![Method Overview](/img/328416cf-075d-4ab0-ad75-02271bb4d763/method-overview.png?fm=jpg&q=80&fit=max&crop=2597%2C697%2C0%2C0)
Retrofitting 2D Latent Diffusion for Controllable Face Image Generation
Weihao Xia1,
Cengiz Öztireli2,
Jing-Hao Xue1
1UCL
2University of Cambridge
In this paper, we propose RetroLaDi, a 3D-aware face image generation method by Retrofitting a 2D Latent Diffusion model. The core procedure is to integrate and reconcile external 3D priors from 3DMMs with the internal knowledge in a pretrained 2D diffusion model. Experimental results demonstrate its ability to generate high-fidelity face images with precise controllability than state-of-the-art 2D-based and 3D-based controllable face synthesis methods.
Links:
Paper Page Data