Skip to content

EBStore dataset for "EMS: 3D Eyebrow Modeling from Single-view Images"(SIGGRAPH Aisa 2023)

License

Notifications You must be signed in to change notification settings

kevinlee09/EMS_dataset

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

EMS EBStore dataset

This repository provides the EBStore dataset of EMS.

EMS: EMS: 3D Eyebrow Modeling from Single-view Images

Chenghong Li*, Leyang Jin*, Yujian Zheng, Yizhou Yu# and Xiaoguang Han#


EBStore is the first high-quality 3D synthetic eyebrow dataset containing 400 high-quality 3D models. These eyebrow models are manually created by artists using particle edit mode in Blender, guided by both the high-resolution texture map of the eyebrow region and the front-facing image of the individual.

Dataset


To download EBStore data, please visit OneDrive. After unzipping the downloaded file, you will find the following directory structure:

├── EBStore_blender_data
│   ├── 1
│   │   ├── 1_uv.jpg
│   │   ├── 1.blend
│   │   ├── 1.obj
│   │   ├── h.mtl
│   │   ├── h.obj
│   │   ├── m.mtl
│   │   └── m.obj
│   ├── 2
│   │   ├── 2_uv.jpg
│   │   ├── 2.blend
│   │   ├── 2.obj
│   │   ├── h.mtl
│   │   ├── h.obj
│   │   ├── m.mtl
│   │   └── m.obj
├── ...

Environment

We test our code on blender-3.4.0 and blender-3.6.14.

Convert hair blend files to npy format

python hair2npy.py --input ./EBStore_blender_data --output ./strand_npy_rekey

Convert npy to obj format

python npy2obj.py --input ./strand_npy_rekey --output ./strand_obj_rekey

License

The data and the code are released under the Attribution-NonCommercial 4.0 International License.

Copyright (c) 2024

Citation

If you find the data and code of this work helpful to your research, please consider citing:

@article{li2023ems,
  title={EMS: 3D Eyebrow Modeling from Single-view Images},
  author={Li, Chenghong and Jin, Leyang and Zheng, Yujian and Yu, Yizhou and Han, Xiaoguang},
  journal={ACM Transactions on Graphics (TOG)},
  volume={42},
  number={6},
  pages={1--19},
  year={2023},
  publisher={ACM New York, NY, USA}
}

About

EBStore dataset for "EMS: 3D Eyebrow Modeling from Single-view Images"(SIGGRAPH Aisa 2023)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages