Skip to content

Files

Latest commit

46ba2da · Dec 26, 2023

History

History

pose_anything

Pose Anything: A Graph-Based Approach for Category-Agnostic Pose Estimation

By Or Hirschorn and Shai Avidan

Teaser Figure

Introduction

We present a novel approach to CAPE that leverages the inherent geometrical relations between keypoints through a newly designed Graph Transformer Decoder. By capturing and incorporating this crucial structural information, our method enhances the accuracy of keypoint localization, marking a significant departure from conventional CAPE techniques that treat keypoints as isolated entities.

Citation

If you find this useful, please cite this work as follows:

@misc{hirschorn2023pose,
      title={Pose Anything: A Graph-Based Approach for Category-Agnostic Pose Estimation},
      author={Or Hirschorn and Shai Avidan},
      year={2023},
      eprint={2311.17891},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Getting Started

📣 Pose Anything is available on OpenXLab now. [Try it online]

Install Dependencies

We recommend using a virtual environment for running our code. After installing MMPose, you can install the rest of the dependencies by running:

pip install timm

Pretrained Weights

The full list of pretrained models can be found in the Official Repo.

Demo on Custom Images

A bigger and more accurate version of the model - COMING SOON!

Download the pretrained model and run:

python demo.py --support [path_to_support_image] --query [path_to_query_image] --config configs/demo_b.py --checkpoint [path_to_pretrained_ckpt]

Note: The demo code supports any config with suitable checkpoint file. More pre-trained models can be found in the official repo.

Training and Testing on MP-100 Dataset

We currently only support demo on custom images through the MMPose repo.

For training and testing on the MP-100 dataset, please refer to the Official Repo.

Acknowledgement

Our code is based on code from:

License

This project is released under the Apache 2.0 license.