Real-time Diverse Motion In-betweening with Space-time Control

TL;DR

This paper introduces a data-driven framework for generating diverse, controllable in-between motions for characters, allowing users to specify detailed spatial and temporal conditions for high-quality animation synthesis.

Contribution

It presents a novel approach that integrates dynamic conditions and explicit controls into motion in-betweening, enabling finer-grained, versatile motion generation.

Findings

Supports both locomotion and unstructured motions

Enables user-specified control over motion parameters

Produces high-quality, diverse animation results

Abstract

In this work, we present a data-driven framework for generating diverse in-betweening motions for kinematic characters. Our approach injects dynamic conditions and explicit motion controls into the procedure of motion transitions. Notably, this integration enables a finer-grained spatial-temporal control by allowing users to impart additional conditions, such as duration, path, style, etc., into the in-betweening process. We demonstrate that our in-betweening approach can synthesize both locomotion and unstructured motions, enabling rich, versatile, and high-quality animation generation.