This is the offical Pytorch implementation of the paper:
Yingxuan You , Hong Liu , Ti Wang , Wenhao Li , Runwei Ding, Xia Li
project page / arXiv / paper / supplementary
- Install dependencies. This project is developed on Ubuntu 18.04 with NVIDIA 3090 GPUs. We recommend you to use an Anaconda virtual environment.
# Create a conda environment.
conda create -n pmce python=3.8
conda activate pmce
# Install PyTorch >= 1.2 according to your GPU driver.
conda install pytorch==1.10.0 torchvision==0.11.0 torchaudio==0.10.0 cudatoolkit=11.3 -c pytorch -c conda-forge
# Pull the code
git clone https://github.com/kasvii/PMCE.git
cd PMCE
# Install other dependencies.
sh requirements.sh
- Prepare SMPL layer.
- For the SMPL layer, We used smplpytorch. The repo is already included in
./smplpytorch
folder. - Download
basicModel_f_lbs_10_207_0_v1.0.0.pkl
,basicModel_m_lbs_10_207_0_v1.0.0.pkl
, andbasicModel_neutral_lbs_10_207_0_v1.0.0.pkl
from here (female & male) and here (neutral) to./smplpytorch/smplpytorch/native/models
.
- Download base data
- Download
base_data
from OneDrive. Put it below./data
folder.
- Install ViTPose. PMCE uses the off-the-shift 2D pose detectors to detect persons from images. Here we take and install ViTPose.
git clone https://github.com/open-mmlab/mmcv.git
cd mmcv
git checkout v1.3.9
MMCV_WITH_OPS=1 pip install -e .
cd ..
git clone https://github.com/ViTAE-Transformer/ViTPose.git
cd ViTPose
pip install -v -e .
- Download the pre-trained ViTPose model
vitpose-h-multi-coco.pth
from OneDrive. Put it below./pose_detector
folder. - Download the pre-trained PMCE model
mesh_vis.pth.tar
from OneDrive. Put it below./experiment/pretrained
folder. - Prepare the input video
*.mp4
and put it below./demo
folder. - Run. The output is at
./output
folder.
# Change 'sample_video' to your video name.
python ./main/run_demo.py --vid_file demo/sample_video.mp4 --gpu 0
The ./data
directory structure should follow the below hierarchy. Download all the processed annotation files from OneDrive
${Project}
|-- data
| |-- base_data
| | |-- J_regressor_extra.npy
| | |-- mesh_downsampling.npz
| | |-- smpl_mean_params.npz
| | |-- smpl_mean_vertices.npy
| | |-- SMPL_NEUTRAL.pkl
| | |-- spin_model_checkpoint.pth.tar
| |-- COCO
| | |-- coco_data
| | |-- __init__.py
| | |-- dataset.py
| | |-- J_regressor_coco.npy
| |-- Human36M
| | |-- h36m_data
| | |-- __init__.py
| | |-- dataset.py
| | |-- J_regressor_h36m_correct.npy
| | |-- noise_stats.py
| |-- MPII
| | |-- mpii_data
| | |-- __init__.py
| | |-- dataset.py
| |-- MPII3D
| | |-- mpii3d_data
| | |-- __init__.py
| | |-- dataset.py
| |-- PW3D
| | |-- pw3d_data
| | |-- __init__.py
| | |-- dataset.py
| |-- multiple_datasets.py
To test on a pre-trained pose estimation model (Stage 1).
# Human3.6M
bash test_pose_h36m.sh
# 3DPW
bash test_pose_3dpw.sh
To test on a pre-trained mesh model (Stage 2).
# Human3.6M
bash test_mesh_h36m.sh
# 3DPW
bash test_mesh_3dpw.sh
# MPII3D
bash test_mesh_mpii3d.sh
Change the weight_path
in the corresponding ./config/test_*.yml
to your model path.
Stage 1 (optional): Train the 3D pose estimation stream or you can directly use our pre-traind pose model ./experiment/pretrained/pose_*.pth.tar
for Stage 2.
# Human3.6M
bash train_pose_h36m.sh
# 3DPW
bash train_pose_3dpw.sh
Stage 2: To train the all network for final mesh. Configs of the experiments can be found and edited in ./config
folder. Change posenet_path
in ./config/train_mesh_*.yml
to the path of the pre-trained pose model.
# Human3.6M
bash train_mesh_h36m.sh
# 3DPW & MPII3D
bash train_mesh_3dpw.sh
Cite as below if you find this repository is helpful to your project:
@inproceedings{you2023co,
title = {Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video},
author = {You, Yingxuan and Liu, Hong and Wang, Ti and Li, Wenhao and Ding, Runwei and Li, Xia},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
pages = {14963--14973},
year = {2023}
}
This repo is extended from the excellent work Pose2Mesh, TCMR. We thank the authors for releasing the codes.