RECONSTRUCTING A SUPER-RESOLUTION IMAGE FOR DEPTH-VARYING SCENES(International Workshop on Advanced Image Technology 2009)
スポンサーリンク
概要
- 論文の詳細を見る
In this paper, we present a novel method for reconstructing a super-resolution image using multi-view low-resolution images captured for depth varying scene without requiring complex analysis such as depth estimation and feature matching. The proposed method is based on the iterative back projection technique that is extended to the 3D volume domain (i.e., space + depth), unlike the conventional superresolution methods that handle only 2D translation among captured images.
- 2009-01-05
著者
-
YOKOYAMA Ami
Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology
-
KUBOTA Akira
Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology
-
HATORI Yoshinori
Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology
関連論文
- RECONSTRUCTING A SUPER-RESOLUTION IMAGE FOR DEPTH-VARYING SCENES(International Workshop on Advanced Image Technology 2009)
- Optimization of MPEG-2 Bit Assignment Scheme with Full Use of Distortion Minimization Oriented Rate Control Technology
- A PERSONAL AUTHENTICATION FROM VIDEO USING HANDHELD CAMERA BY PARAMETRIC EIGENSPACE METHOD(International Workshop on Advanced Image Technology 2009)
- MODEL-BASED OBJECT RECOGNITION METHOD FROM VIDEO SEQUENCE USING COLOR INFORMATION(International Workshop on Advanced Image Technology 2006)
- Free Iris and Focus Image Generation by Merging Multiple Differently Focused Images Based on a Three-Dimensional Filtering(Advanced Image Technology)
- FREE VIEWPOINT VIDEO SYNTHESIS USING TWO DIFFERENTLY FOCUSED VIDEO(International Workshop on Advanced Image Technology 2006)
- FREE IRIS AND FOCUS IMAGE GENERATION BY MERGING MULTIPLE DIFFERENTLY FOCUSED IMAGES IN THE THREE-DIMENSIONAL FREQUENCY DOMAIN(International Workshop on Advanced Image Technology 2006)