GANimator: Neural Motion Synthesis from a Single Sequence

TL;DR

GANimator is a novel neural motion synthesis model that creates diverse, realistic motions from a single input sequence, enabling applications like crowd simulation and style transfer without large datasets.

Contribution

It introduces a single-sequence training framework with hierarchical neural networks for versatile motion synthesis across various skeletal structures.

Findings

Successfully synthesizes diverse motions from one sequence

Works across different skeletal structures like bipeds and quadrupeds

Enables applications such as crowd simulation and style transfer

Abstract

We present GANimator, a generative model that learns to synthesize novel motions from a single, short motion sequence. GANimator generates motions that resemble the core elements of the original motion, while simultaneously synthesizing novel and diverse movements. Existing data-driven techniques for motion synthesis require a large motion dataset which contains the desired and specific skeletal structure. By contrast, GANimator only requires training on a single motion sequence, enabling novel motion synthesis for a variety of skeletal structures e.g., bipeds, quadropeds, hexapeds, and more. Our framework contains a series of generative and adversarial neural networks, each responsible for generating motions in a specific frame rate. The framework progressively learns to synthesize motion from random noise, enabling hierarchical control over the generated motion content across varying levels of detail. We show a number of applications, including crowd simulation, key-frame editing, style transfer, and interactive control, which all learn from a single input sequence. Code and data for this paper are at https://peizhuoli.github.io/ganimator.