Abstract
In this paper, we will present methods for camera pose estimation for mixed and diminished reality visualization in FTV application. We first present Viewpoint Generative Learning (VGL) based on 3D scene model reconstructed using multiple cameras including RGB-D camera. In VGL, a database of feature descriptors is generated for the 3D scene model to make the pose estimation robust to viewpoint change. Then we introduce an application of VGL to diminished reality. We also present our novel line feature descriptor, LEHF, which is also be applied to a line-based SLAM and improving camera pose estimation.
| Original language | English |
|---|---|
| Title of host publication | 3DTV-Conference |
| Publisher | IEEE Computer Society |
| ISBN (Print) | 9781479947584 |
| DOIs | |
| Publication status | Published - 2014 |
| Event | 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video, 3DTV-CON 2014 - Budapest, Hungary Duration: 2014 Jul 2 → 2014 Jul 4 |
Other
| Other | 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video, 3DTV-CON 2014 |
|---|---|
| Country | Hungary |
| City | Budapest |
| Period | 14/7/2 → 14/7/4 |
Fingerprint
Keywords
- augmented reality
- camera calibration
- feature descriptor
- free viewpoint image synthesis
- see-through vision
ASJC Scopus subject areas
- Computer Graphics and Computer-Aided Design
- Computer Networks and Communications
- Computer Vision and Pattern Recognition
- Human-Computer Interaction
- Electrical and Electronic Engineering
Cite this
Camera pose estimation for mixed and diminished reality in FTV. / Saito, Hideo; Honda, Toshihiro; Nakayama, Yusuke; De Sorbier, Francois.
3DTV-Conference. IEEE Computer Society, 2014. 6874756.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Camera pose estimation for mixed and diminished reality in FTV
AU - Saito, Hideo
AU - Honda, Toshihiro
AU - Nakayama, Yusuke
AU - De Sorbier, Francois
PY - 2014
Y1 - 2014
N2 - In this paper, we will present methods for camera pose estimation for mixed and diminished reality visualization in FTV application. We first present Viewpoint Generative Learning (VGL) based on 3D scene model reconstructed using multiple cameras including RGB-D camera. In VGL, a database of feature descriptors is generated for the 3D scene model to make the pose estimation robust to viewpoint change. Then we introduce an application of VGL to diminished reality. We also present our novel line feature descriptor, LEHF, which is also be applied to a line-based SLAM and improving camera pose estimation.
AB - In this paper, we will present methods for camera pose estimation for mixed and diminished reality visualization in FTV application. We first present Viewpoint Generative Learning (VGL) based on 3D scene model reconstructed using multiple cameras including RGB-D camera. In VGL, a database of feature descriptors is generated for the 3D scene model to make the pose estimation robust to viewpoint change. Then we introduce an application of VGL to diminished reality. We also present our novel line feature descriptor, LEHF, which is also be applied to a line-based SLAM and improving camera pose estimation.
KW - augmented reality
KW - camera calibration
KW - feature descriptor
KW - free viewpoint image synthesis
KW - see-through vision
UR - http://www.scopus.com/inward/record.url?scp=84906568736&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84906568736&partnerID=8YFLogxK
U2 - 10.1109/3DTV.2014.6874756
DO - 10.1109/3DTV.2014.6874756
M3 - Conference contribution
AN - SCOPUS:84906568736
SN - 9781479947584
BT - 3DTV-Conference
PB - IEEE Computer Society
ER -