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

Hugging Face Daily Papers Papers
image-translation latent-flow-matching conditional-dit sar-to-eo representation-alignment

Summary

ReFlowSET is a latent flow-matching framework for high-fidelity SAR-to-EO image translation, using codec selection and conditional DiT with vision model alignment to achieve state-of-the-art performance.

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.
Original Article
View Cached Full Text

Cached at: 09/02/26, 03:46 AM

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

Source: https://huggingface.co/papers/2609.00968

Abstract

ReFlowSET selects a latent codec via joint SAR-EO reconstruction and trains a small conditional DiT with dual-stream conditioning and frozen vision-model alignment for high-fidelity SAR-to-EO translation.

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 selectionconstitutes a fundamental design choice; nevertheless, existing methods largely rely on codecs pretrained on natural images. To remedy this, we introduce ReFlowSET, a conditionallatent flow-matchingframework that selects its codec through a joint SAR--EO reconstruction audit. Rather than inheriting a heavyweight pretrained generator, ReFlowSET trains a substantially smallerconditional DiTfrom scratch in the selected latent space, usingdual-stream SAR conditioningfollowed byjoint 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 frozenvision 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.

View arXiv pageView PDFProject pageGitHub2Add to collection

Get this paper in your agent:

hf papers read 2609\.00968

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper1

#### JeonghyeokDo/ReFlowSET Image-to-Image• Updatedabout 2 hours ago • 1

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.00968 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.00968 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

ChangeFlow -- Latent Rectified Flow for Change Detection in Remote Sensing

Hugging Face Daily Papers

ChangeFlow presents a generative framework for remote sensing change detection that synthesizes change masks in latent space using rectified flow, achieving improved accuracy and robustness through sampling-based prediction ensembling, with an average F1 of 80.4% across four benchmarks.

CAT-Flow: Curvature-Adaptive sTeps for Flow Matching

arXiv cs.LG

This paper proposes CAT-OV and CAT-OT, two lightweight, training-free algorithms that adapt step-sizes in Flow Matching sampling based on curvature, improving image quality and reducing generation steps by up to 40%.

LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories

Hugging Face Daily Papers

LeapAlign is a post-training method that improves flow matching model alignment with human preferences by reducing computational costs through two-step trajectory shortcuts while enabling stable gradient propagation to early generation steps. The method outperforms state-of-the-art approaches when fine-tuning Flux models across various image quality and text-alignment metrics.