DiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactment

arXiv:2403.17217v1 Announce Type: new
Abstract: Video-driven neural face reenactment aims to synthesize realistic facial images that successfully preserve the identity and appearance of a source face, while transferring the target head pose and facial expressions. Existing GAN-based methods suffer from either distortions and visual artifacts or poor reconstruction quality, i.e., the background and several important appearance details, such as hair style/color, glasses and accessories, are not faithfully reconstructed. Recent advances in Diffusion Probabilistic Models (DPMs) enable the generation of high-quality …

abstract arxiv autoencoder cs.ai cs.cv diffusion face gan head identity images quality type video visual