P
Paul Debevec
Researcher at Google
Publications - 243
Citations - 20474
Paul Debevec is an academic researcher from Google. The author has contributed to research in topics: Rendering (computer graphics) & Image-based lighting. The author has an hindex of 56, co-authored 240 publications receiving 18468 citations. Previous affiliations of Paul Debevec include AmeriCorps VISTA & Institute for Creative Technologies.
Papers
More filters
Journal ArticleDOI
Neural Light Transport for Relighting and View Synthesis
Xiuming Zhang,Sean Fanello,Yun-Ta Tsai,Tiancheng Sun,Tianfan Xue,Rohit Pandey,Sergio Orts-Escolano,Philip Davidson,Christoph Rhemann,Paul Debevec,Jonathan T. Barron,Ravi Ramamoorthi,William T. Freeman +12 more
TL;DR: In this article, a semi-parametric approach is proposed to learn a neural representation of the light transport of a scene that is embedded in a texture atlas of known but possibly rough geometry.
Proceedings ArticleDOI
Digital Ira: creating a real-time photoreal digital actor
Oleg Alexander,Graham Fyffe,Jay Busch,Xueming Yu,Ryosuke Ichikari,Andrew Jones,Paul Debevec,Jorge Jimenez,Etienne Danvoye,Bernardo Antionazzi,Mike Eheler,Zybnek Kysela,Javier von der Pahlen +12 more
TL;DR: This collaboration between Activision and USC ICT endeavoured to create a real-time, photoreal digital human character which could be seen from any viewpoint, in any lighting, and could perform realistically from video performance capture even in a tight closeup.
Proceedings ArticleDOI
Prototyping a light field display involving direct observation of a video projector array
TL;DR: If today's pico-projectors become sufficiently inexpensive, immersive full-parallax displays with arbitrarily high spatial and angular resolution will become possible, it is shown.
Journal ArticleDOI
Measurement-based Synthesis of Facial Microgeometry
Paul Graham,Borom Tunwattanapong,Jay Busch,Xueming Yu,Andrew Jones,Paul Debevec,Abhijeet Ghosh +6 more
TL;DR: The technique allows for greater realism in facial renderings including more accurate reproduction of skin's specular reflection effects and can be used to synthesize full‐facial microstructure detail for either the same subject or to a different subject.
Journal ArticleDOI
Near-instant capture of high-resolution facial geometry and reflectance
TL;DR: The facial base geometry obtained from multi‐view stereo is refined using estimated diffuse and specular photometric information and allows final submillimeter surface mesostructure detail to be obtained via shape‐from‐specularity.