Fast Terrain-Adaptive Motion Generation using Deep Neural Networks
- Authors
- Yu; M.; Kwon; B.; Kim; J.; Kang, Shinjin; S.; Jang; H.
- Issue Date
- 2019
- Publisher
- ASSOC COMPUTING MACHINERY
- Keywords
- Character Animation; Inverse Kinematics; Deep Neural Networks
- Citation
- SIGGRAPH Asia 2019 Technical Briefs, SA 2019, pp.57 - 60
- Journal Title
- SIGGRAPH Asia 2019 Technical Briefs, SA 2019
- Start Page
- 57
- End Page
- 60
- URI
- https://scholarworks.bwise.kr/hongik/handle/2020.sw.hongik/12826
- DOI
- 10.1145/3355088.3365157
- ISSN
- 0000-0000
- Abstract
- We propose a fast motion adaptation framework using deep neural networks. Traditionally, motion adaptation is performed via iterative numerical optimization. We adopted deep neural networks and replaced the iterative process with the feed-forward inference consisting of simple matrix multiplications. For efficient mapping from contact constraints to character motion, the proposed system is composed of two types of networks: trajectory and pose generators. The networks are trained using augmented motion capture data and are fine-tuned using the inverse kinematics loss. In experiments, our system successfully generates multi-contact motions of a hundred of characters in real-time, and the result motions contain the naturalness existing in the motion capture data.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - School of Games > Game Software Major > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.