ReFlowSET：面向SAR到EO图像转换的表示对齐潜在流匹配

摘要

SAR-to-EO图像翻译旨在从合成孔径雷达（SAR）观测中生成光电（EO）图像。现有的潜在扩散方法通常继承预定的自编码器，尽管重建保真度在不同编解码器和模态之间可能差异显著。由于潜在编解码器影响SAR条件和EO目标在编码-解码往返过程中的保留，编解码器选择构成了一项基本设计选择；然而，现有方法大多依赖在自然图像上预训练的编解码器。针对此问题，我们提出了ReFlowSET，一个条件潜在流匹配框架，通过联合SAR–EO重建审计来选择其编解码器。ReFlowSET并未继承重型预训练生成器，而是在选定的潜在空间中从头训练一个显著更小的条件DiT（Diffusion Transformer），采用双流SAR条件化并随后进行联合特征细化。为了给这种从头训练提供语义指导，我们将中间噪声EO特征与由冻结的视觉基础模型提取的干净目标EO表示进行对齐。这种对齐仅用于训练阶段，不引入额外推理成本。在QXS-SAROPT和SAR2Opt上的实验表明，该方法在多种感知保真度和分布指标上取得了最先进的性能。代码和预训练权重可在https://github.com/KAIST-VICLab/ReFlowSET上公开获取。

English

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.