# condimen

**Repository Path**: mirrors_naver/condimen

## Basic Information

- **Project Name**: condimen
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-07-03
- **Last Updated**: 2026-01-18

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README


<p align="center">
  <h1 align="center">CondiMen: Conditional Multi-Person Mesh Recovery</h1>

  <p align="center">
    <a href="https://europe.naverlabs.com/people_user_naverlabs/Romain-Br%C3%A9gier/">Romain Brégier</a>,
    <a href="https://rbregier.github.io/">Fabien Baradel</a>, 
    <a href="https://europe.naverlabs.com/people_user_naverlabs/Thomas-Lucas/">Thomas Lucas</a>,
    <a href="https://salmag98.github.io/">Salma Galaaoui</a>,  
    <a href="https://europe.naverlabs.com/people_user_naverlabs/matthieu-armando/">Matthieu Armando</a>,      
    <a href="[./](https://europe.naverlabs.com/people_user_naverlabs/Philippe-Weinzaepfel/?asp_highlight=Philippe+Weinzaepfel&p_asid=9)">Philippe Weinzaepfel</a>, 
    <a href="https://europe.naverlabs.com/people_user_naverlabs/Gregory-Rogez/">Grégory Rogez</a>
  </p>

  <p align="center">
    <b>CVPR'25 RHOBIN Workshop</b>
  </p>


  <p align="center">
  <a href="https://arxiv.org/abs/2412.13058"><img alt="arXiv" src="https://img.shields.io/badge/arXiv-2412.13058-00ff00.svg"></a>
  </p>

  <br>
  A Bayesian method for multi-person human mesh recovery, modeling ambiguities in 3D pose and shape while enabling uncertainty handling and multi-view integration.
  <br>
</div>
</p>


## Installation
First, you need to clone the repo. The installation has been tested with python3.9 and CUDA 12.1.

We recommend to use a virtual enviroment for running CondiMen.
Please run the following lines for creating the environment with ```venv```:
```bash
python -m venv .condimen
source .condimen/bin/activate
pip install -r requirements.txt
```

Alternative environment using conda:
```bash
conda create -n condimen python=3.11
conda activate condimen
pip install -r requirements.txt
```

Download the demo checkpoint:
```bash
wget https://download.europe.naverlabs.com/condimen/condimen_checkpoint.pt condimen_checkpoint.pt
```

Besides these files, you also need to download the *SMPLX* model.
You will need the [neutral model](https://smpl-x.is.tue.mpg.de) to run the demo code.
Please go to the corresponding website and register to get access to the downloads section.
Download the model and place `SMPLX_NEUTRAL.npz` in `./models/smplx/`.

## Run CondiMen on images
The following command will run CondiMen on all images in the specified `--img_folder`, and save renderings of the reconstructions in `--out_folder`.
The `--model_name` flag specifies the model to use.
```bash
python demo.py \
    --img_folder example_data \
    --out_folder demo_out \
    --checkpoint_path condimen_checkpoint.pt
```

## License
The code is distributed under a non-commercial license.\
See [LICENSE](LICENSE.txt) and [NOTICE](NOTICE.txt) for more information.

## Citing
If you find this code useful for your research, please consider citing the following paper:
```bibtex
@inproceedings{condimen2025,
    title={CondiMen: Conditional Multi-Person Mesh Recovery},
    author={
            Br{\'e}gier, Romain and 
            Baradel, Fabien and 
            Lucas, Thomas and
            Galaaoui, Salma and 
            Armando, Matthieu and 
            Weinzaepfel, Philippe and 
            Rogez, Gr{\'e}gory
            },
    booktitle={CVPR RHOBIN Workshop},
    year={2025}
}
```