Neural3Points: Learning to Generate Physically Realistic Full-body Motion for Virtual Reality Users
| dc.contributor.author | Ye, Yongjing | en_US |
| dc.contributor.author | Liu, Libin | en_US |
| dc.contributor.author | Hu, Lei | en_US |
| dc.contributor.author | Xia, Shihong | en_US |
| dc.contributor.editor | Dominik L. Michels | en_US |
| dc.contributor.editor | Soeren Pirk | en_US |
| dc.date.accessioned | 2022-08-10T15:19:40Z | |
| dc.date.available | 2022-08-10T15:19:40Z | |
| dc.date.issued | 2022 | |
| dc.description.abstract | Animating an avatar that reflects a user's action in the VR world enables natural interactions with the virtual environment. It has the potential to allow remote users to communicate and collaborate in a way as if they met in person. However, a typical VR system provides only a very sparse set of up to three positional sensors, including a head-mounted display (HMD) and optionally two hand-held controllers, making the estimation of the user's full-body movement a difficult problem. In this work, we present a data-driven physics-based method for predicting the realistic full-body movement of the user according to the transformations of these VR trackers and simulating an avatar character to mimic such user actions in the virtual world in realtime. We train our system using reinforcement learning with carefully designed pretraining processes to ensure the success of the training and the quality of the simulation. We demonstrate the effectiveness of the method with an extensive set of examples. | en_US |
| dc.description.number | 8 | |
| dc.description.sectionheaders | Motion II | |
| dc.description.seriesinformation | Computer Graphics Forum | |
| dc.description.volume | 41 | |
| dc.identifier.doi | 10.1111/cgf.14634 | |
| dc.identifier.issn | 1467-8659 | |
| dc.identifier.pages | 183-194 | |
| dc.identifier.pages | 12 pages | |
| dc.identifier.uri | https://doi.org/10.1111/cgf.14634 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.1111/cgf14634 | |
| dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
| dc.subject | CCS Concepts: Computing methodologies --> Physical simulation; Virtual reality; Motion capture; Theory of computation --> Reinforcement Learning | |
| dc.subject | Computing methodologies | |
| dc.subject | Physical simulation | |
| dc.subject | Virtual reality | |
| dc.subject | Motion capture | |
| dc.subject | Theory of computation | |
| dc.subject | Reinforcement Learning | |
| dc.title | Neural3Points: Learning to Generate Physically Realistic Full-body Motion for Virtual Reality Users | en_US |