Variable 3D Medical Image Modalities](https://mlsanity.com/paper/2504.03589/) (2025)
- [VIViT: Variable-Input Vision Transformer Framework for 3D MR Image Segmentation](https://mlsanity.com/paper/2505.08693/) (2025)
- [DSA-CycleGAN: A Domain Shift Aware CycleGAN for Robust Multi-Stain Glomeruli Segmentation](https://mlsanity.com/paper/2604.18368/) (2026)
- [Spectral Consistent Flow for One-step 3D Medical Image Translation](https://mlsanity.com/paper/2607.10627/) (2026)

## Abstract (arXiv)

Cross-contrast image translation is an important task for completing missing contrasts in clinical diagnosis. However, most existing methods learn separate translator for each pair of contrasts, which is inefficient due to many possible contrast pairs in real scenarios. In this work, we propose a unified Hyper-GAN model for effectively and efficiently translating between different contrast pairs. Hyper-GAN consists of a pair of hyper-encoder and hyper-decoder to first map from the source contrast to a common feature space, and then further map to the target contrast image. To facilitate the translation between different contrast pairs, contrast-modulators are designed to tune the hyper-encoder and hyper-decoder adaptive to different contrasts. We also design a common space loss to enforce that multi-contrast images of a subject share a common feature space, implicitly modeling the shared underlying anatomical structures. Experiments on two datasets of IXI and BraTS 2019 show that our Hyper-GAN achieves state-of-the-art results in both accuracy and efficiency, e.g., improving more than 1.47 and 1.09 dB in PSNR on two datasets with less than half the amount of parameters.