New Publication: Advancing Face Reenactment with Diffusion Models
We are excited to share that the RAIDO Project’s latest paper, “DiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactment,” is now live on IEEE Xplore following its presentation at FG2025. DiffusionAct moves beyond the limitations of traditional GAN-based methods by using Diffusion Probabilistic Models (DPMs) to produce high-fidelity, artifact-free face reenactments. Unlike previous models, DiffusionAct […]