In this paper, we aim to reduce the footskate artifacts when reconstructing human dynamics from monocular RGB videos. Recent work has made substantial progress in improving the temporal smoothness of the reconstructed motion trajectories. Their results, however, still suffer from severe foot skating and slippage artifacts. To tackle this issue, we present a neural network based detector for localizing ground contact events of human feet and use it to impose a physical constraint for optimization of the whole human dynamics in a video. We present a detailed study on the proposed ground contact detector and demonstrate high-quality human motion reconstruction results in various videos.
Yuliang Zou, Jimei Yang, Duygu Ceylan, Jianming Zhang, Federico Perazzi, Jia-Bin Huang: Reducing Footskate in Human Motion Reconstruction with Ground Contact Constraints. WACV 2020: 448-457
- Date of publication:
- May 14, 2020
- IEEE (WACV)
- Page number(s):