Ying-Ying Kong

DSAN: Dual-Scale Aligned Network with Asymmetric Priors and Differentiable Soft-Edge Loss for SAR-to-Optical Image Translation

Experiments on the Nanjing and public SEN1-2 datasets demonstrate that DSAN outperforms state-of-the-art models—including Pix2PixHD, CycleGAN, MSTMNet, and ICMA—in perceptual distribution realism (FID) with the sharpest geometric boundaries.