Imperceptible Protection against Style Imitation from 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_ | 1866918323162185728 |
|---|---|
| author | Ahn, Namhyuk Ahn, Wonhyuk Yoo, KiYoon Kim, Daesik Nam, Seung-Hun |
| author_facet | Ahn, Namhyuk Ahn, Wonhyuk Yoo, KiYoon Kim, Daesik Nam, Seung-Hun |
| contents | Recent progress in diffusion models has profoundly enhanced the fidelity of image generation, but it has raised concerns about copyright infringements. While prior methods have introduced adversarial perturbations to prevent style imitation, most are accompanied by the degradation of artworks' visual quality. Recognizing the importance of maintaining this, we introduce a visually improved protection method while preserving its protection capability. To this end, we devise a perceptual map to highlight areas sensitive to human eyes, guided by instance-aware refinement, which refines the protection intensity accordingly. We also introduce a difficulty-aware protection by predicting how difficult the artwork is to protect and dynamically adjusting the intensity based on this. Lastly, we integrate a perceptual constraints bank to further improve the imperceptibility. Results show that our method substantially elevates the quality of the protected image without compromising on protection efficacy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19254 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Imperceptible Protection against Style Imitation from Diffusion Models Ahn, Namhyuk Ahn, Wonhyuk Yoo, KiYoon Kim, Daesik Nam, Seung-Hun Computer Vision and Pattern Recognition Recent progress in diffusion models has profoundly enhanced the fidelity of image generation, but it has raised concerns about copyright infringements. While prior methods have introduced adversarial perturbations to prevent style imitation, most are accompanied by the degradation of artworks' visual quality. Recognizing the importance of maintaining this, we introduce a visually improved protection method while preserving its protection capability. To this end, we devise a perceptual map to highlight areas sensitive to human eyes, guided by instance-aware refinement, which refines the protection intensity accordingly. We also introduce a difficulty-aware protection by predicting how difficult the artwork is to protect and dynamically adjusting the intensity based on this. Lastly, we integrate a perceptual constraints bank to further improve the imperceptibility. Results show that our method substantially elevates the quality of the protected image without compromising on protection efficacy. |
| title | Imperceptible Protection against Style Imitation from Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.19254 |