This is a repository for practice implementation of 'MeshTransforemr'
Details of Review for blog
Details of implementation process for blog
This is our research code of End-to-End Human Pose and Mesh Reconstruction with Transformers.
MEsh TRansfOrmer is a simple yet effective transformer-based method for human pose and mesh reconsruction from an input image. In this repository, we provide our research code for training and testing our proposed method for the following tasks:
- Human pose and mesh reconstruction
- Hand pose and mesh reconstruction
Check INSTALL.md for installation instructions.
Please download our pre-trained models and other relevant files that are important to run our code.
Check DOWNLOAD.md for details.
We provide demo codes to run end-to-end inference on the test images.
Check DEMO.md for details.
We provide python codes for training and evaluation.
Check EXP.md for details.
We welcome contributions and suggestions. Please check CONTRIBUTE and CODE_OF_CONDUCT for details.
If you find our work useful in your research, please consider citing:
@inproceedings{lin2021end-to-end,
author = {Lin, Kevin and Wang, Lijuan and Liu, Zicheng},
title = {End-to-End Human Pose and Mesh Reconstruction with Transformers},
booktitle = {CVPR},
year = {2021},
}
Our research code is released under the MIT license. See LICENSE for details.
We use submodules from third parties, such as huggingface/transformers and hassony2/manopth. Please see NOTICE for details.
We note that any use of SMPL models and MANO models are subject to Software Copyright License for non-commercial scientific research purposes. See SMPL-Model License and MANO License for details.
Our implementation and experiments are built on top of open-source GitHub repositories. We thank all the authors who made their code public, which tremendously accelerates our project progress. If you find these works helpful, please consider citing them as well.