Nonlinear Multiresolution Image Blending

Mark Grundland



Contrast Enhancement for Multiresolution Image Blending


Nonlinear Multiresolution Image Blending
Mark Grundland, Rahul Vohra, Gareth P. Williams and Neil A. Dodgson
Machine Graphics & Vision, vol. 15, no. 3-4, pp. 381-390, (2006). ISSN 1230-0535.
Presented as a talk at the International Conference on Computer Vision and Graphics (Warsaw, Poland, 25-27 September 2006).


We study contrast enhancement for multiresolution image blending. In image compositing, image stitching, and image fusion, a blending operator combines coefficients of a pixel array, an image pyramid, a wavelet decomposition, or a gradient domain representation. Linear interpolation reduces variation and thereby causes contrast loss, while coefficient selection increases variation and thereby causes color distortion. Offering a continuous range of possibilities between these standard alternatives, the signed weighted power mean enables the user to calibrate the contrast of composite images.


Paper  +  Illustrations  +  Experiments  +  Presentation 

Related Research  +  More Publications



Web Traffic Map
Web Traffic Counter

Website traffic statistics were reset in February 2014.
Copyright © 2015 Mark Grundland. All rights reserved.