ShapeWords: Guiding Text-to-Image Synthesis with 3D Shape-Aware Prompts
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915667002785792 |
|---|---|
| author | Petrov, Dmitry Goyal, Pradyumn Shivashok, Divyansh Tao, Yuanming Averkiou, Melinos Kalogerakis, Evangelos |
| author_facet | Petrov, Dmitry Goyal, Pradyumn Shivashok, Divyansh Tao, Yuanming Averkiou, Melinos Kalogerakis, Evangelos |
| contents | We introduce ShapeWords, an approach for synthesizing images based on 3D shape guidance and text prompts. ShapeWords incorporates target 3D shape information within specialized tokens embedded together with the input text, effectively blending 3D shape awareness with textual context to guide the image synthesis process. Unlike conventional shape guidance methods that rely on depth maps restricted to fixed viewpoints and often overlook full 3D structure or textual context, ShapeWords generates diverse yet consistent images that reflect both the target shape's geometry and the textual description. Experimental results show that ShapeWords produces images that are more text-compliant, aesthetically plausible, while also maintaining 3D shape awareness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_02912 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ShapeWords: Guiding Text-to-Image Synthesis with 3D Shape-Aware Prompts Petrov, Dmitry Goyal, Pradyumn Shivashok, Divyansh Tao, Yuanming Averkiou, Melinos Kalogerakis, Evangelos Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning We introduce ShapeWords, an approach for synthesizing images based on 3D shape guidance and text prompts. ShapeWords incorporates target 3D shape information within specialized tokens embedded together with the input text, effectively blending 3D shape awareness with textual context to guide the image synthesis process. Unlike conventional shape guidance methods that rely on depth maps restricted to fixed viewpoints and often overlook full 3D structure or textual context, ShapeWords generates diverse yet consistent images that reflect both the target shape's geometry and the textual description. Experimental results show that ShapeWords produces images that are more text-compliant, aesthetically plausible, while also maintaining 3D shape awareness. |
| title | ShapeWords: Guiding Text-to-Image Synthesis with 3D Shape-Aware Prompts |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning |
| url | https://arxiv.org/abs/2412.02912 |