https://chen3110.github.io/ImmFusion/index.html

Our codebase is developed based on MeshGraphormer and MeshTransformer. Please check Install.md to install the relevant dependencies. Please also consider citing them if you use this codebase.

Visit mmBody to download mmBody dataset and place it at ./datasets.

The pre-trained models can be downloaded with the following command.

sh download_models.sh

Visit the following websites to download SMPL and SMPL-X models.

• Download basicModel_neutral_lbs_10_207_0_v1.0.0.pkl from SMPLify, and place it at ./src/modeling/data.
• Download SMPLX_NEUTRAL.pkl from SMPL-X, and place it at ./src/modeling/data.

We use the following script to train on the mmBody dataset.

python ./run_immfusion.py \
    --output_dir output/immfusion \
    --dataset mmBodyDataset \
    --data_path datasets/mmBody \
    --mesh_type smplx \
    --model AdaptiveFusion \
    --per_gpu_train_batch_size 10 \
    --train

python ./run_immfusion.py \
    --output_dir output/immfusion \
    --resume_checkpoint output/immfusion/checkpoint \
    --dataset mmBodyDataset \
    --data_path datasets/mmBody \
    --mesh_type smplx \
    --model AdaptiveFusion \
    --test_scene lab1

@inproceedings{chen2023immfusion,
  title={Immfusion: Robust mmwave-rgb fusion for 3d human body reconstruction in all weather conditions},
  author={Chen, Anjun and Wang, Xiangyu and Shi, Kun and Zhu, Shaohao and Fang, Bin and Chen, Yingfeng and Chen, Jiming and Huo, Yuchi and Ye, Qi},
  booktitle={2023 IEEE International Conference on Robotics and Automation (ICRA)},
  pages={2752--2758},
  year={2023},
  organization={IEEE}
}