https://sirui-xu.github.io/STARS/

[ECCV 2022 oral] Official PyTorch implementation of the paper "Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors"
https://sirui-xu.github.io/STARS/

deep-learning disentangled-representations eccv2022 generative-model graph-neural-networks human-motion-prediction motion-forecasting motion-prediction pytorch

Last synced: 3 months ago
JSON representation

[ECCV 2022 oral] Official PyTorch implementation of the paper "Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors"

• Host: GitHub
• URL: https://sirui-xu.github.io/STARS/
• Owner: Sirui-Xu
• License: mit
• Created: 2022-04-02T23:35:40.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2023-03-19T01:04:48.000Z (over 1 year ago)
• Last Synced: 2024-04-05T10:32:15.513Z (7 months ago)
• Topics: deep-learning, disentangled-representations, eccv2022, generative-model, graph-neural-networks, human-motion-prediction, motion-forecasting, motion-prediction, pytorch
• Language: Python
• Homepage:
• Size: 159 MB
• Stars: 58
• Watchers: 4
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-conditional-content-generation - Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors

README

        
# Diverse Human Motion Prediction Guided by Multi-Level *S*patial-*T*emporal *A*ncho*RS*

[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/diverse-human-motion-prediction-guided-by/human-pose-forecasting-on-human36m)](https://paperswithcode.com/sota/human-pose-forecasting-on-human36m?p=diverse-human-motion-prediction-guided-by)

[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/diverse-human-motion-prediction-guided-by/human-pose-forecasting-on-humaneva-i)](https://paperswithcode.com/sota/human-pose-forecasting-on-humaneva-i?p=diverse-human-motion-prediction-guided-by)



---

This repo contains the official implementation of the paper:

Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors

Sirui Xu, Yu-Xiong Wang*, Liang-Yan Gui*

ECCV 2022 (**oral**)

[[website](https://sirui-xu.github.io/STARS/)] [[arxiv](https://arxiv.org/abs/2302.04860)] [[demo](https://sirui-xu.github.io/STARS/images/demo.mp4)] [[poster](https://sirui-xu.github.io/assets/pdf/STARS_poster.pdf)] [[slides](https://sirui-xu.github.io/assets/pdf/STARS_slides.pdf)] [[talk](https://sirui-xu.github.io/STARS/images/talk.mp4)]

Please refer to [deterministic human motion prediction](./deterministic/) and [diverse human motion prediction](./diverse/) for more details. 

## Citation

If you find this work useful in your research, please cite:

```bibtex

@inproceedings{xu22stars,

  title     = {Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors},

  author    = {Xu, Sirui and Wang, Yu-Xiong and Gui, Liang-Yan},

  booktitle = {European Conference on Computer Vision (ECCV)},

  year      = {2022}

}

```

## License

This repo is distributed under an [MIT LICENSE](LICENSE)