Virtual view synthesis using multi-view video sequences

Authors:
Il-Lyong Jung;Taeyoung Chung;Kwanwoong Song;Chang-Su Kim
Affiliations:
School of Electrical Engineering, Korea University, Seoul, Korea;School of Electrical Engineering, Korea University, Seoul, Korea;School of Electrical Engineering, Korea University, Seoul, Korea;School of Electrical Engineering, Korea University, Seoul, Korea
Venue:
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Year:
2009

Citing 4
Cited 1

A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

International Journal of Computer Vision
Symmetric Stereo Matching for Occlusion Handling

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Efficient Belief Propagation for Early Vision

International Journal of Computer Vision
Specifying Virtual Cameras in Uncalibrated View Synthesis

IEEE Transactions on Circuits and Systems for Video Technology

On multi-view video segmentation for object-based coding

Digital Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A virtual view synthesis algorithm using multi-view video sequences, which inherits the advantages of both the forward warping and the inverse warping, is proposed in this work. First, we use the inverse warping to synthesize a virtual view without holes from the nearest two views. Second, we detect occluded regions in the synthesized view based on the uniqueness constraint. Then, we refine the occluded regions using the information in the farther views based on the forward warping technique. Simulation results demonstrate that the proposed algorithm provides significantly higher PSNR performances than the conventional inverse warping scheme.