1 October 2011 Temporally consistent depth map estimation based on 3D-MRF
Author Affiliations +
Proceedings Volume 8285, International Conference on Graphic and Image Processing (ICGIP 2011); 82856B (2011); doi: 10.1117/12.913467
Event: 2011 International Conference on Graphic and Image Processing, 2011, Cairo, Egypt
Abstract
Mutiview plus associated depth information form a typical 3D video representation. Depth map of each frame in a video sequence is usually estimated by stereo matching approaches separately. As a result it has weak temporal consistency. In this paper, we propose a novel framework based on spatio-temporal Markov Random Fields. It enforces temporal correlation by employing additional state in the graphical model. Improved belief propagation-sequential algorithm is exploited as an efficient optimization scheme to minimize the energy function. The experimental results demonstrate that the proposed method produces dependable depth maps in both spatial and temporal domain.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Li Yao, DongXiao Li, Ming Zhang, "Temporally consistent depth map estimation based on 3D-MRF", Proc. SPIE 8285, International Conference on Graphic and Image Processing (ICGIP 2011), 82856B (1 October 2011); doi: 10.1117/12.913467; https://doi.org/10.1117/12.913467
PROCEEDINGS
7 PAGES


SHARE
KEYWORDS
3D modeling

Video

3D image processing

Data modeling

Optimization (mathematics)

3D vision

Magnetorheological finishing

RELATED CONTENT

Rational supershapes for surface reconstruction
Proceedings of SPIE (May 29 2007)
Image-based modeling of objects and human faces
Proceedings of SPIE (December 22 2000)
Vision system for telerobotics operation
Proceedings of SPIE (October 01 1992)

Back to Top