K
Kevin Karsch
Researcher at University of Illinois at Urbana–Champaign
Publications - 47
Citations - 2012
Kevin Karsch is an academic researcher from University of Illinois at Urbana–Champaign. The author has contributed to research in topics: Rendering (computer graphics) & Augmented reality. The author has an hindex of 19, co-authored 47 publications receiving 1766 citations. Previous affiliations of Kevin Karsch include United States Naval Research Laboratory & Adobe Systems.
Papers
More filters
Journal ArticleDOI
Depth Transfer: Depth Extraction from Video Using Non-Parametric Sampling.
TL;DR: The technique can be used to automatically convert a monoscopic video into stereo for 3D visualization, and is demonstrated through a variety of visually pleasing results for indoor and outdoor scenes, including results from the feature film Charade.
Book ChapterDOI
Depth extraction from video using non-parametric sampling
TL;DR: The technique can be used to automatically convert a monoscopic video into stereo for 3D visualization, and is demonstrated through a variety of visually pleasing results for indoor and outdoor scenes, including results from the feature film Charade.
Proceedings ArticleDOI
Rendering synthetic objects into legacy photographs
TL;DR: In this article, a method to realistically insert synthetic objects into existing photographs without requiring access to the scene or any additional scene measurements is proposed, which can be used for home decorating and user content creation.
Journal ArticleDOI
Automatic Scene Inference for 3D Object Compositing
Kevin Karsch,Kalyan Sunkavalli,Sunil Hadap,Nathan A. Carr,Hailin Jin,Rafael Fonte,Michael Sittig,David Forsyth +7 more
TL;DR: a user-friendly image editing system that supports a drag-and-drop object insertion, postprocess illumination editing, and depth-of-field manipulation, and achieves the same level of realism as techniques that require significant user interaction.
Posted Content
Automatic Scene Inference for 3D Object Compositing
Kevin Karsch,Kalyan Sunkavalli,Sunil Hadap,Nathan A. Carr,Hailin Jin,Rafael Fonte,Michael Sittig +6 more
TL;DR: In this article, a user-friendly image editing system that supports a drag-and-drop object insertion (where the user merely drags objects into the image, and the system automatically places them in 3D and relights them appropriately), post-process illumination editing, and depth-of-field manipulation is presented.