Hierarchical block-based incomplete human mocap data recovery using adaptive nonnegative matrix factorization

Shu-Juan Peng, Gao-Feng He, Xin Liu, Hua-zhen Wang

Abstract: Highlights•The human mocap data is represented with five block-based sub-chain motion clips.•The low-rank and nonnegativity properties of the mocap data are well exploited.•An adaptive nonnegative matrix factorization method is proposed for motion recovery.•Much better results have been achieved than state-of-the-art algorithms.