Binocular Image Flows: Steps Toward Stereo-Motion Fusion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Readings in computer vision: issues, problems, principles, and paradigms
Shape and motion from image streams under orthography: a factorization method
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
Bundle Adjustment - A Modern Synthesis
ICCV '99 Proceedings of the International Workshop on Vision Algorithms: Theory and Practice
Stereo-Motion that Complements Stereo and Motion Analyses
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Direct Estimation of Motion and Extended Scene Structure from a Moving Stereo Rig
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Uncalibrated Perspective Reconstruction of Deformable Structures
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Non-Rigid Metric Shape and Motion Recovery from Uncalibrated Images Using Priors
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
SVD-matching using SIFT features
Graphical Models - Special issue on the vision, video and graphics conference 2005
Non-rigid structure from motion using ranklet-based tracking and non-linear optimization
Image and Vision Computing
Structure and motion of nonrigid object under perspective projection
Pattern Recognition Letters
Nonrigid Structure-from-Motion: Estimating Shape and Motion with Hierarchical Priors
IEEE Transactions on Pattern Analysis and Machine Intelligence
Segmentation of Rigid Motion from Non-rigid 2D Trajectories
IbPRIA '07 Proceedings of the 3rd Iberian conference on Pattern Recognition and Image Analysis, Part I
Perspective Nonrigid Shape and Motion Recovery
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
A featureless and stochastic approach to on-board stereo vision system pose
Image and Vision Computing
Video synchronization from human motion using rank constraints
Computer Vision and Image Understanding
Non-rigid metric reconstruction from perspective cameras
Image and Vision Computing
Nonrigid shape and motion from multiple perspective views
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
A unified view on deformable shape factorizations
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI
Hi-index | 0.10 |
Several non-rigid structure from motion methods have been proposed so far in order to recover both the motion and the non-rigid structure of an object. However, these monocular algorithms fail to give reliable 3D shape estimates when the overall rigid motion of the sequence is small. Aiming to overcome this limitation, in this paper we propose a novel approach for the 3D Euclidean reconstruction of deformable objects observed by an uncalibrated stereo rig. Using a stereo setup drastically improves the 3D model estimation when the observed 3D shape is mostly deforming without undergoing strong rigid motion. Our approach is based on the following steps. Firstly, the stereo system is automatically calibrated and used to compute metric rigid structures from pairs of views. Afterwards, these 3D shapes are aligned to a reference view using a RANSAC method in order to compute the mean shape of the object and to select the subset of points which have remained rigid throughout the sequence. The selected rigid points are then used to compute frame-wise shape registration and to robustly extract the motion parameters from frame to frame. Finally, all this information is used as initial estimates of a non-linear optimization which allows us to refine the initial solution and also to recover the non-rigid 3D model. Exhaustive results on synthetic and real data prove the performance of our proposal estimating motion, non-rigid models and stereo camera parameters even when there is no rigid motion in the original sequence.