Pose invariant age estimation of face images in the wild

Wei Wang

Abstract:

The current work proposes a method for age estimation of face videos. To attenuate the effect of pose, our
method is based on facial 𝑢𝑣 texture maps reconstructed from original frames of videos. A Wasserstein-based
GAN is used to restore the full 𝑢𝑣 texture presentation. Age is then predicted from the completed 𝑢𝑣 mappings
such that the proposed AgeGAN method simultaneously learns to capture the facial 𝑢𝑣 texture map and age
characteristics. To train our method, we have created the UvAge dataset, the largest video dataset of face
videos with age annotation (together with identity, gender, and ethnicity labels). The dataset contains videos
in-the-wild from celebrities that are recorded in a variety of imaging settings. In total, we collected 6898
video segments (788,640 frames) from 516 celebrities in 57 events. Extensive experiments demonstrate that
our proposed method outperforms other advanced age estimation methods