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 2209.06314cs.CV
收藏

通过学习交互与几何驱动的关键帧将人体动画置入3D场景

Placing Human Animations into 3D Scenes by Learning Interaction- and Geometry-Driven Keyframes

University of Maryland(马里兰大学);Purdue University(普渡大学)

James F. Mullen, Divya Kothandaraman, Aniket Bera, Dinesh Manocha

AI总结:

该研究提出PAAK方法,通过学习交互与几何驱动的关键帧优化3D人体动画在场景中的放置,保留人-场景交互,感知实验显示其效果优于POSA、PROX基准真值等现有方法。

摘要:

我们提出一种将3D人体动画置入3D场景的新方法,同时保留动画中所有的人-场景交互。我们引入计算动画中与场景交互最重要的网格的概念,将其称为“关键帧”。这些关键帧让我们能更好地优化动画在场景中的放置位置,使动画中的交互(站立、躺卧、就坐等)与场景的可供性(例如站在地板上或躺在床上)相匹配。我们将所提方法PAAK与现有方法(包括POSA、PROX基准真值以及一种运动合成方法)进行对比,并通过感知研究凸显了该方法的优势。人类评估者在64.6%的情况下更偏好我们的PAAK方法,而非PROX基准真值数据。此外,在直接对比中,评估者更偏好PAAK而非其他对比方法,其中相比POSA的偏好占比为61.5%。

英文摘要:

We present a novel method for placing a 3D human animation into a 3D scene while maintaining any human-scene interactions in the animation. We use the notion of computing the most important meshes in the animation for the interaction with the scene, which we call "keyframes." These keyframes allow us to better optimize the placement of the animation into the scene such that interactions in the animations (standing, laying, sitting, etc.) match the affordances of the scene (e.g., standing on the floor or laying in a bed). We compare our method, which we call PAAK, with prior approaches, including POSA, PROX ground truth, and a motion synthesis method, and highlight the benefits of our method with a perceptual study. Human raters preferred our PAAK method over the PROX ground truth data 64.6\% of the time. Additionally, in direct comparisons, the raters preferred PAAK over competing methods including 61.5\% compared to POSA.

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。

↑