Skip to content

About

Code to evaluate segmentation results for MVPS dataset

Resources

Stars

2 stars

Watchers

5 watching

Forks

Latest commit

 

History

1 Commit

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MVPS evaluation

This code is used to evaluate video portrait segmentation results for MVPS dataset.

PDNet

Evaluate

To set the default dataset path, please modify the default_mvps_path parameter in eval.py.

python eval.py path/of/segmentation/results

Dataset

To acquire our MVPS dataset, please contact yuts@buaa.edu.cn via an official email. Please explain the purpose of usage in the email. The dataset is available for academic research only.

Citation

@article{PDNet,
  author={Tianshu Yu and Changqun Xia and Jia Li},
  title={Towards imbalanced motion: part-decoupling network for video portrait segmentation},
  journal={SCIENCE CHINA Information Sciences},
  year={2024},
  volume={67},
  number={7},
  pages={172104},
  doi={10.1007/s11432-023-4030-y}
}

About

Code to evaluate segmentation results for MVPS dataset

Resources

Stars

2 stars

Watchers

5 watching

Forks

Releases

Packages

Contributors

Languages