EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars

arXiv:2404.19110v1 Announce Type: new
Abstract: Head avatars animated by visual signals have gained popularity, particularly in cross-driving synthesis where the driver differs from the animated character, a challenging but highly practical approach. The recently presented MegaPortraits model has demonstrated state-of-the-art results in this domain. We conduct a deep examination and evaluation of this model, with a particular focus on its latent space for facial expression descriptors, and uncover several limitations with its ability to express intense face motions. To address …

abstract animated art arxiv avatars cs.cv domain driver driving emotion evaluation head multimodal practical results state synthesis type visual