arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.01418cs.CVcs.GR
收藏

人体运动扩散作为生成先验

Human Motion Diffusion as a Generative Prior

Tel-Aviv University(特拉维夫大学)

Yonatan Shafir, Guy Tevet, Roy Kapon, Amit H. Bermano

AI总结:

本文提出基于扩散先验的顺序、并行和模型三种组合方式,分别解决长序列生成、双人交互和细粒度控制问题,并引入DoubleTake、ComMDM和DiffusionBlending方法,实验验证其有效性。

摘要:

近期工作已证明去噪扩散模型在生成人体运动方面的巨大潜力,包括文本到运动的能力。然而,这些方法受到标注运动数据匮乏、专注于单人运动以及缺乏精细控制的限制。在本文中,我们引入了基于扩散先验的三种组合形式:顺序组合、并行组合和模型组合。利用顺序组合,我们解决了长序列生成的挑战。我们提出了DoubleTake,一种推理时方法,通过该方法,我们使用仅针对短片段训练的先验,生成由提示区间序列及其过渡组成的长动画。利用并行组合,我们展示了朝向双人生成的有前景的步骤。从两个固定先验以及少量双人训练示例开始,我们学习了一个精简的通信模块ComMDM,以协调两个生成运动之间的交互。最后,利用模型组合,我们首先训练单独的先验来完成实现给定关节规定运动的运动。然后,我们引入了DiffusionBlending,一种插值机制,以有效融合多个此类模型,从而实现灵活高效的细粒度关节和轨迹级控制与编辑。我们使用现成的运动扩散模型评估了组合方法,并进一步将结果与为这些特定任务训练的专用模型进行了比较。

英文摘要:

Recent work has demonstrated the significant potential of denoising diffusion models for generating human motion, including text-to-motion capabilities. However, these methods are restricted by the paucity of annotated motion data, a focus on single-person motions, and a lack of detailed control. In this paper, we introduce three forms of composition based on diffusion priors: sequential, parallel, and model composition. Using sequential composition, we tackle the challenge of long sequence generation. We introduce DoubleTake, an inference-time method with which we generate long animations consisting of sequences of prompted intervals and their transitions, using a prior trained only for short clips. Using parallel composition, we show promising steps toward two-person generation. Beginning with two fixed priors as well as a few two-person training examples, we learn a slim communication block, ComMDM, to coordinate interaction between the two resulting motions. Lastly, using model composition, we first train individual priors to complete motions that realize a prescribed motion for a given joint. We then introduce DiffusionBlending, an interpolation mechanism to effectively blend several such models to enable flexible and efficient fine-grained joint and trajectory-level control and editing. We evaluate the composition methods using an off-the-shelf motion diffusion model, and further compare the results to dedicated models trained for these specific tasks.

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。

↑