|
|
 |
HOME | |
Research | |
Publications | ||||||||
Non-rigid Structure from MotionLourdes de Agapito Vicente, Xavier Llado and Alessio Del BueWe investigate a free-form inference of the 3-D information about the world that can be extracted directly from image sequences taken from a moving camera. Such inference can only succeed if certain assumptions are made, the standard being that the scene observed by the camera is rigid. |
|
Recent studies on non-rigid factorisation have demonstrated that it is possible, under certain viewing conditions, to infer the principal modes of deformation of an object alongside its 3-D shape within a structure from motion estimation framework. The models recovered by these algorithms, in which deformations are represented as linear combinations of a number of detected modes, can subsequently be used as compact representation of the object suitable for use in tracking, animation, or other analysis. |
| We are aiming both to extend and improve factorisation methods and to apply them to the domain of human motion analysis - in particular to the 3-D reconstruction of facial motion. |
Related PublicationsX. Llado, A Del Bue, L. Agapito. Recovering Euclidean Deformable Models from Stereo-motion. To appear in International Conference on Pattern Recognition 2008, Tampa, USA, ICPR 2008. A. Del Bue, F. Smeraldi, L. Agapito. Non-rigid structure from motion using ranklet-based tracking and non-linear optimization. Image and Vision Computing (IVC) 2007. A. Del Bue and L. Agapito. Non-rigid Stereo Factorization. International Journal of Computer Vision (IJCV) 2006. A. Del Bue and L. Agapito. Non-rigid Stereo-Motion. In Scene Reconstruction, Pose Estimation and Tracking, 2007, Edited by: Rustam Stolkin. A. Del Bue, X. Llado and L. Agapito. Segmentation of Rigid Motion from Non-rigid 2D Trajectories. LNCS 4477. Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA2007). A. Del Bue, X. Llado and L. Agapito. Non-Rigid Metric Shape and Motion Recovery from Uncalibrated Images Using Priors. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2006). X. Llado, A. Del Bue and L. Agapito. Euclidean Reconstruction of Deformable Structure Using a Perspective Camera with Varying Intrinsic Parameters. International Conference on Pattern Recognition (ICPR), 20-24 August 2006, Hong Kong. A. Del Bue. Deformable 3-D Modelling from Uncalibrated Video Sequences. Ph.D. Thesis, Queen Mary University of London. 2006. X. Llado, A. Del Bue and L. Agapito. Euclidean Reconstruction of Deformable Structure Using a Perspective Camera with Varying Intrinsic Parameters. International Conference on Pattern Recognition (ICPR), 2006. A. Del Bue, X. Llado and L. Agapito. Non-Rigid Metric Shape and Motion Recovery from Uncalibrated Images Using Priors. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2006). E. Muñoz, A. Del Bue, J. Buenaposada, L. Baumela and L. Agapito. Automatic modelling and efficient tracking of deformable objects. IEE International Conference on Visual Information Engineering, Glasgow, UK, April 2005. A. Del Bue, L. Agapito. Non-rigid 3D shape recovery using stereo factorization. Asian Conference of Computer Vision (ACCV2004), Jeju, South Korea, Vol. 1, 25-30, January 2004 |
Current Research |
|
Non-linear optimization for non-rigid structure from motion
We infer the motion, structure and deformation components of a nonrigid object by minimizing a meaningful geometric cost function. Our minimization framework based on bundle adjustment is capable of estimating reliably the model parameters. |
|
Non-rigid Stereo Factorization
We propose a factorization method for constructing a 3D deformable model from stereo video sequences. The calibration of the stereo setup is unknown, the reconstruction is based only on the 2D correspondences from each sequence. |
|
Efficient tracking of nonrigid objects
We develop an efficient system for tracking deformable objects with models derived from the non-rigid factorization framework. The algorithm can cope with different pose and appearance changes. In collaboration with the Departamento de Inteligencia Artificial of the University Politècnica de Madrid |
| Updated Aug 2008 by Alessio Del Bue |