InsertDiffusion: Identity Preserving Visualization of Objects through a Training-Free Diffusion Architecture
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917722210697216 |
|---|---|
| author | Mueller, Phillip Wiese, Jannik Craciun, Ioan Mikelsons, Lars |
| author_facet | Mueller, Phillip Wiese, Jannik Craciun, Ioan Mikelsons, Lars |
| contents | Recent advancements in image synthesis are fueled by the advent of large-scale diffusion models. Yet, integrating realistic object visualizations seamlessly into new or existing backgrounds without extensive training remains a challenge. This paper introduces InsertDiffusion, a novel, training-free diffusion architecture that efficiently embeds objects into images while preserving their structural and identity characteristics. Our approach utilizes off-the-shelf generative models and eliminates the need for fine-tuning, making it ideal for rapid and adaptable visualizations in product design and marketing. We demonstrate superior performance over existing methods in terms of image realism and alignment with input conditions. By decomposing the generation task into independent steps, InsertDiffusion offers a scalable solution that extends the capabilities of diffusion models for practical applications, achieving high-quality visualizations that maintain the authenticity of the original objects. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_10592 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | InsertDiffusion: Identity Preserving Visualization of Objects through a Training-Free Diffusion Architecture Mueller, Phillip Wiese, Jannik Craciun, Ioan Mikelsons, Lars Computer Vision and Pattern Recognition Recent advancements in image synthesis are fueled by the advent of large-scale diffusion models. Yet, integrating realistic object visualizations seamlessly into new or existing backgrounds without extensive training remains a challenge. This paper introduces InsertDiffusion, a novel, training-free diffusion architecture that efficiently embeds objects into images while preserving their structural and identity characteristics. Our approach utilizes off-the-shelf generative models and eliminates the need for fine-tuning, making it ideal for rapid and adaptable visualizations in product design and marketing. We demonstrate superior performance over existing methods in terms of image realism and alignment with input conditions. By decomposing the generation task into independent steps, InsertDiffusion offers a scalable solution that extends the capabilities of diffusion models for practical applications, achieving high-quality visualizations that maintain the authenticity of the original objects. |
| title | InsertDiffusion: Identity Preserving Visualization of Objects through a Training-Free Diffusion Architecture |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.10592 |