├── README.md
└── docs
    └── teaser_wacv.png


/README.md:
--------------------------------------------------------------------------------
 1 | # DiffBody: Diffusion-based Pose and Shape Editing of Human Images
 2 | <p align="center">
 3 | <img src="docs/teaser_wacv.png" width="1440px"/>
 4 | </p>
 5 |   <a href="https://arxiv.org/abs/2401.02804"><img src="https://img.shields.io/badge/arXiv-2401.02804-b31b1b.svg"></a>
 6 | 
 7 | This repository contains our implementation of the following paper:
 8 | Yuta Okuyama, Yuki Endo, Yoshihiro Kanamori: "Diffbody: Diffusion-based Pose and Shape Editing of Human Images", accepted to WACV2024.  [[Project](https://www.cgg.cs.tsukuba.ac.jp/~okuyama/pub/diffbody/index.html)][[Paper](https://arxiv.org/abs/2401.02804)]
 9 | 
10 | We are preparing for releasing code.
11 | 
12 | ## Milestones
13 | - [ ] Release code for inference (ETA: ~1/12) 
14 | - [ ] Release code for data creation (ETA: ~2/1) 
15 | 
16 | 
17 | ## Citation
18 | Please cite our paper if you find the code useful:
19 | ```
20 | @InProceedings{Okuyama_2024_WACV,
21 |     author    = {Okuyama, Yuta and Endo, Yuki and Kanamori, Yoshihiro},
22 |     title     = {{DiffBody}: Diffusion-Based Pose and Shape Editing of Human Images},
23 |     booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
24 |     month     = {January},
25 |     year      = {2024},
26 |     pages     = {6333-6342}
27 | }
28 | ```
29 | 


--------------------------------------------------------------------------------
/docs/teaser_wacv.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/yutaokuyama/DiffBody/1b25d722b316f19e103be454b5dd2939e6344d40/docs/teaser_wacv.png


--------------------------------------------------------------------------------