Abstract | ||
---|---|---|
Textural style transfer aims to transfer the textural style identified from a reference image to a source image, while retaining the scene of the source image. This article proposes a context-aware style transfer algorithm based on sparse-representation-based textural synthesis. Whereas sparse representation is designed to extract the style component of the exemplar image, textural synthesis is performed in a context-aware setting to preserve the original scene structure of the source image. Unlike existing solutions that require prior knowledge of the textural style of interest or user interaction, this method performs the transfer automatically. Experimental results demonstrate the effectiveness of the proposed method for automatic style transfer from a single style template image that is not accompanied with its original real image. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/MMUL.2016.36 | IEEE MultiMedia |
Keywords | Field | DocType |
Dictionaries,Hafnium,Indexes,Standards,Silicon,Data mining,Image color analysis | Graphics,Computer vision,Computer graphics (images),Computer science,Sparse approximation,Reference image,Artificial intelligence,Real image,Multimedia | Journal |
Volume | Issue | ISSN |
23 | 4 | 1070-986X |
Citations | PageRank | References |
3 | 0.37 | 10 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kai-Han Lo | 1 | 35 | 2.29 |
Yu-Chiang Frank Wang | 2 | 914 | 61.63 |
Kai-Lung Hua | 3 | 265 | 42.99 |