Skip to main content

Research Repository

Advanced Search

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

Wang, Yin; Leng, Zhiying; Li, Frederick W. B.; Wu, Shun-Cheng; Liang, Xiaohui


Yin Wang

Zhiying Leng

Shun-Cheng Wu

Xiaohui Liang


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.


Wang, Y., Leng, Z., Li, F. W. B., Wu, S., & Liang, X. (in press). Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model.

Conference Name The International Conference on Computer Vision (ICCV) 2023
Conference Location Paris
Start Date Oct 2, 2023
End Date Oct 6, 2023
Acceptance Date Aug 11, 2023
Deposit Date Sep 12, 2023
Publicly Available Date Sep 30, 2023
Publisher Institute of Electrical and Electronics Engineers
Public URL
Publisher URL