GANimator: Neural Motion Synthesis from a Single Sequence
This addresses the challenge of motion synthesis for various skeletal structures (e.g., bipeds, quadrupeds) with minimal training data, though it is incremental as it builds on existing generative adversarial network techniques.
The authors tackled the problem of motion synthesis from limited data by developing GANimator, a generative model that synthesizes novel and diverse motions from a single short sequence, enabling applications like crowd simulation and style transfer without requiring large datasets.
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.