Skip to content
/ humr Public

[WACV 2025] Official implementation of "Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery"

License

Notifications You must be signed in to change notification settings

twehrbein/humr

Repository files navigation

HUMR: Heatmap Uncertainty for Mesh Recovery

This is the official implementation of the WACV 2025 Paper Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery by Tom Wehrbein, Marco Rudolph, Bodo Rosenhahn and Bastian Wandt.

Installation instructions

We recommend creating a clean conda environment. You can do this as follows:

conda env create -f environment.yml

A more cross-platform-friendly installation alternative could be to manually follow the commands in install_env.txt.

After the installation is complete, you can activate the conda environment by running:

conda activate humr

Prepare data

  1. SMPL: Please download version 1.1.0, extract it to data/body_models and rename the model files to SMPL_NEUTRAL/FEMALE/MALE.pkl.
  2. SMPL-X: Please download version 1.1 and extract it to data/body_models/smplx.
  3. SMPL Utils: Download utils.zip and extract it to data/utils.
  4. Pretrained Weights: Finally, place all pretrained checkpoints in data/ckpt.

Additionally for training and evaluation, please follow the dataset preparation guide here.

Demo

We provide a few examples in data/examples. Running the following demo will detect each person in each image and then run HUMR for 3D reconstruction. The resulting rendering will be saved to logs/

python demo.py --cfg configs/default_config.yaml --ckpt data/ckpt/humr_best.ckpt

Training and evaluation

Training can be started with:

python train.py --cfg configs/default_config.yaml --name expname

To evaluate the provided trained model:

python train.py --cfg configs/default_config.yaml --ckpt data/ckpt/humr_best.ckpt --test

Acknowledgements

We benefit from many great resources including but not limited to: SPIN, CLIFF, ViTPose, HRNet, BEDLAM, ProHMR, HuManiFlow

Citing

If you find the model and code useful, please consider citing the following paper:

@InProceedings{wehrbein25humr,
    author    = {Wehrbein, Tom and Rudolph, Marco and Rosenhahn, Bodo and Wandt, Bastian},
    title     = {Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery},
    booktitle = {Winter Conference on Applications of Computer Vision (WACV)},
    year      = {2025},
}

About

[WACV 2025] Official implementation of "Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery"

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published