A Survey on Deep Learning for Skeleton‐Based Human Animation

Human character animation is often critical in entertainment content production, including video games, virtual reality or fiction films. To this end, deep neural networks drive most recent advances through learning (DL) and reinforcement (DRL). In article, we propose a comprehensive survey on the state-of-the-art approaches based either DL DRL skeleton-based human animation. First, introduce motion data representations, common datasets how basic models can be enhanced to foster of spatial temporal patterns data. Second, cover divided into three large families applications pipelines: synthesis, control editing. Finally, discuss limitations current methods and/or skeletal possible directions future research alleviate meet animators' needs.