# ReFlowSET: Representation-Aligned Latent Flow Matching for SAR-to-EO Image Translation

arXiv: https://arxiv.org/abs/2609.00968 · HTML: https://mlsanity.com/paper/2609.00968/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 21 of 21)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting](https://mlsanity.com/paper/2307.12348/) (2023)
- [BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models](https://mlsanity.com/paper/2205.07680/) (2022)
- [Hierarchical Integration Diffusion Model for Realistic Image Deblurring](https://mlsanity.com/paper/2305.12966/) (2023)
- [SpaceNet 6: Multi-Sensor All Weather Mapping Dataset](https://mlsanity.com/paper/2004.06500/) (2020)
- [The QXS-SAROPT Dataset for Deep Learning in SAR-Optical Data Fusion](https://mlsanity.com/paper/2103.08259/) (2021)
- [StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation](https://mlsanity.com/paper/2403.20142/) (2024)
- [Conditional Brownian Bridge Diffusion Model for VHR SAR to Optical Image Translation](https://mlsanity.com/paper/2408.07947/) (2024)
- [C-DiffSET: Leveraging Latent Diffusion for SAR-to-EO Image Translation with Confidence-Guided Reliable Object Generation](https://mlsanity.com/paper/2411.10788/) (2024)
- [SARMAE: Masked Autoencoder for SAR Representation Learning](https://mlsanity.com/paper/2512.16635/) (2025)

## Abstract (arXiv)

SAR-to-EO image translation aims to generate electro-optical (EO) imagery from synthetic aperture radar (SAR) observations. Existing latent diffusion approaches typically inherit a predetermined autoencoder, although reconstruction fidelity can vary substantially across codecs and modalities. Because the latent codec affects the round-trip preservation of both SAR conditions and EO targets, codec selection constitutes a fundamental design choice; nevertheless, existing methods largely rely on codecs pretrained on natural images. To remedy this, we introduce ReFlowSET, a conditional latent flow-matching framework that selects its codec through a joint SAR--EO reconstruction audit. Rather than inheriting a heavyweight pretrained generator, ReFlowSET trains a substantially smaller conditional DiT from scratch in the selected latent space, using dual-stream SAR conditioning followed by joint feature refinement. To provide semantic guidance for this from-scratch training, intermediate noisy-EO features are aligned with clean target-EO representations extracted by a frozen vision foundation model. This alignment is used only during training and introduces no additional inference cost. Experiments on QXS-SAROPT and SAR2Opt demonstrate state-of-the-art performance across diverse perceptual fidelity and distributional metrics. Code and pretrained weights are publicly available at https://github.com/KAIST-VICLab/ReFlowSET.