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

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.

Citation

Wang, Y., Leng, Z., Li, F. W. B., Wu, S.-C., & Liang, X. (2023, October). Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model. Presented at 2023 IEEE/CVF International Conference on Computer Vision (ICCV), Paris

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
• Start Date: Oct 2, 2023
• End Date: Oct 6, 2023
• Acceptance Date: Aug 11, 2023
• Online Publication Date: Jan 15, 2024
• Publication Date: 2023
• Deposit Date: Sep 12, 2023
• Publicly Available Date: Dec 31, 2023
• Publisher: Institute of Electrical and Electronics Engineers
• Series ISSN: 1550-5499
• Book Title: 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
• ISBN: 9798350307191
• DOI: https://doi.org/10.1109/ICCV51070.2023.02014
• Public URL: https://durham-repository.worktribe.com/output/1735623