Publication

SimPoE: Simulated Character Control for 3D Human Pose Estimation

Conference on Computer Vision and Pattern Recognition (CVPR)


Abstract

Accurate estimation of 3D human motion from monocular video requires modeling both kinematics (body motion without physical forces) and dynamics (motion with physical forces). To demonstrate this, we present SimPoE, a Simulation-based approach for 3D human Pose Estimation, which integrates image-based kinematic inference and physics-based dynamics modeling. SimPoE learns a policy that takes as input the current-frame pose estimate and the next image frame to control a physically-simulated character to output the next-frame pose estimate. The policy contains a learnable kinematic pose refinement unit that uses 2D key-points to iteratively refine its kinematic pose estimate of the next frame. Based on this refined kinematic pose, the policy learns to compute dynamics-based control (e.g., joint torques) of the character to advance the current-frame pose estimate to the pose estimate of the next frame. This design couples the kinematic pose refinement unit with the dynamics-based control generation unit, which are learned jointly with reinforcement learning to achieve accurate and physically-plausible pose estimation. Furthermore, we propose a meta-control mechanism which dynamically adjusts the character’s dynamics parameters based on the character state to attain more accurate pose estimates. Experiments on large-scale motion datasets demonstrate that our approach establishes new state of the art in pose accuracy while ensuring physical plausibility.

Related Publications

All Publications

ICASSP - June 6, 2021

On the Predictability of HRTFs from Ear Shapes Using Deep Networks

Yaxuan Zhou, Hao Jiang, Vamsi Krishna Ithapu

arXiv - April 2, 2021

Multiview Pseudo-Labeling for Semi-supervised Learning from Video

Bo Xiong, Haoqi Fan, Kristen Grauman, Christoph Feichtenhofer

TASLP - April 24, 2021

Mixed Source Sound Field Translation for Virtual Binaural Application with Perceptual Validation

Lachlan Birnie, Thushara Abhayapala, Vladimir Tourbabin, Prasanga Samarasinghe

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy