A method for novel face view synthesis using stereo vision

Authors:
Jacek Komorowski;Przemyslaw Rokita
Affiliations:
Maria Curie-Skłodowska University, Institute of Computer Science, Lublin, Poland;Warsaw University of Technology, Institute of Computer Science, Warsaw, Poland
Venue:
ICCVG'10 Proceedings of the 2010 international conference on Computer vision and graphics: Part II
Year:
2010

Citing 6
Cited 0

A Flexible New Technique for Camera Calibration

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

International Journal of Computer Vision
Face Recognition Based on Fitting a 3D Morphable Model

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face recognition: A literature survey

ACM Computing Surveys (CSUR)
Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual Information

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
3D Videocommunication: Algorithms, concepts and real-time systems in human centred communication

3D Videocommunication: Algorithms, concepts and real-time systems in human centred communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a method for synthesis of a novel view of a human face using a pair of images from a stereo camera set. Unlike other published methods our approach does not require an a priori knowledge (e.g. 3D head model) of the synthesized object shape. First 3D shape of a face is recovered using stereo vision technique and then an image from a novel viewpoint in synthesized. Proposed method is applicable in various image-based pattern recognition and biometric tasks as it allows to partially alleviate dependency on object orientation in space.