CASIM: Composite Aware Semantic Injection for Text to 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_ | 1866913677850968064 |
|---|---|
| author | Chang, Che-Jui Liu, Qingze Tony Zhou, Honglu Pavlovic, Vladimir Kapadia, Mubbasir |
| author_facet | Chang, Che-Jui Liu, Qingze Tony Zhou, Honglu Pavlovic, Vladimir Kapadia, Mubbasir |
| contents | Recent advances in generative modeling and tokenization have driven significant progress in text-to-motion generation, leading to enhanced quality and realism in generated motions. However, effectively leveraging textual information for conditional motion generation remains an open challenge. We observe that current approaches, primarily relying on fixed-length text embeddings (e.g., CLIP) for global semantic injection, struggle to capture the composite nature of human motion, resulting in suboptimal motion quality and controllability. To address this limitation, we propose the Composite Aware Semantic Injection Mechanism (CASIM), comprising a composite-aware semantic encoder and a text-motion aligner that learns the dynamic correspondence between text and motion tokens. Notably, CASIM is model and representation-agnostic, readily integrating with both autoregressive and diffusion-based methods. Experiments on HumanML3D and KIT benchmarks demonstrate that CASIM consistently improves motion quality, text-motion alignment, and retrieval scores across state-of-the-art methods. Qualitative analyses further highlight the superiority of our composite-aware approach over fixed-length semantic injection, enabling precise motion control from text prompts and stronger generalization to unseen text inputs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_02063 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CASIM: Composite Aware Semantic Injection for Text to Motion Generation Chang, Che-Jui Liu, Qingze Tony Zhou, Honglu Pavlovic, Vladimir Kapadia, Mubbasir Computer Vision and Pattern Recognition Artificial Intelligence Graphics Recent advances in generative modeling and tokenization have driven significant progress in text-to-motion generation, leading to enhanced quality and realism in generated motions. However, effectively leveraging textual information for conditional motion generation remains an open challenge. We observe that current approaches, primarily relying on fixed-length text embeddings (e.g., CLIP) for global semantic injection, struggle to capture the composite nature of human motion, resulting in suboptimal motion quality and controllability. To address this limitation, we propose the Composite Aware Semantic Injection Mechanism (CASIM), comprising a composite-aware semantic encoder and a text-motion aligner that learns the dynamic correspondence between text and motion tokens. Notably, CASIM is model and representation-agnostic, readily integrating with both autoregressive and diffusion-based methods. Experiments on HumanML3D and KIT benchmarks demonstrate that CASIM consistently improves motion quality, text-motion alignment, and retrieval scores across state-of-the-art methods. Qualitative analyses further highlight the superiority of our composite-aware approach over fixed-length semantic injection, enabling precise motion control from text prompts and stronger generalization to unseen text inputs. |
| title | CASIM: Composite Aware Semantic Injection for Text to Motion Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics |
| url | https://arxiv.org/abs/2502.02063 |