NeRMo: Learning Implicit Neural Representations for 3D Human Motion Prediction

Dong Wei, Huaijiang Sun, Xiaoning Sun*, Shengxiang Hu ;

"Predicting accurate future human poses from historically observed motions remains a challenging task due to the spatial-temporal complexity and continuity of motions. Previous historical-value methods typically interpret the motion as discrete consecutive frames, which neglects the continuous temporal dynamics and impedes the capability of handling incomplete observations (with missing values). In this paper, we propose a novel implicit Neural Representation method for the task of human Motion prediction, dubbed NeRMo, which represents the motion as a continuous function parameterized by a neural network. The core idea is to explicitly disentangle the spatial-temporal context and output the corresponding 3D skeleton positions. This separate and flexible treatment of space and time allows NeRMo to combine the following advantages. It extrapolates at arbitrary temporal locations; it can learn from both complete and incomplete observed past motions; it provides a unified framework for repairing missing values and forecasting future poses using a single trained model. In addition, we show that NeRMo exhibits compatibility with meta-learning methods, enabling it to effectively generalize to unseen time steps. Extensive experiments conducted on classical benchmarks have confirmed the superior repairing and prediction performance of our proposed method compared to existing historical-value baselines."