Automatic scene relighting for video conferencing

Authors:
Stephen Mangiat;Jerry Gibson
Affiliations:
Electrical and Computer Engineering Department, University of California, Santa Barbara, CA;Electrical and Computer Engineering Department, University of California, Santa Barbara, CA
Venue:
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Year:
2009

Citing 4
Cited 0

Photographic tone reproduction for digital images

Proceedings of the 29th annual conference on Computer graphics and interactive techniques
High dynamic range video

ACM SIGGRAPH 2003 Papers
Image quality improvement by adaptive exposure correction techniques

ICME '03 Proceedings of the 2003 International Conference on Multimedia and Expo - Volume 2
Recovering high dynamic range radiance maps from photographs

ACM SIGGRAPH 2008 classes

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a new method to automatically improve scene lighting for video conferencing by learning the photometric mapping between a lower exposure and desired exposure created using High Dynamic Range (HDR) imaging techniques. Once the mapping is learned in a calibration step, it can be used to transform all subsequent images, effectively producing higher dynamic range video without ghosting artifacts. A stereo algorithmis also described that allowsmultiple exposures to be taken at every frame, useful if the lighting of a scene changes significantly. Results show that this is an effective way to improve face lighting and therefore the overall experience of video conferencing.