Synthesizing controllable motion for a character using deep learning has been a promising approach due to its potential to learn a compact model without laborious feature engineering. To produce dynamic motion from weak control signals such as desired paths, existing methods often require auxiliary information such as phases for alleviating motion ambiguity, which limits their generalisation capability. As past poses often contain useful auxiliary hints, in this paper, we propose a task-agnostic deep learning method, namely Multi-scale Control Signal-aware Transformer (MCS-T), with an attention based encoder-decoder architecture to discover the auxiliary information implicitly for synthesizing controllable motion without explicitly requiring auxiliary information such as phase. Specifically, an encoder is devised to adaptively formulate the motion patterns of a character's past poses with multi-scale skeletons, and a decoder driven by control signals to further synthesize and predict the character's state by paying context-specialised attention to the encoded past motion patterns. As a result, it helps alleviate the issues of low responsiveness and slow transition which often happen in conventional methods not using auxiliary information. Both qualitative and quantitative experimental results on an existing biped locomotion dataset, which involves diverse types of motion transitions, demonstrate the effectiveness of our method. In particular, MCS-T is able to successfully generate motions comparable to those generated by the methods using auxiliary information.
翻译:利用深层学习合成一个字符的可控性运动是一个很有希望的方法,因为它有可能学习不费力的特点工程的紧凑模型。为了从弱控制信号(如理想路径)中产生动态运动,现有方法往往需要辅助信息,例如减缓运动模糊性的阶段,从而限制其概括性能力。由于过去往往包含有用的辅助提示,我们在本文件中提议了一个任务-不可知的深层次学习方法,即多尺度控制信号-觉变异器(MCS-T),其关注基础是编码-解密器结构,以发现辅助信息,用于合成可控动作,而不需要阶段等辅助信息。具体地说,为了从弱控制信号产生动态动态,例如减缓动作的阶段,现有方法需要适应性地构建一个特性过去所形成的运动模式,并带有多尺度骨架,而由控制信号驱动的解析器进一步综合和预测特性状态,即多尺度控制信号-感知识变变变变器(MCS-T),因此,它有助于缓解低响应率和缓慢转变的问题,这往往是在常规方法下发生的,不需要使用辅助信息(如阶段)辅助信息。具体设计,用定性和定量实验性模型,两种方法都显示一种可比较性试验方法,即产生可变动。</s>