Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence

@article{Campbell2017GloballyOptimalIS,
  title={Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence},
  author={Dylan Campbell and Lars Petersson and Laurent Kneip and Hongdong Li},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={1-10}
}
Estimating the 6-DoF pose of a camera from a single image relative to a pre-computed 3D point-set is an important task for many computer vision applications. Perspective-n-Point (PnP) solvers are routinely used for camera pose estimation, provided that a good quality set of 2D-3D feature correspondences are known beforehand. However, finding optimal correspondences between 2D key-points and a 3D point-set is non-trivial, especially when only geometric (position) information is known. Existing… 

Figures and Tables from this paper

Globally-Optimal Inlier Set Maximisation for Camera Pose and Correspondence Estimation
TLDR
This work proposes a robust and globally-optimal inlier set maximisation approach that jointly estimates the optimal camera pose and correspondences, and outperforms existing approaches on challenging synthetic and real datasets, reliably finding the global optimum.
The Alignment of the Spheres: Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimation
TLDR
This work casts the problem as a 2D-3D mixture model alignment task and proposes the first globally-optimal solution to this formulation under the robust L2 distance between mixture distributions, guaranteeing global optimality without requiring a pose estimate.
Robust and Efficient Estimation of Absolute Camera Pose for Monocular Visual Odometry
TLDR
This work proposes a novel approach based on the robust "L2-minimizing estimate" (L2E) loss that can handle high outlier ratios, leading to high robustness and efficiency, and can run reliably regardless of whether the initial pose is appropriate, providing high generality.
Robust Estimation of Absolute Camera Pose via Intersection Constraint and Flow Consensus
TLDR
This paper proposes a general and accurate outlier removal strategy that can be integrated with various existing pose estimation methods originally vulnerable to outliers, and is applicable to points, lines, and the combination of both.
Robust Camera Pose Estimation via Consensus on Ray Bundle and Vector Field
TLDR
The proposed outlier removal strategy outperforms state-of-the-art outlier rejection methods in terms of accuracy and robustness and can be integrated into various existing camera pose estimation methods which are originally vulnerable to outliers.
2D-3D Point Set Registration Based on Global Rotation Search
TLDR
Compared with existing global optimization approaches, the proposed method utilizes a different problem formulation and more efficiently searches the translation space, which improves the registration speed and significantly outperformed the state-of-the-art local and global methods.
Learning 2D-3D Correspondences To Solve The Blind Perspective-n-Point Problem
TLDR
A deep CNN model which simultaneously solves for both the 6-DoF absolute camera pose and 2D--3D correspondences and is capable of processing thousands of points a second with the state-of-the-art accuracy.
GO-APSR: A Globally Optimal Affine Point Set Registration Method
TLDR
A deterministic global optimization method for affine point set registration, which works very well in the challenging partially-overlap scenarios and its robustness to noise and outliers is verified.
Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry
TLDR
This paper departs from the multi-person 3D pose estimation formulation, and instead reformulate it as crowd pose estimation, and consists of two key components: a graph model for fast cross-view matching, and a maximum a posteriori (MAP) estimator for the reconstruction of the 3D human poses.
Quasi-Globally Optimal and Efficient Vanishing Point Estimation in Manhattan World
TLDR
This work first compute two degrees of freedom of the above rotation by two sampled image lines, and then search for the optimal third DOF based on the branch-and-bound, which accelerates the authors' search by reducing the search space and simplifying the bound computation.
...
...

References

SHOWING 1-10 OF 53 REFERENCES
Pose Priors for Simultaneously Solving Alignment and Correspondence
TLDR
This paper models the camera pose space as a Gaussian Mixture Model that is progressively refine by hypothesizing new correspondences, which rapidly reduces the number of potential matches for each 3D point and lets us explore the pose space more thoroughly than SoftPosit at a similar computational cost.
Simultaneous Camera Pose and Correspondence Estimation with Motion Coherence
TLDR
An algorithm which jointly estimates camera pose and correspondence within a point set registration framework based on motion coherence, with the camera pose helping to localize the edge registration, while the “ambiguous” edge information helps to guide camera pose computation.
SoftPOSIT: Simultaneous Pose and Correspondence Determination
TLDR
A new algorithm, called SoftPOSIT, for determining the pose of a 3D object from a single 2D image when correspondences between object points and image points are not known, which has an asymptotic run-time complexity that is better than previous methods by a factor of the number of image points.
A novel parametrization of the perspective-three-point problem for a direct computation of absolute camera position and orientation
TLDR
This paper proposes a novel closed-form solution to the P3P problem, which computes the aligning transformation directly in a single stage, without the intermediate derivation of the points in the camera frame, at much lower computational cost.
Accurate Localization and Pose Estimation for Large 3D Models
TLDR
Experimental results are given demonstrating that it is possible to reliably estimate the camera pose despite more than 99% of outlier correspondences.
SDICP: Semi-Dense Tracking based on Iterative Closest Points
TLDR
The goal of the present paper is a novel 2D-3D registration paradigm for semi-dense depth maps that relies on the Iterative Closest Point (ICP) technique, and thus a reintroduction of geometric error minimization as a valid alternative for real-time monocular camera tracking in the case of semi-Dense features.
City-Scale Localization for Cameras with Known Vertical Direction
TLDR
This work considers the problem of localizing a novel image in a large 3D model, given that the gravitational vector is known, and extends accurate approximations and fast polynomial solvers to camera pose estimation.
Optimal Relative Pose with Unknown Correspondences
TLDR
This paper shows that it is feasible to compute both the epipolar geometry and the correspondences at the same time based on geometry only and demonstrates that more difficult cases can be handled and that more inlier correspondences can be obtained by being less restrictive in the matching phase.
Branch-and-Bound Methods for Euclidean Registration Problems
TLDR
The optimization scheme is based on ideas from global optimization theory, in particular convex underestimators in combination with branch-and-bound methods, and provides a provably optimal algorithm and demonstrates good performance on both synthetic and real data.
Robust and Optimal Sum-of-Squares-Based Point-to-Plane Registration of Image Sets and Structured Scenes
TLDR
A Sum-of-Squares optimization theory framework is employed for identifying point-to-plane mismatches (i.e. outliers) with certainty and an inliers-maximization approach within a Branch-and-Bound (BnB) search scheme is adopted.
...
...