Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model
This addresses the challenge of precise text-driven human motion generation in computer vision, offering incremental improvements for applications like animation and virtual reality.
The paper tackled the problem of generating human motion sequences from text descriptions, which often results in deterministic or imprecise outputs, by proposing a fine-grained method that improves quality and alignment with text, achieving better performance on HumanML3D and KIT test sets.
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.