面向同胚异构骨骼运动重定向的高阶图卷积网络  

A high-order graph convolutional network for homomorphic and heterogeneous skeletal motion retargeting

作　　者：贾伟[1] 李骏 李书杰[1] 赵洋[1] 闵海[1] Jia Wei;Li Jun;Li Shujie;Zhao Yang;Min Hai(School of Computer Science and Information Engineering,Hefei University of Technology,Hefei 230601,China)

机构地区：[1]合肥工业大学计算机与信息学院,合肥230601

出　　处：《中国图象图形学报》2024年第12期3712-3726,共15页Journal of Image and Graphics

基　　金：国家自然科学基金项目(62076086)。

摘　　要：目的 骨骼运动重定向是指将源角色的骨骼运动数据,修改后运用到另一个具有不同骨架结构的目标角色上,使得目标角色和源角色做出相同的动作。由于骨骼运动数据与骨架结构之间具有高耦合性,重定向算法需要从运动数据中分离出与骨架结构无关、只表示动作类型的特征。当源角色与目标角色骨架结构不同,且两者运动模式(如关节角变化范围)存在较大差异时,特征分离难度加大,重定向网络训练难度变大。针对该问题,提出了特征分离的方法和高阶骨骼卷积算子。方法 在数据处理阶段,首先从运动数据中分离出一部分与骨架结构无关的特征,从而降低重定向网络训练难度,得到更好的重定向结果。另外,结合图卷积网络,本文针对人体骨架结构提出了高阶骨骼卷积算子。使用该算子,本文网络模型可以捕获更多有关骨架结构的信息,提高重定向结果的精度和视觉效果。结果 在异构重定向任务中,本文方法在合成动画数据集Mixamo上与最新方法对比,重定向结果精度提升了38.6%。另外,本文方法也同样适用于同构重定向,结果精度比最新方法提升了74.8%。在从真人采集的运动数据到虚拟动画角色的异构重定向任务中,相比最新方法,本文方法能够明显减少重定向错误,重定向结果有更高的视觉质量。结论 相比较于目前最新的方法,本文方法降低了特征分离的难度且更加充分挖掘了骨架的结构信息,使得重定向结果误差更低且动作更自然合理。Objective Skeletal motion retargeting is a key technology that involves adapting skeletal motion data from a source character,after suitable modification,to a target character with a different skeleton structure,thereby ensuring that the target character performs actions identical to the source.This process,which is particularly crucial in animation production and game development,can greatly promote the reuse of existing motion data and significantly reduce the need to create new motion data from scratch.Skeletal motion data have an inherently strong relationship with a character's skeleton structure,and the core challenge in retargeting lies in extracting motion data features that are independent of the source skeleton and solely embody the essence and pattern of the action.The complexity in this process increases markedly during practical applications,especially when the source and target characters stem from distinct datasets(e.g.,translating motion capture data from real human subjects onto virtual animated characters with heterogeneous skeletal structures).The differences between such datasets extend beyond mere skeletal disparities and may encompass inconsistencies in capturing equipment,physiological variations among individuals,and diverse action execution environments.Collectively,these factors produce significant discrepancies between the source and target characters in terms of global movement ranges,joint angle variation range,and other motion attributes,thus posing formidable challenges for retargeting algorithms.This paper addresses the problem of overcoming data heterogeneity to enable a precise motion retargeting from real human motion data to heterogeneous yet topologically equivalent virtual animated characters.To this end,this paper proposes several strategies for feature separation and high-order skeletal convolution operators.Method During the data preprocessing stage,feature separation is applied on the motion data to isolate those components that are independent of the skeletal structure.T

关 键 词：深度学习 运动重定向 图卷积 自编码器 Human3.6M运动数据 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]