Diffusion Prism: Enhancing Diversity and Morphology Consistency in Mask-to-Image Diffusion
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917889404043264 |
|---|---|
| author | Wang, Hao Chen, Xiwen Bastola, Ashish Qin, Jiayou Razi, Abolfazl |
| author_facet | Wang, Hao Chen, Xiwen Bastola, Ashish Qin, Jiayou Razi, Abolfazl |
| contents | The emergence of generative AI and controllable diffusion has made image-to-image synthesis increasingly practical and efficient. However, when input images exhibit low entropy and sparse, the inherent characteristics of diffusion models often result in limited diversity. This constraint significantly interferes with data augmentation. To address this, we propose Diffusion Prism, a training-free framework that efficiently transforms binary masks into realistic and diverse samples while preserving morphological features. We explored that a small amount of artificial noise will significantly assist the image-denoising process. To prove this novel mask-to-image concept, we use nano-dendritic patterns as an example to demonstrate the merit of our method compared to existing controllable diffusion models. Furthermore, we extend the proposed framework to other biological patterns, highlighting its potential applications across various fields. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_00944 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Diffusion Prism: Enhancing Diversity and Morphology Consistency in Mask-to-Image Diffusion Wang, Hao Chen, Xiwen Bastola, Ashish Qin, Jiayou Razi, Abolfazl Computer Vision and Pattern Recognition Image and Video Processing The emergence of generative AI and controllable diffusion has made image-to-image synthesis increasingly practical and efficient. However, when input images exhibit low entropy and sparse, the inherent characteristics of diffusion models often result in limited diversity. This constraint significantly interferes with data augmentation. To address this, we propose Diffusion Prism, a training-free framework that efficiently transforms binary masks into realistic and diverse samples while preserving morphological features. We explored that a small amount of artificial noise will significantly assist the image-denoising process. To prove this novel mask-to-image concept, we use nano-dendritic patterns as an example to demonstrate the merit of our method compared to existing controllable diffusion models. Furthermore, we extend the proposed framework to other biological patterns, highlighting its potential applications across various fields. |
| title | Diffusion Prism: Enhancing Diversity and Morphology Consistency in Mask-to-Image Diffusion |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2501.00944 |