All Projects → xinxinmiao → lambda-net

xinxinmiao / lambda-net

Licence: other
No description, website, or topics provided.

Programming Languages

103659 projects - #7 most used programming language


This repository contains the coder for the paper: λ-net: Reconstruct Hyperspectral Images from a Snapshot Measurement (International Conference on Computer Vision 2019) by Xin Miao, Xin Yuan, Yunchen Pu, Vassilis Athitsos.

Training and testing data.

The traing and testing data used in our paper is from the paper " Sparse Recovery of Hyperspectral Signal from Natural RGB Images". It can be downlaed from The training scene should be put in the file "training_data/",the testing scenes should be in the file "testing_data/". The data we used and the mask can be downloaded from


0. Download the repository

Requirements are tensorflow, numpy, scipy.

1. Run Lambda-net

Train the model via

The results for testing scene will be saved in 'result/model file/'. If you want to visualize the results after training the model, just run

And the PSNR value for the training and testing data can be found in

result/model file/pnsr.txt
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected]