| Project/Area Number |
19300023
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Media informatics/Database
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
YAMAGUCHI Yasushi The University of Tokyo, 大学院・総合文化研究科, 教授 (80210376)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
KANAI Takashi 東京大学, 大学院・総合文化研究科, 准教授 (60312261)
|
|---|
| Co-Investigator(Renkei-kenkyūsha) |
KANAI Takashi 東京大学, 大学院・総合文化研究科, 准教授 (60312261)
|
|---|
| Project Period (FY) |
2007 – 2009
|
| Project Status |
Completed (Fiscal Year 2009)
|
| Budget Amount *help |
¥18,850,000 (Direct Cost: ¥14,500,000、Indirect Cost: ¥4,350,000)
Fiscal Year 2009: ¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2008: ¥8,840,000 (Direct Cost: ¥6,800,000、Indirect Cost: ¥2,040,000)
Fiscal Year 2007: ¥6,110,000 (Direct Cost: ¥4,700,000、Indirect Cost: ¥1,410,000)
|
|---|
| Keywords | グラフィクス / 実世界情報処理 / メディア情報処理 / 並列計算 / 多次元データ |
|---|
| Research Abstract |
Multi-dimensional data such as 3D spatial data, image, video and so on is rapidly increasing. This research aims at developing a novel method of natural and completion instead of simple interpolation by analyzing multi-dimensional data and extracting characteristic values. Efficiency is one of the most important aspect to achieve natural completion because it is crucial to analyze huge multi-dimensional data. The project tried two approaches to this efficiency, namely, "efficient computation with SIMD processor" and "efficient computation by statistical algorithm". As for the former attempt, we focused on rendering of massive volume data and succeeded to accomplish the efficient implementation which allows GPU's full performance. As for the latter attempt, we experimented on facial-impression operation. We have succeeded to implement facial beautification method which preserves apparent age of the original face.
|
