Shape and motion from image streams under orthography: a factorization method
International Journal of Computer Vision
A Multibody Factorization Method for Independently Moving Objects
International Journal of Computer Vision
Multiple view geometry in computer vision
Multiple view geometry in computer vision
A Factorization Based Algorithm for Multi-Image Projective Structure and Motion
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume II - Volume II
Linear Multi View Reconstruction with Missing Data
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part II
Plane+Parallax, Tensors and Factorization
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part I
Separability of Pose and Expression in Facial Tracking and Animation
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Journal of Cognitive Neuroscience
An iterative image registration technique with an application to stereo vision
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
| Hi-index | 0.00 |
The recovering of 3D shape from video sequences has been one of the most important computer vision problems in the last ten years. For the case of rigid scenes, linear and factorization approaches have been developed. However, for non-rigid scenes only factorization methods for parallel projection, based on the Tomasi-Kanade's factorization method, have been proposed. In this paper we study the case of perspective cameras for non-rigid scenes. Our approach makes use of recent results of the plane+parallax representation for rigid scene. We show that it is possible, from a reference system defined on a particular plane of the scene, to estimate the 3D Euclidean coordinates of the moving points and the camera center.