Non-stationary Texture Synthesis by Adversarial Expansion
|Title:||Non-stationary Texture Synthesis by Adversarial Expansion|
|Date:||September 21, 2018 (Friday)|
|Time:||4:00 pm - 5:00 pm|
|Venue:||Room 121, 1/F, Ho Sin-hang Engineering Building, The Chinese University of Hong Kong, Shatin, N.T.|
|Speaker:|| Prof. Dani LISCHINSKI
School of Computer Science and Engineering
The Hebrew University of Jerusalem
The real world exhibits an abundance of non-stationary textures. Examples include textures with large scale structures, as well as spatially variant and inhomogeneous textures. While existing example-based texture synthesis methods can cope well with stationary textures, non-stationary textures still pose a considerable challenge, which remains unresolved. In this work, we propose a new approach for example-based non-stationary texture synthesis. Our approach uses a generative adversarial network (GAN), trained to double the spatial extent of texture blocks extracted from a specific texture exemplar. Once trained, the fully convolutional generator is able to expand the size of the entire exemplar, as well as of any of its sub-blocks. We demonstrate that this conceptually simple approach is highly effective for capturing large scale structures, as well as other non-stationary attributes of the input exemplar. As a result, it can cope with challenging textures, which, to our knowledge, no other existing method can handle.
Prof. Dani Lischinski received his PhD from Cornell University in 1994, and spent two years as a post-doctoral research associate at the University of Washington. Since 1996, he has been a professor at the School of Computer Science and Engineering of the Hebrew University of Jerusalem, Israel. In 2002/3, he spent a sabbatical year at Pixar Animation Studios. In 2012 he received the Eurographics Outstanding Technical Contributions Award, and served as the Technical Papers Chair for SIGGRAPH Asia 2017.
Prof. Lischinski has made numerous significant contributions in several areas of computer graphics, including photorealistic and non-photorealistic rendering, image-based modeling and rendering, texture synthesis, physically-based animation, high dynamic range tone mapping, and interactive manipulation and editing of images and video.
Joint work with: Yang Zhou, Zhen Zhu, Daniel Cohen-Or, and Hui Huang.
Enquiries: Ms. Crystal Tam at tel. 3943 8439
For more information, please refer to http://www.cse.cuhk.edu.hk/en/events
**** ALL ARE WELCOME ****