Improving Masked Style Transfer using Blended Partial Convolution
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918118517899264 |
|---|---|
| author | Seyed, Seyed Hadi Cansever, Ayberk Hart, David |
| author_facet | Seyed, Seyed Hadi Cansever, Ayberk Hart, David |
| contents | Artistic style transfer has long been possible with the advancements of convolution- and transformer-based neural networks. Most algorithms apply the artistic style transfer to the whole image, but individual users may only need to apply a style transfer to a specific region in the image. The standard practice is to simply mask the image after the stylization. This work shows that this approach tends to improperly capture the style features in the region of interest. We propose a partial-convolution-based style transfer network that accurately applies the style features exclusively to the region of interest. Additionally, we present network-internal blending techniques that account for imperfections in the region selection. We show that this visually and quantitatively improves stylization using examples from the SA-1B dataset. Code is publicly available at https://github.com/davidmhart/StyleTransferMasked. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_05769 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving Masked Style Transfer using Blended Partial Convolution Seyed, Seyed Hadi Cansever, Ayberk Hart, David Computer Vision and Pattern Recognition Artistic style transfer has long been possible with the advancements of convolution- and transformer-based neural networks. Most algorithms apply the artistic style transfer to the whole image, but individual users may only need to apply a style transfer to a specific region in the image. The standard practice is to simply mask the image after the stylization. This work shows that this approach tends to improperly capture the style features in the region of interest. We propose a partial-convolution-based style transfer network that accurately applies the style features exclusively to the region of interest. Additionally, we present network-internal blending techniques that account for imperfections in the region selection. We show that this visually and quantitatively improves stylization using examples from the SA-1B dataset. Code is publicly available at https://github.com/davidmhart/StyleTransferMasked. |
| title | Improving Masked Style Transfer using Blended Partial Convolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.05769 |