Estimating human pose and shape from monocular images is a long-standing problem in
computer vision. Since the release of statistical body models, 3D human mesh recovery has …

Generative adversarial networks (GANs) have been extensively studied in the past few
years. Arguably their most significant impact has been in the area of computer vision where …

We introduce GaussianAvatars a new method to create photorealistic head avatars that are
fully controllable in terms of expression pose and viewpoint. The core idea is a dynamic 3D …

In this paper, we propose HeadNeRF, a novel NeRF-based parametric head model that
integrates the neural radiance field to the parametric representation of the human head. It …

Abstract 3D-aware image generative modeling aims to generate 3D-consistent images with
explicitly controllable camera poses. Recent works have shown promising results by training …

The ability to create realistic animatable and relightable head avatars from casual video
sequences would open up wide ranging applications in communication and entertainment …

Traditional 3D morphable face models (3DMMs) provide fine-grained control over
expression but cannot easily capture geometric and appearance details. Neural volumetric …

Creating high-fidelity 3D head avatars has always been a research hotspot but there
remains a great challenge under lightweight sparse view setups. In this paper we propose …

As 3D facial avatars become more widely used for communication, it is critical that they
faithfully convey emotion. Unfortunately, the best recent methods that regress parametric 3D …

While current monocular 3D face reconstruction methods can recover fine geometric details,
they suffer several limitations. Some methods produce faces that cannot be realistically …