Structure-preserving manipulation of photographs
International Symposium on Non-Photorealistic Animation and Rendering (NPAR) - aug 2007
Visual content is often better communicated by simplified or exaggerated
images than by the “real world like” images. In this paper,
we offer a tool for creating such enhanced representations of photographs
in a way consistent with the original image content. To
do so, we develop a method to identify the relevant image structures
and their importance. Our approach (a) uses edges as the basic
structural unit in the image, (b) proposes tools to manipulate
this structure in a flexible way, and (c) employs gradient domain
image processing techniques to reconstruct the final image from a
“cropped” gradient information. This edge-based approach to nonphotorealistic
image processing is made feasible by two new techniques
we introduce: an addition to the Gaussian scale space theory
to compute a perceptually meaningful hierarchy of structures, and
a contrast estimation method necessary for faithful gradient-based
reconstructions. We finally present various applications that manipulate
image structure in different ways.
Images and movies
See also
Matlab source code available here.
BibTex references
@InProceedings\{OBBT07, author = "Orzan, Alexandrina and Bousseau, Adrien and Barla, Pascal and Thollot, Jo{\"e}lle", title = "Structure-preserving manipulation of photographs", booktitle = "International Symposium on Non-Photorealistic Animation and Rendering (NPAR)", month = "aug", year = "2007", url = "http://artis.inrialpes.fr/Publications/2007/OBBT07" }