C-DiffSET: Leveraging Latent Diffusion for SAR-to-EO Image Translation with Confidence-Guided Reliable Object Generation
†Co-corresponding authors
1Korea Advanced Institute of Science and Technology, South Korea
2Kyungpook National University, South Korea
This repository is the official PyTorch implementation of "C-DiffSET: Leveraging Latent Diffusion for SAR-to-EO Image Translation with Confidence-Guided Reliable Object Generation". C-DiffSET achieves state-of-the-art results on multiple datasets, outperforming the recent image-to-image translation methods and SAR-to-EO image translation methods.
- ⚠ The code will be released later
- Dec 9, 2024: This repository is created
Please visit our project page for more experimental results.
The source codes including the checkpoint can be freely used for research and education only. Any commercial use should get formal permission from the principal investigator (Prof. Munchurl Kim, [email protected]).
This repository is built upon FMA-Net.