CGA-PoseNet: Camera Pose Regression via a 1D-Up Approach to Conformal Geometric Algebra

by   Alberto Pepe, et al.

We introduce CGA-PoseNet, which uses the 1D-Up approach to Conformal Geometric Algebra (CGA) to represent rotations and translations with a single mathematical object, the motor, for camera pose regression. We do so starting from PoseNet, which successfully predicts camera poses from small datasets of RGB frames. State-of-the-art methods, however, require expensive tuning to balance the orientational and translational components of the camera pose.This is usually done through complex, ad-hoc loss function to be minimized, and in some cases also requires 3D points as well as images. Our approach has the advantage of unifying the camera position and orientation through the motor. Consequently, the network searches for a single object which lives in a well-behaved 4D space with a Euclidean signature. This means that we can address the case of image-only datasets and work efficiently with a simple loss function, namely the mean squared error (MSE) between the predicted and ground truth motors. We show that it is possible to achieve high accuracy camera pose regression with a significantly simpler problem formulation. This 1D-Up approach to CGA can be employed to overcome the dichotomy between translational and orientational components in camera pose regression in a compact and elegant way.


page 1

page 2

page 3

page 4


Adversarial Joint Image and Pose Distribution Learning for Camera Pose Regression and Refinement

In this paper we present a deep-learning based framework for direct came...

Homography-Based Loss Function for Camera Pose Regression

Some recent visual-based relocalization algorithms rely on deep learning...

Improving Image-Based Localization with Deep Learning: The Impact of the Loss Function

This work formulates a novel loss term which can be appended to an RGB o...

Geometric Loss Functions for Camera Pose Regression with Deep Learning

Deep learning has shown to be effective for robust and real-time monocul...

Euler angles based loss function for camera relocalization with Deep learning

Deep learning has been applied to camera relocalization, in particular, ...

ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression Framework

In this paper, a computation efficient regression framework is presented...

Please sign up or login with your details

Forgot password? Click here to reset