Style-learning with feature-based texture synthesis.

This source preferred by Feng Tian

Authors: Xie, X.X., Tian, F. and Seah, H.S.

Journal: Computers in Entertainment (CIE)

Volume: 6

Publisher: ACM

ISSN: 1544-3574

DOI: 10.1145/1371216.1371228

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.

This data was imported from DBLP:

Authors: Xie, X., Tian, F. and Seah, H.S.

Journal: Computers in Entertainment

Volume: 6

Pages: 25:1

The data on this page was last updated at 10:28 on April 24, 2019.