T3M: Text Guided 3D Human Motion Synthesis from Speech

TL;DR

T3M introduces a text-guided approach for 3D human motion synthesis from speech, enabling more accurate, diverse, and customizable animations compared to speech-only methods.

Contribution

The paper proposes T3M, a novel method that incorporates textual input to control 3D human motion synthesis, improving flexibility and performance over existing speech-driven approaches.

Findings

T3M outperforms state-of-the-art methods in quantitative metrics.

T3M provides more diverse and user-controlled motion synthesis.

The approach is validated through qualitative evaluations.

Abstract

Speech-driven 3D motion synthesis seeks to create lifelike animations based on human speech, with potential uses in virtual reality, gaming, and the film production. Existing approaches reply solely on speech audio for motion generation, leading to inaccurate and inflexible synthesis results. To mitigate this problem, we introduce a novel text-guided 3D human motion synthesis method, termed \textit{T3M}. Unlike traditional approaches, T3M allows precise control over motion synthesis via textual input, enhancing the degree of diversity and user customization. The experiment results demonstrate that T3M can greatly outperform the state-of-the-art methods in both quantitative metrics and qualitative evaluations. We have publicly released our code at \href{https://github.com/Gloria2tt/T3M.git}{https://github.com/Gloria2tt/T3M.git}