GANimator: Neural Motion Synthesis from a Single Sequence

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.

arXiv commentSIGGRAPH 2022. Project page: https://peizhuoli.github.io/ganimator/ , Video: https://www.youtube.com/watch?v=OV9VoHMEeyI

References in corpus (7)

• DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
• Robust Motion In-betweening
• Skeleton-Aware Networks for Deep Motion Retargeting
• Unpaired Motion Style Transfer from Video to Animation
• MoGlow: Probabilistic and controllable motion synthesis using normalising flows
• Learning Character-Agnostic Motion for Motion Retargeting in 2D
• CARL: Controllable Agent with Reinforcement Learning for Quadruped Locomotion

Cited by in corpus (11)

• ControlVAE: Model-Based Learning of Generative Controllers for Physics-Based Characters
• Learning to Generate 3D Shapes from a Single Example
• MOVIN: Real-time Motion Capture using a Single LiDAR
• A Two-part Transformer Network for Controllable Motion Synthesis
• Matting by Generation
• Progressive Human Motion Generation Based on Text and Few Motion Frames
• ELMO: Enhanced Real-time LiDAR Motion Capture through Upsampling
• Motion Keyframe Interpolation for Any Human Skeleton via Temporally Consistent Point Cloud Sampling and Reconstruction
• MAMM: Motion Control via Metric-Aligning Motion Matching
• Real-time Diverse Motion In-betweening with Space-time Control
• Multi-Resolution Generative Modeling of Human Motion from Limited Data