One-Shot Structure-Aware Stylized Image Synthesis
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929299913703424 |
|---|---|
| author | Cho, Hansam Lee, Jonghyun Chang, Seunggyu Jeong, Yonghyun |
| author_facet | Cho, Hansam Lee, Jonghyun Chang, Seunggyu Jeong, Yonghyun |
| contents | While GAN-based models have been successful in image stylization tasks, they often struggle with structure preservation while stylizing a wide range of input images. Recently, diffusion models have been adopted for image stylization but still lack the capability to maintain the original quality of input images. Building on this, we propose OSASIS: a novel one-shot stylization method that is robust in structure preservation. We show that OSASIS is able to effectively disentangle the semantics from the structure of an image, allowing it to control the level of content and style implemented to a given input. We apply OSASIS to various experimental settings, including stylization with out-of-domain reference images and stylization with text-driven manipulation. Results show that OSASIS outperforms other stylization methods, especially for input images that were rarely encountered during training, providing a promising solution to stylization via diffusion models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_17275 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | One-Shot Structure-Aware Stylized Image Synthesis Cho, Hansam Lee, Jonghyun Chang, Seunggyu Jeong, Yonghyun Computer Vision and Pattern Recognition While GAN-based models have been successful in image stylization tasks, they often struggle with structure preservation while stylizing a wide range of input images. Recently, diffusion models have been adopted for image stylization but still lack the capability to maintain the original quality of input images. Building on this, we propose OSASIS: a novel one-shot stylization method that is robust in structure preservation. We show that OSASIS is able to effectively disentangle the semantics from the structure of an image, allowing it to control the level of content and style implemented to a given input. We apply OSASIS to various experimental settings, including stylization with out-of-domain reference images and stylization with text-driven manipulation. Results show that OSASIS outperforms other stylization methods, especially for input images that were rarely encountered during training, providing a promising solution to stylization via diffusion models. |
| title | One-Shot Structure-Aware Stylized Image Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.17275 |