Loading...
Please wait, while we are loading the content...
Similar Documents
A Variety of Choice Methods for Image-Based Artistic Rendering
| Content Provider | MDPI |
|---|---|
| Author | Lin, Chiu-Chin Hsu, Chih-Bin Lee, Jen-Chun Chen, Chung-Hsien Tu, Te-Ming Huang, Huang-Chu |
| Copyright Year | 2022 |
| Description | Neural style transfer (NST) is a technique based on the deep learning of a convolutional neural network (CNN) to create entertaining pictures by cleverly stylizing ordinary pictures with the predetermined visual art style. However, three issues must be carefully investigated during the generation of neural-stylized artwork: the color scheme, the strength of style of the strokes, and the adjustment of image contrast. To solve these problems and select image colorization based on personal preference, in this paper, we propose modified universal-style transfer (UST) method combined with the image fusion and color enhancement methods to design a good post-processing framework to tackle the three above-mentioned issues simultaneously. This work provides more visual effects for stylized images, and also can integrate into the UST method effectively. In addition, the proposed method is suitable for stylized images generated by any NST method, but it also works similarly to the Multi-Style Transfer (MST) method, which mixes two different stylized images. Finally, our proposed method successfully combined the modified UST method and post-processing method to meet personal preference. |
| Starting Page | 6710 |
| e-ISSN | 20763417 |
| DOI | 10.3390/app12136710 |
| Journal | Applied Sciences |
| Issue Number | 13 |
| Volume Number | 12 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2022-07-02 |
| Access Restriction | Open |
| Subject Keyword | Applied Sciences Artificial Intelligence Blending Technique Deep Learning Neural Style Transfer Intensity Conservation Direct Decorrelation Stretch |
| Content Type | Text |
| Resource Type | Article |
