Learning Virtual Chimeras by Dynamic Motion Reassembly

Seoul National University
Responsive image

Physically based movement of various chimeras.


Abstract

The Chimera is a mythological hybrid creature composed of different animal parts. The chimera’s movements are highly dependent on the spatial and temporal alignments of its composing parts. In this paper, we present a novel algorithm that creates and animates chimeras by dynamically reassembling source characters and their movements. Our algorithm exploits a two-network architecture: part assembler and dynamic controller. The part assembler is a supervised learning layer that searches for the spatial alignment among body parts, assuming that the temporal alignment is provided. The dynamic controller is a reinforcement learning layer that learns robust control policy for a wide variety of potential temporal alignments. These two layers are tightly intertwined and learned simultaneously. The chimera animation generated by our algorithm is energy efficient and expressive in terms of describing weight shifting, balancing, and full-body coordination. We demonstrate the versatility of our algorithm by generating the motor skills of a large variety of chimeras from limited source characters.

Publication

Seyoung Lee, Jiye Lee, and Jehee Lee. 2022.
Learning Virtual Chimeras by Dynamic Motion Reassembly
ACM Trans. Graph. 41, 6, 182. (SIGGRAPH Asia 2022)

Video


Code

Code will be available in GitHub soon

Bibtex

@article{Lee:2022:Chimera,
    author = {Lee, Seyoung and Lee, Jiye and Lee, Jehee},
    title = {Learning Virtual Chimeras by Dynamic Motion Reassembly},
    journal = {ACM Trans. Graph.},
    volume = {41},
    number = {6},
    year = {2022},
    articleno = {182},
}