# DUAL-GLOW: Conditional Flow-Based Generative Model for Modality Transfer

arXiv: https://arxiv.org/abs/1908.08074 · HTML: https://mlsanity.com/paper/1908.08074/

## Key facts

- Cited by 19 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 21 Aug 2019.

## Built on by (most cited first, 19 of 19)

- [Conditional Invertible Neural Networks for Diverse Image-to-Image Translation](https://mlsanity.com/paper/2105.02104/) (2021)
- [Neuralizer: General Neuroimage Analysis without Re-Training](https://mlsanity.com/paper/2305.02644/) (2023)
- [PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularization](https://mlsanity.com/paper/2205.12021/) (2022)
- [Target-aware Molecular Graph Generation](https://mlsanity.com/paper/2202.04829/) (2022)
- [MRI to PET Cross-Modality Translation using Globally and Locally Aware GAN (GLA-GAN) for Multi-Modal Diagnosis of Alzheimer's Disease](https://mlsanity.com/paper/2108.02160/) (2021)
- [PanFlowNet: A Flow-Based Deep Network for Pan-sharpening](https://mlsanity.com/paper/2305.07774/) (2023)
- [Generative Flows with Invertible Attentions](https://mlsanity.com/paper/2106.03959/) (2021)
- [Class-Guided Image-to-Image Diffusion: Cell Painting from Brightfield Images with Class Labels](https://mlsanity.com/paper/2303.08863/) (2023)
- [CAFLOW: Conditional Autoregressive Flows](https://mlsanity.com/paper/2106.02531/) (2021)
- [MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning](https://mlsanity.com/paper/2508.10133/) (2025)
- [Domain Translation via Latent Space Mapping](https://mlsanity.com/paper/2212.03361/) (2022)
- [Variable Augmented Network for Invertible Modality Synthesis-Fusion](https://mlsanity.com/paper/2109.00670/) (2021)
- [U-PET: MRI-based Dementia Detection with Joint Generation of Synthetic FDG-PET Images](https://mlsanity.com/paper/2206.08078/) (2022)
- [PET Tracer Conversion among Brain PET via Variable Augmented Invertible Network](https://mlsanity.com/paper/2311.00735/) (2023)
- [HIDFlowNet: A Flow-Based Deep Network for Hyperspectral Image Denoising](https://mlsanity.com/paper/2306.17797/) (2023)
- [Multiple Noises in Diffusion Model for Semi-Supervised Multi-Domain Translation](https://mlsanity.com/paper/2309.14394/) (2023)
- [LoLiSRFlow: Joint Single Image Low-light Enhancement and Super-resolution via Cross-scale Transformer-based Conditional Flow](https://mlsanity.com/paper/2402.18871/) (2024)
- [Stitching the Story: Creating Panoramic Incident Summaries from Body-Worn Footage](https://mlsanity.com/paper/2509.04370/) (2025)
- [α-Graph: Attention-Infused Normalizing Flow Approach to Tractable Graph Modeling](https://mlsanity.com/paper/2609.07961/) (2026)

## Abstract (arXiv)

Positron emission tomography (PET) imaging is an imaging modality for diagnosing a number of neurological diseases. In contrast to Magnetic Resonance Imaging (MRI), PET is costly and involves injecting a radioactive substance into the patient. Motivated by developments in modality transfer in vision, we study the generation of certain types of PET images from MRI data. We derive new flow-based generative models which we show perform well in this small sample size regime (much smaller than dataset sizes available in standard vision tasks). Our formulation, DUAL-GLOW, is based on two invertible networks and a relation network that maps the latent spaces to each other. We discuss how given the prior distribution, learning the conditional distribution of PET given the MRI image reduces to obtaining the conditional distribution between the two latent codes w.r.t. the two image types. We also extend our framework to leverage 'side' information (or attributes) when available. By controlling the PET generation through 'conditioning' on age, our model is also able to capture brain FDG-PET (hypometabolism) changes, as a function of age. We present experiments on the Alzheimers Disease Neuroimaging Initiative (ADNI) dataset with 826 subjects, and obtain good performance in PET image synthesis, qualitatively and quantitatively better than recent works.