Cross-Conditioned Recurrent Networks For Long-Term Synthesis Of Inter-Person Human Motion Interactions
2020 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV)(2020)
摘要
Modeling dynamics of human motion is one of the most challenging sequence modeling problem, with diverse applications in animation industry, human-robot interaction, motion-based surveillance, etc. Available attempts to use auto-regressive techniques for long-term single-person motion generation usually fails, resulting in stagnated motion or divergence to unrealistic pose patterns. In this paper, we propose a novel cross-conditioned recurrent framework targeting long-term synthesis of inter-person interactions beyond several minutes. We carefully integrate positive implications of both auto-regressive and encoder-decoder recurrent architecture, by interchangeably utilizing two separate fixed-length cross person motion prediction models for long-term generation in a novel hierarchical fashion. As opposed to prior approaches, we guarantee structural plausibility of 3D pose by training the recurrent model to regress latent representation of a separately trained generative pose embedding network. Different variants of the proposed frameworks are evaluated through extensive experiments on SBU-interaction, CMU-MoCAP and an inhouse collection of duet-dance dataset. Qualitative and quantitative evaluation on several tasks, such as Short-term motion prediction, Long-term motion synthesis and Interaction-based motion retrieval against prior state-of-the-art approaches clearly highlight superiority of the proposed framework.
更多查看译文
关键词
generative pose embedding network,3D pose,long-term single-person motion generation,sequence modeling problem,cross-conditioned recurrent framework,short-term motion prediction,long-term motion synthesis,interaction-based motion retrieval,SBU-interaction,recurrent model,long-term generation,fixed-length cross person motion prediction models,encoder-decoder recurrent architecture,inter-person interactions,unrealistic pose patterns,stagnated motion,auto-regressive techniques,inter-person human motion interactions,long-term synthesis,cross-conditioned recurrent networks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要