arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.10399cs.CVcs.AI
收藏

3D场景中4D人体捕捉的运动先验学习

Learning Motion Priors for 4D Human Body Capture in 3D Scenes

ETH Zürich(苏黎世联邦理工学院);Microsoft(微软)

Siwei Zhang, Yan Zhang, Federica Bogo, Marc Pollefeys, Siyu Tang

摘要:

从单目视频中恢复复杂场景中的高质量3D人体运动对于从AR/VR到机器人的许多应用都很重要。然而,捕捉现实的人的场景交互,同时处理遮挡和部分视图,是具有挑战性的,目前的方法仍然远远没有达到令人信服的结果。我们通过提出LEMO:LEarning human MOtion priors for 4D human body capture来解决这个问题。通过利用大规模运动捕捉数据集AMASS,我们引入了一种新的运动平滑先验,它大大减少了在序列中恢复的姿势所表现出的抖动。此外,为了处理身体场景交互中经常发生的接触和遮挡,我们设计了一个接触摩擦项和一个通过每个实例自监督训练获得的接触感知运动填充器。为了证明所提出的运动先验的有效性,我们将它们组合成一个新的管道,用于3D场景中的4D人体捕获。通过我们的管道,我们展示了高质量的4D人体捕捉,重建平滑的运动和物理上合理的身体场景交互。代码和数据可在https://sanweiliti.github.io/LEMO/LEMO.html上获得。

英文摘要:

Recovering high-quality 3D human motion in complex scenes from monocular videos is important for many applications, ranging from AR/VR to robotics. However, capturing realistic human-scene interactions, while dealing with occlusions and partial views, is challenging; current approaches are still far from achieving compelling results. We address this problem by proposing LEMO: LEarning human MOtion priors for 4D human body capture. By leveraging the large-scale motion capture dataset AMASS, we introduce a novel motion smoothness prior, which strongly reduces the jitters exhibited by poses recovered over a sequence. Furthermore, to handle contacts and occlusions occurring frequently in body-scene interactions, we design a contact friction term and a contact-aware motion infiller obtained via per-instance self-supervised training. To prove the effectiveness of the proposed motion priors, we combine them into a novel pipeline for 4D human body capture in 3D scenes. With our pipeline, we demonstrate high-quality 4D human body capture, reconstructing smooth motions and physically plausible body-scene interactions. The code and data are available at https://sanweiliti.github.io/LEMO/LEMO.html.

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。

↑