Learning style translation for the lines of a drawing
- 1 January 2003
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 22 (1), 33-46
- https://doi.org/10.1145/588272.588277
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.Keywords
This publication has 4 references indexed in Scilit:
- Separating Style and Content with Bilinear ModelsNeural Computation, 2000
- Capturing and Re‐Using Rendition Styles for Non‐Photorealistic RenderingComputer Graphics Forum, 1999
- Verbs and adverbs: multidimensional motion interpolationIEEE Computer Graphics and Applications, 1998
- Locally Weighted LearningArtificial Intelligence Review, 1997