Transformer-based Neuro-Animator for Qualitative Simulation of Soft Body Movement

TL;DR

This paper introduces a transformer-based neuro-animator model that qualitatively simulates soft body movements, like flag waving, by learning from previous motion data, inspired by human intuitive physics prediction.

Contribution

It demonstrates the application of transformer architectures for qualitative physical simulation of soft bodies, capturing temporal dynamics without explicit physics modeling.

Findings

Successfully predicts flag motion at next time step

Learns effective temporal embeddings of motion data

Produces realistic flag waving simulations under various conditions

Abstract

The human mind effortlessly simulates the movements of objects governed by the laws of physics, such as a fluttering, or a waving flag under wind force, without understanding the underlying physics. This suggests that human cognition can predict the unfolding of physical events using an intuitive prediction process. This process might result from memory recall, yielding a qualitatively believable mental image, though it may not be exactly according to real-world physics. Drawing inspiration from the intriguing human ability to qualitatively visualize and describe dynamic events from past experiences without explicitly engaging in mathematical computations, this paper investigates the application of recent transformer architectures as a neuro-animator model. The visual transformer model is trained to predict flag motions at the \emph{t+1} time step, given information of previous motions from \emph{t-n} $\cdots$ \emph{t} time steps. The results show that the visual transformer-based architecture successfully learns temporal embedding of flag motions and produces reasonable quality simulations of flag waving under different wind forces.