4 papers
LRC-JEPA: Disentangling Dynamics and Residual Context for Efficient World Models
Luzhe Huang, Lei Chu, Jingyi Liang +1
Compact JEPA world models enable efficient latent-space planning, but low-dimensional representation trained under reward-free self-supervision must encode both action-conditioned…
Diverse Yet Consistent: Context-Guided Diffusion with Energy-Based Joint Refinement for Multi-Agent Motion Prediction
Lei Chu, Yuhuan Zhao
Deepgenerative models havebecomeapromisingapproach for human motion prediction due to their ability to capture multimodal distributions and represent diverse human be haviors. Howe…
EnvPoser: Environment-aware Realistic Human Motion Estimation from Sparse Observations with Uncertainty Modeling
Songpengcheng Xia, Yu Zhang, Zhuo Su +7
Estimating full-body motion using the tracking signals of head and hands from VR devices holds great potential for various applications. However, the sparsity and unique distributi…
Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensors
Yu Zhang, Songpengcheng Xia, Lei Chu +3
This paper introduces a novel human pose estimation approach using sparse inertial sensors, addressing the shortcomings of previous methods reliant on synthetic data. It leverages…