We present Sapiens, a family of models for four fundamental human-centric vision tasks–2D
pose estimation, body-part segmentation, depth estimation, and surface normal prediction …

Talking head generation aims to generate faces that maintain the identity information of the
source image and imitate the motion of the driving image. Most pioneering methods rely …

We present a one-shot method to infer and render a photorealistic 3D representation from a
single unposed image (eg, face portrait) in real-time. Given a single RGB input, our image …

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 …

We propose X-Portrait, an innovative conditional diffusion model tailored for generating
expressive and temporally coherent portrait animation. Specifically, given a single portrait as …

We present Follow-Your-Emoji, a diffusion-based framework for portrait animation, which
animates a reference portrait with target landmark sequences. The main challenge of portrait …

Existing approaches to animatable NeRF-based head avatars are either built upon face
templates or use the expression coefficients of templates as the driving signal. Despite the …

Portrait Animation aims to synthesize a lifelike video from a single source image, using it as
an appearance reference, with motion (ie, facial expressions and head pose) derived from a …

We propose a novel approach for unsupervised 3D animation of non-rigid deformable
objects. Our method learns the 3D structure and dynamics of objects solely from single-view …

With NeRF widely used for facial reenactment, recent methods can recover photo-realistic
3D head avatar from just a monocular video. Unfortunately, the training process of the NeRF …