8000 GitHub - HMS97/Task-driven-Inpainting: Task-driven-Inpainting
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

HMS97/Task-driven-Inpainting

Repository files navigation

Coarse-to-fine Task-driven Inpainting for Geoscience Images

This repository contains the implementation of the research paper "Coarse-to-fine Task-driven Inpainting for Geoscience Images," accepted in IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) in 2023.

Dataset and Pretrained Models for Classification

1.Download the Dataset into the current folder and unzip

2.Download the classification Pretained Models into the save_models folder

Usage

The Requirements

pip install -r requirements.txt

Start the Training

python gan_trainer.py

Start the Testing

python gan_test.py

Start the Evaluation

python baseline.py

Citation

If you find the article or code useful for your project, please refer to

@ARTICLE{10126081,
  author={Sun, Huiming and Ma, Jin and Guo, Qing and Zou, Qin and Song, Shaoyue and Lin, Yuewei and Yu, Hongkai},
  journal={IEEE Transactions on Circuits and Systems for Video Technology}, 
  title={Coarse-to-fine Task-driven Inpainting for Geoscience Images}, 
  year={2023},
  volume={},
  number={},
  pages={1-1},
  doi={10.1109/TCSVT.2023.3276719}}

About

Task-driven-Inpainting

Resources