Style-learning with feature-based texture synthesis

The objective of artistic style learning is to synthesize a new image from a source image with the style learnt from example images. Existing example-based texture synthesis (EBTS) techniques model style with low-level statistical properties. These methods work well with some artistic styles such as oil painting, but have difficulties in preserving image details and features for other styles, such as pencil hatching. In this article, an improved artistic style-learning algorithm with feature-based texture synthesis (FBTS) is introduced. Compared with existing EBTS methods, in our FBTS algorithm, image details and features are better defined with a feature field generated from the source image. Also, an improved L2 neighborhood distance metric which provides better measures of perceptual similarity is proposed. Results and comparisons are given to demonstrate the effectiveness of the FBTS algorithm with applications in the areas of stylized shading and artistic style transfer. © 2008 ACM.

Duke Scholars

Author Feng Tian DKU Faculty