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 2212.04360cs.CVcs.GR
收藏

MIME:人性化的三维场景生成

MIME: Human-Aware 3D Scene Generation

Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Adobe Inc.(奥多比公司)

Hongwei Yi, Chun-Hao P. Huang, Shashank Tripathi, Lea Hering, Justus Thies, Michael J. Black

摘要:

生成由移动的人类占据的逼真3D世界在游戏、建筑和合成数据创建中有许多应用。但是生成这样的场景是昂贵的和劳动密集型的。最近的工作产生人体姿势和运动给定的3D场景。在这里,我们采取相反的方法,并生成3D室内场景的三维人体运动。这些运动可以来自存档运动捕捉或来自佩戴在身体上的IMU传感器,有效地将人类运动转化为3D世界的“扫描仪”。直观地说,人类运动表示房间中的自由空间,人类接触表示支持坐、躺或触摸等活动的表面或物体。我们提出了MIME(挖掘交互和运动来推断3D环境),这是一种室内场景的生成模型,可以生成与人类运动一致的家具布局。MIME使用自回归Transformer架构,将场景中已生成的对象以及人体运动作为输入,并输出下一个可能的对象。为了训练MIME,我们通过用3D人类填充3D FRONT场景数据集来构建数据集。我们的实验表明,MIME产生更多样化和合理的3D场景比最近的生成场景的方法,不知道人体运动。代码和数据将在https://mime.is.tue.mpg.de上提供。

英文摘要:

Generating realistic 3D worlds occupied by moving humans has many applications in games, architecture, and synthetic data creation. But generating such scenes is expensive and labor intensive. Recent work generates human poses and motions given a 3D scene. Here, we take the opposite approach and generate 3D indoor scenes given 3D human motion. Such motions can come from archival motion capture or from IMU sensors worn on the body, effectively turning human movement in a "scanner" of the 3D world. Intuitively, human movement indicates the free-space in a room and human contact indicates surfaces or objects that support activities such as sitting, lying or touching. We propose MIME (Mining Interaction and Movement to infer 3D Environments), which is a generative model of indoor scenes that produces furniture layouts that are consistent with the human movement. MIME uses an auto-regressive transformer architecture that takes the already generated objects in the scene as well as the human motion as input, and outputs the next plausible object. To train MIME, we build a dataset by populating the 3D FRONT scene dataset with 3D humans. Our experiments show that MIME produces more diverse and plausible 3D scenes than a recent generative scene method that does not know about human movement. Code and data will be available for research at https://mime.is.tue.mpg.de.

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。

↑