Scholarlink

<p>Age transformation of facial images is a technique that edits age-related person’s appearances while preserving the identity. Existing deep learning-based methods can reproduce natural age transformations; however, they only reproduce averaged transitions and fail to account for individual-specific appearances influenced by their life histories. In this paper, we propose the first diffusion model-based method for personalized age transformation. Our method takes a facial image, a target age, and <i>self-reference images</i> as input to generate an age-edited face image as output. Self-reference images, which are facial images of the same person at different ages, serve as additional supervision to help the model learn individual-specific features. Specifically, we fine-tune a pretrained diffusion model for personalized adaptation using approximately 3–5 self-reference images. Additionally, we design an effective prompt to enhance the performance of age editing and identity preservation. Experiments demonstrate that our method achieves superior performance both quantitatively and qualitatively compared to existing methods.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Selfage: personalized facial age transformation using self-reference images

  • 期刊论文

  • 发表日期：

    2025年5月24日

查看全文
  • Taishi Ito,
  • Yuki Endo,
  • Yoshihiro Kanamori

摘要

Age transformation of facial images is a technique that edits age-related person’s appearances while preserving the identity. Existing deep learning-based methods can reproduce natural age transformations; however, they only reproduce averaged transitions and fail to account for individual-specific appearances influenced by their life histories. In this paper, we propose the first diffusion model-based method for personalized age transformation. Our method takes a facial image, a target age, and self-reference images as input to generate an age-edited face image as output. Self-reference images, which are facial images of the same person at different ages, serve as additional supervision to help the model learn individual-specific features. Specifically, we fine-tune a pretrained diffusion model for personalized adaptation using approximately 3–5 self-reference images. Additionally, we design an effective prompt to enhance the performance of age editing and identity preservation. Experiments demonstrate that our method achieves superior performance both quantitatively and qualitatively compared to existing methods.