
GloballyOptimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence
Estimating the 6DoF pose of a camera from a single image relative to a ...
read it

GOGMA: GloballyOptimal Gaussian Mixture Alignment
Gaussian mixture alignment is a family of approaches that are frequently...
read it

Solving the Blind PerspectivenPoint Problem EndToEnd With Robust Differentiable Geometric Optimization
Blind PerspectivenPoint (PnP) is the problem of estimating the positio...
read it

An Efficient Solution to NonMinimal Case Essential Matrix Estimation
Finding relative pose between two calibrated views is a fundamental task...
read it

Learning 2D3D Correspondences To Solve The Blind PerspectivenPoint Problem
Conventional absolute camera pose via a PerspectivenPoint (PnP) solver...
read it

Do not Omit Local Minimizer: a Complete Solution for Pose Estimation from 3D Correspondences
Estimating pose from given 3D correspondences, including pointtopoint,...
read it

General techniques for approximate incidences and their application to the camera posing problem
We consider the classical camera pose estimation problem that arises in ...
read it
The Alignment of the Spheres: GloballyOptimal Spherical Mixture Alignment for Camera Pose Estimation
Determining the position and orientation of a calibrated camera from a single image with respect to a 3D model is an essential task for many applications. When 2D3D correspondences can be obtained reliably, perspectivenpoint solvers can be used to recover the camera pose. However, without the pose it is nontrivial to find crossmodality correspondences between 2D images and 3D models, particularly when the latter only contains geometric information. Consequently, the problem becomes one of estimating pose and correspondences jointly. Since outliers and local optima are so prevalent, robust objective functions and global search strategies are desirable. Hence, we cast the problem as a 2D3D mixture model alignment task and propose the first globallyoptimal solution to this formulation under the robust L_2 distance between mixture distributions. We derive novel bounds on this objective function and employ branchandbound to search the 6D space of camera poses, guaranteeing global optimality without requiring a pose estimate. To accelerate convergence, we integrate local optimization, implement GPU bound computations, and provide an intuitive way to incorporate side information such as semantic labels. The algorithm is evaluated on challenging synthetic and real datasets, outperforming existing approaches and reliably converging to the global optimum.
READ FULL TEXT
Comments
There are no comments yet.