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

arXiv: https://arxiv.org/abs/2302.05211 · HTML: https://mlsanity.com/paper/2302.05211/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 53 references that are in the map.
- First posted on arXiv 10 Feb 2023.

## Builds on (most cited first, 18 of 18)

- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [INeRF: Inverting Neural Radiance Fields for Pose Estimation](https://mlsanity.com/paper/2012.05877/) (2020)
- [Geometric Loss Functions for Camera Pose Regression with Deep Learning](https://mlsanity.com/paper/1704.00390/) (2017)
- [Learning to Find Good Correspondences](https://mlsanity.com/paper/1711.05971/) (2017)
- [Image-based localization using LSTMs for structured feature correlation](https://mlsanity.com/paper/1611.07890/) (2016)
- [Modelling Uncertainty in Deep Learning for Camera Relocalization](https://mlsanity.com/paper/1509.05909/) (2015)
- [QuaterNet: A Quaternion-based Recurrent Model for Human Motion](https://mlsanity.com/paper/1805.06485/) (2018)
- [Wide-Baseline Relative Camera Pose Estimation with Directional Learning](https://mlsanity.com/paper/2106.03336/) (2021)
- [Camera-to-Robot Pose Estimation from a Single Image](https://mlsanity.com/paper/1911.09231/) (2019)
- [Relative Camera Pose Estimation Using Convolutional Neural Networks](https://mlsanity.com/paper/1702.01381/) (2017)
- [Deep Learning on Lie Groups for Skeleton-based Action Recognition](https://mlsanity.com/paper/1612.05877/) (2016)
- [RPNet: an End-to-End Network for Relative Camera Pose Estimation](https://mlsanity.com/paper/1809.08402/) (2018)
- [Pose-GNN : Camera Pose Estimation System Using Graph Neural Networks](https://mlsanity.com/paper/2103.09435/) (2021)
- [Estimating 3D Camera Pose from 2D Pedestrian Trajectories](https://mlsanity.com/paper/1912.05758/) (2019)
- [Euler angles based loss function for camera relocalization with Deep learning](https://mlsanity.com/paper/1802.08851/) (2018)

## Built on by (most cited first, 2 of 2)

- [Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environments](https://mlsanity.com/paper/2304.07250/) (2023)
- [NaVIP: An Image-Centric Indoor Navigation Solution for Visually Impaired People](https://mlsanity.com/paper/2410.18109/) (2024)

## Abstract (arXiv)

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.