3D-FM GAN: A Conditional GAN Framework for Face Manipulation
3D-FM GAN: Towards 3D-Controllable Face ManipulationWe propose 3d-fm generative adversarial network (3d-fm), a novel conditional adversarial network designed specifically for 3d-controllable face manipulation.By carefully encoding both the input face image and a physically-based rendering of 3d edits
into a stylegan s latent spaces, our image generator provides high-quality,
identity-preserved, 3d-controllable face manipulation.To effectively learn such novel framework, we develop two essential training strategies and a novel multiplicative co-modulation architecture that improves significantly upon naive schemes.With extensive evaluations,
we show that our method outperforms the prior arts on various tasks, with better editability, stronger identity
preservation, and higher photo-realism.