Deep correlations for texture synthesis

Omry Sendik, Daniel Cohen-Or

Research output: Contribution to journalArticlepeer-review

54 Scopus citations


Example-based texture synthesis has been an active research problem for over two decades. Still, synthesizing textures with nonlocal structures remains a challenge. In this article, we present a texture synthesis technique that builds upon convolutional neural networks and extracted statistics of pretrained deep features. We introduce a structural energy, based on correlations among deep features, which capture the self-similarities and regularities characterizing the texture. Specifically, we show that our technique can synthesize textures that have structures of various scales, local and nonlocal, and the combination of the two.

Original languageEnglish
Article number161
JournalACM Transactions on Graphics
Issue number5
StatePublished - Jul 2017
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2017 ACM.


  • Autocorrelation
  • Neural networks
  • Texture synthesis


Dive into the research topics of 'Deep correlations for texture synthesis'. Together they form a unique fingerprint.

Cite this