A Method for Enforcing Integrability in Shape from Shading Algorithms
IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient Region Tracking With Parametric Models of Geometry and Illumination
IEEE Transactions on Pattern Analysis and Machine Intelligence
International Journal of Computer Vision
Hyperplane Approximation for Template Matching
IEEE Transactions on Pattern Analysis and Machine Intelligence
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Projective registration with difference decomposition
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Lucas-Kanade 20 Years On: A Unifying Framework
International Journal of Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Active Appearance Models Revisited
International Journal of Computer Vision
Deformation Invariant Image Matching
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Recovering 3D Human Pose from Monocular Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Data Driven Image Models through Continuous Joint Alignment
IEEE Transactions on Pattern Analysis and Machine Intelligence
BM3E: Discriminative Density Propagation for Visual Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast Non-Rigid Surface Detection, Registration and Realistic Augmentation
International Journal of Computer Vision
Efficient MRF deformation model for non-rigid image matching
Computer Vision and Image Understanding
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
Continuous regression for non-rigid image alignment
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Hi-index | 0.00 |
Image alignment in the presence of non-rigid distortions is a challenging task. Typically, this involves estimating the parameters of a dense deformation field that warps a distorted image back to its undistorted template. Generative approaches based on parameter optimization such as Lucas-Kanade can get trapped within local minima. On the other hand, discriminative approaches like nearest-neighbor require a large number of training samples that grows exponentially with respect to the dimension of the parameter space, and polynomially with the desired accuracy 1/驴. In this work, we develop a novel data-driven iterative algorithm that combines the best of both generative and discriminative approaches. For this, we introduce the notion of a "pull-back" operation that enables us to predict the parameters of the test image using training samples that are not in its neighborhood (not 驴-close) in the parameter space. We prove that our algorithm converges to the global optimum using a significantly lower number of training samples that grows only logarithmically with the desired accuracy. We analyze the behavior of our algorithm extensively using synthetic data and demonstrate successful results on experiments with complex deformations due to water and clothing.