Generating talking head videos through a face image and a piece of speech audio still
contains many challenges. ie, unnatural head movement, distorted expression, and identity …

Abstract 3D-aware generative adversarial networks (GANs) synthesize high-fidelity and
multi-view-consistent facial images using only collections of single-view 2D imagery …

Recent studies in deepfake detection have yielded promising results when the training and
testing face forgeries are from the same dataset. However, the problem remains challenging …

Talking human face generation aims at synthesizing a natural human face that talks in
correspondence to the given text or audio series. Implementing the recently developed …

Talking face generation has historically struggled to produce head movements and natural
facial expressions without guidance from additional reference videos. Recent developments …

Controllability, generalizability and efficiency are the major objectives of constructing face
avatars represented by neural implicit field. However, existing methods have not managed …

We present a novel one-shot talking head synthesis method that achieves disentangled and
fine-grained control over lip motion, eye gaze&blink, head pose, and emotional expression …

Despite recent advances in syncing lip movements with any audio waves, current methods
still struggle to balance generation quality and the model's generalization ability. Previous …

In this work, we propose an ID-preserving talking head generation framework, which
advances previous methods in two aspects. First, as opposed to interpolating from sparse …

Different people speak with diverse personalized speaking styles. Although existing one-
shot talking head methods have made significant progress in lip sync, natural facial …