CAPREAL
Financiado
Performance Capture of the Real World in Motion
Computer graphics technology for realistic rendering has improved
dramatically; however, the technology to create scene models to be rendered,
e.g., for movies, has not developed at the same pace. In practice, the state
of the art...
Computer graphics technology for realistic rendering has improved
dramatically; however, the technology to create scene models to be rendered,
e.g., for movies, has not developed at the same pace. In practice, the state
of the art in model creation still requires months of complex manual design,
and this is a serious threat to progress. To attack this problem, computer
graphics and computer vision researchers jointly developed methods that
capture scene models from real world examples. Of particular importance is
the capturing of moving scenes. The pinnacle of dynamic scene capture
technology in research is marker-less performance capture. From multi-view
video, they capture dynamic surface and texture models of the real world.
Performance capture is hardly used in practice due to profound limitations:
recording is usually limited to indoor studios, controlled lighting, and
dense static camera arrays. Methods are often limited to single objects, and
reconstructed shape detail is very limited. Assumptions about materials,
reflectance, and lighting in a scene are simplistic, and we cannot easily
modify captured data.
In this project, we will pioneer a new generation of performance capture
techniques to overcome these limitations. Our methods will allow the
reconstruction of dynamic surface models of unprecedented shape detail. They
will succeed on general scenes outside of the lab and outdoors, scenes with
complex material and reflectance distributions, and scenes in which lighting
is general, uncontrolled, and unknown. They will capture dense and crowded
scenes with complex shape deformations. They will reconstruct conveniently
modifiable scene models. They will work with sparse and moving sets of
cameras, ultimately even with mobile phones. This far-reaching,
multi-disciplinary project will turn performance capture from a research
technology into a practical technology, provide groundbreaking scientific
insights, and open up revolutionary new applications.
ver más
Línea de financiación: concedida
El organismo FP7 notifico la concesión del proyecto el día 2018-08-31
Presupuesto
El presupuesto total del proyecto asciende a
1M€
Líder del proyecto
MAXPLANCKGESELLSCHAFT ZUR FORDERUNG DER WISSE...
No se ha especificado una descripción o un objeto social para esta compañía.
Perfil tecnológico
TRL
4-5
Perfil tecnológico
TRL
4-5
1.73M€ |
Participante