Two-Person Interaction Augmentation with Skeleton Priors

Baiyi Li, Edmond S. L. Ho, Hubert P. H. Shum and He Wang
Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024

 H5-Index: 115#

Two-Person Interaction Augmentation with Skeleton Priors
# According to Google Scholar 2024

Abstract

Close and continuous interaction with rich contacts is a crucial aspect of human activities (e.g. hugging, dancing) and of interest in many domains like activity recognition, motion prediction, character animation, etc. However, acquiring such skeletal motion is challenging. While direct motion capture is expensive and slow, motion editing/ generation is also non-trivial, as complex contact patterns with topological and geometric constraints have to be retained. To this end, we propose a new deep learning method for two-body skeletal interaction motion augmentation, which can generate variations of contact-rich interactions with varying body sizes and proportions while retaining the key geometric/topological relations between two bodies. Our system can learn effectively from a relatively small amount of data and generalize to drastically different skeleton sizes. Through exhaustive evaluation and comparison, we show it can generate high-quality motions, has strong generalizability and outperforms traditional optimization-based methods and alternative deep learning solutions.

Downloads

YouTube

Citations

BibTeX

@inproceedings{li24twoperson,
 author={Li, Baiyi and Ho, Edmond S. L. and Shum, Hubert P. H. and Wang, He},
 booktitle={Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
 series={CVPRW '24},
 title={Two-Person Interaction Augmentation with Skeleton Priors},
 year={2024},
 publisher={IEEE/CVF},
 location={Seattle, USA},
}

RIS

TY  - CONF
AU  - Li, Baiyi
AU  - Ho, Edmond S. L.
AU  - Shum, Hubert P. H.
AU  - Wang, He
T2  - Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
TI  - Two-Person Interaction Augmentation with Skeleton Priors
PY  - 2024
PB  - IEEE/CVF
ER  - 

Plain Text

Baiyi Li, Edmond S. L. Ho, Hubert P. H. Shum and He Wang, "Two-Person Interaction Augmentation with Skeleton Priors," in CVPRW '24: Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, USA, IEEE/CVF, 2024.

Supporting Grants

Similar Research

Qianhui Men, Hubert P. H. Shum, Edmond S. L. Ho and Howard Leung, "GAN-Based Reactive Motion Synthesis with Class-Aware Discriminators for Human-Human Interaction", Computers and Graphics (C&G), 2022
Taku Komura, Hubert P. H. Shum and Edmond S. L. Ho, "Simulating Interactions of Characters", Proceedings of the 2008 ACM International Conference on Motion in Games (MIG), 2008
He Wang, Edmond S. L. Ho, Hubert P. H. Shum and Zhanxing Zhu, "Spatio-Temporal Manifold Learning for Human Motions via Long-Horizon Modeling", IEEE Transactions on Visualization and Computer Graphics (TVCG), 2021
Hubert P. H. Shum and Taku Komura, "Generating Realistic Fighting Scenes by Game Tree", Proceedings of the 2006 ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA) Posters, 2006
Hubert P. H. Shum and Taku Komura, "Technical Note: Generating Realistic Fighting Scenes by Game Tree", arXiv Preprint, 2006
Hubert P. H. Shum, Taku Komura and Shuntaro Yamazaki, "Simulating Competitive Interactions using Singly Captured Motions", Proceedings of the 2007 ACM Symposium on Virtual Reality Software and Technology (VRST), 2007
Hubert P. H. Shum, "Simulating Interactions Among Multiple Characters", PhD Thesis from the University of Edinburgh, 2010

 

 

Last updated on 15 July 2024
RSS Feed