Automatic scene relighting for video conferencing

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 algorithm is also described that allows multiple 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.

• Type: Journal
• Year: 2009
• Where: ICIP
• Authors: Stephen Mangiat, Jerry Gibson
• Keywords: Dynamic Range, ICIP 2009, Image Processing, Lighting, Lower Exposure