期刊
ACM TRANSACTIONS ON GRAPHICS
卷 40, 期 4, 页码 -出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3450626.3459792
关键词
human animation; motion capture; skin deformation
资金
- National Science Foundation [IIS-1764071, IIS-2008915, IIS-2008564]
- Activision
- Adobe
The new method captures detailed human motion, outputs precise point coordinates with unique labels, and relies on 2D images only. It utilizes a special motion capture suit and neural networks to process images, making it easy to replicate and deploy. The method can accurately capture various human poses, including challenging motions like yoga and gymnastics.
We present a new method to capture detailed human motion, sampling more than 1000 unique points on the body. Our method outputs highly accurate 4D (spatio-temporal) point coordinates and, crucially, automatically assigns a unique label to each of the points. The locations and unique labels of the points are inferred from individual 2D input images only, without relying on temporal tracking or any human body shape or skeletal kinematics models. Therefore, our captured point trajectories contain all of the details from the input images, including motion due to breathing, muscle contractions and flesh deformation, and are well suited to be used as training data to fit advanced models of the human body and its motion. The key idea behind our system is a new type of motion capture suit which contains a special pattern with checkerboard-like corners and two-letter codes. The images from our multi-camera system are processed by a sequence of neural networks which are trained to localize the corners and recognize the codes, while being robust to suit stretching and self-occlusions of the body. Our system relies only on standard RGB or monochrome sensors and fully passive lighting and the passive suit, making our method easy to replicate, deploy and use. Our experiments demonstrate highly accurate captures of a wide variety of human poses, including challenging motions such as yoga, gymnastics, or rolling on the ground.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据