Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.13632 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916665482018816 |
|---|---|
| author | Zhang, Yimeng Zhi, Tiancheng Liu, Jing Sang, Shen Jiang, Liming Yan, Qing Liu, Sijia Luo, Linjie |
| author_facet | Zhang, Yimeng Zhi, Tiancheng Liu, Jing Sang, Shen Jiang, Liming Yan, Qing Liu, Sijia Luo, Linjie |
| contents | The ability to synthesize personalized group photos and specify the positions of each identity offers immense creative potential. While such imagery can be visually appealing, it presents significant challenges for existing technologies. A persistent issue is identity (ID) leakage, where injected facial features interfere with one another, resulting in low face resemblance, incorrect positioning, and visual artifacts. Existing methods suffer from limitations such as the reliance on segmentation models, increased runtime, or a high probability of ID leakage. To address these challenges, we propose ID-Patch, a novel method that provides robust association between identities and 2D positions. Our approach generates an ID patch and ID embeddings from the same facial features: the ID patch is positioned on the conditional image for precise spatial control, while the ID embeddings integrate with text embeddings to ensure high resemblance. Experimental results demonstrate that ID-Patch surpasses baseline methods across metrics, such as face ID resemblance, ID-position association accuracy, and generation efficiency. Project Page is: https://byteaigc.github.io/ID-Patch/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_13632 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ID-Patch: Robust ID Association for Group Photo Personalization Zhang, Yimeng Zhi, Tiancheng Liu, Jing Sang, Shen Jiang, Liming Yan, Qing Liu, Sijia Luo, Linjie Computer Vision and Pattern Recognition The ability to synthesize personalized group photos and specify the positions of each identity offers immense creative potential. While such imagery can be visually appealing, it presents significant challenges for existing technologies. A persistent issue is identity (ID) leakage, where injected facial features interfere with one another, resulting in low face resemblance, incorrect positioning, and visual artifacts. Existing methods suffer from limitations such as the reliance on segmentation models, increased runtime, or a high probability of ID leakage. To address these challenges, we propose ID-Patch, a novel method that provides robust association between identities and 2D positions. Our approach generates an ID patch and ID embeddings from the same facial features: the ID patch is positioned on the conditional image for precise spatial control, while the ID embeddings integrate with text embeddings to ensure high resemblance. Experimental results demonstrate that ID-Patch surpasses baseline methods across metrics, such as face ID resemblance, ID-position association accuracy, and generation efficiency. Project Page is: https://byteaigc.github.io/ID-Patch/ |
| title | ID-Patch: Robust ID Association for Group Photo Personalization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.13632 |