no code implementations • 29 May 2024 • Simon Giebenhain, Tobias Kirschstein, Martin Rünz, Lourdes Agapito, Matthias Nießner
In contrast to previous work, we condition our avatars' dynamics on the rich expression space of neural parametric head models (NPHM), instead of mesh-based 3DMMs.
no code implementations • 21 Dec 2023 • Artem Sevastopolsky, Philip-William Grassal, Simon Giebenhain, ShahRukh Athar, Luisa Verdoliva, Matthias Niessner
The decomposition of the parametric model and high-quality vertex displacements allows us to animate the model and modify it semantically.
no code implementations • 11 Dec 2023 • Simon Giebenhain, Tobias Kirschstein, Markos Georgopoulos, Martin Rünz, Lourdes Agapito, Matthias Nießner
We present Monocular Neural Parametric Head Models (MonoNPHM) for dynamic 3D head reconstructions from monocular RGB videos.
1 code implementation • 4 Dec 2023 • Shenhan Qian, Tobias Kirschstein, Liam Schoneveld, Davide Davoli, Simon Giebenhain, Matthias Nießner
We introduce GaussianAvatars, a new method to create photorealistic head avatars that are fully controllable in terms of expression, pose, and viewpoint.
no code implementations • 30 Nov 2023 • Tobias Kirschstein, Simon Giebenhain, Matthias Nießner
DiffusionAvatars synthesizes a high-fidelity 3D head avatar of a person, offering intuitive control over both pose and expression.
no code implementations • 4 May 2023 • Tobias Kirschstein, Shenhan Qian, Simon Giebenhain, Tim Walter, Matthias Nießner
We focus on reconstructing high-fidelity radiance fields of human heads, capturing their animations over time, and synthesizing re-renderings from novel viewpoints at arbitrary time steps.
no code implementations • CVPR 2023 • Simon Giebenhain, Tobias Kirschstein, Markos Georgopoulos, Martin Rünz, Lourdes Agapito, Matthias Nießner
We propose a novel 3D morphable model for complete human heads based on hybrid neural fields.
1 code implementation • 22 Oct 2021 • Simon Giebenhain, Bastian Goldlücke
This paper introduces Attentive Implicit Representation Networks (AIR-Nets), a simple, but highly effective architecture for 3D reconstruction from point clouds.