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 …

Deep neural networks (DNNs) have shown remarkable performance improvements on
vision-related tasks such as object detection or image segmentation. Despite their success …

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 …

We present a method that achieves state-of-the-art results for synthesizing novel views of
complex scenes by optimizing an underlying continuous volumetric scene function using a …

In this work we address the challenging problem of multiview 3D surface reconstruction. We
introduce a neural network architecture that simultaneously learns the unknown geometry …

Learning-based 3D reconstruction methods have shown impressive results. However, most
methods require 3D supervision which is often hard to obtain for real-world datasets …

In this paper we present ADOP, a novel point-based, differentiable neural rendering
pipeline. Like other neural renderers, our system takes as input calibrated camera images …

Real-time rendering and animation of humans is a core function in games, movies, and
telepresence applications. Existing methods have a number of drawbacks we aim to …

StyleGAN generates photorealistic portrait images of faces with eyes, teeth, hair and context
(neck, shoulders, background), but lacks a rig-like control over semantic face parameters …