Towards automatic drawing animation using physics-based evolution

Abstract

We demonstrate a system to automatically animate hand-drawn characters. Starting with skeleton extraction, meshing and vertex skinning, our system simulates characters using a neural network in a physics-based environment. Using an evolutionary algorithm, it searches for networks that move characters far while keeping a good posture. We validated the system through a user study with 26 participants. For most drawings (60 %), they felt satisfied with the generated animation, and in 76% of cases, they wished to draw and animate additional characters. The participants reported mostly positive emotions after seeing the animations. Only a minority had feelings of strangeness or had negative emotions. This work demonstrates the possibility of creating an automated 2-D character animation system making little assumption on what is drawn. We believe that this work can enable more children to engage in creative play and explore their imagination.