Fashionability-Enhancing Outfit Image Editing with Conditional Diffusion Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909440313131008 |
|---|---|
| author | Qin, Qice Hirakawa, Yuki Shimizu, Ryotaro Furusawa, Takuya Simo-Serra, Edgar |
| author_facet | Qin, Qice Hirakawa, Yuki Shimizu, Ryotaro Furusawa, Takuya Simo-Serra, Edgar |
| contents | Image generation in the fashion domain has predominantly focused on preserving body characteristics or following input prompts, but little attention has been paid to improving the inherent fashionability of the output images. This paper presents a novel diffusion model-based approach that generates fashion images with improved fashionability while maintaining control over key attributes. Key components of our method include: 1) fashionability enhancement, which ensures that the generated images are more fashionable than the input; 2) preservation of body characteristics, encouraging the generated images to maintain the original shape and proportions of the input; and 3) automatic fashion optimization, which does not rely on manual input or external prompts. We also employ two methods to collect training data for guidance while generating and evaluating the images. In particular, we rate outfit images using fashionability scores annotated by multiple fashion experts through OpenSkill-based and five critical aspect-based pairwise comparisons. These methods provide complementary perspectives for assessing and improving the fashionability of the generated images. The experimental results show that our approach outperforms the baseline Fashion++ in generating images with superior fashionability, demonstrating its effectiveness in producing more stylish and appealing fashion images. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_18421 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fashionability-Enhancing Outfit Image Editing with Conditional Diffusion Models Qin, Qice Hirakawa, Yuki Shimizu, Ryotaro Furusawa, Takuya Simo-Serra, Edgar Computer Vision and Pattern Recognition Image generation in the fashion domain has predominantly focused on preserving body characteristics or following input prompts, but little attention has been paid to improving the inherent fashionability of the output images. This paper presents a novel diffusion model-based approach that generates fashion images with improved fashionability while maintaining control over key attributes. Key components of our method include: 1) fashionability enhancement, which ensures that the generated images are more fashionable than the input; 2) preservation of body characteristics, encouraging the generated images to maintain the original shape and proportions of the input; and 3) automatic fashion optimization, which does not rely on manual input or external prompts. We also employ two methods to collect training data for guidance while generating and evaluating the images. In particular, we rate outfit images using fashionability scores annotated by multiple fashion experts through OpenSkill-based and five critical aspect-based pairwise comparisons. These methods provide complementary perspectives for assessing and improving the fashionability of the generated images. The experimental results show that our approach outperforms the baseline Fashion++ in generating images with superior fashionability, demonstrating its effectiveness in producing more stylish and appealing fashion images. |
| title | Fashionability-Enhancing Outfit Image Editing with Conditional Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.18421 |