GenMotion: Data-driven Motion Generators for Real-time Animation Synthesis

TL;DR

GenMotion is a comprehensive library that enables training, benchmarking, and real-time animation synthesis of deep learning-based human motion models, bridging research and practical animation applications.

Contribution

It introduces a unified platform for data handling, model training, and real-time animation synthesis, facilitating research and industry use of deep motion generation methods.

Findings

Provides a versatile toolkit for skeleton-based human motion synthesis.

Enables real-time 3D character animation with deep learning models.

Supports benchmarking and comparison of different algorithms.

Abstract

With the recent success of deep learning algorithms, many researchers have focused on generative models for human motion animation. However, the research community lacks a platform for training and benchmarking various algorithms, and the animation industry needs a toolkit for implementing advanced motion synthesizing techniques. To facilitate the study of deep motion synthesis methods for skeleton-based human animation and their potential applications in practical animation making, we introduce \genmotion: a library that provides unified pipelines for data loading, model training, and animation sampling with various deep learning algorithms. Besides, by combining Python coding in the animation software \genmotion\ can assist animators in creating real-time 3D character animation. Source code is available at https://github.com/realvcla/GenMotion/.