SelfAge: Personalized Facial Age Transformation Using Self-reference Images

TL;DR

SelfAge introduces a diffusion model-based approach for personalized facial age transformation that leverages self-reference images to better preserve individual features, outperforming existing methods in quality and realism.

Contribution

It is the first to use a diffusion model with self-reference images for personalized age transformation, enabling more accurate and individual-specific results.

Findings

Superior quantitative and qualitative performance over existing methods

Effective use of self-reference images for personalization

Enhanced age editing and identity preservation

Abstract

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 diffusion model takes a facial image and a target age as input and generates an age-edited face image as output. To reflect individual-specific features, we incorporate additional supervision using self-reference images, which are facial images of the same person at different ages. Specifically, we fine-tune a pretrained diffusion model for personalized adaptation using approximately 3 to 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. The code and the pretrained model are available at https://github.com/shiiiijp/SelfAge.