arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.14916cs.CVcs.GR
收藏

人体运动扩散模型

Human Motion Diffusion Model

Tel Aviv University(特拉维夫大学)

Guy Tevet, Sigal Raab, Brian Gordon, Yonatan Shafir, Daniel Cohen-Or, Amit H. Bermano

摘要:

自然和富有表现力的人体运动生成是计算机动画的圣杯。由于可能的运动的多样性、人类对它的感知敏感性以及精确描述它的困难性,这是一项具有挑战性的任务。因此,当前的生成解决方案要么质量低,要么表达能力有限。扩散模型在其他领域已经表现出了显著的生成能力,由于其多对多的性质,它是人类运动的有希望的候选者,但它们往往是资源饥渴和难以控制的。在本文中,我们介绍了运动扩散模型(MDM),一个仔细适应分类器自由扩散为基础的人体运动域生成模型。MDM是基于transformer的,结合了运动生成文献的见解。一个值得注意的设计选择是在每个扩散步骤中预测样本,而不是噪声。这便于使用关于运动的位置和速度的已建立的几何损失,例如脚接触损失。正如我们所展示的,MDM是一种通用的方法,支持不同的调节模式和不同的生成任务。我们表明,我们的模型是用轻量级资源训练的,但在文本到动作和动作到动作的领先基准测试中取得了最先进的结果。https://guytevet.github.io/mdm-page/的网站。

英文摘要:

Natural and expressive human motion generation is the holy grail of computer animation. It is a challenging task, due to the diversity of possible motion, human perceptual sensitivity to it, and the difficulty of accurately describing it. Therefore, current generative solutions are either low-quality or limited in expressiveness. Diffusion models, which have already shown remarkable generative capabilities in other domains, are promising candidates for human motion due to their many-to-many nature, but they tend to be resource hungry and hard to control. In this paper, we introduce Motion Diffusion Model (MDM), a carefully adapted classifier-free diffusion-based generative model for the human motion domain. MDM is transformer-based, combining insights from motion generation literature. A notable design-choice is the prediction of the sample, rather than the noise, in each diffusion step. This facilitates the use of established geometric losses on the locations and velocities of the motion, such as the foot contact loss. As we demonstrate, MDM is a generic approach, enabling different modes of conditioning, and different generation tasks. We show that our model is trained with lightweight resources and yet achieves state-of-the-art results on leading benchmarks for text-to-motion and action-to-motion. https://guytevet.github.io/mdm-page/ .

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。

↑