ReFlowSET: 表徵對齊的潛在流匹配於SAR-to-EO影像轉換

摘要

SAR-to-EO 影像轉換旨在從合成孔徑雷達（SAR）觀測生成電光（EO）影像。現有的潛在擴散方法通常繼承一個預設的自編碼器，然而重建保真度可能因編解碼器和模態而有顯著差異。由於潛在編解碼器會影響 SAR 條件與 EO 目標在往返過程中的保留程度，因此編解碼器的選擇構成基本的設計決策；然而，現有方法大多依賴在自然影像上預訓練的編解碼器。為了解決此問題，我們提出 ReFlowSET——一個條件潛在流匹配框架，透過聯合 SAR–EO 重建審核來選擇其編解碼器。ReFlowSET 並非繼承重量級的預訓練生成器，而是在所選的潛在空間中從零開始訓練一個規模小得多的條件式 DiT，先使用雙流 SAR 條件化，再進行聯合特徵細化。為了對這種從零開始的訓練提供語義引導，我們將中間的含雜訊 EO 特徵與由凍結的視覺基礎模型所抽取的乾淨目標 EO 表徵進行對齊。此對齊僅在訓練期間使用，且不會引入額外的推論成本。在 QXS-SAROPT 與 SAR2Opt 上的實驗，於多種感知保真度與分佈指標上展示了最先進的效能。程式碼與預訓練權重可於 https://github.com/KAIST-VICLab/ReFlowSET 公開取得。

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.