DiffAge3D: Diffusion-based 3D-aware Face Aging

TL;DR

DiffAge3D introduces a novel 3D-aware face aging framework that faithfully ages faces while preserving identity and details, utilizing a diffusion model trained on a newly generated dataset from a 3D GAN and CLIP.

Contribution

This work is the first to propose a 3D-aware face aging method that models aging and camera pose separately using a single image, and introduces a new dataset generation pipeline without inversion bottlenecks.

Findings

Outperforms existing methods in multiview-consistent aging

Preserves fine facial details effectively

Demonstrates robust identity preservation

Abstract

Face aging is the process of converting an individual's appearance to a younger or older version of themselves. Existing face aging techniques have been limited to 2D settings, which often weaken their applications as there is a growing demand for 3D face modeling. Moreover, existing aging methods struggle to perform faithful aging, maintain identity, and retain the fine details of the input images. Given these limitations and the need for a 3D-aware aging method, we propose DiffAge3D, the first 3D-aware aging framework that not only performs faithful aging and identity preservation but also operates in a 3D setting. Our aging framework allows to model the aging and camera pose separately by only taking a single image with a target age. Our framework includes a robust 3D-aware aging dataset generation pipeline by utilizing a pre-trained 3D GAN and the rich text embedding capabilities within CLIP model. Notably, we do not employ any inversion bottleneck in dataset generation. Instead, we randomly generate training samples from the latent space of 3D GAN, allowing us to manipulate the rich latent space of GAN to generate ages even with large gaps. With the generated dataset, we train a viewpoint-aware diffusion-based aging model to control the camera pose and facial age. Through quantitative and qualitative evaluations, we demonstrate that DiffAge3D outperforms existing methods, particularly in multiview-consistent aging and fine details preservation.