/SelfPIFu--PIFu-for-the-Real-World

Dressed Human Reconstrcution from Single-view Real World Image

PIFu for the Real World: A Self-supervised Framework to Reconstruct Dressed Human from Single-view Images. (SelfPIFu)

Code repository for the paper:

Editor

CVM 2024 [paper] [project page (coming soon)]

Overview of our framework

Editor

Depth-guided self-supervised learning

Editor

IoU of using different input

Editor

Comparisons among different PIFu variants

Editor

Comparison with SOTA

Editor Editor

Visual depth maps on real world images

Editor

Citation

If you find the idea or code of this paper useful for your research, please consider citing us:

@misc{xiong2022selfpifu,
  author = {Xiong, Zhangyang and Du, Dong and Wu, Yushuang and Dong, Jingqi and Kang, Di and Bao, Linchao and Han, Xiaoguang},  
  title = {PIFu for the Real World: A Self-supervised Framework to Reconstruct Dressed Human from Single-view Images},
  publisher = {arXiv},
  year = {2022},
}