These limitations arise due to three main factors: i) a scarcity of long-range sequential labelled faces of the same person in existing datasets, which are required for training ii) a focus on texture changes such as wrinkles, which neglects structural variations that are important in aging and limit the effectiveness of these models for large age spans and iii) the tendency to preserve personal identity by minimizing the differences between inputs and synthesized results, which can result in blurry artifacts and insufficient variations. While conditional Generative Adversarial Networks (cGANs) have made significant progress in this field, most current approaches still face challenges in generating convincing age progression while preserving the subject’s identity.
Face aging is an active area of research in multimedia applications that involves modifying a person’s facial photo to resemble their appearance at a different age.
