ReFlowSET：面向SAR到EO图像翻译的表示对齐潜在流匹配方法
ReFlowSET: Representation-Aligned Latent Flow Matching for SAR-to-EO Image Translation
浏览论文内容
中文总结 AI 辅助
本文提出ReFlowSET，通过联合SAR-EO重建审计选择编解码器，在选定潜在空间中从头训练条件DiT，结合视觉基础模型对齐特征，在SAR到EO图像翻译任务上取得最优性能。
中文摘要 AI 辅助
SAR到EO图像翻译旨在从合成孔径雷达（SAR）观测数据生成电光（EO）图像。现有潜在扩散方法通常采用预定义的自编码器，但不同编解码器及模态间的重建保真度差异显著。由于潜在编解码器会影响SAR条件与EO目标的往返保留效果，编解码器选择是核心设计决策；然而现有方法大多依赖在自然图像上预训练的编解码器。为解决该问题，本文提出ReFlowSET，一种通过联合SAR-EO重建审计选择编解码器的条件潜在流匹配框架。ReFlowSET未采用重量级预训练生成器，而是在选定潜在空间中从头训练一个规模小得多的条件DiT，使用双流SAR条件及后续联合特征细化。为给该从头训练提供语义指导，中间带噪EO特征与冻结视觉基础模型提取的干净目标EO表示对齐，该对齐仅在训练阶段使用，不引入额外推理成本。在QXS-SAROPT和SAR2Opt数据集上的实验表明，所提方法在多种感知保真度和分布度量上达到了当前最优性能。代码与预训练权重可在该https URL获取。
英文摘要
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.
发表机构
- KAIST（韩国科学技术院）
- Stellarvision Inc.（Stellarvision公司）
机构由 AI 辅助整理，请以论文原文为准。
