This repository contains several image-to-image translation models, whcih were tested for RGB to NIR image generation. The models are Pix2Pix, Pix2PixHD, CycleGAN and PointWise.


The dataset including RGB and NIR images is located here: https://drive.google.com/drive/folders/1uJx_SLi0ePYqhn-lJ8p5whAy5spUsect?usp=sharing, where “RGB_Images” and “MSI_images containg RGB and mltispectral images acquired with digtial and multispectral 9 band camera at the same time periods, respectively.

How to read and understang RGB image


In this project we used the code and methodolgy by:

@inproceedings{CycleGAN2017, title={Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks}, author={Zhu, Jun-Yan and Park, Taesung and Isola, Phillip and Efros, Alexei A}, booktitle={Computer Vision (ICCV), 2017 IEEE International Conference on}, year={2017} }

@inproceedings{isola2017image, title={Image-to-Image Translation with Conditional Adversarial Networks}, author={Isola, Phillip and Zhu, Jun-Yan and Zhou, Tinghui and Efros, Alexei A}, booktitle={Computer Vision and Pattern Recognition (CVPR), 2017 IEEE Conference on}, year={2017} }


View Github