Skip to Main content Skip to Navigation
Conference papers

Structure-preserving manipulation of photographs

Alexandrina Orzan 1 Adrien Bousseau 1 Pascal Barla 1 Joëlle Thollot 1
1 ARTIS - Acquisition, representation and transformations for image synthesis
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : 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 strucures 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 non-photorealistic 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.
Document type :
Conference papers
Complete list of metadata
Contributor : Pascal Barla Connect in order to contact the contributor
Submitted on : Friday, April 29, 2011 - 10:26:35 AM
Last modification on : Monday, November 8, 2021 - 1:36:07 PM
Long-term archiving on: : Saturday, July 30, 2011 - 2:24:28 AM


Files produced by the author(s)




Alexandrina Orzan, Adrien Bousseau, Pascal Barla, Joëlle Thollot. Structure-preserving manipulation of photographs. International Symposium on Non-Photorealistic Animation and Rendering (NPAR), Aug 2007, San Diego, United States. pp.103-110, ⟨10.1145/1274871.1274888⟩. ⟨inria-00362868⟩



Record views


Files downloads