English

Kinematics-Guided Reinforcement Learning for Object-Aware 3D Ego-Pose Estimation

Computer Vision and Pattern Recognition 2020-12-10 v3

Abstract

We propose a method for incorporating object interaction and human body dynamics into the task of 3D ego-pose estimation using a head-mounted camera. We use a kinematics model of the human body to represent the entire range of human motion, and a dynamics model of the body to interact with objects inside a physics simulator. By bringing together object modeling, kinematics modeling, and dynamics modeling in a reinforcement learning (RL) framework, we enable object-aware 3D ego-pose estimation. We devise several representational innovations through the design of the state and action space to incorporate 3D scene context and improve pose estimation quality. We also construct a fine-tuning step to correct the drift and refine the estimated human-object interaction. This is the first work to estimate a physically valid 3D full-body interaction sequence with objects (e.g., chairs, boxes, obstacles) from egocentric videos. Experiments with both controlled and in-the-wild settings show that our method can successfully extract an object-conditioned 3D ego-pose sequence that is consistent with the laws of physics.

Keywords

Cite

@article{arxiv.2011.04837,
  title  = {Kinematics-Guided Reinforcement Learning for Object-Aware 3D Ego-Pose Estimation},
  author = {Zhengyi Luo and Ryo Hachiuma and Ye Yuan and Shun Iwase and Kris M. Kitani},
  journal= {arXiv preprint arXiv:2011.04837},
  year   = {2020}
}

Comments

Project website: https://zhengyiluo.github.io/projects/contextegopose/

R2 v1 2026-06-23T20:02:01.297Z