This implementation:
Model has been implemented and tested on Ubuntu 18.04 with python >= 3.7. You need a Nvidia GPU.
Clone the repo:
git clone https://github.com/paradoxWu/parallel-branchfor-hpe.git
Install the requirements using virtualenv
or conda
:
# pip
source scripts/install_pip.sh
# conda
source scripts/install_conda.sh
Run the commands below to start training:
python train.py --cfg configs/config.yaml
Note that the training datasets should be downloaded and prepared before running data processing script.
Please see doc/train.md
for details on how to prepare them.
Here we compare VIBE with recent state-of-the-art methods on 3D pose estimation datasets. Evaluation metric is Procrustes Aligned Mean Per Joint Position Error (MPJPE) in mm.
Models | 3DPW↓ | MPI-INF-3DHP↓ |
---|---|---|
SPIN | 96.9 | 105.2 |
Pose2Mesh | 89.2 | - |
VIBE | 93.5 | 96.6 |
Ours | 85.7 | 95.8 |
Models | 3DPW↓ | MPI-INF-3DHP↓ |
---|---|---|
SPIN | 59.2 | 67.5 |
Pose2Mesh | 58.3 | - |
VIBE | 56.5 | 63.4 |
Ours | 53.1 | 65 |
See doc/eval.md
to reproduce the results in this table or
evaluate a pretrained model.
checkpoint | Google Drive | Baidu Pan |
---|---|---|
GRU | Google Drive | Baidu |
Transformer | TBD | TBD |
This code is available for non-commercial scientific research purposes as defined in the LICENSE file. By downloading and using this code you agree to the terms in the LICENSE. Third-party datasets and software are subject to their respective licenses.
How to cite this article:
Wu Y, Wang C. Parallel-branch network for 3D human pose and shape estimation in video. Comput Anim Virtual Worlds. 2022;e2078. https://doi.org/10.1002/cav.2078
We indicate if a function or script is borrowed externally inside each file. Here are some great resources we benefit: