SAR to Optical Image Translation with Color Supervised Diffusion Model

TL;DR

This paper presents a diffusion-based generative model that converts SAR images into optical images with improved interpretability, utilizing color supervision and conditional guidance to enhance visual quality and quantitative metrics.

Contribution

The paper introduces a novel diffusion model for SAR to optical image translation that incorporates color supervision and conditional guidance, outperforming previous methods.

Findings

Outperforms previous methods in quantitative metrics

Enhances visual quality of generated images

Effective use of color supervision in diffusion models

Abstract

Synthetic Aperture Radar (SAR) offers all-weather, high-resolution imaging capabilities, but its complex imaging mechanism often poses challenges for interpretation. In response to these limitations, this paper introduces an innovative generative model designed to transform SAR images into more intelligible optical images, thereby enhancing the interpretability of SAR images. Specifically, our model backbone is based on the recent diffusion models, which have powerful generative capabilities. We employ SAR images as conditional guides in the sampling process and integrate color supervision to counteract color shift issues effectively. We conducted experiments on the SEN12 dataset and employed quantitative evaluations using peak signal-to-noise ratio, structural similarity, and fr\'echet inception distance. The results demonstrate that our model not only surpasses previous methods in quantitative assessments but also significantly enhances the visual quality of the generated images.