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

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

12 Sep 2023ICCV 2023 1arXiv:2309.06284archive 2025-07-28

Yin Wang, Zhiying Leng, Frederick W. B. Li, 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.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Motion GenerationMotion Synthesis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Motion Synthesis HumanML3D Fg-T2M Diversity 9.278 #25 of 37 Archive leaderboard report
Motion Synthesis HumanML3D Fg-T2M FID 0.243 #25 of 37 Archive leaderboard report
Motion Synthesis HumanML3D Fg-T2M Multimodality 1.614 #25 of 37 Archive leaderboard report
Motion Synthesis HumanML3D Fg-T2M R Precision Top3 0.783 #25 of 37 Archive leaderboard report
Motion Synthesis KIT Motion-Language Fg-T2M Diversity 10.93 #22 of 31 Archive leaderboard report
Motion Synthesis KIT Motion-Language Fg-T2M FID 0.571 #22 of 31 Archive leaderboard report
Motion Synthesis KIT Motion-Language Fg-T2M Multimodality 1.019 #22 of 31 Archive leaderboard report
Motion Synthesis KIT Motion-Language Fg-T2M R Precision Top3 0.745 #22 of 31 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections