Stereo Vision for View Synthesis

Authors:
Daniel Scharstein
Affiliations:
-
Venue:
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Year:
1996

Citing 0
Cited 11

Photorealistic Scene Reconstruction by Voxel Coloring

International Journal of Computer Vision
An immersive 3D video-conferencing system using shared virtual team user environments

Proceedings of the 4th international conference on Collaborative virtual environments
Match Propogation for Image-Based Modeling and Rendering

IEEE Transactions on Pattern Analysis and Machine Intelligence
An introduction to image-based rendering

Integrated image and graphics technologies
The PCA reconstruction based approach for extending facial image databases for face recognition systems

Enhanced methods in computer security, biometric and artificial intelligence systems
Image-based rendering

Foundations and Trends® in Computer Graphics and Vision
Virtual view specification and synthesis for free viewpoint television

IEEE Transactions on Circuits and Systems for Video Technology
Stream-centric stereo matching and view synthesis: a high-speed approach on GPUs

IEEE Transactions on Circuits and Systems for Video Technology
View synthesis using stereo vision

View synthesis using stereo vision
Intermediate view synthesis and interpolation based on disparity calibration and region segmentation

MUSP'06 Proceedings of the 6th WSEAS international conference on Multimedia systems & signal processing
Who clicks there!: anonymising the photographer in a camera saturated society

Proceedings of the 10th annual ACM workshop on Privacy in the electronic society

Quantified Score

Hi-index	0.01

Visualization

Abstract

We propose a new method for view synthesis from real images using stereo vision. The method does not explicitly model scene geometry, and enables fast and exact generation of synthetic views. We also re-evaluate the requirements on stereo algorithms for the application of view synthesis and discuss ways of dealing with partially occluded regions of unknown depth and with completely occluded regions of unknown texture. Our experiments demonstrate that it is possible to efficiently synthesize realistic new views even from inaccurate and incomplete depth information.