Search Results

Documents authored by Smith, William

Document
DOI: 10.4230/DagRep.15.5.96
Generative Models for 3D Vision (Dagstuhl Seminar 25202)

Authors: Laura Neschen, Bernhard Egger, Adam Kortylewski, William Smith, and Stefanie Wuhrer

Published in: Dagstuhl Reports, Volume 15, Issue 5 (2025)

Abstract
Generative models that allow synthesis of realistic 3D models have been of interest in computer vision and graphics for over 2 decades. While traditional methods use morphable models for this task, more recent works have adopted powerful tools from the 2D image domain such as generative adversarial networks, neural fields and diffusion models, and have achieved impressive results. The question of which tools are most suitable for applications such as reconstructing 3D geometry from partial data, and creating digital 3D content remains open. This report documents the program and outcomes of Dagstuhl Seminar 25202 titled "Generative Models for 3D Vision". This meeting of 25 researchers covered a variety of topics such as generative models and priors for 2D tasks, medical applications, and digital representations of humans, including how to evaluate and benchmark different methods. We summarise the discussions, presentations, and results of this seminar.
Cite as

Laura Neschen, Bernhard Egger, Adam Kortylewski, William Smith, and Stefanie Wuhrer. Generative Models for 3D Vision (Dagstuhl Seminar 25202). In Dagstuhl Reports, Volume 15, Issue 5, pp. 96-113, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@Article{neschen_et_al:DagRep.15.5.96,
  author =	{Neschen, Laura and Egger, Bernhard and Kortylewski, Adam and Smith, William and Wuhrer, Stefanie},
  title =	{{Generative Models for 3D Vision (Dagstuhl Seminar 25202)}},
  pages =	{96--113},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2025},
  volume =	{15},
  number =	{5},
  editor =	{Neschen, Laura and Egger, Bernhard and Kortylewski, Adam and Smith, William and Wuhrer, Stefanie},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.15.5.96},
  URN =		{urn:nbn:de:0030-drops-252774},
  doi =		{10.4230/DagRep.15.5.96},
  annote =	{Keywords: 3D Computer Vision, Computer Graphics, Generative Models, Implicit Representations, Neural Rendering, Statistical Modelling}
}
Document
DOI: 10.4230/DagRep.12.3.97
3D Morphable Models and Beyond (Dagstuhl Seminar 22121)

Authors: James Gardner, Bernhard Egger, William Smith, Christian Theobalt, and Stefanie Wuhrer

Published in: Dagstuhl Reports, Volume 12, Issue 3 (2022)

Abstract
3D Morphable Models are models separating shape from appearance variation. Typically, they are used as a statistical prior in computer graphics and vision. Recent success with neural representations have caused a resurgence of interest in visual computing problems, leading to more accurate, higher fidelity, more expressive, and memory-efficient solutions. This report documents the program and the outcomes of Dagstuhl Seminar 22121, "3D Morphable Models and Beyond". This meeting of 39 researchers covered various topics, including 3D morphable models, implicit neural representations, physics-inspired approaches, and more. We summarise the discussions, presentations and results of this workshop.
Cite as

James Gardner, Bernhard Egger, William Smith, Christian Theobalt, and Stefanie Wuhrer. 3D Morphable Models and Beyond (Dagstuhl Seminar 22121). In Dagstuhl Reports, Volume 12, Issue 3, pp. 97-116, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)

Copy BibTex To Clipboard

@Article{gardner_et_al:DagRep.12.3.97,
  author =	{Gardner, James and Egger, Bernhard and Smith, William and Theobalt, Christian and Wuhrer, Stefanie},
  title =	{{3D Morphable Models and Beyond (Dagstuhl Seminar 22121)}},
  pages =	{97--116},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2022},
  volume =	{12},
  number =	{3},
  editor =	{Gardner, James and Egger, Bernhard and Smith, William and Theobalt, Christian and Wuhrer, Stefanie},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.12.3.97},
  URN =		{urn:nbn:de:0030-drops-172701},
  doi =		{10.4230/DagRep.12.3.97},
  annote =	{Keywords: 3D Computer Vision, Generative Models, Neural Rendering, Implicit Representations, Computer Graphics, Statistical Modelling}
}
Document
DOI: 10.4230/DagRep.9.3.16
3D Morphable Models (Dagstuhl Seminar 19102)

Authors: Bernhard Egger, William Smith, Christian Theobalt, and Thomas Vetter

Published in: Dagstuhl Reports, Volume 9, Issue 3 (2019)

Abstract
3D Morphable Models is a statistical object model separating shape from appearance variation. Typically, they are used as a statistical prior in computer graphics and vision. This report summarizes the Dagstuhl seminar on 3D Morphable Models, March 3-8, 2019. It was a first specific meeting of a broader group of people working with 3D Morphable Models of faces and bodies. This meeting of 26 researchers was held 20 years after the seminal work was published at Siggraph. We summarize the discussions, presentations and results of this workshop.
Cite as

Bernhard Egger, William Smith, Christian Theobalt, and Thomas Vetter. 3D Morphable Models (Dagstuhl Seminar 19102). In Dagstuhl Reports, Volume 9, Issue 3, pp. 16-38, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)

Copy BibTex To Clipboard

@Article{egger_et_al:DagRep.9.3.16,
  author =	{Egger, Bernhard and Smith, William and Theobalt, Christian and Vetter, Thomas},
  title =	{{3D Morphable Models (Dagstuhl Seminar 19102)}},
  pages =	{16--38},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2019},
  volume =	{9},
  number =	{3},
  editor =	{Egger, Bernhard and Smith, William and Theobalt, Christian and Vetter, Thomas},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.9.3.16},
  URN =		{urn:nbn:de:0030-drops-112894},
  doi =		{10.4230/DagRep.9.3.16},
  annote =	{Keywords: 3D Computer Vision, Analysis-by-Synthesis, Computer Graphics, Generative Models, Statistical Modelling}
}
Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2025 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact