ECON: Explicit Clothed humans Obtained from Normals

Yuliang Xiu · Jinlong Yang · Xu Cao · Dimitrios Tzionas · Michael J. Black

arXiv 2022

ECON is designed for "Human digitization from a color image", which combines the best properties of implicit and explicit representations, to infer high-fidelity 3D clothed humans from in-the-wild images, even with loose clothing or in challenging poses. ECON also supports multi-person reconstruction and SMPL-X based animation.

News 🚩

• [2022/12/22] is now available, created by AroArz!
• [2022/12/15] Both demo and arXiv are available.

TODO

• Blender add-on for FBX export
• Full RGB texture generation

Table of Contents

1. Instructions
2. Demo
3. Applications
4. Tricks
5. Citation

Instructions

• See docs/installation.md to install all the required packages and setup the models

Demo

# For single-person image-based reconstruction
python -m apps.infer -cfg ./configs/econ.yaml -in_dir ./examples -out_dir ./results

# For multi-person image-based reconstruction (see config/econ.yaml)
python -m apps.infer -cfg ./configs/econ.yaml -in_dir ./examples -out_dir ./results -multi

# To generate the demo video of reconstruction results
python -m apps.multi_render -n {filename}

# To animate the reconstruction with SMPL-X pose parameters
python -m apps.avatarizer -n {filename}

Tricks

Some adjustable parameters in config/econ.yaml

• use_ifnet: False
  • True: use IF-Nets+ for mesh completion ( $\text{ECON}_\text{IF}$ - Better quality, ~3min / img)
  • False: use SMPL-X for mesh completion ( $\text{ECON}_\text{EX}$ - Faster speed, ~2min / img)
• use_smpl: ["hand", "face"]
  • [ ]: don't use either hands or face parts from SMPL-X
  • ["hand"]: only use the visible hands from SMPL-X
  • ["hand", "face"]: use both visible hands and face from SMPL-X
• thickness: 2cm
  • could be increased accordingly in case final reconstruction xx_full.obj looks flat
• hps_type: PIXIE
  • "pixie": more accurate for face and hands
  • "pymafx": more robust for challenging poses
• k: 4
  • could be reduced accordingly in case the surface of xx_full.obj has discontinous artifacts

More Qualitative Results

Challenging Poses
Loose Clothes

Applications

ECON could provide pseudo 3D GT for SHHQ Dataset	ECON supports multi-person reconstruction

Citation

@article{xiu2022econ,
    title={{ECON: Explicit Clothed humans Obtained from Normals}},
    author={Xiu, Yuliang and Yang, Jinlong and Cao, Xu and Tzionas, Dimitrios and Black, Michael J.},
    year={2022}
    journal={{arXiv}:2212.07422},
}

Acknowledgments

We thank Lea Hering and Radek Daněček for proof reading, Yao Feng, Haven Feng, and Weiyang Liu for their feedback and discussions, Tsvetelina Alexiadis for her help with the AMT perceptual study.

Here are some great resources we benefit from:

• ICON for SMPL-X Body Fitting
• BiNI for Bilateral Normal Integration
• MonoPortDataset for Data Processing, MonoPort for fast implicit surface query
• rembg for Human Segmentation
• MediaPipe for full-body landmark estimation
• PyTorch-NICP for non-rigid registration
• smplx, PyMAF-X, PIXIE for Human Pose & Shape Estimation
• CAPE and THuman for Dataset
• PyTorch3D for Differential Rendering

Some images used in the qualitative examples come from pinterest.com.

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No.860768 (CLIPE Project).

---

License

This code and model are available for non-commercial scientific research purposes as defined in the LICENSE file. By downloading and using the code and model you agree to the terms in the LICENSE.

Disclosure

MJB has received research gift funds from Adobe, Intel, Nvidia, Meta/Facebook, and Amazon. MJB has financial interests in Amazon, Datagen Technologies, and Meshcapade GmbH. While MJB is a part-time employee of Meshcapade, his research was performed solely at, and funded solely by, the Max Planck Society.

Contact

For technical questions, please contact [email protected]

For commercial licensing, please contact [email protected]