Label-guided Facial Retouching Reversion
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908413888299008 |
|---|---|
| author | Zhao, Guanhua Gu, Yu Sheng, Xuhan Hu, Yujie Zhang, Jian |
| author_facet | Zhao, Guanhua Gu, Yu Sheng, Xuhan Hu, Yujie Zhang, Jian |
| contents | With the popularity of social media platforms and retouching tools, more people are beautifying their facial photos, posing challenges for fields requiring photo authenticity. To address this issue, some work has proposed makeup removal methods, but they cannot revert images involving geometric deformations caused by retouching. To tackle the problem of facial retouching reversion, we propose a framework, dubbed Re-Face, which consists of three components: a facial retouching detector, an image reversion model named FaceR, and a color correction module called Hierarchical Adaptive Instance Normalization (H-AdaIN). FaceR can utilize labels generated by the facial retouching detector as guidance to revert the retouched facial images. Then, color correction is performed using H-AdaIN to address the issue of color shift. Extensive experiments demonstrate the effectiveness of our framework and each module. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_14177 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Label-guided Facial Retouching Reversion Zhao, Guanhua Gu, Yu Sheng, Xuhan Hu, Yujie Zhang, Jian Computer Vision and Pattern Recognition With the popularity of social media platforms and retouching tools, more people are beautifying their facial photos, posing challenges for fields requiring photo authenticity. To address this issue, some work has proposed makeup removal methods, but they cannot revert images involving geometric deformations caused by retouching. To tackle the problem of facial retouching reversion, we propose a framework, dubbed Re-Face, which consists of three components: a facial retouching detector, an image reversion model named FaceR, and a color correction module called Hierarchical Adaptive Instance Normalization (H-AdaIN). FaceR can utilize labels generated by the facial retouching detector as guidance to revert the retouched facial images. Then, color correction is performed using H-AdaIN to address the issue of color shift. Extensive experiments demonstrate the effectiveness of our framework and each module. |
| title | Label-guided Facial Retouching Reversion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.14177 |