Tang, Xiangjun;
Wu, Linjun;
Wang, He;
Hu, Bo;
Gong, Xu;
Liao, Yuchen;
Li, Songnan;
... Jin, Xiaogang; + view all
(2023)
RSMT: Real-time Stylized Motion Transition for Characters.
In: Brunvand, Erik and Sheffer, Alla and Wimmer, Michael, (eds.)
SIGGRAPH '23: ACM SIGGRAPH 2023 Conference Proceedings.
(pp. pp. 1-10).
ACM (Association for Computing Machinery): New York, NY, USA.
Preview |
Text
2409.18401v1.pdf - Accepted Version Download (4MB) | Preview |
Abstract
Styled online in-between motion generation has important application scenarios in computer animation and games. Its core challenge lies in the need to satisfy four critical requirements simultaneously: generation speed, motion quality, style diversity, and synthesis controllability. While the first two challenges demand a delicate balance between simple fast models and learning capacity for generation quality, the latter two are rarely investigated together in existing methods, which largely focus on either control without style or uncontrolled stylized motions. To this end, we propose a Real-time Stylized Motion Transition method (RSMT) to achieve all aforementioned goals. Our method consists of two critical, independent components: a general motion manifold model and a style motion sampler. The former acts as a high-quality motion source and the latter synthesizes styled motions on the fly under control signals. Since both components can be trained separately on different datasets, our method provides great flexibility, requires less data, and generalizes well when no/few samples are available for unseen styles. Through exhaustive evaluation, our method proves to be fast, high-quality, versatile, and controllable. The code and data are available at https://github.com/yuyujunjun/RSMT-Realtime-Stylized-Motion-Transition.
| Type: | Proceedings paper |
|---|---|
| Title: | RSMT: Real-time Stylized Motion Transition for Characters |
| Event: | SIGGRAPH '23: Special Interest Group on Computer Graphics and Interactive Techniques Conference |
| Location: | CA, Los Angeles |
| Dates: | 6 Aug 2023 - 10 Aug 2023 |
| ISBN-13: | 9798400701597 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1145/3588432.3591514 |
| Publisher version: | https://doi.org/10.1145/3588432.3591514 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Animation, real-time, locomotion, motion manifold, conditional transitioning, in-betweening, deep learning |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10215216 |
Archive Staff Only
 |
View Item |
