Learning style translation for the lines of a drawing

  • Authors:
  • William T. Freeman;Joshua B. Tenenbaum;Egon C. Pasztor

  • Affiliations:
  • Mitsubishi Electric Research Labs and MIT Artificial Intelligence Laboratory, Cambridge, MA;MIT Brain and Cognitive Sciences Department;Mitsubishi Electric Research Labs and MIT Media Laboratory

  • Venue:
  • ACM Transactions on Graphics (TOG)
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present an example-based method for translating line drawings into different styles. We fit each line as a linear combination of similar lines in a training set, and interpolate between the corresponding training examples in the output style. The synthesized lines preserve the desired stylistic features of the output style.