By-example Synthesis of Architectural Textures

Sylvain Lefebvre 1, 2 Samuel Hornus 1, 3 Anass Lasram 1
1 ALICE - Geometry and Lighting
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
2 REVES - Rendering and virtual environments with sound
CRISAM - Inria Sophia Antipolis - Méditerranée
3 GEOMETRICA - Geometric computing
CRISAM - Inria Sophia Antipolis - Méditerranée , Inria Saclay - Ile de France
Abstract : Textures are often reused on different surfaces in large virtual environments. This leads to unpleasing stretch and cropping of features when textures contain architectural elements. Existing retargeting methods could adapt each texture to the size of their support surface, but this would imply storing a different image for each and every surface, saturating memory. Our new texture synthesis approach casts synthesis as a shortest path problem in a graph describing the space of images that can be synthesized. Each path in the graph describes how to form a new image by cutting strips of the source image and reassembling them in a different order. Only the paths describing the result need to be stored in memory: synthesized textures are reconstructed at rendering time. The user can control repetition of features, and may specify positional constraints. We demonstrate our approach on a variety of textures, from facades for large city rendering to structured textures commonly used in video games.
Document type :
Journal articles
Liste complète des métadonnées


https://hal.inria.fr/inria-00547754
Contributor : Samuel Hornus <>
Submitted on : Tuesday, February 1, 2011 - 5:21:15 PM
Last modification on : Saturday, January 27, 2018 - 1:30:40 AM
Document(s) archivé(s) le : Tuesday, November 6, 2012 - 1:00:59 PM

Files

paper.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Sylvain Lefebvre, Samuel Hornus, Anass Lasram. By-example Synthesis of Architectural Textures. ACM Transactions on Graphics, Association for Computing Machinery, 2010, Proceedings of ACM SIGGRAPH 2010, 29 (4), pp.84:1-8. ⟨10.1145/1778765.1778821⟩. ⟨inria-00547754⟩

Share

Metrics

Record views

462

Files downloads

848