Multiple-Hypothesis Affine Region Estimation With Anisotropic LoG Filters
We propose a method for estimating multiple-hypothesis affine regions from a keypoint by using an anisotropic Laplacian-of-Gaussian (LoG) filter. Although conventional affine region detectors, such as Hessian/Harris-Affine, iterate to find an affine region that fits a given image patch, such iterative searching is adversely affected by an initial point. To avoid this problem, we allow multiple detections from a single keypoint. We demonstrate that the responses of all possible anisotropic LoG filters can be efficiently computed by factorizing them in a similar manner to spectral SIFT. A large number of LoG filters that are densely sampled in a parameter space are reconstructed by a weighted combination of a limited number of representative filters, called ``eigenfilters", by using singular value decomposition. Also, the reconstructed filter responses of the sampled parameters can be interpolated to a continuous representation by using a series of proper functions. This results in efficient multiple extrema searching in a continuous space. Experiments revealed that our method has higher repeatability than the conventional methods.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Second-order Anisotropic Gaussian Directional Derivative Filters for Blob Detection
Interest point detection methods have received increasing attention and are widely used in computer vision tasks such as image retrieval and 3D reconstruction. In this work, second-order anisotropic Gaussian directional …
3D ReconstructionImage RetrievalInterest Point DetectionRetrievalYau's Affine Normal Descent: Algorithmic Framework and Convergence Analysis
We propose Yau's Affine Normal Descent (YAND), a geometric framework for smooth unconstrained optimization in which search directions are defined by the equi-affine normal of level-set hypersurfaces. The resulting direct…
Dimension-free Private Mean Estimation for Anisotropic Distributions
We present differentially private algorithms for high-dimensional mean estimation. Previous private estimators on distributions over $\mathbb{R}^d$ suffer from a curse of dimensionality, as they require $\Omega(d^{1/2})$…
A registration error estimation framework for correlative imaging
Correlative imaging workflows are now widely used in bioimaging and aims to image the same sample using at least two different and complementary imaging modalities. Part of the workflow relies on finding the transformati…
Making Affine Correspondences Work in Camera Geometry Computation
Local features e.g. SIFT and its affine and learned variants provide region-to-region rather than point-to-point correspondences. This has recently been exploited to create new minimal solvers for classical problems such…
Homography Estimationvalid