Skip to content

PyTorch code for IEEE TCI2022 paper "Deep Hyperspectral Image Fusion Network with Iterative Spatio-Spectral Regularization"

Notifications You must be signed in to change notification settings

TaoHuang95/DHIF-Net

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

40 Commits
 
 
 
 
 
 

Repository files navigation

Deep Hyperspectral Image Fusion Network for HSI Fusion

This repository contains the PyTorch codes for paper "Deep Hyperspectral Image Fusion Network with Iterative Spatio-Spectral Regularization" (IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING (IEEE TCI), VOL. 6, 2022) by Tao Huang, Weisheng Dong, Xin Li.

[pdf] [Project]

Contents

  1. Overview
  2. Architecture
  3. Usage
  4. Citation
  5. Contact

Overview

Physical acquisition of high-resolution hyperspectral images (HR-HSI) has remained difficult, despite its potential of resolving material-related ambiguities in vision applications. Deep hyperspectral image fusion, aiming at reconstructing an HR-HSI from a pair of low-resolution hyperspectral image (LRHSI) and high-resolution multispectral image (HR-MSI), has become an appealing computational alternative. Existing fusion methods either rely on hand-crafted image priors or treat fusion as a nonlinear mapping problem, ignoring important physical imaging models. In this paper, we propose a novel regularization strategy to fully exploit the spatio-spectral dependency by a spatially adaptive 3D filter. Moreover, the joint exploitation of spatio-spectral regularization and physical imaging models inspires us to formulate deep hyperspectral image fusion as a differentiable optimization problem. We show how to solve this optimization problem by an end-to-end training of a model-guided unfolding network named DHIF-Net. Unlike existing works of simply concatenating spatial with spectral regularization, our approach aims at an end-to-end optimization of iterative spatio-spectral regularization by multistage network implementations. Our extensive experimental results on both synthetic and real datasets have shown that our DHIF-Net outperforms other competing methods in terms of both objective and subjective visual quality.

Architecture

Fig. 1: Architecture of the proposed network for hyperspectral image fusion. The architecture of (a) the overall network; (b) the spatio-spectral regularization module; (c) the 3D filter generator.

Usage

Download the DHIF-Net repository

  1. Requirements are Python 3 and PyTorch 1.7.0.

  2. Download this repository via git

git clone https://github.com/TaoHuang95/DHIF-Net

or download the [zip file] manually.

Download the training data

  1. [The Original CAVE Dataset]:[HSI&RGB]

Training

  1. Training simulation model

    1. Put hyperspectral image datasets (Ground truth) and RGB datasets into corrsponding path, i.e., 'CAVE/Data/Train/HSI (RGB)'.

    2. Run CAVE/Train.py.

Testing

  1. Testing on simulation data [Checkpoint]

    1. Run CAVE/Test.py to reconstruct 12 synthetic datasets. The results will be saved in 'CAVE/Result/' in the MAT File format.

Citation

If you find our work useful for your research, please consider citing the following papers :)

@article{huang2022deep,
  title={Deep hyperspectral image fusion network with iterative spatio-spectral regularization},
  author={Huang, Tao and Dong, Weisheng and Wu, Jinjian and Li, Leida and Li, Xin and Shi, Guangming},
  journal={IEEE Transactions on Computational Imaging},
  volume={8},
  pages={201--214},
  year={2022},
  publisher={IEEE}
}

Contact

Tao Huang, Xidian University, Email: thuang_666@stu.xidian.edu.cn, thuang951223@163.com

Weisheng Dong, Xidian University, Email: wsdong@mail.xidian.edu.cn

Xin Li, West Virginia University, Email: xin.li@ieee.org

About

PyTorch code for IEEE TCI2022 paper "Deep Hyperspectral Image Fusion Network with Iterative Spatio-Spectral Regularization"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages