Exploiting spatial-temporal coherence in the construction of multiple perspective videos

Authors:
Mau-Tsuen Yang;Shih-Yu Huang;Kuo-Hua Lo;Wen-Kai Tai;Cheng-Chin Chiang
Affiliations:
Department of Computer Science & Information Engineering, National Dong-Hua University, Taiwan;Department of Computer Science & Information Engineering, National Dong-Hua University, Taiwan;Department of Computer Science & Information Engineering, National Dong-Hua University, Taiwan;Department of Computer Science & Information Engineering, National Dong-Hua University, Taiwan;Department of Computer Science & Information Engineering, National Dong-Hua University, Taiwan
Venue:
PSIVT'06 Proceedings of the First Pacific Rim conference on Advances in Image and Video Technology
Year:
2006

Citing 10
Cited 0

View interpolation for image synthesis

SIGGRAPH '93 Proceedings of the 20th annual conference on Computer graphics and interactive techniques
View morphing

SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
SUSAN—A New Approach to Low Level Image Processing

International Journal of Computer Vision
Computer Vision

Computer Vision
Digital Image Processing

Digital Image Processing
Spatio-temporal view interpolation

EGRW '02 Proceedings of the 13th Eurographics workshop on Rendering
Scalable 3D Representation for 3D Video Display in a Large-scale Space

VR '03 Proceedings of the IEEE Virtual Reality 2003
Generation of multiviewpoint video from stereoscopic video

IEEE Transactions on Consumer Electronics
Real-time dynamic 3-D object shape reconstruction and high-fidelity texture mapping for 3-D video

IEEE Transactions on Circuits and Systems for Video Technology
Adaptive reconstruction of intermediate views from stereoscopic images

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

We implement an image-based system that constructs multiple perspective videos with active objects using an off-the-shelf PC and digital video camcorders without the need of advanced calibration and 3D model reconstruction. Especially, temporal coherence is exploited to speedup the correspondence search. Spatial coherence is exploited for occlusion recovery to improve the quality of the generated images. The proposed system can automatically establish dense correspondence and construct virtual views on-line according to user instructions.