Journal
ACM TRANSACTIONS ON GRAPHICS
Volume 37, Issue 6, Pages -Publisher
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3272127.3275071
Keywords
Character animation; interactive motion control; motion grammar; deep learning; recurrent neural network; multi-objective control
Categories
Funding
- MSIP(Ministry of Science, ICT and Future Planning), Korea under the SW STARLab support program [IITP-2017-0536-20170040]
- National Research Foundation of Korea [21A20151113068] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
Ask authors/readers for more resources
We present an approach that learns to act from raw motion data for interactive character animation. Our motion generator takes a continuous stream of control inputs and generates the character's motion in an online manner. The key insight is modeling rich connections between a multitude of control objectives and a large repertoire of actions. The model is trained using Recurrent Neural Network conditioned to deal with spatiotemporal constraints and structural variabilities in human motion. We also present a new data augmentation method that allows the model to be learned even from a small to moderate amount of training data. The learning process is fully automatic if it learns the motion of a single character, and requires minimal user intervention if it deals with props and interaction between multiple characters.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available