TechRxiv
_Yuxuan__2022_EGOFISH3D_main_final.pdf (17.13 MB)
Download file

EgoFish3D: Egocentric 3D Pose Estimation from a Fisheye Camera via Self-Supervised Learning

Download (17.13 MB)
preprint
posted on 03.03.2022, 16:42 by Yuxuan LiuYuxuan Liu, Jianxin Yang, Xiao Gu, Yijun Chen, Yao Guo, Guang-Zhong Yang
Egocentric vision has a wide range of applications for human-centric activity recognition. However, the use of the egocentric fisheye camera allows wide angle coverage but image distortion is introduced along with strong human body self-occlusion, which can impose significant challenges in data processing and model reconstruction. Unlike previous work only leveraging synthetic data for model training, this paper first presents a new real-world EgoCentric Human Action (ECHA) dataset. By using the self-supervised learning under multi-view constraints, we propose a simple yet effective framework, namely EgoFish3D, for egocentric 3D pose estimation from a single image in different real-world scenarios.

History

Email Address of Submitting Author

20000905lyx@sjtu.edu.cn

Submitting Author's Institution

Institute of Medical Robotics, Shanghai Jiao Tong University

Submitting Author's Country

China

Usage metrics

Licence

Exports