Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model

TL;DR

This paper introduces Fg-T2M, a novel diffusion-based method for fine-grained, text-driven human motion generation that achieves high accuracy and control over motion sequences by leveraging linguistic structures and progressive reasoning.

Contribution

The paper presents a new approach combining linguistics-structure assistance and context-aware reasoning for precise text-driven human motion generation, outperforming existing methods.

Findings

Outperforms previous methods on HumanML3D and KIT datasets.

Generates motion sequences that better match detailed text descriptions.

Achieves higher visual and semantic consistency in generated motions.

Abstract

Text-driven human motion generation in computer vision is both significant and challenging. However, current methods are limited to producing either deterministic or imprecise motion sequences, failing to effectively control the temporal and spatial relationships required to conform to a given text description. In this work, we propose a fine-grained method for generating high-quality, conditional human motion sequences supporting precise text description. Our approach consists of two key components: 1) a linguistics-structure assisted module that constructs accurate and complete language feature to fully utilize text information; and 2) a context-aware progressive reasoning module that learns neighborhood and overall semantic linguistics features from shallow and deep graph neural networks to achieve a multi-step inference. Experiments show that our approach outperforms text-driven motion generation methods on HumanML3D and KIT test sets and generates better visually confirmed motion to the text conditions.