ParTY: Part-Guidance for Expressive Text-to-Motion Synthesis

TL;DR

ParTY introduces a novel framework for expressive text-to-motion synthesis that explicitly aligns textual semantics with body parts and generates coherent full-body motions, improving over prior methods.

Contribution

The paper proposes ParTY, a new method combining part-guided generation, text grounding, and holistic-part fusion to enhance expressiveness and coherence in text-to-motion synthesis.

Findings

Significant improvement in motion realism and expressiveness.

Better alignment of text semantics with individual body parts.

Enhanced coherence in full-body motion generation.

Abstract

Text-to-motion synthesis aims to generate natural and expressive human motions from textual descriptions. While existing approaches primarily focus on generating holistic motions from text descriptions, they struggle to accurately reflect actions involving specific body parts. Recent part-wise motion generation methods attempt to resolve this but face two critical limitations: (i) they lack explicit mechanisms for aligning textual semantics with individual body parts, and (ii) they often generate incoherent full-body motions due to integrating independently generated part motions. To overcome these issues and resolve the fundamental trade-off in existing methods, we propose ParTY, a novel framework that enhances part expressiveness while generating coherent full-body motions. ParTY comprises: (1) Part-Guided Network, which first generates part motions to obtain part guidance, then uses it to generate holistic motions; (2) Part-aware Text Grounding, which diversely transforms text embeddings and appropriately aligns them with each body part; and (3) Holistic-Part Fusion, which adaptively fuses holistic motions and part motions. Extensive experiments, including part-level and coherence-level evaluations, demonstrate that ParTY achieves substantial improvements over previous methods.