Abstract
Synthesizing multi‐character interactions is a challenging task due to the complex and varied interactions between the characters. In particular, precise spatiotemporal alignment between characters is required in generating close interactions such as dancing and fighting. Existing work in generating multi‐character interactions focuses on generating a single type of reactive motion for a given sequence which results in a lack of variety of the resultant motions. In this paper, we propose a novel way to create realistic human reactive motions which are not presented in the given dataset by mixing and matching different types of close interactions. We propose a Conditional Hierarchical Generative Adversarial Network with Multi‐Hot Class Embedding to generate the Mix and Match reactive motions of the follower from a given motion sequence of the leader. Experiments are conducted on both noisy (depth‐based) and high‐quality (MoCap‐based) interaction datasets. The quantitative and qualitative results show that our approach outperforms the state‐of‐the‐art methods on the given datasets. We also provide an augmented dataset with realistic reactive motions to stimulate future research in this area.
Original language | English |
---|---|
Pages (from-to) | 327-338 |
Number of pages | 12 |
Journal | Computer Graphics Forum |
Volume | 41 |
Issue number | 8 |
DOIs | |
Publication status | Published - 1 Dec 2022 |
Event | ACM SIGGRAPH / Eurographics Symposium on Computer Animation 2022 - Durham University, Durham, United Kingdom Duration: 13 Sept 2022 → 15 Sept 2022 https://computeranimation.org/2022/#:~:text=This%20year%2C%20the%2021st%20annual,on%2013th%2D15th%2C%20September. |
Keywords
- Learning
- CCS Concepts
- • Computing methodologies → Motion capture
- Machine learning
- Motion processing
- Animation