Demos
Demonstrations provide researchers and practitioners with an exciting and interactive opportunity to present their systems, artifacts and/or research prototypes, either at a regular session or at the technical exhibition. In any case, it is required to avoid a commercial format, even if the demo consists of presenting a business product or service. Instead, the presentation should focus on technical aspects.
Any written support materials may be distributed locally but not published in the proceedings. Authors who already present a paper at the conference may apply for a demonstration, to complement but not to replace their paper presentation. Demonstrations can also be made by sponsor companies or as a mixed initiative involving researchers and industrial partners.
Demonstrations are based on an informal setting that encourages presenters and participants to engage in discussions about the presented work. This is an opportunity for the participants to disseminate practical results of their research and to network with other applied researchers or business partners.
Concerning the format of the demo, we can accommodate it either as a demonstration in a booth (physical area of 4 sq. meter, with a table and 2 chairs) at the exhibition area, as a poster or as a 20 min oral presentation at a session especially set up for demonstrations. It is also possible to organize the presentation of the same demo in more than one format.
Please contact the
event secretariat.
Super Resolution for Smartphones
Lecturer
|
Seiichi Gohshi
Kogakuin University
Japan
|
|
|
|
Brief Bio
Seiichi Gohshi is a professor of Kugakuin University. He received his BS degree, MS degree and PhD degree from Waseda University in 1979, 1981 and 1997. He joined Japan Broadcasting Corporation (NHK) in 1981. He started his research at NHK Science Technical Research Laboratories (STRL) in 1984. He helped to develop the HDTV broadcasting system, transmission systems, and signal processing systems. He was the project leader of the Super Hi-Vision (8K) transmission system and successfully conducted the first Super Hi-Vision transmission test at IBC2008. He also developed a watermark system that was used in movie theaters. He joined Sharp Corporation as a division deputy general manager in 2008 and developed high resolution systems. He is currently a professor of Kogakuin University. His research interests are video and image signal processing especially for super resolution and forensic technologies.
|
Smartphones are used for various applications, communication and work as an entertainment display for TV and film content, and video games. Compared with television (TV) and cinema screens, the display size of a smartphone is small. Despite the small display size, users enjoy various types of content on smartphones. Recently, Super Resolution (SR) technology has been proposed to improve image and video resolution. However, SR has been developed for TV and computer displays. At least a PC monitor is required to take advantage of the resolution improvement provided by SR. If SR were to be applied to smartphones, it would be difficult to see the improvement because of the small display size. In addition, SR technology algorithms are complex. All SR tasks, including video processing, are conducted by the CPU, and it is very difficult for CPUs to process videos in SR in real time. Consequently, there has been no report of SR being implemented on smartphones. Here, we propose SR for smartphones. The proposed method works in real time for video and can be handled by a smartphone CPU. The proposed method significantly improves video resolution without frame loss.
There is stiff competition in the smartphone market, and manufacturers are constantly trying to make their products stand out. Display resolution is one characteristic that is often used to bolster competitive advantage. HDTV resolution is common, and recently smartphones with 4K displays have become available. However, 4K displays are expensive, which increases the cost of smartphones. We demonstrate that a new software-based SR technique can improve resolution, which can make the product more desirable without changing the LCD panel from HD to 4K.
Our SR technique is a simple algorithm which can be handled by a smartphone’s CPU. At present, we have adopted the SR function only for videos. We plan to extend our SR method for still images and text. According to subjective assessments, SR processed text is crisp and easy to read even though the display contrast is reduced. We think that SR for text has the potential to extend the duration of smartphone batteries.
Plan for the Session: A smart phone with SR and similar products will be demonstrated to show image quality differences. A manual switch is implemented into the smartphone to turn the SR function on or off to compare resolution.