Conditional Brownian Bridge Diffusion Model for VHR SAR to Optical Image Translation

TL;DR

This paper introduces a novel conditional diffusion model for translating very-high-resolution SAR images into optical images, outperforming GAN-based methods in quality and stability on the MSAW dataset.

Contribution

It presents a new Brownian Bridge Diffusion Model for SAR to optical translation, addressing low resolution and training instability issues of prior GAN-based approaches.

Findings

Outperforms GAN-based models in perceptual quality metrics

Effective on 0.5m VHR SAR and optical image dataset

Surpasses existing conditional diffusion models in translation quality

Abstract

Synthetic Aperture Radar (SAR) imaging technology provides the unique advantage of being able to collect data regardless of weather conditions and time. However, SAR images exhibit complex backscatter patterns and speckle noise, which necessitate expertise for interpretation. Research on translating SAR images into optical-like representations has been conducted to aid the interpretation of SAR data. Nevertheless, existing studies have predominantly utilized low-resolution satellite imagery datasets and have largely been based on Generative Adversarial Network (GAN) which are known for their training instability and low fidelity. To overcome these limitations of low-resolution data usage and GAN-based approaches, this letter introduces a conditional image-to-image translation approach based on Brownian Bridge Diffusion Model (BBDM). We conducted comprehensive experiments on the MSAW dataset, a paired SAR and optical images collection of 0.5m Very-High-Resolution (VHR). The experimental results indicate that our method surpasses both the Conditional Diffusion Models (CDMs) and the GAN-based models in diverse perceptual quality metrics.