A batch Algorithm for Implicit Non-Rigid Shape and Motion Recovery

TY - GEN

T1 - A batch Algorithm for Implicit Non-Rigid Shape and Motion Recovery

AU - Bartoli, Adrien

AU - Olsen, Søren Ingvor

N1 - Conference code: 10

PY - 2007

Y1 - 2007

N2 - The recovery of 3D shape and camera motion for non-rigid scenes from single-camera video footage is a very important problem in computer vision. The low-rank shape model consists in regarding the deformations as linear combinations of basis shapes. Most algorithms for reconstructing the parameters of this model along with camera motion are based on three main steps. Given point tracks and the rank, or equivalently the number of basis shapes, they factorize a measurement matrix containing all point tracks, from which the camera motion and basis shapes are extracted and refined in a bundle adjustment manner. There are several issues that have not been addressed yet, among which, choosing the rank automatically and dealing with erroneous point tracks and missing data. We introduce theoretical and practical contributions that address these issues. We propose an implicit imaging model for non-rigid scenes from which we derive non-rigid matching tensors and closure constraints. We give a non-rigid Structure-From-Motion algorithm based on computing matching tensors over subsequences, from which the implicit cameras are extrated. Each non-rigid matching tensor is computed, along with the rank of the subsequence, using a robust estimator incorporating a model selection criterion that detects erroneous image points. Preliminary experimental results on real and simulated data show that our algorithm deals with challenging video sequences.

AB - The recovery of 3D shape and camera motion for non-rigid scenes from single-camera video footage is a very important problem in computer vision. The low-rank shape model consists in regarding the deformations as linear combinations of basis shapes. Most algorithms for reconstructing the parameters of this model along with camera motion are based on three main steps. Given point tracks and the rank, or equivalently the number of basis shapes, they factorize a measurement matrix containing all point tracks, from which the camera motion and basis shapes are extracted and refined in a bundle adjustment manner. There are several issues that have not been addressed yet, among which, choosing the rank automatically and dealing with erroneous point tracks and missing data. We introduce theoretical and practical contributions that address these issues. We propose an implicit imaging model for non-rigid scenes from which we derive non-rigid matching tensors and closure constraints. We give a non-rigid Structure-From-Motion algorithm based on computing matching tensors over subsequences, from which the implicit cameras are extrated. Each non-rigid matching tensor is computed, along with the rank of the subsequence, using a robust estimator incorporating a model selection criterion that detects erroneous image points. Preliminary experimental results on real and simulated data show that our algorithm deals with challenging video sequences.

U2 - 10.1007/978-3-540-70932-9_20

DO - 10.1007/978-3-540-70932-9_20

M3 - Article in proceedings

SN - 978-3-540-70931-2

T3 - Lecture notes in computer science

SP - 257

EP - 269

BT - Dynamical Vision

A2 - Vidal, Rene

A2 - Heyden, Anders

A2 - Ma, Yi

PB - Springer

T2 - Workshop of Dynamical Models for Computer Vision at IEEE International Conference on Computer Vision (ICCV)

Y2 - 21 October 2005

ER -