D
David Salesin
Researcher at Google
Publications - 136
Citations - 21825
David Salesin is an academic researcher from Google. The author has contributed to research in topics: Rendering (computer graphics) & Non-photorealistic rendering. The author has an hindex of 66, co-authored 135 publications receiving 21135 citations. Previous affiliations of David Salesin include Cornell University & Microsoft.
Papers
More filters
Proceedings ArticleDOI
Image analogies
TL;DR: This paper describes a new framework for processing images by example, called “image analogies,” based on a simple multi-scale autoregression, inspired primarily by recent results in texture synthesis.
Journal ArticleDOI
Interactive digital photomontage
Aseem Agarwala,Mira Dontcheva,Maneesh Agrawala,Steven M. Drucker,Alex Colburn,Brian Curless,David Salesin,Michael Cohen +7 more
TL;DR: The framework makes use of two techniques primarily: graph-cut optimization, to choose good seams within the constituent images so that they can be combined as seamlessly as possible; and gradient-domain fusion, a process based on Poisson equations, to further reduce any remaining visible artifacts in the composite.
Proceedings ArticleDOI
A Bayesian approach to digital matting
TL;DR: This paper proposes a new Bayesian framework for solving the matting problem, i.e. extracting a foreground element from a background image by estimating an opacity for each pixel of the foreground element by using a maximum-likelihood criterion.
Proceedings ArticleDOI
Fast multiresolution image querying
TL;DR: An “image querying metric” is introduced that operates on how many significant wavelet coefficients the query has in common with potential targets, and includes parameters that can be tuned, using a statistical analysis, to accommodate the kinds of image distortions found in different types of image queries.
Proceedings ArticleDOI
Synthesizing realistic facial expressions from photographs
TL;DR: This work presents new techniques for creating photorealistic textured 3D facial models from photographs of a human subject, and for creating smooth transitions between different facial expressions by morphing between these different models.