articleACM Transactions on GraphicsJul 1, 2003BRONZE OA

Graphcut textures

Georgia Institute of Technology

Indexed incrossref

Abstract

In this paper we introduce a new algorithm for image and video texture synthesis. In our approach, patch regions from a sample image or video are transformed and copied to the output and then stitched together along optimal seams to generate a new (and typically larger) output. In contrast to other techniques, the size of the patch is not chosen a-priori , but instead a graph cut technique is used to determine the optimal patch region for any given offset between the input and output texture. Unlike dynamic programming, our graph cut technique for seam optimization is applicable in any dimension. We specifically explore it in 2D and 3D to perform video texture synthesis in addition to regular image synthesis.…

Citation impact

770
total citations
FWCI
15.90
Percentile
100%
References
23
Citations per year

Authors

5

Topics & keywords

Keywords
  • Texture synthesis
  • Computer science
  • Merge (version control)
  • Offset (computer science)
  • Computer vision
  • Artificial intelligence
  • Cut
  • Dynamic programming
UN Sustainable Development Goals
  • Life below water
No related works found for this paper.

Funding