Synthetic data provide low-cost, accurately annotated samples for geometry-sensitive vision tasks, but appearance and imaging differences between synthetic and real domains cause severe domain shift and degrade downstream performance. Unpaired synthetic-to-real translation can reduce this gap without paired supervision, yet existing methods often face a trade-off between photorealism and structural stability: unconstrained generation may introduce deformation or spurious textures, while overly rigid constraints limit adaptation to real-domain statistics. We propose FD-DB, a frequency-decoupled dual-branch model that separates appearance transfer into low-frequency interpretable editing and high-frequency residual compensation. The interpretable branch predicts physically meaningful editing parameters (white balance, exposure, contrast, saturation, blur, and grain) to build a stable low-frequency appearance base with strong content preservation. The free branch complements fine details through residual generation, and a gated fusion mechanism combines the two branches under explicit frequency constraints to limit low-frequency drift. We further adopt a two-stage training schedule that first stabilizes the editing branch and then releases the residual branch to improve optimization stability. Experiments on the YCB-V dataset show that FD-DB improves real-domain appearance consistency and significantly boosts downstream semantic segmentation performance while preserving geometric and semantic structures.

翻译：合成数据为几何敏感的视觉任务提供了低成本、精确标注的样本，但合成域与真实域之间的外观和成像差异会导致严重的域偏移并降低下游性能。无配对的合成到真实转换可以在无需配对监督的情况下缩小这一差距，然而现有方法通常在照片真实感与结构稳定性之间面临权衡：无约束的生成可能引入变形或虚假纹理，而过于严格的约束则会限制对真实域统计特性的适应。我们提出了FD-DB，一种频率解耦的双分支模型，它将外观转换分解为低频可解释编辑与高频残差补偿。可解释分支预测具有物理意义的编辑参数（白平衡、曝光、对比度、饱和度、模糊和颗粒），以构建一个具有强内容保持能力的稳定低频外观基础。自由分支通过残差生成补充精细细节，而门控融合机制在显式频率约束下结合两个分支，以限制低频漂移。我们进一步采用两阶段训练策略，首先稳定编辑分支，然后释放残差分支，以提高优化稳定性。在YCB-V数据集上的实验表明，FD-DB提高了真实域外观一致性，在保持几何和语义结构的同时，显著提升了下游语义分割性能。