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 …

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 …

We present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D
meshes generation from a single unposed image in the wild using both2D and 3D priors. In …

Existing 3D-aware facial generation methods face a dilemma in quality versus editability:
they either generate editable results in low resolution, or high-quality ones with no editing …

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

We present AvatarReX, a new method for learning NeRF-based full-body avatars from video
data. The learnt avatar not only provides expressive control of the body, hands and the face …

We present PyMAF-X, a regression-based approach to recovering a parametric full-body
model from a single image. This task is very challenging since minor parametric deviation …

As virtual avatars have become increasingly popular in recent years, current needs indicate
that “interactivity” is crucial for inducing a positive response from users towards these …

We address the problem of learning person-specific facial priors from a small number (eg,
20) of portrait photos of the same person. This enables us to edit this specific person's facial …

We propose ClipFace, a novel self-supervised approach for text-guided editing of textured
3D morphable model of faces. Specifically, we employ user-friendly language prompts to …