Skip to content

This is the official source of our ICCV 2023 paper " D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field"

Notifications You must be signed in to change notification settings

psyai-net/D-IF_release

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field [ICCV2023]

Official PyTorch implementation for the paper:

D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field. ICCV 2023.

Xueting Yang*, Yihao Luo*, Yuliang Xiu, Wei Wang, Hao Xu, Zhaoxin Fan (*equally contributed)

License ↗

Implicit Distance Field → Implicit Distribution Field, pointwise uncertainty is modeled as the magnitude of variance in Gaussian. This simple trick enhances multiple baselines (PIFu, PaMIR, ICON) significantly.

Environment

  • Linux
  • Python 3.8
  • Pytorch 1.13.0
  • CUDA 11.3
  • CUDA=11.3, GPU Memory > 12GB
  • PyTorch3D

Clone the repo:

git clone https://github.com/psyai-net/D-IF_release.git
cd D-IF_release

Create conda environment:

conda env create -f environment.yaml
conda init bash
source ~/.bashrc
source activate D-IF
pip install -r requirements.txt --use-deprecated=legacy-resolver

Demo

The pretrained D-IF model has been uploaded here. You could change the resume path in ./configs/d_if.yaml.

python -m apps.infer -cfg ./configs/d_if.yaml -gpu 0 -in_dir ./examples -out_dir ./results -export_video -loop_smpl 100 -loop_cloth 200 -hps_type pixie

Training & Testing

Train dataset: Thuman2.0, for download, please follow the steps of ICON_train completely.

CUDA_VISIBLE_DEVICES=7 python -m apps.train -cfg ./configs/train/d_if.yaml

Test dataset: CAPE, for download, please follow the steps of ICON_test completely.

python -m apps.train -cfg ./configs/train/d_if.yaml -test

Citation

If you find this work useful for your research, please cite our paper:

@inproceedings{yang2023dif,
  title={{D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field}},
  author={Yang, Xueting and Luo, Yihao and Xiu, Yuliang and Wang, Wei and Xu, Hao and Fan, Zhaoxin},
  booktitle={Proceedings of the IEEE/CVF international conference on computer vision},
  year={2023}
}

Acknowledgement

Here are some great resources we benefit:

Contact

For research purpose, please contact [email protected]

For commercial licensing, please contact [email protected] and [email protected]

License

This project is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License. Please read the LICENSE file for more information.

Invitation

We invite you to join Psyche AI Inc to conduct cutting-edge research and business implementation together. At Psyche AI Inc, we are committed to pushing the boundaries of what's possible in the fields of artificial intelligence and computer vision, especially their applications in avatars. As a member of our team, you will have the opportunity to collaborate with talented individuals, innovate new ideas, and contribute to projects that have a real-world impact.

If you are passionate about working on the forefront of technology and making a difference, we would love to hear from you. Please visit our website at Psyche AI Inc to learn more about us and to apply for open positions. You can also contact us by [email protected].

Let's shape the future together!!

About

This is the official source of our ICCV 2023 paper " D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published