Accelerating Diffusion for SAR-to-Optical Image Translation via Adversarial Consistency Distillation

TL;DR

This paper introduces a novel training framework that combines diffusion models and adversarial learning to accelerate SAR-to-optical image translation, achieving 131 times faster inference while maintaining high image quality.

Contribution

The proposed method effectively reduces inference steps through consistency distillation and incorporates adversarial learning to preserve image quality, offering a flexible speed-quality trade-off.

Findings

Inference speed improved by 131 times

Maintains high image quality with PSNR, SSIM, FID metrics

Effective on SEN12 and GF3 datasets

Abstract

Synthetic Aperture Radar (SAR) provides all-weather, high-resolution imaging capabilities, but its unique imaging mechanism often requires expert interpretation, limiting its widespread applicability. Translating SAR images into more easily recognizable optical images using diffusion models helps address this challenge. However, diffusion models suffer from high latency due to numerous iterative inferences, while Generative Adversarial Networks (GANs) can achieve image translation with just a single iteration but often at the cost of image quality. To overcome these issues, we propose a new training framework for SAR-to-optical image translation that combines the strengths of both approaches. Our method employs consistency distillation to reduce iterative inference steps and integrates adversarial learning to ensure image clarity and minimize color shifts. Additionally, our approach allows for a trade-off between quality and speed, providing flexibility based on application requirements. We conducted experiments on SEN12 and GF3 datasets, performing quantitative evaluations using Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Frechet Inception Distance (FID), as well as calculating the inference latency. The results demonstrate that our approach significantly improves inference speed by 131 times while maintaining the visual quality of the generated images, thus offering a robust and efficient solution for SAR-to-optical image translation.