Name
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. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1145/1833349.1778821 | ACM Trans. Graph. |
Keywords | Field | DocType |
shortest path problem,image retargeting,texture synthesis,virtual environment | Computer vision,Shortest path problem,Computer graphics (images),Computer science,Seam carving,Image editing,Retargeting,STRIPS,Artificial intelligence,Rendering (computer graphics),Texture atlas,Texture synthesis | Journal |
Volume | Issue | ISSN |
29 | 4 | 0730-0301 |
Citations | PageRank | References |
16 | 0.83 | 14 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sylvain Lefebvre | 1 | 1074 | 62.54 |
| Samuel Hornus | 2 | 166 | 12.52 |
| Anass Lasram | 3 | 70 | 4.12 |