Y
Yun-Ta Tsai
Researcher at Google
Publications - 33
Citations - 1395
Yun-Ta Tsai is an academic researcher from Google. The author has contributed to research in topics: Standard illuminant & Color balance. The author has an hindex of 13, co-authored 33 publications receiving 949 citations. Previous affiliations of Yun-Ta Tsai include University of Southern California & Nokia.
Papers
More filters
Journal ArticleDOI
FlexISP: a flexible camera image processing framework
Felix Heide,Markus Steinberger,Yun-Ta Tsai,Mushfiqur Rouf,Dawid Pająk,Dikpal Reddy,Orazio Gallo,Jing Liu,Wolfgang Heidrich,Karen Egiazarian,Jan Kautz,Kari Pulli +11 more
TL;DR: This work proposes an end-to-end system that is aware of the camera and image model, enforces natural-image priors, while jointly accounting for common image processing steps like demosaicking, denoising, deconvolution, and so forth, all directly in a given output representation.
Proceedings ArticleDOI
Fast Fourier Color Constancy
Jonathan T. Barron,Yun-Ta Tsai +1 more
TL;DR: Fast Fourier Color Constancy (FFCC) as discussed by the authors is a color constancy algorithm which solves illuminant estimation by reducing it to a spatial localization task on a torus.
Journal ArticleDOI
Single image portrait relighting
Tiancheng Sun,Jonathan T. Barron,Yun-Ta Tsai,Zexiang Xu,Xueming Yu,Graham Fyffe,Christoph Rhemann,Jay Busch,Paul Debevec,Ravi Ramamoorthi +9 more
TL;DR: In this paper, a neural network is trained on a small database of 18 individuals captured under different directional light sources in a controlled light stage setup consisting of a densely sampled sphere of lights.
Journal ArticleDOI
Mobile Augmented Reality: Indirect augmented reality
TL;DR: This paper replaces the live camera view used in video see through AR with a previously captured panoramic image to improve the perceived quality of the tracking while still maintaining a similar overall experience and evaluates this technique on both a performance and experiential basis.
Journal ArticleDOI
Single Image Portrait Relighting
Tiancheng Sun,Jonathan T. Barron,Yun-Ta Tsai,Zexiang Xu,Xueming Yu,Graham Fyffe,Christoph Rhemann,Jay Busch,Paul Debevec,Ravi Ramamoorthi +9 more
TL;DR: In this article, a neural network is trained on a small database of 18 individuals captured under different directional light sources in a controlled light stage setup consisting of a densely sampled sphere of lights.