Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909484091179008 |
|---|---|
| author | Wang, Yin Li, Mu Liu, Jiapeng Leng, Zhiying Li, Frederick W. B. Zhang, Ziyao Liang, Xiaohui |
| author_facet | Wang, Yin Li, Mu Liu, Jiapeng Leng, Zhiying Li, Frederick W. B. Zhang, Ziyao Liang, Xiaohui |
| contents | We address the challenging problem of fine-grained text-driven human motion generation. Existing works generate imprecise motions that fail to accurately capture relationships specified in text due to: (1) lack of effective text parsing for detailed semantic cues regarding body parts, (2) not fully modeling linguistic structures between words to comprehend text comprehensively. To tackle these limitations, we propose a novel fine-grained framework Fg-T2M++ that consists of: (1) an LLMs semantic parsing module to extract body part descriptions and semantics from text, (2) a hyperbolic text representation module to encode relational information between text units by embedding the syntactic dependency graph into hyperbolic space, and (3) a multi-modal fusion module to hierarchically fuse text and motion features. Extensive experiments on HumanML3D and KIT-ML datasets demonstrate that Fg-T2M++ outperforms SOTA methods, validating its ability to accurately generate motions adhering to comprehensive text semantics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_05534 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation Wang, Yin Li, Mu Liu, Jiapeng Leng, Zhiying Li, Frederick W. B. Zhang, Ziyao Liang, Xiaohui Computer Vision and Pattern Recognition We address the challenging problem of fine-grained text-driven human motion generation. Existing works generate imprecise motions that fail to accurately capture relationships specified in text due to: (1) lack of effective text parsing for detailed semantic cues regarding body parts, (2) not fully modeling linguistic structures between words to comprehend text comprehensively. To tackle these limitations, we propose a novel fine-grained framework Fg-T2M++ that consists of: (1) an LLMs semantic parsing module to extract body part descriptions and semantics from text, (2) a hyperbolic text representation module to encode relational information between text units by embedding the syntactic dependency graph into hyperbolic space, and (3) a multi-modal fusion module to hierarchically fuse text and motion features. Extensive experiments on HumanML3D and KIT-ML datasets demonstrate that Fg-T2M++ outperforms SOTA methods, validating its ability to accurately generate motions adhering to comprehensive text semantics. |
| title | Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.05534 |