Text-driven Motion Generation: Overview, Challenges and Directions

TL;DR

This paper provides a comprehensive survey of text-driven human motion generation, discussing current methods, datasets, challenges, and future directions in the field.

Contribution

It offers a structured overview of modern approaches, categorizing them by architecture and motion representation, and highlights key challenges and promising research directions.

Findings

Survey of VAE, diffusion, and hybrid models for text-to-motion

Analysis of discrete vs. continuous motion generation strategies

Overview of datasets, evaluation methods, and benchmarks

Abstract

Text-driven motion generation offers a powerful and intuitive way to create human movements directly from natural language. By removing the need for predefined motion inputs, it provides a flexible and accessible approach to controlling animated characters. This makes it especially useful in areas like virtual reality, gaming, human-computer interaction, and robotics. In this review, we first revisit the traditional perspective on motion synthesis, where models focused on predicting future poses from observed initial sequences, often conditioned on action labels. We then provide a comprehensive and structured survey of modern text-to-motion generation approaches, categorizing them from two complementary perspectives: (i) architectural, dividing methods into VAE-based, diffusion-based, and hybrid models; and (ii) motion representation, distinguishing between discrete and continuous motion generation strategies. In addition, we explore the most widely used datasets, evaluation methods, and recent benchmarks that have shaped progress in this area. With this survey, we aim to capture where the field currently stands, bring attention to its key challenges and limitations, and highlight promising directions for future exploration. We hope this work offers a valuable starting point for researchers and practitioners working to push the boundaries of language-driven human motion synthesis.