D2Styler: Advancing Arbitrary Style Transfer with Discrete Diffusion Methods
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909280903364608 |
|---|---|
| author | Susladkar, Onkar Deshmukh, Gayatri Mittal, Sparsh Shastri, Parth |
| author_facet | Susladkar, Onkar Deshmukh, Gayatri Mittal, Sparsh Shastri, Parth |
| contents | In image processing, one of the most challenging tasks is to render an image's semantic meaning using a variety of artistic approaches. Existing techniques for arbitrary style transfer (AST) frequently experience mode-collapse, over-stylization, or under-stylization due to a disparity between the style and content images. We propose a novel framework called D$^2$Styler (Discrete Diffusion Styler) that leverages the discrete representational capability of VQ-GANs and the advantages of discrete diffusion, including stable training and avoidance of mode collapse. Our method uses Adaptive Instance Normalization (AdaIN) features as a context guide for the reverse diffusion process. This makes it easy to move features from the style image to the content image without bias. The proposed method substantially enhances the visual quality of style-transferred images, allowing the combination of content and style in a visually appealing manner. We take style images from the WikiArt dataset and content images from the COCO dataset. Experimental results demonstrate that D$^2$Styler produces high-quality style-transferred images and outperforms twelve existing methods on nearly all the metrics. The qualitative results and ablation studies provide further insights into the efficacy of our technique. The code is available at https://github.com/Onkarsus13/D2Styler. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_03558 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | D2Styler: Advancing Arbitrary Style Transfer with Discrete Diffusion Methods Susladkar, Onkar Deshmukh, Gayatri Mittal, Sparsh Shastri, Parth Computer Vision and Pattern Recognition Artificial Intelligence In image processing, one of the most challenging tasks is to render an image's semantic meaning using a variety of artistic approaches. Existing techniques for arbitrary style transfer (AST) frequently experience mode-collapse, over-stylization, or under-stylization due to a disparity between the style and content images. We propose a novel framework called D$^2$Styler (Discrete Diffusion Styler) that leverages the discrete representational capability of VQ-GANs and the advantages of discrete diffusion, including stable training and avoidance of mode collapse. Our method uses Adaptive Instance Normalization (AdaIN) features as a context guide for the reverse diffusion process. This makes it easy to move features from the style image to the content image without bias. The proposed method substantially enhances the visual quality of style-transferred images, allowing the combination of content and style in a visually appealing manner. We take style images from the WikiArt dataset and content images from the COCO dataset. Experimental results demonstrate that D$^2$Styler produces high-quality style-transferred images and outperforms twelve existing methods on nearly all the metrics. The qualitative results and ablation studies provide further insights into the efficacy of our technique. The code is available at https://github.com/Onkarsus13/D2Styler. |
| title | D2Styler: Advancing Arbitrary Style Transfer with Discrete Diffusion Methods |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2408.03558 |