解决群像照个性化生成中的身份错乱问题，实现精准定位与高保真人脸还原。
ID-Patch: Robust ID Association for Group Photo Personalization
- 用同一面部特征生成位置贴图和嵌入向量，实现身份与位置的强关联。
- 在多个指标上优于基线方法，尤其在人脸相似度和位置准确性上提升显著。
- 无需依赖分割模型，推理更快，适合实际应用中的个性化图像生成。
生成可指定每个人身份位置的个性化群像照片具有巨大的创意潜力。然而，现有技术面临身份泄露问题：注入的面部特征相互干扰，导致人脸相似度低、位置错误和视觉伪影。现有方法存在依赖分割模型、运行时间增加或身份泄露概率高等局限。为此，我们提出ID-Patch，一种在身份与二维位置间建立鲁棒关联的新方法。该方法从相同面部特征中生成身份贴图和身份嵌入：身份贴图用于条件图像上的精确空间控制，身份嵌入则与文本嵌入融合以确保高人脸相似度。实验结果表明，ID-Patch在多个指标上超越基线方法，包括人脸身份相似度、身份-位置关联准确率和生成效率。项目页面：https://byteaigc.github.io/ID-Patch/
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。