Computer Graphics Forum (Proc. Eurographics Symposium on Rendering) 2024
Xiaohui Li ¹ ² Giuseppe Claudio Guarnera ² ³ Arvin Lin ¹ ² Abhijeet Ghosh ¹ ²
Imperial College London ¹
Lumirithmic Ltd ²
University of York ³
Fig. 1: Given a single input image (column 1), our method can produce realistic re-aging results (10 years old to 80 years old) in both facial appearances with skin color changes (column 2 − 5) and detailed shapes with high-frequency geometric changes, such as skin wrinkles (column 6 − 7).
Abstract: While current facial re-ageing methods can produce realistic results, they purely focus on the 2D age transformation. In this work, we present an approach to transform the age of a person in both facial appearance and shape across different ages while preserving their identity. We employ an α-(de)blending diffusion network with an age-to-α transformation to generate coarse structure changes, such as wrinkles. Additionally, we edit biophysical skin properties, including melanin and hemoglobin, to simulate skin color changes, producing realistic re-ageing results from ages 10 to 80 years. We also propose a geometric neural network that alters the coarse scale facial geometry according to age, followed by a lightweight and efficient network that adds appropriate skin displacement on top of the coarse geometry. Both qualitative and quantitative comparisons show that our method outperforms current state-of-the-art approaches.
Publication: Realistic_Facial_Age_Transformation_with_3D_Uplifting. Xiaohui Li, Giuseppe Claudio Guarnera, Arvin Lin, Abhijeet Ghosh. Computer Graphics Forum (Proc. EGSR), 43(4), 2024
