Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Kirschstein, Tobias"'
Autor:
Kirschstein, Tobias, Giebenhain, Simon, Tang, Jiapeng, Georgopoulos, Markos, Nießner, Matthias
Learning 3D head priors from large 2D image collections is an important step towards high-quality 3D-aware human modeling. A core requirement is an efficient architecture that scales well to large-scale datasets and large image resolutions. Unfortuna
Externí odkaz:
http://arxiv.org/abs/2406.09377
Publikováno v:
SIGGRAPH Asia 2024 Conference Papers (SA Conference Papers '24), December 3-6, 2024, Tokyo, Japan
The creation of high-fidelity, digital versions of human heads is an important stepping stone in the process of further integrating virtual components into our everyday lives. Constructing such avatars is a challenging research problem, due to a high
Externí odkaz:
http://arxiv.org/abs/2405.19331
Autor:
Giebenhain, Simon, Kirschstein, Tobias, Georgopoulos, Markos, Rünz, Martin, Agapito, Lourdes, Nießner, Matthias
We present Monocular Neural Parametric Head Models (MonoNPHM) for dynamic 3D head reconstructions from monocular RGB videos. To this end, we propose a latent appearance space that parameterizes a texture field on top of a neural parametric model. We
Externí odkaz:
http://arxiv.org/abs/2312.06740
Autor:
Qian, Shenhan, Kirschstein, Tobias, Schoneveld, Liam, Davoli, Davide, Giebenhain, Simon, Nießner, Matthias
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 representation based on 3D Gaussian splats that are rigged to a pa
Externí odkaz:
http://arxiv.org/abs/2312.02069
DiffusionAvatars synthesizes a high-fidelity 3D head avatar of a person, offering intuitive control over both pose and expression. We propose a diffusion-based neural renderer that leverages generic 2D priors to produce compelling images of faces. Fo
Externí odkaz:
http://arxiv.org/abs/2311.18635
Publikováno v:
ACM Transactions on Graphics, Volume 42, Issue 4, Article No. 161 (2023) 1-14
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. To this end, we propose a new multi-view capture setup compos
Externí odkaz:
http://arxiv.org/abs/2305.03027
Autor:
Giebenhain, Simon, Kirschstein, Tobias, Georgopoulos, Markos, Rünz, Martin, Agapito, Lourdes, Nießner, Matthias
We propose a novel 3D morphable model for complete human heads based on hybrid neural fields. At the core of our model lies a neural parametric representation that disentangles identity and expressions in disjoint latent spaces. To this end, we captu
Externí odkaz:
http://arxiv.org/abs/2212.02761
Source code (Context) and its parsed abstract syntax tree (AST; Structure) are two complementary representations of the same computer program. Traditionally, designers of machine learning models have relied predominantly either on Structure or Contex
Externí odkaz:
http://arxiv.org/abs/2103.11318
Source code (Context) and its parsed abstract syntax tree (AST; Structure) are two complementary representations of the same computer program. Traditionally, designers of machine learning models have relied predominantly either on Structure or Contex
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d0a175ea8213638ea45f2b8b26629d7c
http://arxiv.org/abs/2103.11318
http://arxiv.org/abs/2103.11318