GRLGSep 30, 2024

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

arXiv:2410.00270v14 citationsh-index: 10
Originality Incremental advance
AI Analysis

This work addresses the need for more controlled and diverse motion generation in animation, though it appears incremental by building on existing data-driven methods with added user controls.

The paper tackles the problem of generating diverse in-betweening motions for kinematic characters by introducing a data-driven framework that integrates dynamic conditions and explicit spatial-temporal controls, such as duration and path, resulting in versatile and high-quality animations for both locomotion and unstructured motions.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes