yutaokuyama/diffbody

DiffBody: Diffusion-based Pose and Shape Editing of Human Images

This repository contains our implementation of the following paper: Yuta Okuyama, Yuki Endo, Yoshihiro Kanamori: "Diffbody: Diffusion-based Pose and Shape Editing of Human Images", accepted to WACV2024. [Project][Paper]

We are preparing for releasing code.

Milestones

• Release code for inference (ETA: ~1/12)
• Release code for data creation (ETA: ~2/1)

Citation

Please cite our paper if you find the code useful:

@InProceedings{Okuyama_2024_WACV,
    author    = {Okuyama, Yuta and Endo, Yuki and Kanamori, Yoshihiro},
    title     = {{DiffBody}: Diffusion-Based Pose and Shape Editing of Human Images},
    booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
    month     = {January},
    year      = {2024},
    pages     = {6333-6342}
}

diffbody's Issues

Regarding inference release date

Dear Authors,
Thanks for the great work and share. Could you please confirm what ~1/12 for inference code milestone means? Wondered if it was 1 Dec 2024, but that seems too far off. Could you please clarify.

Thanks,
Arun