Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimization

07/29/2020
by   Dylan Campbell, et al.
0

Blind Perspective-n-Point (PnP) is the problem of estimating the position and orientation of a camera relative to a scene, given 2D image points and 3D scene points, without prior knowledge of the 2D-3D correspondences. Solving for pose and correspondences simultaneously is extremely challenging since the search space is very large. Fortunately it is a coupled problem: the pose can be found easily given the correspondences and vice versa. Existing approaches assume that noisy correspondences are provided, that a good pose prior is available, or that the problem size is small. We instead propose the first fully end-to-end trainable network for solving the blind PnP problem efficiently and globally, that is, without the need for pose priors. We make use of recent results in differentiating optimization problems to incorporate geometric model fitting into an end-to-end learning framework, including Sinkhorn, RANSAC and PnP algorithms. Our proposed approach significantly outperforms other methods on synthetic and real data.

READ FULL TEXT
research
03/15/2020

Learning 2D-3D Correspondences To Solve The Blind Perspective-n-Point Problem

Conventional absolute camera pose via a Perspective-n-Point (PnP) solver...
research
09/27/2017

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

Estimating the 6-DoF pose of a camera from a single image relative to a ...
research
03/17/2019

General techniques for approximate incidences and their application to the camera posing problem

We consider the classical camera pose estimation problem that arises in ...
research
12/04/2018

The Alignment of the Spheres: Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimation

Determining the position and orientation of a calibrated camera from a s...
research
08/07/2019

Expert Sample Consensus Applied to Camera Re-Localization

Fitting model parameters to a set of noisy data points is a common probl...
research
11/16/2017

Learning to Find Good Correspondences

We develop a deep architecture to learn to find good correspondences for...
research
03/10/2020

PnP-Net: A hybrid Perspective-n-Point Network

We consider the robust Perspective-n-Point (PnP) problem using a hybrid ...

Please sign up or login with your details

Forgot password? Click here to reset