Principal Warps: Thin-Plate Splines and the Decomposition of Deformations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape Matching and Object Recognition Using Shape Contexts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Approximate Thin Plate Spline Mappings
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
A new point matching algorithm for non-rigid registration
Computer Vision and Image Understanding - Special issue on nonrigid image registration
Robust Regression with Projection Based M-estimators
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Matching with PROSAC " Progressive Sample Consensus
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
The Modified pbM-Estimator Method and a Runtime Analysis Technique for the RANSAC Family
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Flexible Spatial Configuration of Local Image Features
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast Non-Rigid Surface Detection, Registration and Realistic Augmentation
International Journal of Computer Vision
Maximizing the Predictivity of Smooth Deformable Image Warps through Cross-Validation
Journal of Mathematical Imaging and Vision
Direct Estimation of Nonrigid Registrations with Image-Based Self-Occlusion Reasoning
IEEE Transactions on Pattern Analysis and Machine Intelligence
Rejecting Mismatches by Correspondence Function
International Journal of Computer Vision
Feature-Based Deformable Surface Detection with Self-Occlusion Reasoning
International Journal of Computer Vision
Hi-index | 0.00 |
This paper concerns the robust estimation of non-rigid deformations from feature correspondences. We advance the surprising view that for many realistic physical deformations, the error of the mismatches (outliers) usually dwarfs the effects of the curvature of the manifold on which the correct matches (inliers) lie, to the extent that one can tightly enclose the manifold within the error bounds of a low-dimensional hyperplane for accurate outlier rejection. This justifies a simple RANSAC-driven deformable registration technique that is at least as accurate as other methods based on the optimisation of fully deformable models. We support our ideas with comprehensive experiments on synthetic and real data typical of the deformations examined in the literature.