/MSDTGP

Satellite Video Super-resolution via Multi-Scale Deformable Convolution Alignment and Temporal Grouping Projection, IEEE TGRS, 2021

Primary LanguagePython

Satellite Video Super-resolution via Multi-Scale Deformable Convolution Alignment and Temporal Grouping Projection (TGRS)

Introuction

This is the official implementation of our paper Satellite Video Super-resolution via Multi-Scale Deformable Convolution Alignment and Temporal Grouping Projection published on IEEE Transactions on Geoscience and Remote Sensing (TGRS).

The network structure

image

Quantitive results

image

Qualitive results

image

More details can be found in our paper!

Environment

  • CUDA 10.0
  • pytorch 1.x
  • build DCNv2

Dataset Preparation

Please download our dataset Jilin-189 Code:31ct
You can also train your dataset following the directory sturture below!

Data directory structure

trainset--
 | train--
  | LR4x---
   | 000.png
   | ···.png
   | 099.png
  | GT---
  | Bicubic4x---

testset--
 | eval--
  | LR4x---
   | 000.png
   | ···.png
   | 099.png
  | GT---
  | Bicubic4x---

Training

python main.py

Test

python eval.py

Citation

If you find our work helpful, please cite:

@ARTICLE{9530280,  
author={Xiao, Yi and Su, Xin and Yuan, Qiangqiang and Liu, Denghong and Shen, Huanfeng and Zhang, Liangpei},  
journal={IEEE Transactions on Geoscience and Remote Sensing},  
title={Satellite Video Super-Resolution via Multiscale Deformable Convolution Alignment and Temporal Grouping Projection},   
year={2021},  
volume={60},  
number={},  
pages={1-19},  
doi={10.1109/TGRS.2021.3107352}
}

Acknowledgement

Our work is built upon RBPN and TDAN.
Thanks to the author for the source code !