Seg-CycleGAN : SAR-to-optical image translation guided by a downstream task
This work addresses the problem of generating optical-like images from SAR data for earth observation applications, offering an incremental improvement by integrating semantic guidance.
The paper tackles SAR-to-optical image translation by proposing Seg-CycleGAN, which uses a pre-trained semantic segmentation model to guide the translation process, resulting in improved accuracy for ship target translation as demonstrated in experiments.
Optical remote sensing and Synthetic Aperture Radar(SAR) remote sensing are crucial for earth observation, offering complementary capabilities. While optical sensors provide high-quality images, they are limited by weather and lighting conditions. In contrast, SAR sensors can operate effectively under adverse conditions. This letter proposes a GAN-based SAR-to-optical image translation method named Seg-CycleGAN, designed to enhance the accuracy of ship target translation by leveraging semantic information from a pre-trained semantic segmentation model. Our method utilizes the downstream task of ship target semantic segmentation to guide the training of image translation network, improving the quality of output Optical-styled images. The potential of foundation-model-annotated datasets in SAR-to-optical translation tasks is revealed. This work suggests broader research and applications for downstream-task-guided frameworks. The code will be available at https://github.com/NPULHH/