Skip to content

spran180/SAR-Image-Colorization

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 

Repository files navigation

SAR Image Colorization with UNet2DModel

📖 Overview

This repository contains the implementation of a Synthetic Aperture Radar (SAR) image colorization model using a UNet2DModel. The model transforms grayscale SAR images into their optical (colorized) counterparts, enhancing the interpretability of SAR data for various applications such as remote sensing and environmental monitoring.

Screenshot 2024-11-17 193920


Features

  • Encoder-Decoder Architecture: Built using the flexible UNet2DModel.
  • Attention Mechanisms: Incorporated to improve the quality of colorization.
  • Custom Dataset Support: Compatible with paired SAR and optical image datasets.
  • High Performance: Optimized for efficient GPU usage and minimal memory consumption.
  • Training Logs: Includes visualizations for loss, PSNR, and SSIM metrics.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published