Animatable Virtual Humans: Learning Pose-Dependent Human Representations in UV Space for Interactive Performance Synthesis.

We propose a novel representation of virtual humans for highly realistic real-time animation and rendering in 3D applications. We learn pose dependent appearance and geometry from highly accurate dynamic mesh sequences obtained from state-of-the-art multiview-video reconstruction. Learning pose-dependent appearance and geometry from mesh sequences poses significant challenges, as it requires the network to learn the intricate shape and articulated motion of a human body.

Realness of face images can be decoded from non-linear modulation of EEG responses.

Artificially created human faces play an increasingly important role in our digital world. However, the so-called uncanny valley effect may cause people to perceive highly, yet not perfectly human-like faces as eerie, bringing challenges to the interaction with virtual agents. At the same time, the neurocognitive underpinnings of the uncanny valley effect remain elusive.

A low-dimensional representation for individual head geometries.

In the estimation of individual head geometries for source localization and electrical stimulation in neuroelectric investigations and application, mostly complex geometrical models are directly extracted from anatomical images. We present a novel method that uses a dimensionality reduction from thousands down to the range of tens of parameters to successfully represent an individual 4-shell Boundary Element Method (BEM) head model, which can successively be fitted to any kind of data from an individual head (e.g.