Preprint
Aug 2026
Gaussian-Mixture Latent Flow for Stochastic 3D Human Motion Prediction
This work proposes a latent flow-based model equipped with a data-driven Gaussian mixture prior that more effectively disentangles diverse human behaviors than conventional single-modal priors and enables natural uncertainty quantification through tractable likelihood computation.
Yue Ma, Frederick W. B. Li, Xiaohui Liang
· 0 citations