arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.05897cs.CV
收藏

MultiAct:基于多个动作标签的长期三维人体运动生成

MultiAct: Long-Term 3D Human Motion Generation from Multiple Action Labels

IPAI;Seoul National University(首尔大学);Meta Reality Labs Research(Meta现实实验室)

Taeryung Lee, Gyeongsik Moon, Kyoung Mu Lee

摘要:

我们解决了从多个动作标签生成长期3D人体运动的问题。两个主要的以前的方法,如动作和运动条件的方法,有局限性,以解决这个问题。动作条件方法从单个动作生成运动序列。因此,它不能生成由多个动作和动作之间的转换组成的长期运动。同时,运动条件方法从初始运动生成未来运动。生成的未来运动仅依赖于过去,因此它们不能由用户的期望动作控制。我们提出了MultiAct,第一个框架,以产生长期的三维人体运动从多个动作标签。MultiAct通过统一的循环生成系统同时考虑动作和运动条件。它重复使用先前的运动和动作标签;然后,它生成平滑的过渡和给定动作的运动。因此,MultiAct可生成由给定序列的多个动作标签控制的逼真的长期运动。代码可在https://github.com/TaeryungLee/MultiAct_RELEASE上获得。

英文摘要:

We tackle the problem of generating long-term 3D human motion from multiple action labels. Two main previous approaches, such as action- and motion-conditioned methods, have limitations to solve this problem. The action-conditioned methods generate a sequence of motion from a single action. Hence, it cannot generate long-term motions composed of multiple actions and transitions between actions. Meanwhile, the motion-conditioned methods generate future motions from initial motion. The generated future motions only depend on the past, so they are not controllable by the user's desired actions. We present MultiAct, the first framework to generate long-term 3D human motion from multiple action labels. MultiAct takes account of both action and motion conditions with a unified recurrent generation system. It repetitively takes the previous motion and action label; then, it generates a smooth transition and the motion of the given action. As a result, MultiAct produces realistic long-term motion controlled by the given sequence of multiple action labels. Codes are available here at https://github.com/TaeryungLee/MultiAct_RELEASE.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑