| Paper ID | C-3-3.3 |
| Paper Title |
NITES: A NON-PARAMETRIC INTERPRETABLE TEXTURE SYNTHESIS METHOD |
| Authors |
Xuejing Lei, Ganning Zhao, C.-C. Jay Kuo, University of Southern California, United States |
| Session |
C-3-3: Machine Learning for Small-sample Data Analysis |
| Time | Thursday, 10 December, 17:30 - 19:30 |
| Presentation Time: | Thursday, 10 December, 18:00 - 18:15 Check your Time Zone |
|
All times are in New Zealand Time (UTC +13) |
| Topic |
Machine Learning and Data Analytics (MLDA): Special Session: Machine Learning for Small-sample Data Analysis |
| Abstract |
A non-parametric interpretable texture synthesis method, called NITES, is proposed in this work. Although automatic synthesis of visually pleasant texture can currently be achieved by deep neural networks, the associated generation models are mathematically intractable and their training demands higher computational cost. NITES offers a new texture synthesis solution to address these shortcomings. NITES is mathematically transparent and efficient in training and inference. The input is a single exemplary texture image. The NITES method crops out patches from the input and analyzes the statistical properties of these texture patches to obtain their joint spatial-spectral representations. Then, the probabilistic distributions of samples in the joint spatial-spectral spaces are characterized. Finally, numerous texture images that are visually similar to the exemplary texture image can be generated automatically. Experimental results are provided to show the superior quality of generated texture images and efficiency of the proposed NITES method in terms of both training and inference time. |