TruncHierVFM: Truncated Hierarchical Vision Foundation Model for Human Mesh Recovery & Human Pose Estimation
Official code repository for the paper: On the Use of Hierarchical Vision Foundation Models for Low-Cost Human Mesh Recovery and Pose Estimation
Shuhei Tarashima, Yushan Wang, Norio Tagawa
- [11/17/2025] Repository released.
- [10/14/2025] arXiv preprint is released.
Please refer to GET_STARTED.md for detailed setup instructions.
We tested our implementation with:
- Python3.10.13
- CUDA11.6
- Ubuntu 20.04
- 8x NVIDIA A100 GPUs
We recommend using the privide Dockerfile for environment setup. See Docker Container Preparation for more details.
If you find this work useful, please cite:
@inproceedings{tarashima2025trunc,
title={On the Use of Hierarchical Vision Foundation Models for Low-Cost Human Mesh Recovery and Pose Estimation},
author={Tarashima, Shuhei and Wang, Yushan and Tagawa, Norio},
booktitle={ICCV Workshops},
year={2025}
}
This repository builds upon publicly available implementations of:
We gratefully acknowledge the authors of these projects.